RAIN: Reinforcement Algorithms for Improving Numerical Weather and Climate Models

TL;DR

This paper investigates the application of reinforcement learning algorithms to improve parameterisation in climate models, demonstrating their potential to enhance accuracy and computational efficiency in idealised climate scenarios.

Contribution

It introduces the use of multiple RL algorithms for climate model parameterisation and evaluates their performance in idealised climate environments, a novel approach in climate science.

Findings

Different RL algorithms excel in different climate scenarios.

Exploration algorithms perform better in bias correction tasks.

Exploitation algorithms are more effective for radiative-convective equilibrium.

Abstract

This study explores integrating reinforcement learning (RL) with idealised climate models to address key parameterisation challenges in climate science. Current climate models rely on complex mathematical parameterisations to represent sub-grid scale processes, which can introduce substantial uncertainties. RL offers capabilities to enhance these parameterisation schemes, including direct interaction, handling sparse or delayed feedback, continuous online learning, and long-term optimisation. We evaluate the performance of eight RL algorithms on two idealised environments: one for temperature bias correction, another for radiative-convective equilibrium (RCE) imitating real-world computational constraints. Results show different RL approaches excel in different climate scenarios with exploration algorithms performing better in bias correction, while exploitation algorithms proving more effective for RCE. These findings support the potential of RL-based parameterisation schemes to be integrated into global climate models, improving accuracy and efficiency in capturing complex climate dynamics. Overall, this work represents an important first step towards leveraging RL to enhance climate model accuracy, critical for improving climate understanding and predictions. Code accessible at https://github.com/p3jitnath/climate-rl.