A machine learning model for skillful climate system prediction

2025-05-06

AI Summary

To address the low coupling efficiency of conventional climate models and their insufficient subseasonal prediction capability, this study develops FengShun-CSM—the first fully coupled AI-based climate system model. Built upon a deep learning–driven multi-source spatiotemporal fusion architecture, it achieves dynamic, four-component coupling among the atmosphere, ocean, land surface, and sea ice—marking the first such implementation in AI-driven climate modeling—and incorporates physics-informed constraints to ensure interpretability. In a 60-day global daily forecasting task, FengShun-CSM simultaneously predicts 29 key variables, significantly outperforming the ECMWF S2S model in capturing intraseasonal variability (e.g., the Madden–Julian Oscillation) and extreme events, particularly for precipitation, sea surface temperature, and land surface state variables. This work establishes a new paradigm for high-accuracy subseasonal-to-seasonal (S2S) prediction, with direct applications in meteorological disaster mitigation, marine ecosystem assessment, and agro-climatic services.

Technology Category

• Machine Learning: Deep Neural Architectures and Foundation Models
• Cognitive Modeling & Cognitive Systems: Conceptual Inference and Reasoning
• Computer Vision: Remote Sensing / Geospatial AI

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

Climate system models (CSMs), through integrating cross-sphere interactions among the atmosphere, ocean, land, and cryosphere, have emerged as pivotal tools for deciphering climate dynamics and improving forecasting capabilities. Recent breakthroughs in artificial intelligence (AI)-driven meteorological modeling have demonstrated remarkable success in single-sphere systems and partially spheres coupled systems. However, the development of a fully coupled AI-based climate system model encompassing atmosphere-ocean-land-sea ice interactions has remained an unresolved challenge. This paper introduces FengShun-CSM, an AI-based CSM model that provides 60-day global daily forecasts for 29 critical variables across atmospheric, oceanic, terrestrial, and cryospheric domains. The model significantly outperforms the European Centre for Medium-Range Weather Forecasts (ECMWF) subseasonal-to-seasonal (S2S) model in predicting most variables, particularly precipitation, land surface, and oceanic components. This enhanced capability is primarily attributed to its improved representation of intra-seasonal variability modes, most notably the Madden-Julian Oscillation (MJO). Remarkably, FengShun-CSM exhibits substantial potential in predicting subseasonal extreme events. Such breakthroughs will advance its applications in meteorological disaster mitigation, marine ecosystem conservation, and agricultural productivity enhancement. Furthermore, it validates the feasibility of developing AI-powered CSMs through machine learning technologies, establishing a transformative paradigm for next-generation Earth system modeling.

Problem

• Develop AI-based fully coupled climate system model
• Improve 60-day global forecasts for 29 key variables
• Enhance prediction of subseasonal extreme climate events

Innovation

• AI-based fully coupled climate system model
• 60-day global forecasts for 29 variables
• Improved intra-seasonal variability representation