Inspiration
Wanted to combat the problem of deforestation as it leads to deterioration of terrestrial ecosystems.
What it does
An AI powered web-app that can automatically detect deforestation in an area over a period of time.
How we built it
Used deep learning (transfer learning) to build and train an AI model to predict percentage of forestation cover from an image
Challenges we ran into
Challenges with ngrok, making of the AI model, streamlit etc.
Accomplishments that we're proud of
Got a working prototype of the problem with a root mean squared error of 4%.
What we learned
Multiple new technologies, manipulating large datasets, Working in a tight time frame, bias for action.
What's next for TimberTrack
Collaborate with government forest officials to help combat deforestation
Built With
- ai
- deep-learning
- keras
- python
- streamlit
Log in or sign up for Devpost to join the conversation.