Learning to Correct Climate Projection Biases

Baoxiang Pan, Gemma J. Anderson, André Ricardo Gonçalves, Donald D. Lucas, C. Bonfils, Jiwoo Lee, Yang Tian, Hsi‐Yen Ma

Journal of Advances in Modeling Earth Systems · 01 October 2021

In one sentence. Regularized adversarial domain adaptation corrects climate model daily precipitation biases over the contiguous US across moments while keeping spatiotemporal consistency.

Abstract

Abstract The fidelity of climate projections is often undermined by biases in climate models due to their simplification or misrepresentation of unresolved climate processes. While various bias correction methods have been developed to post‐process model outputs to match observations, existing approaches usually focus on limited, low‐order statistics, or break either the spatiotemporal consistency of the target variable, or its dependency upon model resolved dynamics. We develop a Regularized Adversarial Domain Adaptation (RADA) methodology to overcome these deficiencies, and enhance efficient identification and correction of climate model biases. Instead of pre‐assuming the spatiotemporal characteristics of model biases, we apply discriminative neural networks to distinguish historical climate simulation samples and observation samples. The evidences based on which the discriminative neural networks make distinctions are applied to train the domain adaptation neural networks to bias correct climate simulations. We regularize the domain adaptation neural networks using cycle‐consistent statistical and dynamical constraints. An application to daily precipitation projection over the contiguous United States shows that our methodology can correct all the considered moments of daily precipitation at approximately resolution, ensures spatiotemporal consistency and inter‐field correlations, and can discriminate between different dynamical conditions. Our methodology offers a powerful tool for disentangling model parameterization biases from their interactions with the chaotic evolution of climate dynamics, opening a novel avenue toward big‐data enhanced climate predictions.

Labels

Labels and summary are generated by Claude and reviewed weekly. Wrong? Edit this entry.