Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Toward Artificial Intelligence Enabled Earth System Coupling

Maria Kaselimi, Anna Belehaki

Abstract

Coupling constitutes a foundational mechanism in the Earth system, regulating the interconnected physical, chemical, and biological processes that link its spheres. This review examines how emerging artificial intelligence (AI) methods create new opportunities to enhance Earth system coupling and address long-standing limitations in multi-component models. Rather than surveying next-generation modelling efforts broadly, we focus specifically on how state-of-the-art AI techniques can strengthen cross-domain interactions, support more coherent multi-component representations, and enable progress toward unified Earth system frameworks. The scope extends beyond climate models to include any modelling system in which Earth spheres interact. We outline emerging opportunities, persistent limitations, and conceptual pathways through which AI may enhance physical consistency, interpretability, and integration across domains. In doing so, this review provides a structured foundation for understanding the role of AI in advancing coupled Earth system modelling.

Toward Artificial Intelligence Enabled Earth System Coupling

Abstract

Coupling constitutes a foundational mechanism in the Earth system, regulating the interconnected physical, chemical, and biological processes that link its spheres. This review examines how emerging artificial intelligence (AI) methods create new opportunities to enhance Earth system coupling and address long-standing limitations in multi-component models. Rather than surveying next-generation modelling efforts broadly, we focus specifically on how state-of-the-art AI techniques can strengthen cross-domain interactions, support more coherent multi-component representations, and enable progress toward unified Earth system frameworks. The scope extends beyond climate models to include any modelling system in which Earth spheres interact. We outline emerging opportunities, persistent limitations, and conceptual pathways through which AI may enhance physical consistency, interpretability, and integration across domains. In doing so, this review provides a structured foundation for understanding the role of AI in advancing coupled Earth system modelling.

Paper Structure

This paper contains 17 sections, 3 equations, 4 figures.

Table of Contents

  1. Introduction
  2. Scope and Boundaries of This Review
  3. Background: Earth System Coupling
  4. What is Coupling?
  5. Coupling Interfaces and Fluxes
  6. Emerging Cross-Domain Coupling Beyond Traditional ESMs
  7. Traditional Approaches to Coupling and their Limitations
  8. Coupled Model Architectures
  9. Challenges in Numerical Coupling
  10. AI Approaches for Earth System Coupling
  11. AI for Interface and Flux Learning
  12. AI for Cross-Component Dynamical Modeling
  13. AI for Spatial Interaction Learning
  14. Multi-Domain Foundation Models for Coupling
  15. Causal & Explainable AI for Coupling Pathways
  16. ...and 2 more sections

Figures (4)

  • Figure 1: Earth System Interaction Diagram
  • Figure 2: Traditional numerical coupling challenges and illustrative AI-enabled opportunities.
  • Figure 3: Comparison of single-system and coupling-oriented foundation models in Earth system science. Single-system models focus on Earth observation or atmospheric prediction without explicit physical coupling, whereas coupling-oriented models learn cross-domain dependencies by training on integrated multi-domain Earth system datasets.
  • Figure 4: Structural AI Taxonomy for Representing and Enhancing Earth System Coupling. The taxonomy organizes AI approaches by their purpose, methodological subclasses, and representative coupled-domain applications.