Interpretable Machine Learning‑Based Radiation Emulation for ICON
Published in Journal of Geophysical Research: Machine Learning and Computation, 2025
This is the first study of my PhD thesis, where I developed an ML-based radiation emulator using BiLSTMs. I implemented physical constraints regarding energy conservation and interpreted the BiLSTM using Shapley values.
Recommended citation: Hafner, K., and Iglesias‑Suarez, Fernando and Shamekh, Sara and Gentine, Pierre and Giorgetta, Marco A. and Pincus, Robert and Eyring, Veronika (2023). "Interpretable Machine Learning‑Based Radiation Emulation for ICON." Journal of Geophysical Research: Machine Learning and Computation.e2024JH000501. DOI: 10.1029/2024JH000501
Download Paper