Data-driven algorithms, in particular neural networks, can emulate the effect of sub-grid scale processes in coarse-resolution climate models if trained on high-resolution climate simulations. However, they may violate key physical constraints and lack the ability to generalize outside of their training set. Here, we show that physical constraints can be enforced in neural networks, either approximately by adapting the loss function or to within machine precision by adapting the architecture. As these physical constraints are insufficient to guarantee generalizability, we additionally propose to physically rescale the training and validation data to improve the ability of neural networks to generalize to unseen climates.
@article{arxiv.2002.08525,
title = {Towards Physically-consistent, Data-driven Models of Convection},
author = {Tom Beucler and Michael Pritchard and Pierre Gentine and Stephan Rasp},
journal= {arXiv preprint arXiv:2002.08525},
year = {2020}
}
Comments
Accepted for oral presentation at the 2020 IEEE International Geoscience and Remote Sensing Symposium (IGARSS) 5 pages, 5 figures, 1 table