Interpretable vs. noninterpretable machine learning models for data-driven hydro-climatological process modeling

Abstract

Due to their enhanced predictive capabilities, noninterpretable machine learning (ML) models (e.g. deep learning) have recently gained a growing interest in analyzing and modeling earth & planetary science data. However, noninterpretable ML models are often treated as “black boxes” by end-users, which could limit their applicability in critical decision making processes. In this paper, we compared the predictive capabilities of three interpretable ML models with three noninterpretable ML models to answer the overarching question: Is it essential to use noninterpretable ML models for enhanced model predictions from hydro-climatological datasets? The ML model development and comparative analysis were performed using measured climate data and synthetic reference crop evapotranspiration (ETo) data, with varying levels of missing values, from five weather stations across the karstic Edwards aquifer region in semi-arid south-central Texas. Our analysis revealed that interpretable tree-based ensemble models produce comparable results to noninterpretable deep learning models on structured hydro-climatological datasets. We showed that the tree-based ensemble model is also capable of imputing varying levels of missing climate data at the weather stations, employing the newly developed sequential transfer-learning technique. We applied an explainable machine learning (eXML) framework to quantify the global order of importance of hydro-climatic (predictor) variables on ETo, while highlighting the local dependencies and interactions amongst the predictors and ETo. The eXML framework also revealed the inflection points of the climate variables at which the transition from low to high daily ETo rates occur. The ancillary explainability of ML models are expected to increase users’ confidence and support any future decision-making process in water resource management.