Impacts of climate change on groundwater quality: a systematic literature review of analytical models and machine learning techniques

Abstract

Abstract The increasing impact of global climate change on hydrogeological and hydrological systems presents substantial challenges to the sustainable management of groundwater quality (GWQ). Changes in precipitation regimes, temperature fluctuations, and the frequency of extreme hydro-climatic events driven by climate change accelerate the deterioration of GWQ, thereby threatening ecosystems and human health. In response to these challenges, recent research has increasingly focused on developing and refining analytical models (AM) and machine learning (ML) techniques to understand better and predict the impacts of climate change on GWQ. This systematic literature review critically examines the current state of knowledge on applying AM and ML models in the context of GWQ assessment under climate-induced stressors. By synthesizing findings from a comprehensive review of existing studies, this paper discusses the capabilities, limitations, and future directions of hybrid ML and traditional AM in GWQ prediction, vulnerability, and threshold estimation. The review reveals that while ML approaches significantly enhance predictive accuracy and model robustness, there remain substantial challenges in their application due to the complexity of climate-induced variables and the scarcity of high-resolution data. This paper aims to provide GWQ researchers, water resource managers, and policymakers with an advanced understanding of the interactions between climate change and GWQ and the innovative AM and ML modelling approaches available to address these challenges. By highlighting the potential and limitations of current models, this review offers insights into developing more effective and adaptive management strategies for safeguarding GWQ in an era of rapid climatic change.