Inspiration
We were inspired by the recent fires that burned across Southern California. The immense devastation, especially from the Palisades Fire, was both horrific and eye-opening, compelling us to help raise awareness about the risk of wildfires.
What it does
We built a website that hosts three maps: one displaying all the fires in California since 2000, another showing property values throughout California, and the last indicating wildfire risk near a given location. Users can input a ZIP code to automatically zoom in and center the maps on the specified area.
How we built it
The front end was designed using Figma and developed with HTML, CSS, JavaScript, and various libraries. The back end was built using scikit-learn, PyTorch, Pandas, NumPy, and Python to model wildfire probability and risk.
Challenges we ran into
We encountered several challenges and had to pivot in multiple areas. One of the main difficulties was integrating all our work into a fully functional website. Another significant challenge was learning multiple new programming languages. The biggest obstacle we faced was time constraints, particularly as the project neared completion.
Accomplishments that we’re proud of
Creating a website that integrates various tools and datasets for public use was a significant achievement. This was our team’s first time building an interactive website that processes and visualizes such extensive data.
What we learned
We are proud of how much we learned throughout this process. Nikita significantly improved her UX/UI design skills. Rex focused on modeling and enhanced his ability to create simulations. Ahnika learned to work with GeoJSON and became familiar with new programming techniques. Ben gained experience integrating backend and frontend components to create an interactive user experience.
What’s next for FireGuard
We plan to fully integrate the model into the website in future iterations and incorporate additional datasets to improve the model’s accuracy. Moving forward, we aim to develop a layering system that allows users to analyze different aspects of data visualization within a single interface.
Log in or sign up for Devpost to join the conversation.