Multi-fidelity climate model parameterization for better generalization and extrapolation

TL;DR

This paper introduces a multi-fidelity machine learning framework that combines datasets of varying accuracy to improve climate model predictions, enabling better generalization and extrapolation to unobserved scenarios like climate change.

Contribution

The authors develop MF-RPNs, a novel multi-fidelity approach that integrates physical and high-fidelity data, enhancing climate projection accuracy and extrapolation capabilities.

Findings

MF-RPNs outperform single-fidelity models in accuracy.

The approach effectively extrapolates to +4K warming scenarios.

Uncertainty quantification remains reliable across scenarios.

Abstract

Machine-learning-based parameterizations (i.e. representation of sub-grid processes) of global climate models or turbulent simulations have recently been proposed as a powerful alternative to physical, but empirical, representations, offering a lower computational cost and higher accuracy. Yet, those approaches still suffer from a lack of generalization and extrapolation beyond the training data, which is however critical to projecting climate change or unobserved regimes of turbulence. Here we show that a multi-fidelity approach, which integrates datasets of different accuracy and abundance, can provide the best of both worlds: the capacity to extrapolate leveraging the physically-based parameterization and a higher accuracy using the machine-learning-based parameterizations. In an application to climate modeling, the multi-fidelity framework yields more accurate climate projections without requiring major increase in computational resources. Our multi-fidelity randomized prior networks (MF-RPNs) combine physical parameterization data as low-fidelity and storm-resolving historical run's data as high-fidelity. To extrapolate beyond the training data, the MF-RPNs are tested on high-fidelity warming scenarios, $+4K$, data. We show the MF-RPN's capacity to return much more skillful predictions compared to either low- or high-fidelity (historical data) simulations trained only on one regime while providing trustworthy uncertainty quantification across a wide range of scenarios. Our approach paves the way for the use of machine-learning based methods that can optimally leverage historical observations or high-fidelity simulations and extrapolate to unseen regimes such as climate change.