🤖 AI Summary
Identifying and quantifying downstream impact pathways of climate system perturbations remains challenging due to complex, nonlinear, and spatiotemporally distributed dependencies among climate variables.
Method: This paper proposes a novel source–impact pathway discovery and ranking framework integrating Random Forest Regression (RFR) with SHAP-based feature importance analysis, constructing a weighted directed path network to characterize multimodal climate variable interactions across space and time.
Contribution/Results: First, it pioneers the use of RFR-SHAP not for prediction but for interpretable causal pathway network construction. Second, it introduces a modular, plug-and-play workflow compatible with arbitrary regression models and sensitivity analysis methods. Third, it establishes a hierarchical validation framework comprising synthetic dynamical equations and high-fidelity E3SMv2 simulations. Evaluated on benchmark datasets—including the Pinatubo volcanic eruption simulation and a synthetic coupled system—the method accurately recovers known causal chains, demonstrating robustness in identifying physically plausible, interpretable causal pathways within complex Earth system dynamics.
📝 Abstract
Disturbances to the climate system, both natural and anthropogenic, have far reaching impacts that are not always easy to identify or quantify using traditional climate science analyses or causal modeling techniques. In this paper, we develop a novel technique for discovering and ranking the chain of spatio-temporal downstream impacts of a climate source, referred to herein as a source-impact pathway, using Random Forest Regression (RFR) and SHapley Additive exPlanation (SHAP) feature importances. Rather than utilizing RFR for classification or regression tasks (the most common use case for RFR), we propose a fundamentally new workflow in which we: (i) train random forest (RF) regressors on a set of spatio-temporal features of interest, (ii) calculate their pair-wise feature importances using the SHAP weights associated with those features, and (iii) translate these feature importances into a weighted pathway network (i.e., a weighted directed graph), which can be used to trace out and rank interdependencies between climate features and/or modalities. Importantly, while herein we employ RFR and SHAP feature importance in steps (i) and (ii) of our algorithm, our novel workflow is in no way tied to these approaches, which could be replaced with any regression method and sensitivity method. We adopt a tiered verification approach to verify our new pathway identification methodology. In this approach, we apply our method to ensembles of data generated by running two increasingly complex benchmarks: (i) a set of synthetic coupled equations, and (ii) a fully coupled simulation of the 1991 eruption of Mount Pinatubo in the Philippines performed using a modified version 2 of the U.S. Department of Energy's Energy Exascale Earth System Model (E3SMv2). We find that our RFR feature importance-based approach can accurately detect known pathways of impact for both test cases.