Data for 'Interpretability of AI weather models via intermediate decoding' (part 1 of 3)

Data for the paper Interpretability of AI weather models via intermediate decoding, part 1 of 3 (part 2: 10.5281/zenodo.23345099, part 3: 10.5281/zenodo.23345101). Code and instructions: https://github.com/MatthiasBey/intermediate-decoding. Use download_data.sh from the code repository to download and extract the archives. The archives are split into pieces of 1 GiB. To join them by hand: cat <name>.tar.* > <name>.tar. The md5 checksums of the joined archives are in md5sums.txt in part 1. Contains modified Copernicus Climate Change Service information 2026.