Prediction of the Arctic Sea Ice using Deep Learning

Authors

Saksham Garg^a, Divyanshi Gupta^a, Mayuna Gupta^a, Hariprasad Kodamana^{a, c}, and S. Sandeep^b

^a Department of Chemical Engineering, Indian Institute of Technology Delhi, New Delhi 110016, India

^b Centre for Atmospheric Sciences, Indian Institute of Technology Delhi, New Delhi 110016, India

^c School of Artificial Intelligence, Indian Institute of Technology Delhi, New Delhi 110016, India

Files

Input SIC data HadISST_ice dataset.nc.gz, as retreived from Hadley centre website on October 19, 2020.

Code file Code for all models.ipynb contatins the codes for the entire year Neural network (NN), Convolutional Neural network (CNN), and Convolutional Long-Short Term Memory (ConvLSTM) models. It also contains the code for the ConvLSTM melting season model.

Output files are contained in folders Outputs for entire year models and Outputs for melting season models.

The code was written in Google Colab environment. Keras library and tensorflow framework were primarily used. To run in Google Colab, the permission to access the input files from your Google drive is required. After executing the code, you can download the generated output files from runtime for later use.