Learning bias corrections for climate models using deep neural operators

TL;DR

This paper introduces a deep neural operator approach to improve bias correction in climate models, replacing traditional methods with a more efficient and accurate surrogate model based on DeepONet and auto-encoder architectures.

Contribution

It develops a novel DeepONet-based surrogate model for climate bias correction, integrating auto-encoders to handle high-dimensional data efficiently.

Findings

DeepONet accurately predicts nudging tendencies.

The combined DeepONet and auto-encoder architecture effectively reduces dimensionality.

Model shows good agreement with E3SMv2 data.

Abstract

Numerical simulation for climate modeling resolving all important scales is a computationally taxing process. Therefore, to circumvent this issue a low resolution simulation is performed, which is subsequently corrected for bias using reanalyzed data (ERA5), known as nudging correction. The existing implementation for nudging correction uses a relaxation based method for the algebraic difference between low resolution and ERA5 data. In this study, we replace the bias correction process with a surrogate model based on the Deep Operator Network (DeepONet). DeepONet (Deep Operator Neural Network) learns the mapping from the state before nudging (a functional) to the nudging tendency (another functional). The nudging tendency is a very high dimensional data albeit having many low energy modes. Therefore, the DeepoNet is combined with a convolution based auto-encoder-decoder (AED) architecture in order to learn the nudging tendency in a lower dimensional latent space efficiently. The accuracy of the DeepONet model is tested against the nudging tendency obtained from the E3SMv2 (Energy Exascale Earth System Model) and shows good agreement. The overarching goal of this work is to deploy the DeepONet model in an online setting and replace the nudging module in the E3SM loop for better efficiency and accuracy.