LLM над “Искусством аттриционной войны: Уроки войны России против Украины”

Введение

Этот блог пост использует различные запросы к Большим Языковым Моделям (БЯМ) для суммаризации статьи “Искусство аттриционной войны: Уроки войны России против Украины” от Алекса Вершинина.

Замечание: Мы тоже будем пользоваться сокращением “LLM” (для “Large Language Models”).

В этой статье для Королевского института объединенных служб (RUSI), Алекс Вершинин обсуждает необходимость для Запада пересмотреть свою военную стратегию в отношении аттрициона в предвидении затяжных конфликтов. Статья противопоставляет аттриционную и маневренную войну, подчеркивая важность промышленной мощности, генерации сил и экономической устойчивости в победе в затяжных войнах.

Эта (полученная с помощью LLM) иерархическая диаграмма хорошо суммирует статью:

Примечание: Мы планируем использовать этот пост/статью в качестве ссылки в предстоящем посте/статье с соответствующей математической моделью
(на основе Системной динамики.)

Структура поста:

  1. Темы
    Табличное разбиение содержания.
  2. Ментальная карта
    Структура содержания и связи концепций.
  3. Суммарное изложение, идеи и рекомендации
    Основная помощь в понимании.
  4. Модель системной динамики
    Как сделать данный наблюдения операциональными?

Темы

Вместо суммарного изложения рассмотрите эту таблицу тем:

темасодержание
ВведениеСтатья начинается с подчеркивания необходимости для Запада подготовиться к аттриционной войне, контрастируя это с предпочтением коротких, решающих конфликтов.
Понимание Аттриционной ВойныОпределяет аттриционную войну и подчеркивает ее отличия от маневренной войны, акцентируя важность промышленной мощности и способности заменять потери.
Экономическое ИзмерениеОбсуждает, как экономика и промышленные мощности играют ключевую роль в поддержании войны аттрициона, с примерами из Второй мировой войны.
Генерация СилИсследует, как различные военные доктрины и структуры, такие как НАТО и Советский Союз, влияют на способность генерировать и поддерживать силы в аттриционной войне.
Военное ИзмерениеДетализирует военные операции и стратегии, подходящие для аттриционной войны, включая важность ударов над маневрами и фазы таких конфликтов.
Современная ВойнаИсследует сложности современной войны, включая интеграцию различных систем и вызовы координации наступательных операций.
Последствия для Боевых ОперацийОписывает, как аттриционная война влияет на глубинные удары и стратегическое поражение способности противника регенерировать боевую мощь.
ЗаключениеРезюмирует ключевые моменты о том, как вести и выигрывать аттриционную войну, подчеркивая важность стратегического терпения и тщательного планирования.

Ментальная карта

Вот ментальная карта показывает структуру статьи и суммирует связи между представленными концепциями:


Суммарное изложение, идеи и рекомендации

СУММАРНОЕ ИЗЛОЖЕНИЕ

Алекс Вершинин в “Искусстве аттриционной войны: Уроки войны России против Украины” для Королевского института объединенных служб обсуждает необходимость для Запада пересмотреть свою военную стратегию в отношении аттрициона в предвидении затяжных конфликтов.
Статья противопоставляет аттриционную и маневренную войну, подчеркивая важность промышленной мощности, генерации сил и экономической устойчивости в победе в затяжных войнах.

ИДЕИ:

  • Аттриционные войны требуют уникальной стратегии, сосредоточенной на силе, а не на местности.
  • Западная военная стратегия традиционно отдает предпочтение быстрым, решающим битвам, не готова к затяжному аттриционному конфликту.
  • Войны аттрициона со временем выравнивают шансы между армиями с различными начальными возможностями.
  • Победа в аттриционных войнах больше зависит от экономической силы и промышленной мощности, чем от военного мастерства.
  • Интеграция гражданских товаров в военное производство облегчает быстрое вооружение в аттриционных войнах.
  • Западные экономики сталкиваются с трудностями в быстром масштабировании военного производства из-за мирного эффективности и аутсорсинга.
  • Аттриционная война требует массового и быстрого расширения армий, что требует изменения стратегий производства и обучения.
  • Эффективность военной доктрины НАТО ухудшается в аттриционной войне из-за времени, необходимого для замены опытных некомиссированных офицеров (NCOs).
  • Советская модель генерации сил, с ее массовыми резервами и офицерским управлением, более адаптируема к аттриционной войне.
  • Соединение профессиональных сил с массово мобилизованными войсками создает сбалансированную стратегию для аттриционной войны.
  • Современная война интегрирует сложные системы, требующие продвинутого планирования и координации, что затрудняет быстрые наступательные маневры.
  • Аттриционные стратегии сосредоточены на истощении способности противника регенерировать боевую мощь, защищая свою собственную.
  • Начальная фаза аттриционной войны подчеркивает удерживающие действия и наращивание боевой мощи, а не завоевание территории.
  • Наступательные операции в аттриционной войне следует откладывать до тех пор, пока резервы и промышленная мощность противника достаточно не истощены.
  • Глубинные удары по инфраструктуре и производственным возможностям противника имеют решающее значение в аттриционной войне.
  • Аттриционная война требует стратегического терпения и акцента на оборонительных операциях для подготовки к будущим наступлениям.
  • Ожидание Запада коротких, решающих конфликтов не соответствует реальности потенциальных аттриционных войн с равными противниками.
  • Признание важности экономических стратегий и промышленной мобилизации ключево для подготовки к и выигрышу затяжного конфликта.
  • Информационные операции могут манипулировать движениями и распределением ресурсов противника в свою выгоду в аттриционной войне.

ЦИТАТЫ:

  • “Аттриционные войны требуют своего ‘Искусства войны’ и ведутся с ‘подходом, сосредоточенным на силе’.”
  • “Та сторона, которая принимает аттриционный характер войны и сосредотачивается на уничтожении вражеских сил, а не на завоевании территории, скорее всего, победит.”
  • “Войны аттрициона выигрываются экономиками, позволяющими массовую мобилизацию армий через их промышленные сектора.”
  • “Проще и быстрее производить большое количество дешевого оружия и боеприпасов, особенно если их подкомпоненты взаимозаменяемы с гражданскими товарами.”
  • “Эффективность военной доктрины НАТО ухудшается в аттриционной войне

Модель системной динамики

В этом разделе мы показываем модель системной динамики, полученную с помощью запроса:

Сгенерируйте модель системной динамики для войны на истощение, описанной в следующей статье:

Описание модели, полученное с помощью LLM, имеет смысл, но для получения соответствующей рабочей модели требуются дополнительные запросы к LLM и/или (математическое) программирование и моделирование.

Результат LLM представлен ниже.


Разработка модели системной динамики для войны на истощение, описанной в предоставленном тексте, включает создание структуры, которая улавливает ключевые динамики истощения, генерации сил, экономической поддержки и влияния промышленной мощности на ведение войны. Эта модель будет сосредоточена на взаимодействиях между этими элементами для понимания долгосрочных результатов войны на истощение, особенно в контексте российской войны на Украине, как обсуждаетс

Компоненты модели системной динамики:

  1. Запасы: Это накопления в системе, которые изменяются со временем. Для модели войны на истощение актуальные запасы могут включать:
    • Военный персонал: Сюда входят как высококвалифицированные профессиональные солдаты, так и мобилизованные или призванные военнослужащие низкого уровня.
    • Промышленная мощность: Способность производить военное оборудование, которое может быть разделено на высокотехнологичные сложные системы и массово производимые предметы низкого уровня.
    • Экономические ресурсы: Это финансовые и материальные ресурсы, доступные для поддержки военного производства и операций.
    • Боевая мощь: Общая эффективность и сила военных сил, на которую влияют как количество, так и качество сил и оборудования.
  2. Потоки: Это скорости, которые изменяют запасы, представляя процессы внутри системы.
    • Набор и обучение: Добавление личного состава к запасу военного персонала.
    • Скорость истощения: Уменьшение военного персонала через боевые потери.
    • Скорость производства: Скорость, с которой промышленная мощность производит военное оборудование.
    • Распределение ресурсов: Поток экономических ресурсов в военное производство и операции.
  3. Петли обратной связи: Эти петли помогают понять, как разные части системы влияют друг на друга, усиливая или уравновешивая динамику системы.
    • Усиливающая петля (R1): Увеличение промышленной мощности приводит к большему количеству военного оборудования, что повышает боевую мощь, потенциально приводя к военному успеху, который оправдывает дальнейшие инвестиции в промышленную мощность.
    • Уравновешивающая петля (B1): Высокие скорости истощения сокращают военный персонал, снижая боевую мощь, что может привести к переоценке военных стратегий и потенциальному сокращению агрессивных операций для сохранения сил.
  4. Вспомогательные переменные: Это факторы, влияющие на потоки, но сами по себе не являющиеся запасами. Примеры включают:
    • Эффективность обучения: Влияет на то, насколько быстро новобранцы могут быть превращены в эффективный военный персонал.
    • Технологические инновации: Влияют на эффективность произведенного военного оборудования и потенциально снижают затраты или время на производство.
    • Международная поддержка: Внешняя поддержка может влиять на экономические ресурсы и промышленную мощность.
  5. Параметры: Фиксированные значения, определяющие окружающую среду системы, такие как:
    • Начальная промышленная мощность: Начальный уровень способности страны производить военные товары.
    • Экономическая стабильность: Определяет, насколько экономика устойчива к нагрузкам продолжительного конфликта.

Процесс моделирования:

  1. Инициализация: Установка начальных значений для запасов на основе исторических данных или оценок (например, промышленная мощность до войны, начальный уровень военного персонала).
  2. Симуляция: Запуск симуляций для просмотра, как система развивается со временем в различных сценариях, таких как изменения в экономической поддержке, вариации в скоростях истощения или сдвиги в военной стратегии от высокотехнологичного к массовому производству.
  3. Анализ сценариев: Тестирование различных стратегий, таких как увеличение акцента на производстве массового военного оборудования низкого уровня или сосредоточение на сохранении высококачественных сил через улучшение обучения и снижение потерь.
  4. Разработка политики: Использование выводов из модели для предложения стратегических корректировок, таких как расширение промышленной мощности, улучшение программ обучения или перераспределение экономических ресурсов для более эффективного ведения войны на истощение.

Эта модель системной динамики предоставляет структурированный способ анализа сложных взаимодействий в войне на истощение, помогая стратегам и политикам понимать долгосрочные последствия различных военных и экономических стратегий.

Диаграмма модели системной динамики

Вот диаграмма описания модели, указанной выше:

Примечание: Приведенная выше диаграмма не представляет собой модель системной динамики как таковую. Она представляет концептуальные связи такой модели. В предстоящей статье мы планируем представить фактическую модель системной динамики с соответствующим описанием, диаграммами, уравнениями и результатами симуляции.

Generalized Lanchester combat models

Introduction

In this blog post (based on a WL notebook) we present generalized Lanchester combat models and use one of them for simulation and calibration examples with data of the Battle of Iwo Jima.

Remark: The content of this notebook is intentionally theoretically fundamental, but short and simple both mathematically and code-wise. Author’s intent is to develop similar computational workflows for (1) field battles, like the Normandy campaign during Word War II, 1944, or (2) urban warfare, like Second Battle of Fallujah, Iraq 2009, or Battle of Bakhmut, Ukraine 2023.

The main computational workflows are done with a System Dynamics (SD) software monad implemented in the paclet “MonadicSystemDynamics”, [AAp2]. That paclet is based on the monad implementation presented in “A monad for Epidemiologic Compartmental Modeling Workflows”, [AA1]. The functions provided by the paclet [AAp2] have the prefix “SDMon”, which stands for “System Dynamics Monad”.

Why use the Battle of Iwo Jima in examples?

The examples below use the Battle of Iwo Jima because that is convenient both data-wise and mathematics-wise. Here are our reasons:

  • The battle is important for the USA military, hence well documented and used in multiple contexts.
    • See, for example, mathematical articles like [JE1] and [RS1].
  • (Relatively) well curated data can be found. Like:
    • Sizes of the military forces
    • Battle duration
  • There is no need to:
    • Take care of negative stocks
    • Simulate “will to fight” — Japanese soldiers fought to the last one
      • Japanese Prisoners Of War (POWs) became POWs because they were found unconscious…

Here is the invasion map of Iwo Jima, prepared in February 1945, [DR1]:

Document structure

  • Generalized model and variants Main theory.
  • SDMon Model Programmer’s version.
  • Direct model simulation Using the Battle of Iwo Jima data and related pre-computed rates.
  • Calibration We can get the theoretically computed rates by using numerics!
  • Future plans Make models, not war.

Generalized models

This section presents a translation to English of introductory paragraphs of [NM1]. (The same general model and breakdown is presented in [AS1].)

In the most general form, the Lanchester models can be described by the by the equation:

where:

  • $a$ and $e$ define the rate of non-combat losses
  • $b$ and $f$ define the rate of losses due to exposure to area targets
  • $c$ and $g$ are losses due to forward enemy exposure
  • $d$ and $h$ are approaching or retreating reserves

To determine the casualties of wars, actual or potential, the following four models are of greatest importance.

1. Lanchester proper model (only the coefficients $b$ and $f$ are available)

In this case:

  • The number of casualties is proportional to the number of encounters between individuals.
  • The number of encounters between individuals of the opposing sides is proportional to the number of victims.
  • The number of victims is proportional to the number of encounters between individuals of the opposing parties.
    • Product of the number of parties: $x \times y$.
  • This interaction is most relevant when the two sides are located in a common territory:
    • Guerrilla warfare, repression, enmity between two ethnic groups, etc.

2. Osipov model (coefficients $a$ and $e$)

  • The number of victims is proportional to the number of the opposing side.
  • This could be a classic military engagement where the two sides are in contact only on the front lines.

3. Peterson model (coefficients $a$ and $e$)

  • The number of casualties is determined by the size of one’s side.
  • This could be a model of the Cold War, where the more of their submarines are on alert, the more of them die.

4. Brackney model (coefficients $a$ and $f$ or $b$ and $e$)

  • The casualties of one side is proportional to the number of encounters and the other to the number of its opponent.
  • The model was inspired of the Vietnam War and describes quite satisfactory.
    • I.e. a conflict in which one side is engaged in classical warfare and the other in guerrilla warfare.

Model “rigidness”

The simplest, with Osipov terms only, generalized Lanchester model is:

That model is a “rigid model” that admits an exact solution. (See Arnold’s book “«Rigid» and «soft» mathematical models”, [VA1].)

Here is the solution:

The evolution of the number of soldiers of armies $x$ and $y$ occurs along the hyperbola given by the equation $a x(t) ^2- b y(t)^2\text{==}\text{const}.$ The war evolves along that hyperbola, hence it depends on the starting point.

The corresponding manifold of hyperbolas is separated by the line $a x = b y$. If the starting point lies above this line, then the hyperbola finishes on the $y$-axis. This means that in the course of the war army $x$ decreases to zero and army $y$ wins.

Remark: Note that if the efficiency coefficients $a$ and $b$ are not constant then the equation $a x = b y$ determines a curve.

