Robust causality and false attribution in data-driven earth science discoveries.

Abstract

Causal and attribution studies are essential for earth scientific discoveries and critical for informing climate, ecology, and water policies. However, the current generation of methods needs to keep pace with the complexity of scientific, data availability, and stakeholder challenges, combined with the adequacy of data-driven methods. Unless carefully informed by physics, they run the risk of conflating correlation with causation or getting overwhelmed by estimation inaccuracies. In particular, information-theoretic approaches such as transfer entropy (TE), despite their recent popularity and widespread use, can yield spurious causal links, even when statistical significance testing is applied. To address this, we introduce CAST (Causal Analysis Spuriousness Test), a subsample-based ensemble framework that quantifies the robustness of inferred links via the CAST index. Through extensive simulations across systems with varying dynamics as well as applications to real-world climate datasets, we demonstrate that CAST effectively filters unreliable connections while preserving true causal relationships. Our findings underscore the need for consistency-based evaluation in causal discovery and provide a generalizable strategy to enhance the reliability of TE-based and other data-driven causal methods in Earth sciences.