Abstract: Predicting groundwater levels is pivotal in curbing overexploitation and ensuring effective water resource governance. However, groundwater level prediction is intricate, driven by dynamic nonlinear factors. To comprehend the dynamic interaction among these drivers, leveraging machine learning models can provide valuable insights. The drastic increase in computational capabilities has catalysed a substantial surge in the utilisation of machine learning-based solutions for effective groundwater management. The performance of these models highly depends on the selection of hyperparameters. The optimisation of hyperparameters is a complex process that often requires application-specific expertise for a skillful prediction. To mitigate the challenge posed by hyperparameter tuning’s problem-specific nature, we present an innovative approach by introducing the automated machine learning (AutoML-GWL) framework. This framework is specifically designed for precise groundwater level mapping. It seamlessly integrates the selection of best machine learning model and adeptly fine-tunes its hyperparameters by using Bayesian optimisation. We used long time series (1997-2018) data of precipitation, temperature, evaporation, soil type, relative humidity, and lag of groundwater level as input features to train the AutoML-GWL model while considering the influence of Land Use Land Cover (LULC) as a contextual factor. Among these input features, the lag of groundwater level emerged as the most relevant input feature. Once the model is trained, it performs well over the unseen data with a strong correlation of coefficient (R = 0.90), low root mean square error (RMSE = 1.22), and minimal bias = 0.23. Further, we compared the performance of the proposed AutoML-GWL with sixteen benchmark algorithms comprising baseline and novel algorithms. The AutoML-GWL outperforms all the benchmark algorithms. Furthermore, the proposed algorithm ranked first in Friedman’s statistical test, confirming its reliability. Moreover, we conducted a spatial distribution and uncertainty analysis for the proposed algorithm. The outcomes of this analysis affirmed that the AutoML-GWL can effectively manage data with spatial variations and demonstrates remarkable stability when faced with small uncertainties in the input parameters. This study holds significant promise in revolutionising groundwater management practices by establishing an automated framework for simulating groundwater levels for sustainable water resource management.

Abstract: Groundwater resources in the crystalline basement complex of India are crucial for supplying drinking water in both rural and urban settings. Groundwater depletion is recognised as a challenge across parts of India due to over-abstraction, but groundwater quality constraints are perhaps even more widespread and often overlooked at the local scale. Uranium contamination in basement aquifers has been reported in many parts of India, locally exceeding WHO drinking water guideline values of 30 μg/L and posing a potential health risk. In this study 130 water samples were collected across three crystalline basement catchments to assess hydrochemical, geological and anthropogenic controls on uranium mobility and occurrence in drinking water sources. Groundwaters with uranium concentrations exceeding 30 μg/L were found in all three study catchments (30% of samples overall), with concentrations up to 589 μg/L detected. There appears to be a geological control on the occurrence of uranium in groundwater with the granitic gneiss of the Halli and Bengaluru study areas having higher mean uranium concentrations (51 and 68 μg/L respectively) compared to the sheared gneiss of the Berambadi catchment (6.4 μg/L). Uranium – nitrate relationships indicate that fertiliser sources are not a major control on uranium occurrence in these case studies which include two catchments with a long legacy of intense agricultural land use. Geochemical modelling confirmed uranium speciation was dominated by uranyl carbonate species, particularly ternary complexes with calcium, consistent with uranium mobility being affected by redox controls and the presence of carbonates. Urban leakage in Bengaluru led to low pH and low bicarbonate groundwater hydrochemistry, reducing uranium mobility and altering uranium speciation. Since the majority of inhabitants in Karnataka depend on groundwater abstraction from basement aquifers for drinking water and domestic use, exposure to elevated uranium is a public health concern. Improved monitoring, understanding and treatment of high uranium drinking water sources in this region is essential to safeguard public health.