Here is an interactive interface that illustrates the properties of the simplest model:

Manipulate[
ContourPlot[fX[a, x] x - fY[b, y] y, {x, 0, 10}, {y, 0, 10},
PlotLegends -> Automatic,
Contours -> Evaluate[Join[{{0, {Red, Thick}}}, DeleteCases[Table[{i, Blue}, {i, -100, 100, 0.25}], {0 | 0., _}]]],
ContourShading -> False,
FrameLabel -> {"x", "y"}],
{{a, 0.1, "a, efficiency constant X:"}, 0, 1, 0.001, Appearance -> "Open"},
{{b, 0.2, "b, efficiency constant Y:"}, 0, 1, 0.001, Appearance -> "Open"},
{{fX, Sqrt[#1 Sqrt[#2]] &, "efficiency function X:"},
{(Sqrt[#1] &) -> "\!\(\*SqrtBox[\(a\)]\)",
(Sqrt[#1 Sqrt[#2]] &) -> "\!\(\*SqrtBox[\(a \*SqrtBox[\(x\)]\)]\)"},
ControlType -> SetterBar},
{{fY, Sqrt[#1] &, "efficiency function Y:"},
{(Sqrt[#1] &) -> "\!\(\*SqrtBox[\(b\)]\)",
(Sqrt[#1 Sqrt[#2]] &) -> "\!\(\*SqrtBox[\(b \*SqrtBox[\(y\)]\)]\)"},
ControlType -> SetterBar}]

SDMon model

In this section we define the general model in a simple programmatic form using the paclet “MonadicSystemDynamics”, [AAp2].

Remark: A better programmatic form would have equation elements that prevent (army) stocks to become negative.

Remark: Compared to the previous section, below we follow “wordier” but self-explanatory notation that helps model understanding, evaluation, and enhancements.

Here are the stocks:

aStocks = <| X[t] -> "Soldiers of army X", Y[t] -> "Soldiers of army Y" |>;

Here are the rates:

aRates = <|
    fireEfficiencyX -> "Efficiency of force X ", 
    fireEfficiencyY -> "Efficiency of force Y", 
    fireEfficiencyXonY -> "Efficiency of force X on Y", 
    fireEfficiencyYonX -> "Efficiency of force Y on X", 
    growthX -> "Growth rate of force X due to new recruits", 
    growthY -> "Growth rate of force Y due to new recruits", 
    diseaseX -> "Disease rate in force X", 
    diseaseY -> "Disease rate in force Y", 
    fireFriendlyX -> "Friendly fire rate in force X", 
    fireFriendlyY -> "Friendly fire rate in force Y" 
   |>;

Here are rules that assign concrete values to the rates:

aRateRules = <| fireEfficiencyX -> 0.01, fireEfficiencyY -> 0.015, fireEfficiencyXonY -> 0.05, fireEfficiencyYonX -> 0.03, growthX -> 0, growthY -> 0, diseaseX -> 0.01, diseaseY -> 0.01, fireFriendlyX -> 0.001, fireFriendlyY -> 0.001 |>;

Initial conditions (number of soldiers):

lsInitConds = {X[0] == 100000, Y[0] == 100000};

Lanchester (or Lotka-Volterra) interactions:

lotkaVolterraX = fireEfficiencyYonX*X[t]*Y[t]; lotkaVolterraY = fireEfficiencyXonY*X[t]*Y[t];

Osipov interactions:

osipovX = fireEfficiencyY*Y[t]; osipovY = fireEfficiencyX*X[t];

Equations:

lsEquations = { X'[t] == growthX - diseaseX*X[t] - fireFriendlyX*X[t] - lotkaVolterraX - osipovX, Y'[t] == growthY - diseaseY*Y[t] - fireFriendlyY*Y[t] - lotkaVolterraY - osipovY };

Make the model data structure:

model1 = <| "Rates" -> aRates, "Stocks" -> aStocks, "RateRules" -> aRateRules, "InitialConditions" -> lsInitConds, "Equations" -> lsEquations |>;

Display the model in tabular format:

ModelGridTableForm[model1]


Direct model simulation

Here we follow the equations setup and data in the article [JE1].

Remark: The data in [JE1] is later revisited and new computations were made with almost the same results. See [RS1].

Clear[growthIwoJimaX]; growthIwoJimaX[t_] := Piecewise[{{54000, 0 <= t < 1}, {6000, 2 <= t < 3}, {13000, 5 <= t < 6}}, 0]

Here replace the constant term of the first equation in the generalized model with the growth function growthIwoJimaX.

model1a = model1 /. growthX -> growthIwoJimaX[t];

Here create the monadic pipeline, put the fire efficiency rates found in [JE1], simulate the for battles number of days, and plot the result:

sdObj =
  SDMonUnit[]⟹
   SDMonSetSingleSiteModel[model1a]⟹
   SDMonAssignRateRules[<|
     growthY -> 0,
     diseaseX -> 0, diseaseY -> 0,
     fireEfficiencyYonX -> 0, fireEfficiencyXonY -> 0,
     fireEfficiencyX -> 0.0106, fireEfficiencyY -> 0.0544
     |>]⟹
   SDMonAssignInitialConditions[<|X[0] -> 0, Y[0] -> 21000|>]⟹
   SDMonEcho[Style["Model's tabular form:", Bold, Purple, FontSize -> 18, FontFamily -> "Times"]]⟹
   SDMonEchoModelGridTableForm⟹
   SDMonSimulate[35]⟹
   SDMonEcho[Style["Plot simulated stocks evolution:", Bold, Purple, FontSize -> 18, FontFamily -> "Times"]]⟹
   SDMonPlotSolutions[];

Calibration

In this section we show that using optimization methods — calibration — we can obtain the same efficiency rates as the ones theoretically computed in [JE1] using the same data.

Remark: This should bring some confidence in using SDMon; and since the calibration process is easy to specify, it should encourage SDMon’s use for other SD models.

aTargets2 = N@
    <|
     X -> Map[Interpolation[{{0, Total@Map[growthIwoJimaX, Range[0, 36]]}, {35, 51300}}, InterpolationOrder -> 1], Range[0, 35]], 
     Y -> Interpolation[{{0, 21000}, {35, 0}}, InterpolationOrder -> 1] /@ Range[0, 35] 
    |>;

ListLinePlot[aTargets2, PlotTheme -> "Detailed"]

Here is the first point of the stock $X$ (USA soldiers):

Total@Map[growthIwoJimaX, Range[0, 35]] (*73000*)

Here is a model setup pipeline:

sdObj2 = 
SDMonUnit[]⟹
SDMonSetSingleSiteModel[model1a]⟹
SDMonAssignRateRules[<|
growthY -> 0,
diseaseX -> 0, diseaseY -> 0,
fireEfficiencyYonX -> 0, fireEfficiencyXonY -> 0
|>]⟹
SDMonAssignInitialConditions[<|X[0] -> 0, Y[0] -> 21000|>]⟹
SDMonEchoModelGridTableForm;

Here is a calibration pipeline that specifies:

  1. Target time series of the stocks
  2. Parameters to calibrate
  3. Parameter ranges, within which to search the calibration values
  4. Distance function from the computed time series to the target time series
  5. Parameters for NMinimize
resCalibration = 
  sdObj2⟹
   SDMonCalibrate[
    "Target" -> KeyTake[aTargets2, {X, Y}], 
    "Parameters" -> <|fireEfficiencyX -> {0, 0.1}, fireEfficiencyY -> {0, 0.1}|>, 
    DistanceFunction -> EuclideanDistance, 
    Method -> {"NelderMead", "PostProcess" -> False}, 
    MaxIterations -> 1000]⟹
   SDMonTakeValue

(*{83614.5, {fireEfficiencyX -> 0.00990159, fireEfficiencyY -> 0.0399577}}*)

Here we plot the simulated army sizes using the calibrated values:

sdObj2⟹
SDMonSimulate[35]⟹
SDMonAssignRateRules[
Association@resCalibration[[2]]]⟹
SDMonEcho[
Style["Plot simulated stocks evolution with calibrated values:",
Bold, Purple, FontSize -> 18,
FontFamily -> "Times"]]⟹
SDMonPlotSolutions[];

Here we use a more “complicated” distance function that takes only the known points of the time series:

resCalibration2 = 
  sdObj2⟹
   SDMonCalibrate[
    "Target" -> KeyTake[aTargets2, {X, Y}], 
    "Parameters" -> <|fireEfficiencyX -> {0, 0.1}, fireEfficiencyY -> {0, 0.1}|>, 
    DistanceFunction -> (EuclideanDistance[#1[[{1, -1}]], #2[[{1, -1}]]] &), 
    Method -> {"NelderMead", "PostProcess" -> False}, MaxIterations -> 1000]⟹
   SDMonTakeValue

(*{73000., {fireEfficiencyX -> 0.0106351, fireEfficiencyY -> 0.0547895}}*)

Remark: Note that with that new calibration distance function we get almost the same results as the theoretically computed efficiency rates in [JE1]:

<|fireEfficiencyX -> 0.0106, fireEfficiencyY -> 0.0544|>

Remark: Proper calibration time series for the USA soldiers stock $X$ can be obtained from the web page “Iwo Jima, a look back”. (The corresponding data ingestion notebook is going to be published soon.)


Future plans

Here are a few directions to extend this work into:

  • Inclusion of different types of forces
  • Simulation of “will to fight”
    • Easy with NDSolve and, hence, with SDMon.
  • Inclusion of weapon and ammunition production stocks and related supply rates
    • For example, as in [AA2].
  • Modeling the war impact on countries’ economics and populations
  • Modeling the role of propaganda
  • Make interactive interfaces with knobs for the parameters
    • With selectors of scenarios based on known battles.

Setup

PacletInstall["AntonAntonov/EpidemiologicalModeling"]; PacletInstall["AntonAntonov/MonadicSystemDynamics"];
Needs["AntonAntonov`EpidemiologicalModeling`"] Needs["AntonAntonov`MonadicSystemDynamics`"]

References

Articles

[AA1] Anton Antonov, “A monad for Epidemiologic Compartmental Modeling Workflows”, (2021), MathematicaForPrediction at WordPress.

[AS1] Andrei Shatyrko, Bedrik Puzha, Veronika Novotná, “Comparative Analysis and New Field of Application Lanchester’s Combat Models”, (2018), Post-conference proceedings of selected papers extended version Conference MITAV-2018, Brno, Czech Republic, 2018. P.118-133. ISBN 978-80-7582-065-5.

[JE1] J.H. Engel, “A verification of Lanchester’s law”, (1953), Journal of the Operations Research Society of America, Vol. 2, No. 2. (May, 1954), pp. 163-171. (JSTOR link.)

[DR1] J. David Rogers, “Iwo Jima: The costliest battle in American history”, Missouri S&T. (jdavidrogers.net.)

[NM1] Nikolai V. Mityukov. Determining the casualties of wars through Lanchester models, (2009), Historical Psychology and Sociology of History.

[NM1ru] Н. В. МИТЮКОВ, ОПРЕДЕЛЕНИЕ ЖЕРТВ ВОЙН ЧЕРЕЗ ЛАНЧЕСТЕРСКИЕ МОДЕЛИИсторическая психология и социология истории 2/2009 122–140.

[RS1] Robert W. Samz, ⎡Some Comments on Engel’s “A Verification of Lanchester’s Law”⎦, (1972), Operations Research, Vol. 20, No. 1 (Jan. – Feb., 1972), pp. 49-52 (4 pages) (JSTOR link.)

[Wk1] Lanchester’s laws, Wikipedia.

[Wk2] Battle of Iwo Jima, Wikipedia.

Books

[VA1] Vladimir I. Arnold, Rigid and soft mathematical models, 2nd ed. (2008), Moscow Center of Continuous Mathematical Education. In Russian: Владимир И. Арнольд, “«Жесткие» и «мягкие» математические модели”, (2008), М.: МЦНМО, 2014, 32 с. ISBN 978-5-94057-427-9.

Packages, paclets

[AAp1] Anton Antonov, EpidemiologicalModeling, WL paclet, (2023), Wolfram Language Paclet Repository.

[AAp2] Anton Antonov, MonadicSystemDynamics, WL paclet, (2023), Wolfram Language Paclet Repository.

Repositories

[AAr1] Anton Antonov, System Modeling, (2020-2023), GitHub/antononcube.

Wolfram Language conference in St. Petersburg

Two weeks ago (June 1st and 2nd) I participated in the Wolfram Language conference in St. Petersburg, Russia.
Here are the corresponding announcements:

The conference was co-organized by Kirill Belov and Petr Genadievich Tenishev.

Link to the GitHub repository with my conference presentation materials.

Here is a mind-map of the potential presentations Kirill and I discussed:

System dynamics presentation

I presented “Динамические системы : Расширение и улучшение эпидемиологических моделей”
(in English: “Dynamics systems: extending and improving epidemiological models”.)

The main presentation slides had a dozen supplements:

Making two presentations

Interestingly, I first prepared a Latent Semantic Analysis (LSA) talk, but then found out that the organizers listed another talk I discussed with them, on extending dynamic systems models. (The latter one is the first we discussed, so, it was my “fault” that I wanted to talk about LSA.)

Here are the presentation notebooks for LSA in English and Russian .

Some afterthoughts

  • Тhe conference was very “strong”, my presentation was the “weakest.”
    • With “strong” I refer to the content and style of the presentations.
  • This was also the first scientific presentation I gave in Russian. I also got a participation diploma .

to demonstrate generation of epidemiological modeling code.

  • Preparing for the conference reminded me of some the COVID-19 modeling hackathons I participated in.
  • I prepared the initial models of artillery shells manufacturing, but much more work has to be done in order to have a meaningful article or presentation. (Hopefully, I am finishing that soon.)

References

Articles, posts, presentations

[AA1] Антон Антонов,
“Динамические системы : Расширение и улучшение эпидемиологических моделей” .

[AA2] Антон Антонов,
“COVID-19 modeling over Botswana” ,

[AA3] Anton Antonov,
“WirVsVirus 2020 hackathon participation” ,
(2020),
MathematicaForPrediction at WordPress .

Making Graphs over System Dynamics Models

Introduction

In this document we give usage examples for the functions of the package, “SystemDynamicsModelGraph.m”, [AAp1]. The package provides functions for making dependency graphs for the stocks in System Dynamics (SD) models. The primary motivation for creating the functions in this package is to have the ability to introspect, proofread, and verify the (typical) ODE models made in SD.

A more detailed explanation is:

  • For a given SD system S of Ordinary Differential Equations (ODEs) we make Mathematica graph objects that represent the interaction of variable dependent functions in S.
  • Those graph objects give alternative (and hopefully convenient) way of visualizing the model of S.

