Climate Surrogates for Scalable Multi-Agent Reinforcement Learning: A Case Study with CICERO-SCM

• URL: http://arxiv.org/abs/2510.07971v1
• Date: Thu, 09 Oct 2025 09:02:49 GMT
• Title: Climate Surrogates for Scalable Multi-Agent Reinforcement Learning: A Case Study with CICERO-SCM
• Authors: Oskar Bohn Lassen, Serio Angelo Maria Agriesti, Filipe Rodrigues, Francisco Camara Pereira,
• Abstract summary: We present a multi-agent reinforcement learning framework that integrates a high-fidelity, highly efficient climate surrogate directly in the environment loop.<n>As a proof of concept, we introduce a recurrent neural network architecture pretrained on ($20,000$) multi-gas emission pathways to surrogate the climate model CICERO-SCM.<n>The surrogate model attains near-simulator accuracy with global-mean temperature RMSE $approx 0.0004 mathrmK$ and approximately $1000times$ faster one-step inference.
• Score: 4.330506300153804
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Climate policy studies require models that capture the combined effects of multiple greenhouse gases on global temperature, but these models are computationally expensive and difficult to embed in reinforcement learning. We present a multi-agent reinforcement learning (MARL) framework that integrates a high-fidelity, highly efficient climate surrogate directly in the environment loop, enabling regional agents to learn climate policies under multi-gas dynamics. As a proof of concept, we introduce a recurrent neural network architecture pretrained on ($20{,}000$) multi-gas emission pathways to surrogate the climate model CICERO-SCM. The surrogate model attains near-simulator accuracy with global-mean temperature RMSE $\approx 0.0004 \mathrm{K}$ and approximately $1000\times$ faster one-step inference. When substituted for the original simulator in a climate-policy MARL setting, it accelerates end-to-end training by $>\!100\times$. We show that the surrogate and simulator converge to the same optimal policies and propose a methodology to assess this property in cases where using the simulator is intractable. Our work allows to bypass the core computational bottleneck without sacrificing policy fidelity, enabling large-scale multi-agent experiments across alternative climate-policy regimes with multi-gas dynamics and high-fidelity climate response.

