When a tsunami strikes, every second counts — yet most predictive tools either focus purely on physics or purely on data. Our project bridges both.
This is SimulWave, an interactive web app that visualizes the real-time impact of a simulated tsunami on a 3D model of a city, while dynamically estimating financial losses and infrastructure damage.
Users can adjust key parameters (such as tsunami severity, population density, city location, and GDP factor) to explore how different conditions influence vulnerability. The system then computes a damage score and economic cost estimate, calibrated with data from historical tsunami events. A sensitivity analysis investigates small perturbations in our calculations.
With Blender-inspired 3D modeling through Three.js and Cannon.js, users can then visualize the physical impact and timeline of a tsunami through a chosen city, simulating the path of destruction in real time.
Built with Python, Streamlit, NumPy, pandas, and Folium, our model merges computational modeling with intuitive visualization. By transforming complex math into interactive insight, we aim to help city planners, researchers, and policymakers visualize disaster risk before it happens — and act on it.
While still in its infant stages today, we are proud to present SimulWave. In the long term, we aim to expand SimulWave into a comprehensive disaster response platform, using machine learning and integrating live oceanographic and seismic data to develop more informed predictions on not only infrastructure vulnerabilities, but also on human impact.
The path of tsunamis remains chaotic. We may never be able to predict when or where tsunamis may occur. But in preparation for those crucial moments when disaster does strike, SimulWave aims to be that vital tool to merge sophisticated data analysis with advanced visualization and accessibility, providing actionable insights for city planners and coastal communities worldwide.
Log in or sign up for Devpost to join the conversation.