Load packages

The following commands load the packages [AAp1, AAp2, AAp3]:

Import["https://raw.githubusercontent.com/antononcube/SystemModeling/master/WL/SystemDynamicsModelGraph.m"]
Import["https://raw.githubusercontent.com/antononcube/SystemModeling/master/Projects/Coronavirus-propagation-dynamics/WL/EpidemiologyModels.m"]
Import["https://raw.githubusercontent.com/antononcube/MathematicaForPrediction/master/Misc/CallGraph.m"]

Usage examples

Equations

Here is a system of ODEs of a slightly modified SEIR model:

lsEqs = {Derivative[1][SP][t] == -((IP[t] SP[t] \[Beta][IP])/TP[t]) - SP[t] \[Mu][TP], Derivative[1][EP][t] == (IP[t] SP[t] \[Beta][IP])/TP[t] - EP[t] (1/aincp + \[Mu][TP]), Derivative[1][IP][t] == EP[t]/aincp - IP[t]/aip - IP[t] \[Mu][IP], Derivative[1][RP][t] == IP[t]/aip - RP[t] \[Mu][TP], TP[t] == Max[0, EP[t] + IP[t] + RP[t] + SP[t]]};
ResourceFunction["GridTableForm"][List /@ lsEqs, TableHeadings -> {"Equations"}]
01xbi9kqh0cfv

Model graph

Here is a graph of the dependencies between the populations:

ModelDependencyGraph[lsEqs, {EP, IP, RP, SP, TP}, t]
08d1a9tfgog31

When the second argument given to ModelDependencyGraph is Automatic the stocks in the equations are heuristically found with the function ModelHeuristicStocks:

ModelHeuristicStocks[lsEqs, t]

(*{EP, IP, RP, SP, TP}*)

Also, the function ModelDependencyGraph takes all options of Graph:

ModelDependencyGraph[lsEqs, Automatic, t, 
  GraphLayout -> "GravityEmbedding", VertexLabels -> "Name", VertexLabelStyle -> Directive[Red, Bold, 16], EdgeLabelStyle -> Directive[Blue, 16], ImageSize -> Large]
0nbr2tt4704fd

Dependencies only

The dependencies in the model can be found with the function ModelDependencyGraphEdges:

lsEdges = ModelDependencyGraphEdges[lsEqs, Automatic, t]
0oqkkrnakv89r
lsEdges[[4]] // FullForm
0x9s286b3noms

Focus stocks

Here is a graph for a set of “focus” stocks-sources to a set of “focus” stocks-destinations:

gr = ModelDependencyGraph[lsEqs, {IP, SP}, {EP}, t]
13di08vbzgsyi

Compare with the graph in which the argument positions of sources and destinations of the previous command are swapped:

ModelDependencyGraph[lsEqs, {EP}, {IP, SP}, t]
009we6s5tmxek

Additional interfacing

The functions of this package work with the models from the package “EpidemiologyModels.m”, [AAp2].

Here is a model from [AAp2]:

model = SEIRModel[t, "TotalPopulationRepresentation" -> "AlgebraicEquation"];
ModelGridTableForm[model]
0aojbcw5zogfw

Here we make the corresponding graph:

ModelDependencyGraph[model, t]
1v1sbwz9d6peq

Generating equations from graph specifications

A related, dual, or inverse task to the generation of graphs from systems of ODEs is the generation of system of ODEs from graphs.

Here is a model specifications through graph edges (using DirectedEdge):

0qp613dyiglzo

Here is the corresponding graph:

grModel = Graph[lsEdges, VertexLabels -> "Name", EdgeLabels -> "EdgeTag", ImageSize -> Large]
1vrnyvwpgmcz9

Here we generate the system of ODEs using the function ModelGraphEquations:

lsEqsGen = ModelGraphEquations[grModel, t];
ResourceFunction["GridTableForm"][List /@ lsEqsGen, TableHeadings -> {"Equations"}]
1dl7z5ohgof6h

Remark: ModelGraphEquations works with both graph and list of edges as a first argument.

Here we replace the symbolically represented rates with concrete values:

08ewn5gxhx8d5
1e4wq9d04yhro

Here we solve the system of ODEs:

sol = First@NDSolve[{lsEqsGen2, SP[0] == 99998, EP[0] == 0, IP[0] == 1, RP[0] == 0,MLP[0] == 0, TP[0] == 100000}, Union[First /@ lsEdges], {t, 0, 365}]
1p9civying0hn

Here we plot the results:

ListLinePlot[sol[[All, 2]], PlotLegends -> sol[[All, 1]]]
13xvmif6i6o2n

Call graph

The functionalities provided by the presented package “SystemDynamicsModelGraph.m”, [AAp1], resemble in spirit those of the package “CallGraph.m”, [AAp3].

Here is call graph for the functions in the package [AAp1] made with the function CallGraph from the package [AAp3]:

CallGraph`CallGraph[Context[ModelDependencyGraph], "PrivateContexts" -> False, "UsageTooltips" -> True]
0c1vpbf585pe9

References

Packages

[AAp1] Anton Antonov, “System Dynamics Model Graph Mathematica package”, (2020), SystemsModeling at GitHub/antononcube.

[AAp2] Anton Antonov, “Epidemiology models Mathematica package”, (2020), SystemsModeling at GitHub/antononcube.

[AAp3] Anton Antonov, “Call graph generation for context functions Mathematica package”, (2018), MathematicaForPrediction at GitHub/antononcube.

Articles

[AA1] Anton Antonov, “Call graph generation for context functions”, (2019), MathematicaForPrediction at WordPress.

SEI2HR-Econ model with quarantine and supplies scenarios

Introduction

The epidemiology compartmental model, [Wk1], presented in this notebook – SEI2HR-Econ – deals with all three rectangles in this diagram:

ImageResize[Import["https://github.com/antononcube/SystemModeling/raw/master/Projects/Coronavirus-propagation-dynamics/Diagrams/Coronavirus-propagation-simple-dynamics.jpeg"], 900]
1nfurrmjzvnjk

“SEI2HR” stands for “Susceptible, Exposed, Infected two, Hospitalized, Recovered” (populations.) “Econ” stands for “Economic”.

In this notebook we also deal with both quarantine scenarios and medical supplies scenarios. In the notebook [AA4] we deal with quarantine scenarios over a simpler model, SEI2HR.

Remark: We consider the contagious disease propagation models as instances of the more general System Dynamics (SD) models. We use SD terminology in this notebook.

The models

SEI2R

The model SEI2R is introduced and explained in the notebook [AA2]. SEI2R differs from the classical SEIR model, [Wk1, HH1], with the following elements:

  1. Two separate infected populations: one is “severely symptomatic”, the other is “normally symptomatic”
  2. The monetary equivalent of lost productivity due to infected or died people is tracked

SEI2HR

For the formulation of SEI2HR we use a system of Differential Algebraic Equations (DAE’s). The package [AAp1] allows the use of a formulation that has just Ordinary Differential Equations (ODE’s).

Here are the unique features of SEI2HR:

  • People stocks
    • There are two types of infected populations: normally symptomatic and severely symptomatic.
    • There is a hospitalized population.
    • There is a deceased from infection population.
  • Hospital beds
    • Hospital beds are a limited resource that determines the number of hospitalized people.
    • Only severely symptomatic people are hospitalized according to the available hospital beds.
    • The hospital beds stock is not assumed constant, it has its own change rate.
  • Money stocks
    • The money from lost productivity is tracked.
    • The money for hospital services is tracked.

SEI2HR-Econ

SEI2HR-Econ adds the following features to SEI2HR:

  • Medical supplies
    • Medical supplies production is part of the model.
    • Medical supplies delivery is part of the model..
    • Medical supplies accumulation at hospitals is taken into account.
    • Medical supplies demand tracking.
  • Hospitalization
    • Severely symptomatic people are hospitalized according to two limited resources: hospital beds and medical supplies.
  • Money stocks
    • Money for medical supplies production is tracked.

SEI2HR-Econ’s place a development plan

This graph shows the “big picture” of the model development plan undertaken in [AAr1] and SEI2HR (discussed in this notebook) is in that graph:

0led86ishkred

Notebook structure

The rest of notebook has the following sequence of sections:

  • Package load section
  • SEI2HR-Econ structure in comparison of SEI2HR
  • Explanations of the equations of SEI2HR-Econ
  • Quarantine scenario modeling preparation
  • Medical supplies production and delivery scenario modeling preparation
  • Parameters and initial conditions setup
    • Populations, hospital beds, quarantine scenarios, medical supplies scenarios
  • Simulation solutions
  • Interactive interface
  • Sensitivity analysis

Load packages

The epidemiological models framework used in this notebook is implemented with the packages [AAp1-AAp4, AA3]; many of the plot functions are from the package [AAp5].

Import["https://raw.githubusercontent.com/antononcube/SystemModeling/master/Projects/Coronavirus-propagation-dynamics/WL/EpidemiologyModels.m"];
Import["https://raw.githubusercontent.com/antononcube/SystemModeling/master/Projects/Coronavirus-propagation-dynamics/WL/EpidemiologyModelModifications.m"];
Import["https://raw.githubusercontent.com/antononcube/SystemModeling/master/Projects/Coronavirus-propagation-dynamics/WL/EpidemiologyModelingVisualizationFunctions.m"];
Import["https://raw.githubusercontent.com/antononcube/SystemModeling/master/Projects/Coronavirus-propagation-dynamics/WL/EpidemiologyModelingSimulationFunctions.m"];
Import["https://raw.githubusercontent.com/antononcube/SystemModeling/master/WL/SystemDynamicsInteractiveInterfacesFunctions.m"];

SEI2HR-Econ extends SEI2HR

The model SEI2HR-Econ is an extension of the model SEI2HR, [AA4].

Here is SEI2HR:

reprTP = "AlgebraicEquation";
lsModelOpts = {"Tooltips" -> True, 
   TooltipStyle -> {Background -> Yellow, CellFrameColor -> Gray, 
     FontSize -> 20}};
modelReference = 
  SEI2HRModel[t, "InitialConditions" -> True, "RateRules" -> True, 
   "TotalPopulationRepresentation" -> reprTP];
ModelGridTableForm[modelReference, lsModelOpts]
123yrlk2zl1zu

Here is SEI2HR-Econ:

modelSEI2HREcon = 
  SEI2HREconModel[t, "InitialConditions" -> True, "RateRules" -> True,
    "TotalPopulationRepresentation" -> reprTP];
ModelGridTableForm[modelSEI2HREcon, lsModelOpts]
10vmc7pwzubaa

Here are the “differences” between the two models:

ModelGridTableForm@
 Merge[{modelSEI2HREcon, modelReference}, 
  If[AssociationQ[#[[1]]], KeyComplement[#], Complement @@ #] &]
036glal3iv3uy

Equations explanations

In this section we provide rationale for the equations of SEI2HR-Econ.

The equations for Susceptible, Exposed, Infected, Recovered populations of SEI2R are “standard” and explanations about them are found in [WK1, HH1]. For SEI2HR those equations change because of the stocks Hospitalized Population and Hospital Beds. For SEI2HR-Econ the SEI2HR equations change because of the stocks Medical Supplies, Medical Supplies Demand, and Hospital Medical Supplies.

The equations time unit is one day. The time horizon is one year. Since we target COVID-19, [Wk2, AA1], we do not consider births.

Remark: For convenient reading the equations in this section have tooltips for the involved stocks and rates.

Verbalization description of the model

We start with one infected (normally symptomatic) person, the rest of the people are susceptible. The infected people meet other people directly or get in contact with them indirectly. (Say, susceptible people touch things touched by infected.) For each susceptible person there is a probability to get the decease. The decease has an incubation period: before becoming infected the susceptible are (merely) exposed. The infected recover after a certain average infection period or die. A certain fraction of the infected become severely symptomatic. The severely symptomatic infected are hospitalized if there are enough hospital beds and enough medical supplies. The hospitalized severely infected have different death rate than the non-hospitalized ones. The number of hospital beds might change: hospitals are extended, new hospitals are build, or there are not enough medical personnel or supplies.

The different types of populations (infected, hospitalized, recovered, etc.) have their own consumption rates of medical supplies. The medical supplies are produced with a certain rate (units per day) and delivered after a certain delay period. The hospitals have their own storage for medical supplies. Medical supplies are delivered to the hospitals only, non-hospitalized people go to the medical supplies producer to buy supplies. The hospitals have precedence for the medical supplies: if the medical supplies are not enough for everyone, the hospital needs are covered first (as much as possible.)

The medical supplies producer has a certain storage capacity (for supplies.) The medical supplies delivery vehicles have a certain – generally speaking, smaller – capacity. The hospitals have a certain capacity to store medical supplies. It is assumed that both producer and hospitals have initial stocks of medical supplies. (Following a certain normal, general preparedness protocol.)

The combined demand from all populations for medical supplies is tracked (accumulated.) The deaths from infection are tracked (accumulated.) Money for medical supplies production, money for hospital services, and money from lost productivity are tracked (accumulated.)

The equations below give mathematical interpretation of the model description above.

Code for the equations

Each equation in this section are derived with code like this:

ModelGridTableForm[modelSEI2HREcon, lsModelOpts]["Equations"][[1, 
 EquationPosition[modelSEI2HREcon, RP] + 1, 2]]

and then the output cell is edited to be “DisplayFormula” and have CellLabel value corresponding to the stock of interest.

The infected and hospitalized populations

SEI2HR has two types of infected populations: a normally symptomatic one and a severely symptomatic one. A major assumption for SEI2HR is that only the severely symptomatic people are hospitalized. (That assumption is also reflected in the diagram in the introduction.)

Each of those three populations have their own contact rates and mortality rates.

Here are the contact rates from the SEI2HR-Econ dictionary

ColumnForm@
 Cases[Normal@modelSEI2HREcon["Rates"], 
  HoldPattern[\[Beta][_] -> _], \[Infinity]]
1nlv3w1o6bvs1

Here are the mortality rates from the SEI2HR-Econ dictionary

ColumnForm@
 Cases[Normal@modelSEI2HREcon["Rates"], 
  HoldPattern[\[Mu][_] -> _], \[Infinity]]
1ile9wky2yqy5

Remark: Below with “Infected Population” we mean both stocks Infected Normally Symptomatic Population (INSP) and Infected Severely Symptomatic Population (ISSP).

Total Population

In this notebook we consider a DAE’s formulation of SEI2HR-Econ. The stock Total Population has the following (obvious) algebraic equation:

0z7878rbvh3ut
0z7878rbvh3ut

Note that with Max we specified that the total population cannot be less than 0.

Remark: As mentioned in the introduction, the package [AAp1] allows for the use of non-algebraic formulation, without an equation for TP.

Susceptible Population

The stock Susceptible Population (SP) is decreased by (1) infections derived from stocks Infected Populations and Hospitalized Population (HP), and (2) morality cases derived with the typical mortality rate.

1gercwr5szizt
1gercwr5szizt

Because we hospitalize the severely infected people only instead of the term

09xmdu8xq7e0p
09xmdu8xq7e0p

we have the terms

0dkc6td55qv7p
0dkc6td55qv7p

The first term is for the infections derived from the hospitalized population. The second term for the infections derived from people who are infected severely symptomatic and not hospitalized.

Births term

Note that we do not consider in this notebook births, but the births term can be included in SP’s equation:

Block[{m = SEI2HREconModel[t, "BirthsTerm" -> True]},
 ModelGridTableForm[m]["Equations"][[1, EquationPosition[m, SP] + 1, 
  2]]
 ]
16thktzpo0dk9
16thktzpo0dk9

The births rate is the same as the death rate, but it can be programmatically changed. (See [AAp2].)

Exposed Population

The stock Exposed Population (EP) is increased by (1) infections derived from the stocks Infected Populations and Hospitalized Population, and (2) mortality cases derived with the typical mortality rate. EP is decreased by (1) the people who after a certain average incubation period (aincp) become ill, and (2) mortality cases derived with the typical mortality rate.

083x1htqp0kkx
083x1htqp0kkx

Infected Normally Symptomatic Population

INSP is increased by a fraction of the people who have been exposed. That fraction is derived with the parameter severely symptomatic population fraction (sspf). INSP is decreased by (1) the people who recover after a certain average infection period (aip), and (2) the normally symptomatic people who die from the disease.

