Double machine learning for causal hybrid modeling -- applications in the Earth sciences

arXiv:2402.13332v1 Announce Type: new
Abstract: Hybrid modeling integrates machine learning with scientific knowledge with the goal of enhancing 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. …

abstract applications arxiv biases challenges cs.lg earth earth sciences hybrid interpretability knowledge laws machine machine learning modeling natural novel paper regularization stat.me type