Pinecone | Devpost

Inspiration

December 2021 was one of the worst months for tornadoes in the United States. Tornadoes ripped across the East Coast, leading to numerous deaths and wiping out cities. This inspired me to create Pinecone, a website that uses machine learning to predict the damage of natural disasters, as well as show users reported disasters in their area.

How I built it

I used React, Node JS, TensorFlow, and Supabase to build the website.

Challenges I ran into

One of the biggest challenges was collecting historical data for the ML model to learn from. Finding and cleaning this data took multiple hours.

Accomplishments that I'm proud of

I'm proud of the UI of the website, as well as the map integration. The ML model also works really well.

What I learned

I learned how to use TensorFlow on the backend for predicting the damage of natural disasters.

What's next for Pinecone

I want to eventually make this into a mobile app, as well as add more support for what happens if there is a natural disaster in your area (e.g. alerting emergency services). Overall, I think this can be extremely useful and save lives, all across the world.