Earth System Modeling 2.0: A Blueprint for Models That Learn From Observations and Targeted High-Resolution Simulations

TL;DR

This paper proposes a new Earth system modeling approach that integrates observations and high-resolution simulations using machine learning to improve climate projections and reduce uncertainties.

Contribution

It introduces a blueprint for models that learn parameterizations from data and simulations, advancing climate modeling capabilities.

Findings

Demonstrated learning algorithms with a simplified climate-like system

Outlined how to match statistics between models, observations, and simulations

Discussed opportunities and challenges in implementing the framework

Abstract

Climate projections continue to be marred by large uncertainties, which originate in processes that need to be parameterized, such as clouds, convection, and ecosystems. But rapid progress is now within reach. New computational tools and methods from data assimilation and machine learning make it possible to integrate global observations and local high-resolution simulations in an Earth system model (ESM) that systematically learns from both. Here we propose a blueprint for such an ESM. We outline how parameterization schemes can learn from global observations and targeted high-resolution simulations, for example, of clouds and convection, through matching low-order statistics between ESMs, observations, and high-resolution simulations. We illustrate learning algorithms for ESMs with a simple dynamical system that shares characteristics of the climate system; and we discuss the opportunities the proposed framework presents and the challenges that remain to realize it.