01cfzpu1jv3o4
01cfzpu1jv3o4

Infected Severely Symptomatic Population

ISSP is increased by a fraction of the people who have been exposed. That fraction is corresponds to the parameter severely symptomatic population fraction (sspf). ISSP is decreased by (1) the people who recover after a certain average infection period (aip), (2) the hospitalized severely symptomatic people who die from the disease, and (3) the non-hospitalized severely symptomatic people who die from the disease.

0zhs2d6lt6gz8
0zhs2d6lt6gz8

Note that we do not assume that severely symptomatic people recover faster if they are hospitalized, only that they have a different death rate.

Hospitalized Population

The amount of people that can be hospitalized is determined by the available Hospital Beds (HB) – the stock Hospitalized Population (HP) is subject to a resource limitation by the stock HB.

The equation of the stock HP can be easily understood from the following dynamics description points:

  • If the number of hospitalized people is less that the number of hospital beds we hospitalize the new ISSP people.
  • The Available Hospital Beds (AHB) are determined by the minimum of (i) the non-occupied hospital beds, and (ii) the hospital medical supplies divided by the ISSP consumption rate.
  • If the new ISSP people are more than AHB the hospital takes as many as AHB.
  • Hospitalized people have the same average infection period (aip).
  • Hospitalized (severely symptomatic) people have their own mortality rate.

Here is the HP equation:

1c35mhvi92ffe
1c35mhvi92ffe

Note that although we know that in a given day some hospital beds are going to be freed they are not considered in the hospitalization plans for that day. Similarly, we know that new medical supplies are coming but we do not include them into AHB.

Recovered Population

The stock Recovered Population (RP) is increased by the recovered infected people and decreased by mortality cases derived with the typical mortality rate.

04y15eqwki71f
04y15eqwki71f

Deceased Infected Population

The stock Deceased Infected Population (DIP) accumulates the deaths of the people who are infected. Note that we utilize the different death rates for HP and ISSP.

1ikrv4a51h9xo
1ikrv4a51h9xo

Hospital Beds

The stock Hospital Beds (HB) can change with a rate that reflects the number of hospital beds change rate (nhbcr) per day. Generally speaking, using nhbcr we can capture scenarios, like, extending hospitals, building new hospitals, recruitment of new medical personnel, loss of medical personnel (due to infections.)

1is45mamhsayd
1is45mamhsayd

Hospital Medical Supplies

The Hospital Medical Supplies (HMS) are decreased according to the medical supplies consumption rate (mscr) of HP and increased by a Medical Supplies (MS) delivery term (to be described next.)

The MS delivery term is build with the following assumptions / postulates:

  • Every day the hospital attempts to order MS that correspond to HB multiplied by mscr.
  • The hospital has limited capacity of MS storage, \kappa [\text{HMS}].
  • The MS producer has limited capacity for delivery, \kappa [\text{MDS}].
  • The hospital demand for MS has precedence over the demands for the non-hospitalized populations.
  • Hence, if the MS producer has less stock of MS than the demand of the hospital then MS producer’s whole amount of MS goes to the hospital.
  • The supplies are delivered with some delay period: the medical supplies delivery period (msdp).

Here is the MS delivery term:

1uxby6ipa49dw
1uxby6ipa49dw

Here is the corresponding HMS equation:

0ri4ohdddjxle
0ri4ohdddjxle

Medical Supplies

The equation of the Medical Supplies (MS) stock is based on the following assumptions / postulates:

  • The non-hospitalized people go to the MS producer to buy supplies. (I.e. MS delivery is to the hospital only.)
  • The MS producer vehicles have certain capacity, \kappa [\text{MSD}].
  • The MS producer has a certain storage capacity (for MS stock.)
  • Each of the populations INSP, ISSP, and HP has its own specific medical supplies consumption rate (mscr). EP, RP, and TP have the same mscr.
  • The hospital has precedence in its MS order. I.e. the demand from the hospital is satisfied first, and then the demand of the rest of the populations.

Here is the MS delivery term described in the previous section:

1dy38wd13b0h6
1dy38wd13b0h6

Here is the MS formula with the MS delivery term replaced with “Dlvr”:

ModelGridTableForm[modelSEI2HREcon, "Tooltips" -> False][
   "Equations"][[1, EquationPosition[modelSEI2HREcon, MS] + 1, 2]] /. 
 dlvr -> Dlvr
1r0u6ie10kbi4
1r0u6ie10kbi4

We can see from that equation that MS is increased by medical supplies production rate (mspr) with measuring dimension number of units per day. The production is restricted by the storage capacity, \kappa [\text{MS}]:

(*Min[mspr[HB], -MS[t] + \[Kappa][MS]]*)

MS is decreased by the MS delivery term and the demand from the non-hospitalized populations. Because the hospital has precedence, we use this term form in the equation:

(*Min[-Dlvr + MS[t], "non-hospital demand"]*)

Here is the full MS equation:

0xc7vujwb2npw
0xc7vujwb2npw

Medical Supplies Demand

The stock Medical Supplies Demand (MSD) simply accumulates the MS demand derived from population stocks and their corresponding mscr:

0ut8smszrobx2
0ut8smszrobx2

Money for Hospital Services

The stock Money for Hospital Services (MHS) simply tracks expenses for hospitalized people. The parameter hospital services cost rate (hscr) with unit money per bed per day simply multiplies HP.

0evzoim1tjwsj
0evzoim1tjwsj

Money from Lost Productivity

The stock Money from Lost Productivity (MLP) simply tracks the work non-availability of the infected and died from infection people. The parameter lost productivity cost rate (lpcr) with unit money per person per day multiplies the total count of the infected and dead from infection.

1fhewr6izy46n
1fhewr6izy46n

Quarantine scenarios

In order to model quarantine scenarios we use piecewise constant functions for the contact rates \beta [\text{ISSP}] and \beta [\text{INSP}].

Remark: Other functions can be used, like, functions derived through some statistical fitting.

Here is an example plot :

Block[{func = \[Beta]*
    Piecewise[{{1, t < qsd}, {qcrf, qsd <= t <= qsd + ql}}, 1]},
 Legended[
  Block[{\[Beta] = 0.56, qsd = 60, ql = 8*7, qcrf = 0.25},
   ListLinePlot[Table[func, {t, 0, 365}], PlotStyle -> "Detailed"]
   ], func]]
1nf41pq3u0gvg

To model quarantine with a piecewise constant function we use the following parameters:

  • \text{qsd} for quarantine’s start
  • \text{ql} for quarantines duration
  • \text{qcrf} for the effect on the quarantine on the contact rate

Medical supplies scenarios

We consider three main scenarios for the medical supplies:

  1. Constant production rate and consistent delivery (constant delivery period)
  2. Constant production rate and disrupted delivery
  3. Disrupted production and disrupted delivery

The disruptions are simulated with simple pulse functions – we want to see how the system being modeled reacts to singular, elementary disruption.

Here is an example plot of a disruption of delivery period plot :

Block[{func = 
   dbp*Piecewise[{{1, t < dds}, {dsf, dds <= t <= dds + ddl}}, 1]},
 Legended[
  Block[{dbp = 1, dds = 70, ddl = 7, dsf = 1.8},
   ListLinePlot[Table[func, {t, 0, 365}], PlotStyle -> "Detailed"]
   ], func]]
093okrtfqf4bj
093okrtfqf4bj

To model disruption of delivery with a piecewise constant function we use the following parameters:

  • \text{dbp} for the delivery base period
  • \text{dds} for delivery disruption start
  • \text{ddl} for delivery disruption duration
  • \text{dsf} for how much slower or faster the delivery period becomes

Parameters and actual simulation equations code

Here are the parameters we want to experiment with (or do calibration with):

lsFocusParams = {aincp, aip, sspf[SP], \[Beta][HP], qsd, ql, qcrf, 
   nhbcr[ISSP, INSP], nhbr[TP], mspr[HB]};

Here we set custom rates and initial conditions:

population = 10^6;
modelSEI2HREcon =
  SetRateRules[
   modelSEI2HREcon,
   <|
    TP[0] -> population,
    \[Beta][ISSP] -> 
     0.5*Piecewise[{{1, t < qsd}, {qcrf, qsd <= t <= qsd + ql}}, 1],
    \[Beta][INSP] -> 
     0.5*Piecewise[{{1, t < qsd}, {qcrf, qsd <= t <= qsd + ql}}, 1],
    qsd -> 60,
    ql -> 8*7,
    qcrf -> 0.25,
    \[Beta][HP] -> 0.01,
    \[Mu][ISSP] -> 0.035/aip,
    \[Mu][INSP] -> 0.01/aip,
    nhbr[TP] -> 3/1000,
    lpcr[ISSP, INSP] -> 1,
    hscr[ISSP, INSP] -> 1,
    msdp[HB] -> 
     dbp*Piecewise[{{1, t < dds}, {dsf, dds <= t <= dds + ddl}}, 1],
    dbp -> 1,
    dds -> 70,
    ddl -> 7,
    dsf -> 2
    |>
   ];

Remark: Note the piecewise functions for \beta [\text{ISSP}], \beta [\text{INSP}], and \text{msdp}[\text{HB}].

Here is the system of ODE’s we use to do parametrized simulations:

lsActualEquations = 
  ModelNDSolveEquations[modelSEI2HREcon, 
   KeyDrop[modelSEI2HREcon["RateRules"], lsFocusParams]];
ResourceFunction["GridTableForm"][List /@ lsActualEquations]
1gymf7m70fgyh
1gymf7m70fgyh
lsActualEquations = 
  ModelNDSolveEquations[modelSEI2HREcon, modelSEI2HREcon["RateRules"]];
ResourceFunction["GridTableForm"][List /@ lsActualEquations]
1avljj6kz4oeo
1avljj6kz4oeo

Simulation

Instead of using ParametricNDSolve as in [AA4] in this notebook we use ModelNDSolve and SetRateRules from the package [AAp4].

Different quarantine starts

Here we compute simulation solutions for a set of quarantine starts:

AbsoluteTiming[
 aVarSolutions =
   Association@
    Map[
     Function[{qsdVar},
      qsdVar -> 
       Association[
        ModelNDSolve[
          SetRateRules[
           modelSEI2HREcon, <|ql -> 56, qsd -> qsdVar|>], {t, 365}][[
         1]]]
      ],
     Range[40, 120, 20]
     ];
 ]

(*{0.366168, Null}*)

Here we plot the results for ISSP only:

SeedRandom[2532]
aVals = #[ISSP][Range[0, 365]] & /@ aVarSolutions;
ListLinePlot[
 KeyValueMap[
  Callout[Tooltip[#2, #1], #1, {If[#1 <= 70, 
      RandomInteger[{120, 200}], RandomInteger[{80, 110}]], Above}] &,
   aVals], PlotLegends -> 
  SwatchLegend[Keys[aVals], LegendLabel -> "Quarantine start"], 
 PlotRange -> All, ImageSize -> Large, 
 PlotLabel -> ISSP[t] /. modelSEI2HREcon["Stocks"]]
0idl7dzxetaox

Remark: We use the code in this section to do the computations in the section “Sensitivity Analysis”.

Interactive interface

Using the interface in this section we can interactively see the effects of changing parameters. (This interface is programmed without using parametrized NDSolve solutions in order to be have code that corresponds to the interface implementations in [AAr2].)

opts = {PlotRange -> All, PlotLegends -> None, 
   PlotTheme -> "Detailed", PerformanceGoal -> "Speed", 
   ImageSize -> 400};
lsPopulationKeys = {TP, SP, EP, ISSP, INSP, HP, RP, DIP, HB};
lsSuppliesKeys = {MS, MSD, HMS};
lsMoneyKeys = {MHS, MLP, MMSP};
Manipulate[
 DynamicModule[{modelLocal = modelSEI2HREcon, 
   aStocks = modelSEI2HREcon["Stocks"], aSolLocal = aParSol, 
   lsPopulationPlots, lsMoneyPlots, lsSuppliesPlots},
  
  modelLocal = 
   SetRateRules[
    modelLocal, <|aincp -> aincpM, aip -> aipM, 
     sspf[SP] -> sspfM, \[Beta][HP] -> crhpM, qsd -> qsdM, ql -> qlM, 
     qcrf -> qcrfM, nhbr[TP] -> nhbrM/1000, 
     nhbcr[ISSP, ISNP] -> nhbcrM, mspr[HB] -> msprM, 
     msdp[HB] -> msdpM|>];
  aSolLocal = Association[ModelNDSolve[modelLocal, {t, ndays}][[1]]];
  
  lsPopulationPlots =
   Quiet@ParametricSolutionsPlots[
     aStocks,
     KeyTake[aSolLocal, 
      Intersection[lsPopulationKeys, displayPopulationStocks]],
     None, ndays,
     "LogPlot" -> popLogPlotQ, "Together" -> popTogetherQ, 
     "Derivatives" -> popDerivativesQ, 
     "DerivativePrefix" -> "\[CapitalDelta]", opts, 
     Epilog -> {Gray, Dashed, 
       Line[{{qsdM, 0}, {qsdM, 1.5*population}}], 
       Line[{{qsdM + qlM, 0}, {qsdM + qlM, 1.5*population}}]}];
  
  lsSuppliesPlots =
   If[Length[
      KeyDrop[aSolLocal, Join[lsPopulationKeys, lsMoneyKeys]]] == 
     0, {},
    (*ELSE*)
    Quiet@ParametricSolutionsPlots[
      aStocks,
      KeyTake[KeyDrop[aSolLocal, Join[lsPopulationKeys, lsMoneyKeys]],
        displaySupplyStocks],
      None, ndays,
      "LogPlot" -> supplLogPlotQ, "Together" -> supplTogetherQ, 
      "Derivatives" -> supplDerivativesQ, 
      "DerivativePrefix" -> "\[CapitalDelta]", opts]
    ];
  
  lsMoneyPlots =
   Quiet@ParametricSolutionsPlots[
     aStocks,
     KeyTake[aSolLocal, Intersection[lsMoneyKeys, displayMoneyStocks]],
     None, ndays,
     "LogPlot" -> moneyLogPlotQ, "Together" -> moneyTogetherQ, 
     "Derivatives" -> moneyDerivativesQ, 
     "DerivativePrefix" -> "\[CapitalDelta]", opts];
  
