Achieving Conservation of Energy in Neural Network Emulators for Climate Modeling

Abstract

Artificial neural-networks have the potential to emulate cloud processes with higher accuracy than the semi-empirical emulators currently used in climate models. However, neural-network models do not intrinsically conserve energy and mass, which is an obstacle to using them for long-term climate predictions. Here, we propose two methods to enforce linear conservation laws in neural-network emulators of physical models: Constraining (1) the loss function or (2) the architecture of the network itself. Applied to the emulation of explicitly-resolved cloud processes in a prototype multi-scale climate model, we show that architecture constraints can enforce conservation laws to satisfactory numerical precision, while all constraints help the neural-network better generalize to conditions outside of its training set, such as global warming.

ICML 2019 Workshop. Climate Change: How Can AI Help? 3 pages, 3 figures, 1 table

Cited by in corpus (4)

• On closures for reduced order models $-$ A spectrum of first-principle to machine-learned avenues
• DC3: A learning method for optimization with hard constraints
• Using Machine Learning at Scale in HPC Simulations with SmartSim: An Application to Ocean Climate Modeling
• Machine learning structure preserving brackets for forecasting irreversible processes