Future Ground Water Predictor

Actual Vs Prediction
Actual Vs Prediction
Actual Vs Prediction
Actual Vs Prediction
Actual Vs Prediction
Actual Vs Prediction

Inspiration

We were inspired by the book 2084. In this book a character discusses the effects of ground water shortages in the future.

What it does

This AI uses Gravitometer Data from Nasa satellites to predict future ground water availability.

How we built it

We built this AI using a Convolutional Neural Network based on the Pytorch framework.

Challenges we ran into

The first challenge we ran into was accessing the data from NASA's APIs this took 5 hours of time to work out. The other challenge we ran into was creating a model that was sufficiently accurate this issue was remedied by a modification to the AI's model.

Accomplishments that we're proud of

We were able to parse the gravity data from NASA. Aswell as create predictions that are sufficiently accurate.

What we learned

Pytorch is a new framework to us which caused many setbacks but ultimately became much clearer. We were unfamiliar with .nc file format but are now able to use it.