Inspiration

The intensity of a tropical cyclone is correlated strongly to the damage it causes when it makes landfall. Most of the time, tropical cyclones are located over the open ocean, where direct intensity measurements are difficult to obtain. So our team wanted to find a solution to estimate the cyclone intensity during the initial stage of cyclone formation.

What it does

Our CNN model calculates the intensity of a tropical cyclone's maximum sustained wind speed.

How we built it

The language used: python we collected the dataset from HURSAT data project and HURDAT2 database. We used Keras’s ImageDataGenerator to augment data from existing hurricanes in the dataset.

Challenges we ran into

Collection of the opensource dataset from the net.

Accomplishments that we're proud of

we were able to make a CNN model and predict the result on satellite images of tropical cyclone.

What we learned

We learned to use deep learning models and understand the cyclone characteristics.

What's next for Cyclone Intensity estimation using INSAT-3D IR imagery

In the future, we can implement a frontend for our project and deploy it universally so that its accessible to all users. Also, the accuracy of the model can be improved if more data of satellite images of tropical cyclones is available.

Built With

Share this project:

Updates