This is a repository for the paper "Optimal sampling of spatial patterns improves deep learning based early warning signals of critical transitions" by Smita Deb, Ekansh Mahendru, Paras Goyal, Vishwesha Guttal, Partha Sharathi Dutta and Narayanan C. Krishnan.
Compilation of the given codes require Python 3.
Download model weights and unzip them Run the code S-EWSNet_trained.ipynb to load the model weights followed by testing on a given sample data "data1" undergoing critical transition. The code allows enterign your own sample data and testing on S-EWSNet.