  Multicolumn[Join[lsPopulationPlots, lsSuppliesPlots, lsMoneyPlots], 
   nPlotColumns, Dividers -> All, FrameStyle -> GrayLevel[0.8]],
  SaveDefinitions -> True
  ],
 {{ndays, 365, "Number of days"}, 1, 365, 1, Appearance -> {"Open"}},
 Delimiter,
 {{aincpM, 6., "Average incubation period (days)"}, 1, 60., 1, 
  Appearance -> {"Open"}},
 {{aipM, 21., "Average infectious period (days)"}, 1, 60., 1, 
  Appearance -> {"Open"}},
 {{sspfM, 0.2, "Severely symptomatic population fraction"}, 0, 1, 
  0.025, Appearance -> {"Open"}},
 {{crhpM, 0.1, "Contact rate of the hospitalized population"}, 0, 30, 
  0.1, Appearance -> {"Open"}},
 Delimiter,
 {{qsdM, 55, "Quarantine start days"}, 0, 365, 1, 
  Appearance -> {"Open"}},
 {{qlM, 8*7, "Quarantine length (in days)"}, 0, 120, 1, 
  Appearance -> {"Open"}},
 {{qcrfM, 0.25, "Quarantine contact rate fraction"}, 0, 1, 0.01, 
  Appearance -> {"Open"}},
 Delimiter,
 {{nhbrM, 2.9, "Number of hospital beds rate (per 1000 people)"}, 0, 
  100, 0.1, Appearance -> {"Open"}},
 {{nhbcrM, 0, "Number of hospital beds change rate"}, -0.5, 0.5, 
  0.001, Appearance -> {"Open"}},
 {{msprM, 200, "Medical supplies production rate"}, 0, 50000, 10, 
  Appearance -> {"Open"}},
 {{msdpM, 1.2, "Medical supplies delivery period"}, 0, 10, 0.1, 
  Appearance -> {"Open"}},
 Delimiter,
 {{displayPopulationStocks, lsPopulationKeys, 
   "Population stocks to display:"}, lsPopulationKeys, 
  ControlType -> TogglerBar},
 {{popTogetherQ, True, "Plot populations together"}, {False, True}},
 {{popDerivativesQ, False, "Plot populations derivatives"}, {False, 
   True}},
 {{popLogPlotQ, False, "LogPlot populations"}, {False, True}},
 Delimiter,
 {{displaySupplyStocks, lsSuppliesKeys, 
   "Supplies stocks to display:"}, lsSuppliesKeys, 
  ControlType -> TogglerBar},
 {{supplTogetherQ, True, "Plot supplies functions together"}, {False, 
   True}},
 {{supplDerivativesQ, False, 
   "Plot supplies functions derivatives"}, {False, True}},
 {{supplLogPlotQ, True, "LogPlot supplies functions"}, {False, 
   True}},
 Delimiter,
 {{displayMoneyStocks, lsMoneyKeys, "Money stocks to display:"}, 
  lsMoneyKeys, ControlType -> TogglerBar},
 {{moneyTogetherQ, True, "Plot money functions together"}, {False, 
   True}},
 {{moneyDerivativesQ, False, 
   "Plot money functions derivatives"}, {False, True}},
 {{moneyLogPlotQ, True, "LogPlot money functions"}, {False, True}},
 {{nPlotColumns, 1, "Number of plot columns"}, Range[5]},
 ControlPlacement -> Left, ContinuousAction -> False]
1nbd62e0zn26p

Sensitivity analysis

When making and using this kind of dynamics models it is important to see how the solutions react to changes of different parameters. For example, we should try to find answers to questions like “What ranges of which parameters bring dramatic changes into important stocks?”

Sensitivity Analysis (SA) is used to determine how sensitive is a SD model to changes of the parameters and to changes of model’s equations, [BC1]. More specifically, parameter sensitivity, which we apply below, allows us to see the changes of stocks dynamic behaviour for different sequences (and combinations) of parameter values.

Remark: This section to mirrors to a point the section with same name in [AA4], except in this notebook we are more interested in medical supplies related SA because quarantine related SA is done in [AA4].

Remark: SA shown below should be done for other stocks and rates. In order to keep this exposition short we focus on ISSP, DIP, and HP. Also, it is interesting to think in terms of “3D parameter sensitivity plots.” We also do such plots.

Evaluations by Area under the curve

For certain stocks we might be not just interested in their evolution in time but also in their cumulative values. I.e. we are interested in the so called Area Under the Curve (AUC) metric for those stocks.

There are three ways to calculate AUC for stocks of interest:

  1. Add aggregation equations in the system of ODE’s. (Similar to the stock DIP in SEI2HR.)
    • For example, in order to compute AUC for ISSP we can add to SEI2HR the equation:
(*aucISSP'[t] = ISSP[t]*)
- More details for such equation addition are given in [AA2].
  1. Apply NIntegrate over stocks solution functions.
  2. Apply Trapezoidal rule to stock solution function values over a certain time grid.

Below we use 1 and 3.

Variation of medical supplies delivery period

Here we calculate the solutions for a certain combination of capacities and rates:

AbsoluteTiming[
 aVarSolutions =
   Association@
    Map[
     Function[{msdpVar},
      model2 = SEI2HREconModel[t];
      model2 = 
       SetRateRules[
        model2, <|\[Kappa][MS] -> 10000, \[Kappa][HMS] -> 100, 
         mspr[HB] -> 100, msdp[HB] -> msdpVar|>];
      msdpVar -> Association[ModelNDSolve[model2, {t, 365}][[1]]]
      ],
     Union[Join[Range[0.2, 1, 0.2], Range[1, 3, 0.5]]]
     ];
 ]

(*{0.231634, Null}*)

As expected more frequent delivery results in fuller utilization of the non-occupied hospital beds:

SeedRandom[23532]
focusStock = HP;
aVals = #[focusStock][Range[0, 365]] & /@ aVarSolutions;
ListLinePlot[
 KeyValueMap[
  Callout[Tooltip[#2, #1], #1, {If[#1 < 1, RandomInteger[{120, 150}], 
      RandomInteger[{160, 260}]], Above}] &, aVals], 
 PlotLegends -> 
  SwatchLegend[Keys[aVals], 
   LegendLabel -> "Medical supplies\ndelivery period"], 
 PlotRange -> All, ImageSize -> Large, 
 PlotLabel -> focusStock[t] /. modelSEI2HREcon["Stocks"]]
0xacdbpxbv6yo

Here are the corresponding AUC values:

aAUCs = TrapezoidalRule[Transpose[{Range[0, 365], #}]] & /@ aVals;
ResourceFunction["GridTableForm"][aAUCs]
1a3d3me9wh6bh
BarChart[aAUCs, ChartLabels -> Keys[aAUCs], ColorFunction -> "Pastel",
  PlotLabel -> 
  Row[{focusStock[t] /. modelSEI2HREcon["Stocks"], Spacer[5], "AUC"}]]
1ncranm3ufw0h

Variation of medical supplies production rate

In order to demonstrate the effect of medical supplies production rate (mspr) it is beneficial to eliminate the hospital beds availability restriction – we assume that we have enough hospital beds for all infected severely symptomatic people.

Here we calculate the solutions for a certain combination of capacities and rates:

AbsoluteTiming[
 aVarSolutions =
   Association@
    Map[
     Function[{msprVar},
      model2 = SEI2HREconModel[t];
      model2 = 
       SetRateRules[
        model2, <|\[Kappa][MS] -> 100000, \[Kappa][HMS] -> 
          10000, \[Kappa][MSD] -> 1000, mspr[HB] -> msprVar, 
         msdp[HB] -> 1.5, mscr[ISSP] -> 0.2, mscr[TP] -> 0.001, 
         mscr[ISSP] -> 1, nhbr[TP] -> 100/1000|>];
      msprVar -> Association[ModelNDSolve[model2, {t, 365}][[1]]]
      ],
     {20, 60, 100, 200, 300, 1000, 10000}
     ];
 ]

(*{0.156794, Null}*)

Hospitalized Population

As expected we can see that with smaller production rates we get less hospitalized people:

SeedRandom[1232]
focusStock = HP;
aVals = #[focusStock][Range[0, 365]] & /@ aVarSolutions;
ListLinePlot[
 KeyValueMap[
  Callout[Tooltip[#2, #1], #1, {RandomInteger[{180, 240}], Above}] &, 
  aVals], PlotLegends -> 
  SwatchLegend[Keys[aVals], 
   LegendLabel -> "Medical supplies\nproduction rate"], 
 PlotRange -> All, ImageSize -> Large, 
 PlotLabel -> focusStock[t] /. modelSEI2HREcon["Stocks"]]
0vxim0nbznmmi

Here are the corresponding AUC values:

aAUCs = TrapezoidalRule[Transpose[{Range[0, 365], #}]] & /@ aVals;
ResourceFunction["GridTableForm"][aAUCs]
07nfkyx6s9mjo
BarChart[aAUCs, ChartLabels -> Keys[aAUCs], ColorFunction -> "Pastel",
  PlotLabel -> 
  Row[{focusStock[t] /. modelSEI2HREcon["Stocks"], Spacer[5], "AUC"}]]
08xdwgkj6ljeh

Medical Supplies

Here we plot the availability of MS at MS producer’s storage:

SeedRandom[821]
focusStock = MS;
aVals = #[MS][Range[0, 365]] & /@ aVarSolutions;
ListLinePlot[
 KeyValueMap[
  Callout[Tooltip[#2, #1], #1, {RandomInteger[{100, 160}], Above}] &, 
  aVals], PlotLegends -> 
  SwatchLegend[Keys[aVals], 
   LegendLabel -> "Medical supplies\nproduction rate"], 
 PlotRange -> All, ImageSize -> Large, 
 PlotLabel -> focusStock[t] /. modelSEI2HREcon["Stocks"]]
05il7vfu2msga

Here are the corresponding AUC values:

aAUCs = TrapezoidalRule[Transpose[{Range[0, 365], #}]] & /@ aVals;
ResourceFunction["GridTableForm"][aAUCs]
03yccn85qjh1a
BarChart[aAUCs, 
 ChartLabels -> Map[Rotate[ToString[#], \[Pi]/6] &, Keys[aAUCs]], 
 ColorFunction -> "Pastel", 
 PlotLabel -> 
  Row[{focusStock[t] /. modelSEI2HREcon["Stocks"], Spacer[5], "AUC"}],
  ImageSize -> Medium]
0z5dthm5iuod6

Variation of delivery disruption starts

Here we compute simulation solutions for a set of delivery disruption starts using disruption length of 7 days and disruption “slowing down” factor 2:

AbsoluteTiming[
 aVarSolutions =
   Association@
    Map[
     Function[{ddsVar},
      ddsVar -> 
       Association[
        ModelNDSolve[
          SetRateRules[
           modelSEI2HREcon, <|\[Kappa][MS] -> 100000, \[Kappa][HMS] ->
              1000, mspr[HB] -> 100, ql -> 56, qsd -> 60, 
            nhbr[TP] -> 3/1000, dbp -> 1, dds -> ddsVar, ddl -> 7, 
            dsf -> 2|>], {t, 365}][[1]]]
      ],
     Append[Range[40, 120, 20], 365]
     ];
 ]

(*{0.45243, Null}*)

Note, that disruption start at day 365 means no disruption. Also, we use three hospital beds per thousand people.

Here we plot the results for HP only:

SeedRandom[009]
focusStock = HP;
aVals = #[focusStock][Range[0, 365]] & /@ aVarSolutions;
ListLinePlot[
 KeyValueMap[
  Callout[Tooltip[#2, #1], #1, {RandomInteger[{60, 140}], Bottom}] &, 
  aVals], PlotLegends -> 
  SwatchLegend[Keys[aVals], 
   LegendLabel -> "Medical supplies\ndisruption start"], 
 PlotRange -> All, ImageSize -> Large, 
 PlotLabel -> focusStock[t] /. modelSEI2HREcon["Stocks"]]
1sdi97njh54gj
1sdi97njh54gj

Here are the corresponding AUC values:

aAUCs = TrapezoidalRule[Transpose[{Range[0, 365], #}]] & /@ aVals;
ResourceFunction["GridTableForm"][aAUCs]
0s1zcqcmvxbrs
0s1zcqcmvxbrs
BarChart[aAUCs, 
 ChartLabels -> Map[Rotate[ToString[#], \[Pi]/6] &, Keys[aAUCs]], 
 ColorFunction -> "Pastel", 
 PlotLabel -> 
  Row[{focusStock[t] /. modelSEI2HREcon["Stocks"], Spacer[5], "AUC"}],
  ImageSize -> Medium]
0vq0berxbjf9v

Combined variability of delivery start and disruption

Here we calculate the solutions for a set of combinations of delivery periods and delivery disruption starts:

AbsoluteTiming[
 aVarSolutions =
   Association@
    Map[
     Function[{par},
      model2 = modelSEI2HREcon;
      model2 = 
       SetRateRules[
        model2, <|\[Kappa][MS] -> 100000, \[Kappa][HMS] -> 10000, 
         mspr[HB] -> 1000, dbp -> par[[1]], dds -> par[[2]], ddl -> 7,
          dsf -> 4, nhbr[TP] -> 3/1000|>];
      par -> Association[ModelNDSolve[model2, {t, 365}][[1]]]
      ],
     Flatten[Outer[List, {0.5, 1, 1.5}, {60, 100, 365}], 1]
     ];
 ]

(*{0.759922, Null}*)

As expected more frequent, less disrupted delivery brings fuller utilization of the non-occupied hospital beds:

SeedRandom[3233]
focusStock = HP;
aVals = #[focusStock][Range[0, 365]] & /@ aVarSolutions;
ListLinePlot[
 KeyValueMap[
  Callout[Tooltip[#2, ToString[#1]], 
    ToString[#1], {RandomInteger[{60, 160}], Left}] &, aVals], 
 PlotLegends -> 
  SwatchLegend[ToString /@ Keys[aVals], 
   LegendLabel -> 
    "Medical supplies\ndelivery period & disruption start"], 
 PlotRange -> All, ImageSize -> Large, 
 PlotLabel -> focusStock[t] /. modelSEI2HREcon["Stocks"]]
1qqm9hcj40qmx
1qqm9hcj40qmx

Here are the corresponding AUC values:

aAUCs = TrapezoidalRule[Transpose[{Range[0, 365], #}]] & /@ aVals;
ResourceFunction["GridTableForm"][aAUCs]
19kpmr551tt1c
19kpmr551tt1c
BarChart[aAUCs, 
 ChartLabels -> Map[Rotate[ToString[#], \[Pi]/6] &, Keys[aAUCs]], 
 ColorFunction -> "Pastel", 
 PlotLabel -> 
  Row[{focusStock[t] /. modelSEI2HREcon["Stocks"], Spacer[5], "AUC"}],
  ImageSize -> Medium]
1ia6ik6cr7kg5
1ia6ik6cr7kg5
SeedRandom[3233]
focusStock = DIP;
aVals = #[focusStock][Range[0, 365]] & /@ aVarSolutions;
ListLinePlot[
 KeyValueMap[
  Callout[Tooltip[#2, ToString[#1]], 
    ToString[#1], {RandomInteger[{60, 160}], Left}] &, aVals], 
 PlotLegends -> 
  SwatchLegend[ToString /@ Keys[aVals], 
   LegendLabel -> 
    "Medical supplies\ndelivery period & disruption start"], 
 PlotRange -> All, ImageSize -> Large, 
 PlotLabel -> focusStock[t] /. modelSEI2HREcon["Stocks"]]
0xwdkry34kcfq
0xwdkry34kcfq
ResourceFunction["GridTableForm"][Last /@ aVals]
1u293ap7k53o5
1u293ap7k53o5
BarChart[Last /@ aVals, 
 ChartLabels -> Map[Rotate[ToString[#], \[Pi]/6] &, Keys[aAUCs]], 
 ColorFunction -> "Pastel", 
 PlotLabel -> "Deceased Population at day 365", ImageSize -> Medium]
0m5va3qv461nx
0m5va3qv461nx

References

Articles

[Wk1] Wikipedia entry, “Compartmental models in epidemiology”.

[Wl2] Wikipedia entry, “Coronavirus disease 2019”.

[HH1] Herbert W. Hethcote (2000). “The Mathematics of Infectious Diseases”. SIAM Review. 42 (4): 599–653. Bibcode:2000SIAMR..42..599H. doi:10.1137/s0036144500371907.

