Physically Constrained Generative Adversarial Networks for Improving Precipitation Fields from Earth System Models
This work addresses the challenge of generating realistic precipitation fields for climate modeling, offering a computationally efficient solution that corrects both local and spatial errors, though it is incremental as it builds on existing GAN methods with physical constraints.
The paper tackled the problem of correcting errors in precipitation simulations from Earth System Models (ESMs), which often have inaccurate spatial patterns, by proposing a physically constrained GAN framework that improved local distributions and spatial structure, removing issues like a double-peaked Intertropical Convergence Zone and enabling generalization to unseen climate scenarios.
Precipitation results from complex processes across many scales, making its accurate simulation in Earth system models (ESMs) challenging. Existing post-processing methods can improve ESM simulations locally, but cannot correct errors in modelled spatial patterns. Here we propose a framework based on physically constrained generative adversarial networks (GANs) to improve local distributions and spatial structure simultaneously. We apply our approach to the computationally efficient ESM CM2Mc-LPJmL. Our method outperforms existing ones in correcting local distributions, and leads to strongly improved spatial patterns especially regarding the intermittency of daily precipitation. Notably, a double-peaked Intertropical Convergence Zone, a common problem in ESMs, is removed. Enforcing a physical constraint to preserve global precipitation sums, the GAN can generalize to future climate scenarios unseen during training. Feature attribution shows that the GAN identifies regions where the ESM exhibits strong biases. Our method constitutes a general framework for correcting ESM variables and enables realistic simulations at a fraction of the computational costs.