Causal hybrid modeling with double machine learning—applications in carbon flux modeling

• Published in: Machine Learning: Science and Technology
• Main Authors: Kai-Hendrik Cohrs, Gherardo Varando, Nuno Carvalhais, Markus Reichstein, Gustau Camps-Valls
• Format: Article in Journal/Newspaper
• Language: English
• Published: IOP Publishing 2024
• Subjects: knowledge-guided machine learning; hybrid modeling; causal effect estimation; double machine learning; temperature sensitivity; carbon flux partitioning; Computer engineering. Computer hardware; TK7885-7895; Electronic computers. Computer science; QA75.5-76.95; DML
• Online Access: https://doi.org/10.1088/2632-2153/ad5a60; https://doaj.org/article/5f8cd148b4a14b0fb860bcef7d6ba5e2

Hybrid modeling integrates machine learning with scientific knowledge to enhance interpretability, generalization, and adherence to natural laws. Nevertheless, equifinality and regularization biases pose challenges in hybrid modeling to achieve these purposes. This paper introduces a novel approach to estimating hybrid models via a causal inference framework, specifically employing double machine learning (DML) to estimate causal effects. We showcase its use for the Earth sciences on two problems related to carbon dioxide fluxes. In the Q _10 model, we demonstrate that DML-based hybrid modeling is superior in estimating causal parameters over end-to-end deep neural network approaches, proving efficiency, robustness to bias from regularization methods, and circumventing equifinality. Our approach, applied to carbon flux partitioning, exhibits flexibility in accommodating heterogeneous causal effects. The study emphasizes the necessity of explicitly defining causal graphs and relationships, advocating for this as a general best practice. We encourage the continued exploration of causality in hybrid models for more interpretable and trustworthy results in knowledge-guided machine learning.