Explainable Machine Learning for Scientific Insights and Discoveries

TLDR

Machine learning has proven effective across many domains, and its recent adoption in the natural sciences aims to generate novel insights, but achieving scientific outcomes requires domain knowledge to ensure explainability and consistency. This review examines explainable machine learning in natural science applications, focusing on the core elements of transparency, interpretability, and explainability. The authors survey recent studies that integrate machine learning with domain knowledge, illustrating how explainable techniques are applied in practice.

Abstract

Machine learning methods have been remarkably successful for a wide range of application areas in the extraction of essential information from data. An exciting and relatively recent development is the uptake of machine learning in the natural sciences, where the major goal is to obtain novel scientific insights and discoveries from observational or simulated data. A prerequisite for obtaining a scientific outcome is domain knowledge, which is needed to gain explainability, but also to enhance scientific consistency. In this article, we review explainable machine learning in view of applications in the natural sciences and discuss three core elements that we identified as relevant in this context: transparency, interpretability, and explainability. With respect to these core elements, we provide a survey of recent scientific works that incorporate machine learning and the way that explainable machine learning is used in combination with domain knowledge from the application areas.