Application of machine learning models in groundwater quality assessment and prediction:progress and challenges

Groundwater quality assessment and prediction(GQAP)is vital for protecting groundwater resources.Traditional GQAP methods can not adequately capture the complex relationships among attributes and have the disadvantage of being computationally demanding.Recently,the application of machine learning(ML)in GAQP(GQAPxML)has been widely studied due to ML’s reliability and efficiency.While many GQAPxML publications exist,a thorough review is missing.This review provides a comprehensive summary of the development of ML applications in the field of GQAP.First,the workflow of ML modeling is briefly introduced,as are data preparation,model development,model evaluation,and model application.Second,299 publications related to the topic are filtered,mainly through ML modeling.Subsequently,many aspects of GQAPxML,such as publication trends,the spatial distribution of study areas,the size of data sets,and ML algorithms,are discussed from a bibliometric perspective.In addition,we review in detail the well-established applications and recent findings for several subtopics,including groundwater quality assessment,groundwater quality modeling using groundwater quality parameters,groundwater quality spatial mapping,probability estimation of exceeding the groundwater quality threshold,groundwater quality temporal prediction,and the hybrid use of ML and physics-based models.Finally,the development of GQAPxML is explored from three perspectives:data collection and preprocessing,model building and evaluation,and the broadening of model applications.This review provides a reference for environmental scientists to better understand GQAPxML and promotes the development of innovative methods and improvements in modeling quality.

Evaluation of hydro-chemistry in a phreatic aquifer in the Vindhyan Region, India, using entropy weighted approach and geochemical modelling

Groundwater quality monitoring and geochemical characterization in the phreatic aquifer are critical for ensuring universal and equitable access to clean,reliable,and inexpensive drinking water for all.This research was intended to investigate the hydrogeochemical attributes and mechanisms regulating the chemistry of groundwater as well as to assess spatial variation in groundwater quality in Satna district,India.To accomplish this,the groundwater data comprising 13 physio-chemical parameters from thirty-eight phreatic aquifer locations were analysed for May 2020 by combining entropy-weighted water quality index(EWQI),multivariate statistics,geochemical modelling,and geographical information system.The findings revealed that the groundwater is fresh and slightly alkaline.Hardness was a significant concern as 57.89% of samples were beyond the permissible limit of the World Health Organisation.The dominance of ions were in the order of Ca^(2+)> Na^(+)> Mg^(2+)> K^(+) and HCO_(3)^(-)> SO_(4)^(2-)> Cl^-> NO_(3)^(-)> F^(-).Higher concentration of these ions is mainly concentrated in the northeast and eastern regions.Pearson correlation analysis and principal component analysis(PCA) demonstrated that both natural and human factors regulate groundwater chemistry in the region.The analysis of Q-mode agglomerative hierarchical clustering highlighted three significant water clusters.Ca-HCO_3 was the most prevalent hydro-chemical facies in all three clusters.Geochemical modelling through various conventional plots indicated that groundwater chemistry in the research region is influenced by the dissolution of calcite/dolomite,reverse ion exchange,and by silicate and halite weathering.EWQI data of the study area disclosed that 73.69% of the samples were appropriate for drinking.Due to high salinity,Magnesium(Mg^(2+)),Nitrate(NO_(3)^(-)),and Bicarbonate(HCO_(3)^(-)) concentrations,the north-central and north-eastern regions are particularly susceptible.The findings of the study may be accomplished by policymakers and groundwater managers to achieve sustainable groundwater development at the regional scale.