Is there a data preprocessing script and inference example available

[cicichena]

Hi, I'm currently trying to work with the dataset used in this repository, and I was wondering if you have any scripts or guidelines for the data preprocessing step — particularly how the raw data (e.g., ERA5 or MODIS) is processed into the .npy format used in the training pipeline.

Additionally, is there an inference script or example available to demonstrate how to run the trained model on new data?

Any pointers to existing scripts, notebooks, or instructions would be greatly appreciated. Thanks in advance!