Review: Theory-guided machine learning applied to hydrogeology—state of the art, opportunities and future challenges

• Published in: Hydrogeology journal Vol. 29; no. 8; pp. 2671 - 2683
• Main Authors: Adombi, Adoubi Vincent De Paul, Chesnaux, Romain, Boucher, Marie-Amélie
• Format: Journal Article
• Language: English
• Published: Berlin/Heidelberg Springer Berlin Heidelberg 01.12.2021; Springer Nature B.V
• Subjects: Aquatic Pollution; Artificial intelligence; Convergence; Data acquisition; Earth and Environmental Science; Earth Sciences; Feature extraction; Geology; Geophysics/Geodesy; Hydrogeology; Hydrology/Water Resources; Learning algorithms; Machine learning; Methods; Modelling; Opacity; Optimization; Theories; Waste Water Technology; Water Management; Water Pollution Control; Water Quality/Water Pollution; Machine learning limitations; Groundwater flow; Statistical modelling; Optimization; Theory-guided machine learning
• ISSN: 1431-2174; 1435-0157
• DOI: 10.1007/s10040-021-02403-2

Thanks to recent technological advances, hydrogeologists now have access to large amounts of data acquired in real time. Processing these data using traditional modelling tools is difficult and poses a number of challenges especially for tasks such as extracting useful features, uncertainty quantification or identifying links between variables. Artificial intelligence, and more specifically its subset ‘machine learning (ML)’, may represent a way of the future in hydrogeological research and applications. Unfortunately, several aspects of machine-learning methods hamper its adoption as a complementary tool for hydrogeologists, namely the black-box nature of most models, an often-limited generalization ability, a hypothetical convergence, and uncertain transferability. Recently, an entirely novel paradigm in the field of machine learning has been identified—theory-guided machine learning–in which the models integrate some specific theoretical knowledge, laws or principles of the field of study. This review article sets out to examine three theory-guided methods in their ability to overcome the limitations of machine learning for hydrogeological research and applications. These methods are, respectively, theory-guided constrained optimization (TGCO), theory-guided refinement of outputs (TGRO) and theory-guided architecture (TGA). The analyses led to the following conclusions: the opacity of ML models can be reduced by any of the three theory-guided ML methods; convergence and generalizability can be enhanced by TGCO, TGA, or a combination of at least two of the theory-guided ML methods; and no study conducted to date has made it possible to deduce the effectiveness of these methods on the transferability of ML models.