[BC1] Lucia Breierova, Mark Choudhari, An Introduction to Sensitivity Analysis, (1996), Massachusetts Institute of Technology.

[AA1] Anton Antonov, “Coronavirus propagation modeling considerations”, (2020), SystemModeling at GitHub.

[AA2] Anton Antonov, “Basic experiments workflow for simple epidemiological models”, (2020), SystemModeling at GitHub.

[AA3] Anton Antonov, “Scaling of Epidemiology Models with Multi-site Compartments”, (2020), SystemModeling at GitHub.

[AA4] Anton Antonov, “SEI2HR model with quarantine scenarios”, (2020), SystemModeling at GitHub.

Repositories, packages

[WRI1] Wolfram Research, Inc., “Epidemic Data for Novel Coronavirus COVID-19”, WolframCloud.

[AAr1] Anton Antonov, Coronavirus propagation dynamics project, (2020), SystemModeling at GitHub.

[AAr2] Anton Antonov, “Epidemiology Compartmental Modeling Monad in R”, (2020), ECMon-R at GitHub.

[AAp1] Anton Antonov, “Epidemiology models Mathematica package”, (2020), SystemModeling at GitHub.

[AAp2] Anton Antonov, “Epidemiology models modifications Mathematica package”, (2020), SystemModeling at GitHub.

[AAp3] Anton Antonov, “Epidemiology modeling visualization functions Mathematica package”, (2020), SystemModeling at GitHub.

[AAp4] Anton Antonov, “Epidemiology modeling simulation functions Mathematica package”, (2020), SystemModeling at GitHub.

[AAp5] Anton Antonov, “System dynamics interactive interfaces functions Mathematica package”, (2020), SystemsModeling at GitHub.

SEI2HR model with quarantine scenarios

Introduction

The epidemiology compartmental model, [Wk1], presented in this notebook – SEI2HR – deals with the left-most and middle rectangles in this diagram:

0y1f7ckbmwf5i
0y1f7ckbmwf5i

“SEI2HR” stands for “Susceptible, Exposed, Infected two, Hospitalized, Recovered” (populations.)

In this notebook we also deal with quarantine scenarios.

Remark: We consider the contagious disease propagation models as instances of the more general System Dynamics (SD) models. We use SD terminology in this notebook.

The models

SEI2R

The model SEI2R are introduced and explained in the notebook [AA2]. SEI2R differs from the classical SEIR model , [Wk1, HH1], with the following elements:

  1. Two separate infected populations: one is “severely symptomatic”, the other is “normally symptomatic”
  2. The monetary equivalent of lost productivity due to infected or died people is tracked.

SEI2HR

For the formulation of SEI2HR we use a system of Differential Algebraic Equations (DAE’s). The package [AAp1] allows the use of a formulation that has just Ordinary Differential Equations (ODE’s).

Here are the unique features of SEI2HR:

  • People stocks
    • Two types of infected populations: normally symptomatic and severely symptomatic
    • Hospitalized population
    • Deceased from infection population
  • Hospital beds
    • Hospital beds are a limited resource that determines the number of hospitalized people
    • Only severely symptomatic people are hospitalized according to the available hospital beds
    • The hospital beds stock is not assumed constant, it has its own change rate.
  • Money stocks
    • The money from lost productivity are tracked
    • The money for hospital services are tracked

SEI2HR’s place a development plan

This graph shows the “big picture” of the model development plan undertaken in [AAr1] and SEI2HR (discussed in this notebook) is in that graph:

1cg8j8gglqwi1
1cg8j8gglqwi1

Notebook structure

The rest of notebook has the following sequence of sections:

  • Package load section
  • SEI2HR structure in comparison of SEI2R
  • Explanations of the equations of SEI2HR
  • Quarantine scenario modeling preparation
  • Parameters and initial conditions setup
    • Populations, hospital beds, quarantine scenarios
  • Parametric simulation solution
  • Interactive interface
  • Sensitivity analysis

Load packages

The epidemiological models framework used in this notebook is implemented with the packages [AAp1, AAp2, AA3]; many of the plot functions are from the package [AAp4].

SEI2HR extends SEI2R

The model SEI2HR is an extension of the model SEI2R, [AA2].

Here is SEI2R:

0een3ni1vr18e
0een3ni1vr18e

Here is SEI2HR:

0dsi0svozimcl
0dsi0svozimcl

Here are the “differences” between the two models:

0h6b6x7di5e05
0h6b6x7di5e05

Equations explanations

In this section we provide rationale of the model equations of SEI2HR.

The equations for Susceptible, Exposed, Infected, Recovered populations of SEI2R are “standard” and explanations about them are found in [WK1, HH1]. For SEI2HR those equations change because of the stocks Hospitalized Population and Hospital Beds.

The equations time unit is one day. The time horizon is one year. Since we target COVID-19, [Wk2, AA1], we do not consider births.

Remark: For convenient reading the equations in this section have tooltips for the involved stocks and rates.

Verbalization description of the model

We start with one infected (normally symptomatic) person, the rest of the people are susceptible. The infected people meet other people directly or get in contact with them indirectly. (Say, susceptible people touch things touched by infected.) For each susceptible person there is a probability to get the decease. The decease has an incubation period: before becoming infected the susceptible are (merely) exposed. The infected recover after a certain average infection period or die. A certain fraction of the infected become severely symptomatic. If there are enough hospital beds the severely symptomatic infected are hospitalized. The hospitalized severely infected have different death rate than the non-hospitalized ones. The number of hospital beds might change: hospitals are extended, new hospitals are build, or there are not enough medical personnel or supplies. The deaths from infection are tracked (accumulated.) Money for hospital services and money from lost productivity are tracked (accumulated.)

The equations below give mathematical interpretation of the model description above.

Code for the equations

Each equation in this section are derived with code like this:

and then the output cell is edited to be “DisplayFormula” and have CellLabel value corresponding to the stock of interest.

The infected and hospitalized populations

SEI2HR has two types of infected populations: a normally symptomatic one and a severely symptomatic one. A major assumption for SEI2HR is that only the severely symptomatic people are hospitalized. (That assumption is also reflected in the diagram in the introduction.)

Each of those three populations have their own contact rates and mortality rates.

Here are the contact rates from the SEI2HR dictionary

0ooy1eklv8ies
0ooy1eklv8ies

Here are the mortality rates from the SEI2HR dictionary

0kskzm0nsvjo3
0kskzm0nsvjo3

Remark: Below with “Infected Population” we mean both stocks Infected Normally Symptomatic Population (INSP) and Infected Severely Symptomatic Population (ISSP).

Total Population

In this notebook we consider a DAE’s formulation of SEI2HR. The stock Total Population has the following (obvious) algebraic equation:

0peb290e1lx2d
0peb290e1lx2d

Note that with Max we specified that the total population cannot be less than 0.

Remark: As mentioned in the introduction, the package [AAp1] allows for the use of non-algebraic formulation, without an equation for TP.

Susceptible Population

The stock Susceptible Population (SP) is decreased by (1) infections derived from stocks Infected Populations and Hospitalized Population (HP), and (2) morality cases derived with the typical mortality rate.

0h1zwgod2xs4g
0h1zwgod2xs4g

Because we hospitalize the severely infected people only instead of the term

09xmdu8xq7e0p
09xmdu8xq7e0p

we have the terms

0dkc6td55qv7p
0dkc6td55qv7p

The first term is for the infections derived from the hospitalized population. The second term for the infections derived from people who are infected severely symptomatic and not hospitalized.

Births term

Note that we do not consider in this notebook births, but the births term can be included in SP’s equation:

0ny25blzp2rub
0ny25blzp2rub

The births rate is the same as the death rate, but it can be programmatically changed. (See [AAp2].)

Exposed Population

The stock Exposed Population (EP) is increased by (1) infections derived from the stocks Infected Populations and Hospitalized Population, and (2) mortality cases derived with the typical mortality rate. EP is decreased by (1) the people who after a certain average incubation period (aincp) become ill, and (2) mortality cases derived with the typical mortality rate.

0mrj0gt13ppsn
0mrj0gt13ppsn

Infected Normally Symptomatic Population

INSP is increased by a fraction of the people who have been exposed. That fraction is derived with the parameter severely symptomatic population fraction (sspf). INSP is decreased by (1) the people who recover after a certain average infection period (aip), and (2) the normally symptomatic people who die from the disease.

0hy96yb7pg654
0hy96yb7pg654

Infected Severely Symptomatic Population

ISSP is increased by a fraction of the people who have been exposed. That fraction is corresponds to the parameter severely symptomatic population fraction (sspf). ISSP is decreased by (1) the people who recover after a certain average infection period (aip), (2) the hospitalized severely symptomatic people who die from the disease, and (3) the non-hospitalized severely symptomatic people who die from the disease.

19hml5ravi0a8
19hml5ravi0a8

Note that we do not assume that severely symptomatic people recover faster if they are hospitalized, only that they have a different death rate.

Hospitalized Population

The amount of people that can be hospitalized is determined by the available Hospital Beds (HB) – the stock Hospitalized Population (HP) is subject to a resource limitation by the stock HB.

The equation of the stock HP can be easily understood from the following dynamics description points:

  • If the number of hospitalized people is less that the number of hospital beds we hospitalize the new ISSP people.
  • If the new ISSP people are more than the Available Hospital Beds (AHB) we take as many as AHB.
  • Hospitalized people have the same average infection period (aip).
  • Hospitalized (severely symptomatic) people have their own mortality rate.
0ippnyp2hf90k
0ippnyp2hf90k

Note that although we know that in a given day some hospital beds are going to be freed they are not considered in the hospitalization plans for that day.

Recovered Population

The stock Recovered Population (RP) is increased by the recovered infected people and decreased by mortality cases derived with the typical mortality rate.

042iy3oy8o454
042iy3oy8o454

Deceased Infected Population

The stock Deceased Infected Population (DIP) accumulates the deaths of the people who are infected. Note that we utilize the different death rates for HP and ISSP.

1glekhgj1v0e7
1glekhgj1v0e7

Hospital Beds

The stock Hospital Beds (HB) can change with a rate that reflects the number of hospital beds change rate (nhbcr) per day. Generally speaking, using nhbcr we can capture scenarios, like, extending hospitals, building new hospitals, recruitment of new medical personnel, loss of medical personnel (due to infections.)

1is45mamhsayd
1is45mamhsayd

Money for Hospital Services

The stock Money for Hospital Services (MHS) simply tracks expenses for hospitalized people. The parameter hospital services cost rate (hscr) with unit money per bed per day simply multiplies HP.

0evzoim1tjwsj
0evzoim1tjwsj

Money from Lost Productivity

The stock Money from Lost Productivity (MLP) simply tracks the work non-availability of the infected and died from infection people. The parameter lost productivity cost rate (lpcr) with unit money per person per day multiplies the total count of the infected and dead from infection.

1133o7bm975sr
1133o7bm975sr

Quarantine scenarios

In order to model quarantine scenarios we use piecewise constant functions for the contact rates \beta [\text{ISSP}] and \beta [\text{INSP}].

Remark: Other functions can be used, like, functions derived through some statistical fitting.

Here is an example plot :

0gtvprtffih1o
0gtvprtffih1o

To model quarantine with a piecewise constant function we use the following parameters:

  • \text{qsd} for quarantine’s start
  • \text{ql} for quarantines duration
  • \text{qcrf} for the effect on the quarantine on the contact rate

Parameters and actual simulation equations code

Here are the parameters we want to experiment with (or do calibration with):

Here we set custom rates and initial conditions:

Remark: Note the piecewise functions for \beta [\text{ISSP}] and \beta [\text{INSP}].

Here is the system of ODE’s we use to do parametrized simulations:

0i35a50x9mdtq
0i35a50x9mdtq

Simulation

Solutions

Straightforward simulation for one year using ParametricNDSolve :

Example evaluation

Here are the parameters of a stock solution:

Here we replace the parameters with concrete rate values (kept in the model object):

0m3ccwuzjtg7d
0m3ccwuzjtg7d

Here is an example evaluation of a solution using the parameter values above:

Interactive interface

Using the interface in this section we can interactively see the effects of changing the focus parameters.

opts = {PlotRange -> All, PlotLegends -> None, 
   PlotTheme -> "Detailed", PerformanceGoal -> "Speed", 
   ImageSize -> 400};
lsPopulationKeys = {TP, SP, EP, ISSP, INSP, HP, RP, DIP, HB};
lsEconKeys = {MHS, MLP};
Manipulate[
 DynamicModule[{lsPopulationPlots, lsEconPlots, lsRestPlots},
  
  lsPopulationPlots =
   ParametricSolutionsPlots[
    modelSEI2HR["Stocks"],
    KeyTake[aSol, Intersection[lsPopulationKeys, displayStocks]],
    {aincp, aip, spf, crhp, qsd, ql, qcrf, nhbcr, nhbr/1000}, ndays,
    "LogPlot" -> popLogPlotQ, "Together" -> popTogetherQ, 
    "Derivatives" -> popDerivativesQ, 
    "DerivativePrefix" -> "\[CapitalDelta]", opts];
  
  lsEconPlots =
   ParametricSolutionsPlots[
    modelSEI2HR["Stocks"],
    KeyTake[aSol, Intersection[lsEconKeys, displayStocks]],
    {aincp, aip, spf, crhp, qsd, ql, qcrf, nhbcr, nhbr/1000}, ndays,
    "LogPlot" -> econLogPlotQ, "Together" -> econTogetherQ, 
    "Derivatives" -> econDerivativesQ, 
    "DerivativePrefix" -> "\[CapitalDelta]", opts];
  
  lsRestPlots =
   If[Length[KeyDrop[aSol, Join[lsPopulationKeys, lsEconKeys]]] == 
     0, {},
    (*ELSE*)
    ParametricSolutionsPlots[
     modelSEI2HR["Stocks"],
     KeyTake[KeyDrop[aSol, Join[lsPopulationKeys, lsEconKeys]], 
      displayStocks],
     {aincp, aip, spf, crhp, qsd, ql, qcrf, nhbcr, nhbr/1000}, ndays,
     "LogPlot" -> econLogPlotQ, "Together" -> econTogetherQ, 
     "Derivatives" -> econDerivativesQ, 
     "DerivativePrefix" -> "\[CapitalDelta]", opts]
    ];
  
  Multicolumn[Join[lsPopulationPlots, lsEconPlots, lsRestPlots], 
   nPlotColumns, Dividers -> All, FrameStyle -> GrayLevel[0.8]]
  ],
 {{displayStocks, Join[lsPopulationKeys, lsEconKeys], 
   "Stocks to display:"}, Join[lsPopulationKeys, lsEconKeys], 
  ControlType -> TogglerBar},
 {{aincp, 6., "Average incubation period (days)"}, 1, 60., 1, 
  Appearance -> {"Open"}},
 {{aip, 21., "Average infectious period (days)"}, 1, 60., 1, 
  Appearance -> {"Open"}},
 {{spf, 0.2, "Severely symptomatic population fraction"}, 0, 1, 0.025,
   Appearance -> {"Open"}},
 {{qsd, 65, "Quarantine start days"}, 0, 365, 0.01, 
  Appearance -> {"Open"}},
 {{ql, 8*7, "Quarantine length (in days)"}, 0, 120, 1, 
  Appearance -> {"Open"}},
 {{qcrf, 0.25, "Quarantine contact rate fraction"}, 0, 1, 0.01, 
  Appearance -> {"Open"}},
 {{crhp, 0.1, "Contact rate of the hospitalized population"}, 0, 30, 
  0.1, Appearance -> {"Open"}},
 {{nhbcr, 0, "Number of hospital beds change rate"}, -0.5, 0.5, 0.001,
   Appearance -> {"Open"}},
 {{nhbr, 2.9, "Number of hospital beds rate (per 1000 people)"}, 0, 
  100, 0.1, Appearance -> {"Open"}},
 {{ndays, 365, "Number of days"}, 1, 365, 1, Appearance -> {"Open"}},
 {{popTogetherQ, True, "Plot populations together"}, {False, True}},
 {{popDerivativesQ, False, "Plot populations derivatives"}, {False, 
   True}},
 {{popLogPlotQ, False, "LogPlot populations"}, {False, True}},
 {{econTogetherQ, True, "Plot economics functions together"}, {False, 
   True}},
 {{econDerivativesQ, False, 
   "Plot economics functions derivatives"}, {False, True}},
 {{econLogPlotQ, True, "LogPlot economics functions"}, {False, 
   True}},
 {{nPlotColumns, 1, "Number of plot columns"}, Range[5]},
 ControlPlacement -> Left, ContinuousAction -> False]
1su0ilr7pjpgz
1su0ilr7pjpgz

Sensitivity analysis

When making and using this kind of dynamics models it is important to see how the solutions react to changes of different parameters. For example, we should try to find answers to questions like “What ranges of which parameters bring dramatic changes into important stocks?”

