Source code for
Yik, W., Silva, S. J., Geiss, A., Watson-Parris, D. (2023). Exploring Randomly Wired Neural Networks for Climate Model Emulation. Artificial Intelligence for the Earth Systems. https://doi.org/10.1175/AIES-D-22-0088.1
The code to generate the randomly wired neural networks is adapted from
Geiss, A., Ma, P.-L., Singh, B., and Hardin, J. C.: Emulating aerosol optics with randomly generated neural networks, Geosci. Model Dev., 16, 2355–2370, https://doi.org/10.5194/gmd-16-2355-2023, 2023.
The original repository for which can be found here: https://github.com/avgeiss/aerosol_optics_ml
We make use of the publicly available ClimateBench dataset. See
Watson-Parris, D., Rao, Y., Olivié, D., Seland, Ø., Nowack, P., Camps-Valls, G., et al. (2022). ClimateBench v1.0: A benchmark for data-driven climate projections. Journal of Advances in Modeling Earth Systems, 14, e2021MS002954. https://doi.org/10.1029/2021MS002954
The ClimateBench repository can be found here: https://github.com/duncanwp/ClimateBench
The processed training, validation and test data can be obtained from Zenodo: 10.5281/zenodo.5196512
Feel free to contact us if you have any questions!
William Yik: wyik@hmc.edu