NexDrop

User Authentication - Landing
Dashboard
List of Buildings in Area
Annual rainfall analysis
Roof area analysis
Utility rate analysis
Documentation - User Guide

Inspiration

Commercial and industrial buildings sit on massive untapped water reuse potential, but identifying the right buildings at the right time is difficult. Rising utility costs, stricter environmental pressures, and increasing climate risk make water reuse more valuable than ever, yet prospecting is still fragmented and manual. We built NexDrop to turn that challenge into a scalable, data driven opportunity pipeline for Grundfos.

What it does

NexDrop is an intelligent prospecting platform that identifies high potential commercial buildings for rainwater reuse. It combines large roof catchment analysis with financial, regulatory, and sustainability signals to rank where a Grundfos water reuse system can create the strongest impact.

For each building, NexDrop can estimate potential rainwater capture using:

$$ \text{Annual Capture (gallons)} = \text{Roof Area (sq ft)} \times \text{Rainfall (in)} \times \text{Runoff Coefficient} \times 0.623 $$

It then uses that estimate with utility pricing and policy context to simulate value, including savings, payback, and overall viability.

How we built it

We built NexDrop as a layered pipeline:

Geospatial layer: building footprints and large roof candidates were identified and filtered for high potential commercial and industrial sites
Financial layer: city level commercial water and wastewater rates were normalized into a common format
Regulatory layer: policy and incentive signals were curated from official Texas and city level sources
Corporate layer: sustainability and climate commitment signals were structured for future company level enrichment
Scoring layer: deterministic formulas were used to estimate capture, savings, payback, and viability
Frontend layer: the application was designed around an interactive digital twin style experience, where users can inspect buildings and evaluate opportunity

Our scoring logic emphasized explainability over black box modeling. For example, annual savings were estimated with:

$$ \text{Annual Savings} = \frac{\min(\text{Capture}, \text{Reuse Demand})}{1000} \times (\text{Water Rate} + \text{Wastewater Rate}) $$

Challenges we ran into

One of the biggest challenges was data integration. Useful information existed across geospatial datasets, city utility rate sheets, policy resources, and sustainability disclosures, but none of it came in one clean format.

We also ran into challenges around:

selecting the most defensible commercial utility rates instead of residential ones
standardizing different units such as dollars per CCF versus dollars per 1,000 gallons
building a system that remained useful even when some enrichment data was missing
balancing speed for a hackathon with enough rigor to make the results credible

Accomplishments that we're proud of

We are proud that NexDrop is not just a concept, but a structured decision platform. Instead of showing a static map, we created a framework that can rank buildings, estimate value, and support scenario based analysis.

We are especially proud of:

building a realistic multi-layer pipeline under time pressure
keeping the system explainable with transparent formulas and assumptions
focusing the product on real commercial impact, not just technical novelty
creating a foundation that can scale from a hackathon prototype into a serious prospecting tool

What we learned

We learned that the hardest part of a data product is often not the model, but the data contracts, normalization, and assumptions behind it. We also learned that a simple, transparent scoring system can be more valuable in a hackathon setting than a more complicated black box approach.

Most importantly, we learned that strong product design comes from connecting technical depth to a clear business outcome.