Sensitivity analysis is used to determine how sensitive is a SD model to changes of the parameters and to changes of model’s equations, [BC1]. More specifically, parameter sensitivity, which we apply below, allows us to see the changes of stocks dynamic behaviour for different sequences (and combinations) of parameter values.

Remark: The sensitivity analysis shown below should be done for other stocks and rates. In order to keep this exposition short we focus on ISSP, DIP, and HP.

It is interesting to think in terms of “3D parameter sensitivity plots.” We also do such plots.

Evaluations by Area under the curve

For certain stocks we might be not just interested in their evolution in time but also in their cumulative values. I.e. we are interested in the so called Area Under the Curve (AUC) metric for those stocks.

There are three ways to calculate AUC for stocks of interest:

  1. Add aggregation equations in the system of ODE’s. (Similar to the stock DIP in SEI2HR.)
    • For example, in order to compute AUC for ISSP we can add to SEI2HR the equation:
(*aucISSP'[t] = ISSP[t]*)
- More details for such equation addition are given in [AA2].
  1. Apply NIntegrate over stocks solution functions.
  2. Apply Trapezoidal rule to stock solution function values over a certain time grid.

Below we use 1 and 3.

Remark: The AUC measure for a stock is indicated with the prefix “∫”. For example AUC for ISSP is marked with “∫ISSP”.

Ranges

Below we use the following sets of quarantine starts and quarantine durations.

Note that putting the quarantine start to be at day 365 means “no quarantine.”

Number of infected people

Quarantine starts sensitivity

13ewmnrwebn37
13ewmnrwebn37

Note that the plots and tabulated differences with “no quarantine” indicate that there is a very narrow range to choose an effective quarantine start.

Quarantine duration sensitivity

0jgocyy3n73g1
0jgocyy3n73g1

Number of deceased people

Quarantine starts sensitivity

0upvp860txpwb
0upvp860txpwb

Number of hospitalized people

Quarantine starts sensitivity

0jtq60dibh8ns
0jtq60dibh8ns

Infected Severely Symptomatic Population stock integral with respect to quarantine start and length

In this section the 3D plot of AUC of ISSP is calculated using Trapezoidal rule.

1pm82rs4erlsy
1pm82rs4erlsy

Deceased Infected Population stock with respect to quarantine start and length

We can see from SEI2HR’s equations that DIP is already an AUC type of value. We can just plot the DIP values at the time horizon (one year.)

1mtkajep4247q
1mtkajep4247q

Hospitalized Population stock integral with respect to quarantine start and length

In this section the 3D plot of AUC of HP is calculated using Trapezoidal rule.

16mnmktwxtv14
16mnmktwxtv14

References

Articles

[Wk1] Wikipedia entry, “Compartmental models in epidemiology”.

[Wl2] Wikipedia entry, “Coronavirus disease 2019”.

[HH1] Herbert W. Hethcote (2000). “The Mathematics of Infectious Diseases”. SIAM Review. 42 (4): 599–653. Bibcode:2000SIAMR..42..599H. doi:10.1137/s0036144500371907.

[BC1] Lucia Breierova, Mark Choudhari, An Introduction to Sensitivity Analysis, (1996), Massachusetts Institute of Technology.

[AA1] Anton Antonov, “Coronavirus propagation modeling considerations”, (2020), SystemModeling at GitHub.

[AA2] Anton Antonov, “Basic experiments workflow for simple epidemiological models”, (2020), SystemModeling at GitHub.

[AA3] Anton Antonov, “Scaling of Epidemiology Models with Multi-site Compartments”, (2020), SystemModeling at GitHub.

Repositories, packages

[WRI1] Wolfram Research, Inc., “Epidemic Data for Novel Coronavirus COVID-19”, WolframCloud.

[AAr1] Anton Antonov, Coronavirus propagation dynamics project, (2020), SystemModeling at GitHub.

[AAp1] Anton Antonov, “Epidemiology models Mathematica package”, (2020), SystemsModeling at GitHub.

[AAp2] Anton Antonov, “Epidemiology models modifications Mathematica package”, (2020), SystemsModeling at GitHub.

[AAp3] Anton Antonov, “Epidemiology modeling visualization functions Mathematica package”, (2020), SystemsModeling at GitHub.

[AAp4] Anton Antonov, “System dynamics interactive interfaces functions Mathematica package”, (2020), SystemsModeling at GitHub.

Project management files

[AAo1] Anton Antonov, WirVsVirus-Hackathon-work-plan.org, (2020), SystemsModeling at GitHub.

[AAo2] Anton Antonov, WirVsVirus-hackathon-Geo-spatial-temporal-model-mind-map, (2020), SystemsModeling at GitHub.

WirVsVirus 2020 hackathon participation

Introduction

Last weekend – 2020-03-20 ÷ 2020-03-22 – I participated in the (Germany-centric) hackathon WirVsVirus. (I friend of mine who lives in Germany asked me to team up and sign up.)

Our idea proposal was accepted, listed in the dedicated overview table (see item 806). The title of our hackathon project is:

“Geo-spatial-temporal Economic Model for COVID-19 Propagation and Management in Germany”

Nearly a dozen of people enlisted to help. (We communicated through Slack.)

13dzfagts8105

Multiple people helped with the discussion of ideas, directions where to find data, with actual data gathering, and related documented analysis. Of course, just discussing the proposed solutions was already a great help!

What was accomplished

Work plans

The following mind-map reflects pretty well what was planned and done:

15n5cjaej10q8

There is also a related org-mode file with the work plan.

Data

I obtained Germany city data with Mathematica’s build-in functions and used it to heuristically derive a traveling patterns graph, [AA1].

Here is the data:

Here is Geo-histogram of that data:

0t08vw1kjdzbc

We considered a fair amount of other data. But because of the time limitations of the hackathon we had to use only the one above.

Single-site models

During the development phase I used the model SEI2R, but since we wanted to have a “geo-spatial-temporal epidemiological economics model” I productized the implementation of SEI2HR-Econ, [AAp1].

Here are the stocks, rates, and equations of SEI2HR-Econ:

0tbp6de6zdez0

Multi-site SEI2R (SEI2HR-Econ) over a hexagonal grid graph

I managed to follow through with a large part of the work plan for the hackathon and make multi-site scaled model that “follows the money”, [AA1]. Here is a diagram that shows the travelling patterns graph and solutions at one of the nodes:

1vnygv6t7chgg

Here is (a snapshot of) an interactive interface for studying and investigating the solution results:

1pgmngb4uyuzb

For more details see the notebook [AA1]. Different parameters can be set in the “Parameters” section. Especially of interest are the quarantine related parameters: start, duration, effect on contact rates and traffic patterns.

I also put in that notebook code for exporting simulations results and programmed visualization routines in R, [AA2]. (In order other members of team to be able to explore the results.)

References

[DP1] 47_wirtschaftliche Auswirkung_Geo-spatial-temp-econ-modell, DevPost.

[WRI1] Wolfram Research, Inc., Germany city data records, (2020), SystemModeling at GitHub.

[AA1] Anton Antonov, “WirVsVirus hackathon multi-site SEI2R over a hexagonal grid graph”, (2020), SystemModeling at GitHub.

[AA2] Anton Antonov, “WirVsVirus-Hackathon in R”, (2020), SystemModeling at GitHub.

[AAp1] Anton Antonov, “Epidemiology models Mathematica package”, (2020), SystemsModeling at GitHub.

Scaling of epidemiology models with multi-site compartments

Version 1.0

Introduction

In this notebook we describe and exemplify an algorithm that allows the specification and execution geo-spatial-temporal simulations of infectious disease spreads. (Concrete implementations and examples are given.)

The assumptions of the typical compartmental epidemiological models do not apply for countries or cities that are non-uniformly populated. (For example, China, USA, Russia.) There is a need to derive epidemiological models that take into account the non-uniform distribution of populations and related traveling patterns within the area of interest.

Here is a visual aid (made with a random graph over the 30 largest cities of China):

1acjs15vamk0b
1acjs15vamk0b

In this notebook we show how to extend core, single-site epidemiological models into larger models for making spatial-temporal simulations. In the explanations and examples we use SEI2R, [AA2, AAp1], as a core epidemiological model, but other models can be adopted if they adhere to the model data structure of the package “EpidemiologyModels.m”, [AAp1].

From our experiments with we believe that the proposed multi-site extension algorithm gives a modeling ingredient that is hard emulate by other means within single-site models.

Definitions

Single-site: A geographical location (city, neighbourhood, campus) for which the assumptions of the classical compartmental epidemiological models hold.

Single site epidemiological model: A compartmental epidemiological model for a single site. Such model has a system of Ordinary Differential Equations (ODE’s) and site dependent initial conditions.

Multi-site area: An area comprised of multiple single sites with known traveling patterns between them. The area has a directed graph G with nodes that correspond to the sites and a positive matrix \text{\textit{tpm}}(G) for the traveling patterns between the sites.

Problem definition: Given (i) a single site epidemiological model M, (ii) a graph G connecting multiple sites, and (iii) a traveling patterns matrix \text{\textit{tpm}}(G) between the nodes of G derive an epidemiological model S(M,\text{\textit{tpm}}(G)) that simulates more adequately viral decease propagation over G.

Multi-Site Epidemiological Model Extension Algorithm (MSEMEA): An algorithm that derives from a given single site epidemiological model and multi-site area an epidemiological model that can be used to simulate the geo-spatial-temporal epidemics and infectious disease spreads. (The description of MSEMEA is the main message of this notebook.)

Load packages

The epidemiological models framework used in this notebook is implemented with the packages [AAp1, AAp2, AA3]; the interactive plots functions are from the package [AAp4].

Notebook structure

The section “General algorithm description” gives rationale and conceptual steps of MSEMEA.

The next two sections of the notebook follow the procedure outline using the SEI2R model as M, a simple graph with two nodes as G, and both constant and time-dependent matrices for \text{\textit{tpm}}(G).

The section “Constant traveling patterns over a grid graph” presents an important test case with a grid graph that we use to test and build confidence in MSEMEA. The sub-section “Observations” is especially of interest.

The section “Time-dependent traveling patterns over a random graph” presents a nearly “real life” application of MSEMEA using a random graph and a time dependent travelling patterns matrix.

The section “Money from lost productivity” shows how to track the money losses across the sites.

The last section “Future plans” outlines envisioned (immediate) extensions work presented in this notebook.

General algorithm description

In this section we describe a modeling approach that uses different mathematical modeling approaches for (i) the multi-site travelling patterns and (ii) the single-site disease spread interactions, and then (iii) unifies them into a common model.

Splitting and scaling

The traveling between large, densely populated cities is a very different process of the usual people mingling in those cities. The usual large, dense city mingling is assumed and used in the typical compartmental epidemiological models. It seems it is a good idea to split the two processes and derive a common model.

Assume that all journeys finish within a day. We can model the people arriving (flying in) into a city as births, and people departing a city as deaths.

Let as take a simple model like SIR or SEIR and write the equation for every site we consider. This means for every site we have the same ODE’s with site-dependent initial conditions.

Consider the traveling patterns matrix K, which is a contingency matrix derived from source-destination traveling records. (Or the adjacency matrix of a travelling patterns graph.) The matrix entry of K(i,j) tells us how many people traveled from site i to site j. We systematically change the ODE’s of the sites in following way.

Assume that site a had only travelers coming from site b and going to site b. Assume that the Total Population (TP) sizes for sites a and b are N_a and N_b respectively. Assume that only people from the Susceptible Population (SP) traveled. If the adopted single-site model is SIR, [Wk1], we take the SP equation of site a

\text{SP}_a'(t)=-\frac{\beta  \text{IP}_a(t) \text{SP}_a(t)}{N_a}-\text{SP}_a(t) \mu

and change into the equation

\text{SP}_a'(t)=-\frac{\beta  \text{IP}_a(t) \text{SP}_a(t)}{N_a}-\text{SP}_a(t) \mu -\frac{K(a,b)\text{SP}_a(t)}{N_a}+\frac{K(b,a)\text{SP}_b(t)}{N_b},

assuming that

\frac{K(a,b)\text{SP}_a(t)}{N_a}\leq N_a ,\frac{K(b,a)\text{SP}_b(t)}{N_b}\leq N_b.

Remark: In the package [AAp3] the transformations above are done with the more general and robust formula:

\min \left(\frac{K(i,j)\text{SP}_i(t)}{\text{TP}_i(t)},\text{TP}_i(t)\right).

The transformed systems of ODE’s of the sites are joined into one “big” system of ODE’s, appropriate initial conditions are set, and the “big” ODE system is solved. (The sections below show concrete examples.)

Steps of MSEMEA

MSEMEA derives a compartmental model that combines (i) a graph representation of multi-site traveling patterns with (ii) a single-site compartmental epidemiological model.

Here is a visual aid for the algorithm steps below:

0i0g3m8u08bj4
0i0g3m8u08bj4
05c2sz8hd3ryj
05c2sz8hd3ryj
  1. Get a single-site epidemiological compartmental model data structure, M.
    1. The model data structure has stocks and rates dictionaries, equations, initial conditions, and prescribed rate values; see [AA2, AAp1].
  2. Derive the site-to-site traveling patterns matrix K for the sites in the graph G.
  3. For each of node i of G make a copy of the model M and denote with M[i].
    1. In general, the models M[i], i\in G have different initial conditions.
    2. The models can also have different death rates, contact rates, etc.
  4. Combine the models M[i], i\in G into the scaled model S.
    1. Change the equations of M[i], i\in G to reflect the traveling patterns matrix K.
    2. Join the systems of ODE’s of M[i], i\in G into one system of ODE’s.
  5. Set appropriate or desired initial conditions for each of the populations in S.
  6. Solve the ODE’s of S.
  7. Visualize the results.