Related papers

• ArchesClimate: Probabilistic Decadal Ensemble Generation With Flow Matching [7.758482151941547]
  We present ArchesClimate, a deep learning-based climate model emulator that aims to reduce the cost of climate model simulations.<n> ArchesClimate is trained on decadal hindcasts of the IPSL-CM6A-LR climate model at a spatial resolution of approximately 2.5x1.25 degrees.<n>We show that for several important climate variables, ArchesClimate generates simulations that are interchangeable with the IPSL model.
  arXiv  Detail & Related papers  (2025-09-19T12:53:24Z)
• Vision Transformers for Multi-Variable Climate Downscaling: Emulating Regional Climate Models with a Shared Encoder and Multi-Decoder Architecture [0.0]
  We propose a multi-task, multi-variable Vision Transformer (ViT) architecture with a shared encoder and variable-specific decoders (1EMD)<n>We show that our multi-variable approach achieves positive cross-variable knowledge transfer and consistently outperforms single-variable baselines trained under identical conditions.
  arXiv  Detail & Related papers  (2025-06-12T11:48:41Z)
• Fourier Neural Operator based surrogates for $CO_2$ storage in realistic geologies [57.23978190717341]
  We develop a Neural Operator (FNO) based model for real-time, high-resolution simulation of $CO$ plume migration.<n>The model is trained on a comprehensive dataset generated from realistic subsurface parameters.<n>We present various strategies for improving the reliability of predictions from the model, which is crucial while assessing actual geological sites.
  arXiv  Detail & Related papers  (2025-03-14T02:58:24Z)
• MERCURY: A fast and versatile multi-resolution based global emulator of compound climate hazards [0.0]
  We present the Multi-resolution EmulatoR for CompoUnd climate Risk analYsis: MERCURY.<n>MerCURY extends multi-resolution analysis to atemporal framework for versatile emulation of multiple variables.<n>We demonstrate MERCURY's capabilities on representing the humid-heat metric, Wet Bulb Globe Temperature.
  arXiv  Detail & Related papers  (2024-12-24T04:56:21Z)
• ClimSim-Online: A Large Multi-scale Dataset and Framework for Hybrid ML-physics Climate Emulation [45.201929285600606]
  We present ClimSim-Online, which includes an end-to-end workflow for developing hybrid ML-physics simulators. The dataset is global and spans ten years at a high sampling frequency. We provide a cross-platform, containerized pipeline to integrate ML models into operational climate simulators.
  arXiv  Detail & Related papers  (2023-06-14T21:26:31Z)
• ClimaX: A foundation model for weather and climate [51.208269971019504]
  ClimaX is a deep learning model for weather and climate science. It can be pre-trained with a self-supervised learning objective on climate datasets. It can be fine-tuned to address a breadth of climate and weather tasks.
  arXiv  Detail & Related papers  (2023-01-24T23:19:01Z)
• Multi-scale Digital Twin: Developing a fast and physics-informed surrogate model for groundwater contamination with uncertain climate models [53.44486283038738]
  Climate change exacerbates the long-term soil management problem of groundwater contamination. We develop a physics-informed machine learning surrogate model using U-Net enhanced Fourier Neural Contaminated (PDENO) In parallel, we develop a convolutional autoencoder combined with climate data to reduce the dimensionality of climatic region similarities across the United States.
  arXiv  Detail & Related papers  (2022-11-20T06:46:35Z)
• AI for Global Climate Cooperation: Modeling Global Climate Negotiations, Agreements, and Long-Term Cooperation in RICE-N [75.67460895629348]
  Achieving long-term cooperation on climate change mitigation with n strategic agents poses a complex game-theoretic problem. We introduce RICE-N, a multi-region integrated assessment model that simulates the global climate and economy. We describe how to use multi-agent reinforcement learning to train rational agents using RICE-N.
  arXiv  Detail & Related papers  (2022-08-15T04:38:06Z)
• Computationally-Efficient Climate Predictions using Multi-Fidelity Surrogate Modelling [0.0]
  We investigate the potential of multi-fidelity surrogate modelling as a way to produce high-fidelity climate predictions at low cost. Our model combines the predictions of a low-fidelity Global Climate Model (GCM) and those of a high-fidelity Regional Climate Model (RCM) We are able to produce high-fidelity temperature predictions at significantly lower computational cost compared to the high-fidelity model alone.
  arXiv  Detail & Related papers  (2021-08-03T15:26:42Z)
• DeepClimGAN: A High-Resolution Climate Data Generator [60.59639064716545]
  Earth system models (ESMs) are often used to generate future projections of climate change scenarios. As a compromise, emulators are substantially less expensive but may not have all of the complexity of an ESM. Here we demonstrate the use of a conditional generative adversarial network (GAN) to act as an ESM emulator.
  arXiv  Detail & Related papers  (2020-11-23T20:13:37Z)
• HECT: High-Dimensional Ensemble Consistency Testing for Climate Models [1.7587442088965226]
  Climate models play a crucial role in understanding the effect of environmental changes on climate to help mitigate climate risks and inform decisions. Large global climate models such as the Community Earth System Model (CESM), are very complex with millions of lines of code describing interactions of the atmosphere, land, oceans, and ice. Our work uses probabilistics like tree-based algorithms and deep neural networks to perform a statistically rigorous goodness-of-fit test of high-dimensional and man-made data.
  arXiv  Detail & Related papers  (2020-10-08T15:16:16Z)
• Global Convergence of Policy Gradient for Linear-Quadratic Mean-Field Control/Game in Continuous Time [109.06623773924737]
  We study the policy gradient method for the linear-quadratic mean-field control and game. We show that it converges to the optimal solution at a linear rate, which is verified by a synthetic simulation.
  arXiv  Detail & Related papers  (2020-08-16T06:34:11Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.