Bridging Idealized and Operational Models: An Explainable AI Framework for Earth System Emulators

2025-10-14

AI Summary

Earth system models face a fundamental trade-off: operational high-resolution models suffer from biases in extreme events and statistical distributions, while idealized coarse-resolution models accurately represent specific dynamical or statistical features but lack interoperability across disciplinary domains. To bridge this gap, we propose an interpretable AI framework that synergistically integrates both model types via reconstructed implicit data assimilation—leveraging idealized models to enforce statistical consistency and operational models to deliver multivariate, high-resolution outputs. Our approach replaces black-box bias correction with physics-constrained calibration and enables cross-complexity joint modeling. Applied to CMIP6 El Niño simulations, it significantly reduces spatiotemporal mode biases and improves global-scale predictive skill. This work establishes a new paradigm for physics-guided digital twins and uncertainty quantification in climate modeling.

Technology Category

• Machine Learning: Calibration & Uncertainty Quantification
• Cognitive Modeling & Cognitive Systems: Simulating Human Behavior
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Computer models are indispensable tools for understanding the Earth system. While high-resolution operational models have achieved many successes, they exhibit persistent biases, particularly in simulating extreme events and statistical distributions. In contrast, coarse-grained idealized models isolate fundamental processes and can be precisely calibrated to excel in characterizing specific dynamical and statistical features. However, different models remain siloed by disciplinary boundaries. By leveraging the complementary strengths of models of varying complexity, we develop an explainable AI framework for Earth system emulators. It bridges the model hierarchy through a reconfigured latent data assimilation technique, uniquely suited to exploit the sparse output from the idealized models. The resulting bridging model inherits the high resolution and comprehensive variables of operational models while achieving global accuracy enhancements through targeted improvements from idealized models. Crucially, the mechanism of AI provides a clear rationale for these advancements, moving beyond black-box correction to physically insightful understanding in a computationally efficient framework that enables effective physics-assisted digital twins and uncertainty quantification. We demonstrate its power by significantly correcting biases in CMIP6 simulations of El Niño spatiotemporal patterns, leveraging statistically accurate idealized models. This work also highlights the importance of pushing idealized model development and advancing communication between modeling communities.

Problem

• Bridging idealized and operational Earth system models
• Correcting biases in extreme events and statistical distributions
• Providing explainable AI framework for climate emulators

Innovation

• Bridging model hierarchy with latent data assimilation
• Exploiting sparse idealized outputs for accuracy enhancement
• Providing explainable AI framework for physical insights