Precaution

Care should be taken when specifying the initial conditions of MSEMEA’s system of ODE’s (sites’ populations) and the traveling patterns matrix. For example, the simulations can “blow up” if the traveling patterns matrix values are too large. As it was indicated above, the package [AAp3] puts some safe-guards, but in our experiments with random graphs and random traveling patterns matrices occasionally we still get “wild” results.

Analogy with Large scale air-pollution modeling

There is a strong analogy between MSEMEA and Eulerian models of Large Scale Air-Pollution Modeling (LSAPM), [AA3, ZZ1].

The mathematical models of LSAPM have a “chemistry part” and an “advection-diffusion part.” It is hard to treat such mathematical model directly – different kinds of splittings are used. If we consider 2D LSAPM then we can say that we cover the modeling area with steer tank reactors, then with the chemistry component we simulate the species chemical reactions in those steer tanks, and with the advection-diffusion component we change species concentrations in the steer tanks (according to some wind patterns.)

Similarly, with MSEMEA we separated the travel of population compartments from the “standard” epidemiological modeling interaction between the population compartments.

Similarly to the so called “rotational test” used in LSAPM to evaluate numerical schemes, we derive and study the results of “grid graph tests” for MSEMEA.

Single site epidemiological model

Here is the SEI2R model from the package [AAp1]:

18y99y846b10m
18y99y846b10m

Here we endow the SEI2R model with a (prominent) ID:

0alzg909zg4h0
0alzg909zg4h0

Thus we demonstrated that we can do Step 3 of MSEMEA.

Below we use ID’s that correspond to the nodes of graphs (and are integers.)

Scaling the single-site SIR model over a small complete graph

Constant travel matrices

Assume we have two sites and the following graph and matrix describe the traveling patterns between them.

Here is the graph:

0vgm31o9drq4f
0vgm31o9drq4f

And here is the traveling patterns matrix:

0lbp0xgso2tgt
0lbp0xgso2tgt

Note that there are much more travelers from 1 to 2 than from 2 to 1.

Here we obtain the core, single-site model (as shown in the section above):

Make the multi-site compartments model with SEI2R and the two-node travel matrix using the function ToSiteCompartmentsModel of [AAp2]:

Show the unique stocks in the multi-site model:

From the symbolic form of the multi-model equations derive the specific equations with the adopted rate values:

0mjliik7acoyd
0mjliik7acoyd

Show the initial conditions:

Show the total number of equations:

Solve the system of ODE’s of the extended model:

Display the solutions for each site separately:

1o9362wmczxo6
1o9362wmczxo6

From the plots above we see that both sites start with total populations of 100000 people. Because more travelers go from 1 to 2 we see that the exposed, infected, and recovered populations are larger at 2.

Time dependent travel matrices

Instead of using constant traveling patterns matrices we can use matrices with time functions as entries. It is instructive to repeat the computations above using this matrix:

1gsoh03lixm6y
1gsoh03lixm6y

Here are the corresponding number of traveling people functions:

0qh7kbtwxyatf
0qh7kbtwxyatf

Here we scale the SIR model, solve the obtained system of ODE’s, and plot the solutions:

0trv1vnslv1rm
0trv1vnslv1rm

Note that the oscillatory nature of the temporal functions in the travelling patterns matrix are reflected in the simulation results.

Constant traveling patterns over a grid graph

In this section we do the model extension and simulation over a regular grid graph with a constant traveling patterns matrix.

Here we create a grid graph with directed edges:

0l2m5npcrlnvw
0l2m5npcrlnvw

Note that:

  • There is one directed edge between any two edge-connected nodes
  • All horizontal edges point in one direction
  • All vertical edges point in one direction
  • The edges are directed from nodes with smaller indexes to nodes with larger indexes.

Here we make a constant traveling matrix and summarize it:

0d4ocoa6gibfj
0d4ocoa6gibfj

Here we scale the SEI2R model with the grid graph constant traveling matrix:

Change the initial conditions in the following way:

  • Pick initial population size per site (same for all sites)
  • Make a constant populations vector
  • At all sites except the first one put the infected populations to zero; the first site has one severely symptomatic person
  • Set the susceptible populations to be consistent with the total and infected populations.

Solve the system of ODE’s of the scaled model:

Randomly sample the graph sites and display the solutions separately for each site in the sample:

030qbpok8qfmc
030qbpok8qfmc

Display solutions of the first and last site:

0mcxwp8l1vqlb
0mcxwp8l1vqlb

As expected from the graph structure, we can see in the first site plot that its total population is decreasing – nobody is traveling to the first site. Similarly, we can see in the last site plot that its total population is increasing – nobody leaves the last site.

Graph evolution visualizations

We can visualize the spatial-temporal evolution of model’s populations using sequences of graphs. The graphs in the sequences are copies of the multi-site graph each copy having its nodes colored according to the populations in the solutions steps.

Here is a sub-sequence for the total populations:

070ld135tkf7y
070ld135tkf7y

Here is a sub-sequence for the sum of the infected populations:

0rv8vap59g8vk
0rv8vap59g8vk

Here is a sub-sequence for the recovered population:

0dnvpy20nafpz
0dnvpy20nafpz

Here is an animation of the sum of the infected populations:

1hfd1mqh0iwk7
1hfd1mqh0iwk7

Curve shapes of the globally-aggregated solutions

Let us plot for each graph vertex the sum of the solutions of the two types of infected populations. Here is a sample of those graphs:

0jwgipeg8uznn
0jwgipeg8uznn

We can see from the plot above that at the grid vertexes we have typical SEIR curve shapes for the corresponding infected populations.

Let us evaluate the solutions for the infected populations for over all graph vertexes and sum them. Here is the corresponding “globally-aggregated” plot:

03nzzmh7yydeu
03nzzmh7yydeu

We can see that the globally aggregated plot has a very different shape than the individual vertex plots. The globally aggregated plot has more symmetric look; the individual vertex plots have much steeper gradients on their left sides.

We can conjecture that a multi-site model made by MSEMEA would capture better real life situations than any single-site model. For example, by applying MSEMEA we might be more successful in our calibration attempts for the Hubei data shown (and calibrated upon) in [AA2.].

Interactive interface

With this interactive interface we see the evolution of all populations across the graph:

0fv3dbwmah3sh
0fv3dbwmah3sh

Observations

Obviously the simulations over the described grid graph, related constant traveling patterns matrix, and constant populations have the purpose to build confidence in conceptual design of MSEMEA and its implementation.

The following observations agree with our expectations for MSEMEA’s results over the “grid graph test”.

  1. The populations plots at each site resemble the typical plots of SEI2R.
  2. The total population at the first site linearly decreases.
  3. The total population at the last site linearly increases.
  4. The plots of the total populations clearly have gradually increasing gradients from the low index value nodes to the high index value nodes.
  5. For the infected populations there is a clear wave that propagates diagonally from the low index value nodes to the high index value nodes.
    1. In the direction of the general “graph flow.“
  6. The front of the infected populations wave is much steeper (gives “higher contrast”) than the tail.
    1. This should be expected from the single-site SEI2R plots.
  7. For the recovered populations there is a clear “saturation wave” pattern that indicates that the recovered populations change from 0 to values close to the corresponding final total populations.
  8. The globally aggregated solutions might have fairly different shapes than the single-site solutions. Hence, we think that MSEMEA gives a modeling ingredient that is hard to replicate or emulate by other means in single-site models.

Time-dependent traveling patterns over a random graph

In this section we apply the model extension and simulation over a random graph with random time-dependent traveling patterns matrix.

1elzu67nqndly
1elzu67nqndly

Remark: The computations in this section work with larger random graphs; we use a small graph for more legible presentation of the workflow and results. Also, the computations should clearly demonstrate the ability to do simulations with real life data.

Derive a traveling patterns matrix with entries that are random functions:

Here is a fragment of the matrix:

17ym9q0uehfbt
17ym9q0uehfbt

Summarize and plot the matrix at t=1:

0bw9rrd64615r
0bw9rrd64615r

Here we scale the SEI2R model with the random traveling matrix:

Change the initial conditions in the following way:

  • Pick maximum population size per site
  • Derive random populations for the sites
  • At all sites except the first one put the infected populations to zero; the first site has one severely symptomatic person
  • Set the susceptible populations to be consistent with the total and infected populations.

Here solve the obtained system of ODE’s:

Here we plot the solutions:

1pzmli04rbchr
1pzmli04rbchr

Graph evolution visualizations

As in the previous section we can visualize the spatial-temporal evolution of model’s populations using sequences of graphs.

Here is a globally normalized sequence:

1v8xq8jzm6ll5
1v8xq8jzm6ll5

Here is a locally normalized (“by vertex”) sequence:

029w2jtxsyaen
029w2jtxsyaen

Money from lost productivity

The model SEI2R from [AAp1] has the stock “Money from Lost Productivity” shown as \text{MLP}(t) in the equations:

1sareh7ovkmtt
1sareh7ovkmtt

Here are MLP plots from the two-node graph model:

0cm5n3xxlewns
0cm5n3xxlewns

Here we plot the sum of the accumulated money losses:

0n6gz7j3qlq07
0n6gz7j3qlq07

Here is the corresponding “daily loss” (derivative):

0jrk2ktzeeled
0jrk2ktzeeled

Future plans

There are multiple ways to extend the presented algorithm, MSEMEA. Here are a few most immediate ones:

  1. Investigate and describe the conditions under which MSEMEA performs well, and under which it “blows up”
  2. Apply MSEMEA together with single site models that have large economics parts
  3. Do real data simulations related to the spread of COVID-19.

References

Articles, books

[Wk1] Wikipedia entry, “Compartmental models in epidemiology”.

[HH1] Herbert W. Hethcote (2000). “The Mathematics of Infectious Diseases”. SIAM Review. 42 (4): 599–653. Bibcode:2000SIAMR..42..599H. doi:10.1137/s0036144500371907.

[AA1] Anton Antonov, “Coronavirus propagation modeling considerations”, (2020), SystemModeling at GitHub.

[AA2] Anton Antonov, “Basic experiments workflow for simple epidemiological models”, (2020), SystemModeling at GitHub.

[AA3] Anton Antonov, “Air pollution modeling with gridMathematica”, (2006), Wolfram Technology Conference.

[ZZ1] Zahari Zlatev, Computer Treatment of Large Air Pollution Models. 1995. Kluwer.

Repositories, packages

[WRI1] Wolfram Research, Inc., “Epidemic Data for Novel Coronavirus COVID-19”, WolframCloud.

[AAr1] Anton Antonov, Coronavirus propagation dynamics project, (2020), SystemModeling at GitHub.

[AAp1] Anton Antonov, “Epidemiology models Mathematica package”, (2020), SystemsModeling at GitHub.

[AAp2] Anton Antonov, “Epidemiology models modifications Mathematica package”, (2020), SystemsModeling at GitHub.

[AAp3] Anton Antonov, “Epidemiology modeling visualization functions Mathematica package”, (2020), SystemsModeling at GitHub.

[AAp4] Anton Antonov, “System dynamics interactive interfaces functions Mathematica package”, (2020), SystemsModeling at GitHub.

UML diagrams creation and generation

This post is to show how to create and generate Unified Modeling Language (UML) diagrams in Mathematica. It is related to programming in Mathematica using Object-Oriented Design Patterns.

Although this post is not about prediction per se it is going to be referenced and used in future posts about predictive algorithms and challenges.

Package functions

This command imports the package UMLDiagramGeneration.m :

Import["https://raw.githubusercontent.com/antononcube/MathematicaForPrediction/master/Misc/UMLDiagramGeneration.m"]

The package provides the functions UMLClassNode and UMLClassGraph.

The function UMLClassNode has the signature

UMLClassNode[classSymbol, opts]

UMLClassNode creates a Grid object with a class name and its methods for the specified class symbol. The option “Abstact” can be used to specify abstract class names and methods. The option “EntityColumn” can be used to turn on and off the explanations column.

The function UMLClassGraph that has the signature:

UMLClassGraph[symbols, abstractMethodsPerSymbol, symbolAssociations, symbolAggregations, opts]

UMLClassGraph creates an UML graph diagram for the specified symbols (representing classes) and their relationships. It takes as options the options of UMLClassNode and Graph.

UML diagrams creation

Let us visualize a simple relationship between buildings, people, books, and a client program.

UMLClassGraph[{Library \[DirectedEdge] Building,
Museum \[DirectedEdge] Building,
Member \[DirectedEdge] Person}, {}, {Library <-> Member,
Museum \[DirectedEdge] Member, Client \[DirectedEdge] Building,
Client \[DirectedEdge] Person}, {Library \[DirectedEdge] Book},
"Abstract" -> {Building, Person},
"EntityColumn" -> False, VertexLabelStyle -> "Text",
ImageSize -> Large, GraphLayout -> "LayeredDigraphEmbedding"]

UML-diagram-for-Inheritance-Composition-Association

In the diagram above the classes Person and Building are abstract (that is why are in italic). Member inherits Person, Library and Museum inherit Building. Library can contain (many) Book objects and it is associated with Member. Client associates with Building and Person.

UML diagram generation

The main package function UMLClassGraph is capable of generating UML diagrams over Design Patterns code written in the style exemplified and described in my WTC 2015 talk Object-Oriented Design Patterns.

Let us look into a simple UML generation example for the design pattern Template Method.

Here is the Mathematica code for that design pattern:

 Clear[AbstractClass, ConcreteOne, ConcreteTwo];
 
 CLASSHEAD = AbstractClass;
 AbstractClass[d_]["Data"[]] := d;
 AbstractClass[d_]["PrimitiveOperation1"[]] := d[[1]];
 AbstractClass[d_]["PrimitiveOperation2"[]] := d[[2]];
 AbstractClass[d_]["TemplateMethod"[]] :=
 CLASSHEAD[d]["PrimitiveOperation1"[]] + CLASSHEAD[d]["PrimitiveOperation2"[]]
 
 ConcreteOne[d_][s_] := Block[{CLASSHEAD = ConcreteOne}, AbstractClass[d][s]]
 ConcreteOne[d_]["PrimitiveOperation1"[]] := d[[1]];
 ConcreteOne[d_]["PrimitiveOperation2"[]] := d[[1]]*d[[2]];
 
 ConcreteTwo[d_][s_] := Block[{CLASSHEAD = ConcreteTwo}, AbstractClass[d][s]]
 ConcreteTwo[d_]["PrimitiveOperation1"[]] := d[[1]];
 ConcreteTwo[d_]["PrimitiveOperation2"[]] := d[[3]]^d[[2]];

This command generates an UML diagram over the code above:

UMLClassGraph[{AbstractClass, ConcreteOne,
ConcreteTwo}, {AbstractClass -> {"PrimitiveOperation1",
"PrimitiveOperation2"}}, "Abstract" -> {AbstractClass},
VertexLabelStyle -> "Subsubsection"]

UML-diagram-generated-over-TemplateMethod-code

Here is a diagram generated over a Mathematica implementation of Decorator:

UML-diagram-for-Decorator

And here is a diagram for a concrete implementation of Interpreter for Boolean expressions:

UML-diagram-for-Interpreter-of-BooleanExpr

(Interpreter is my favorite Design Pattern and I have made several Mathematica implementations that facilitate and extend its application. See these blog posts of mine: “Functional parsers” category in MathematicaForPrediction at WordPress).