SamudrACE: Fast and Accurate Coupled Climate Modeling with 3D Ocean and Atmosphere Emulators

2025-09-15

AI Summary

Traditional global climate models rely on decoupled, multi-component simulations—such as atmosphere and ocean—that exchange boundary conditions, resulting in limited computational efficiency and accuracy. To address this, we propose the first fully coupled machine learning–based climate emulator, enabling synchronous 3D evolution of atmospheric and oceanic dynamics under a physics-informed flux coupler. We employ deep neural networks to independently parameterize atmospheric and oceanic processes, supporting 1° spatial resolution and dual temporal outputs (6-hourly and 5-daily). Over century-scale free integrations, the emulator maintains low climate drift, accurately reproduces key modes of variability—including ENSO—and preserves spatiotemporal consistency across 145 two-dimensional field variables. Its climatological statistics closely match observational benchmarks, substantially overcoming the accuracy–efficiency trade-offs inherent in conventional decoupled modeling frameworks.

Technology Category

• Machine Learning: Efficient ML / Green AI
• Cognitive Modeling & Cognitive Systems: Simulating Human Behavior
• Humans and AI: Human-in-the-loop Machine Learning

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs

Abstract

Traditional numerical global climate models simulate the full Earth system by exchanging boundary conditions between separate simulators of the atmosphere, ocean, sea ice, land surface, and other geophysical processes. This paradigm allows for distributed development of individual components within a common framework, unified by a coupler that handles translation between realms via spatial or temporal alignment and flux exchange. Following a similar approach adapted for machine learning-based emulators, we present SamudrACE: a coupled global climate model emulator which produces centuries-long simulations at 1-degree horizontal, 6-hourly atmospheric, and 5-daily oceanic resolution, with 145 2D fields spanning 8 atmospheric and 19 oceanic vertical levels, plus sea ice, surface, and top-of-atmosphere variables. SamudrACE is highly stable and has low climate biases comparable to those of its components with prescribed boundary forcing, with realistic variability in coupled climate phenomena such as ENSO that is not possible to simulate in uncoupled mode.

Problem

• Developing fast coupled climate model emulators with 3D ocean-atmosphere interactions
• Achieving stable century-scale simulations with realistic climate variability
• Reducing climate biases while maintaining high spatiotemporal resolution

Innovation

• Coupled machine learning-based emulators
• Global climate model with 1-degree resolution
• Stable century-long simulations with realistic variability