Groundwater is a critical resource in India for the supply of drinking water and for irrigation. Its usage is limited not only by its quantity but also by its quality. Among the most important contaminants of groundwater in India is arsenic, which naturally accumulates in some aquifers. In this study we create a random forest model with over 145,000 arsenic concentration measurements and over two dozen predictor variables of surface environmental parameters to produce hazard and exposure maps of the areas and populations potentially exposed to high arsenic concentrations (>10 µg/L) in groundwater. Statistical relationships found between the predictor variables and arsenic measurements are broadly consistent with major geochemical processes known to mobilize arsenic in aquifers. In addition to known high arsenic areas, such as along the Ganges and Brahmaputra rivers, we have identified several other areas around the country that have hitherto not been identified as potential arsenic hotspots. Based on recent reported rates of household groundwater use for rural and urban areas, we estimate that between about 18–30 million people in India are currently at risk of high exposure to arsenic through their drinking water supply. The hazard models here can be used to inform prioritization of groundwater quality testing and environmental public health tracking programs.

Geogenic arsenic contamination in groundwaters poses a severe health risk to hundreds of millions of people globally. Notwithstanding the particular risks to exposed populations in the Indian sub-continent, at the time of writing, there was a paucity of geostatistically based models of the spatial distribution of groundwater hazard in India. In this study, we used logistic regression models of secondary groundwater arsenic data with research-informed secondary soil, climate and topographic variables as principal predictors generate hazard and risk maps of groundwater arsenic at a resolution of 1 km across Gujarat State. By combining models based on different arsenic concentrations, we have generated a pseudo-contour map of groundwater arsenic concentrations, which indicates greater arsenic hazard ([ 10 lg/L) in the northwest, northeast and southeast parts of Kachchh District as well as northwest and southwest Banas Kantha District. The total number of people living in areas in Gujarat with groundwater arsenic concentration exceeding 10 lg/L is estimated to be around 122,000, of which we estimate approximately 49,000 people consume groundwater exceeding 10 lg/L. Using simple previously published doseresponse relationships, this is estimated to have given rise to 700 (prevalence) cases of skin cancer and around 10 cases of premature avoidable mortality/ annum from internal (lung, liver, bladder) cancersthat latter value is on the order of just 0.001% of internal cancers in Gujarat, reflecting the relative low groundwater arsenic hazard in Gujarat State.

Groundwater arsenic in Uruguay is an important environmental hazard, hence, predicting its distribution is important to inform stakeholders. Furthermore, occurrences in Uruguay are known to variably show dependence on depth and geology, arguably reflecting different processes controlling groundwater arsenic concentrations. Here, we present the distribution of groundwater arsenic in Uruguay modelled by a variety of machine learning, basic expert systems, and hybrid approaches. A pure random forest approach, using 26 potential predictor variables, gave rise to a groundwater arsenic distribution model with a very high degree of accuracy (AUC = 0.92), which is consistent with known high groundwater arsenic hazard areas. These areas are mainly in southwest Uruguay, including the Paysandú, Río Negro, Soriano, Colonia, Flores, San José, Florida, Montevideo, and Canelones departments, where the Mercedes, Cuaternario Oeste, Raigón, and Cretácico main aquifers occur. A hybrid approach separating the country into sedimentary and crystalline aquifer domains resulted in slight material improvement in a high arsenic hazard distribution. However, a further hybrid approach separately modelling shallow (<50 m) and deep aquifers (>50 m) resulted in the identification of more high hazard areas in Flores, Durazno, and the northwest corner of Florida departments in shallow aquifers than the pure model. Both hybrid models considering depth (AUC = 0.95) and geology (AUC = 0.97) produced improved accuracy. Hybrid machine learning models with expert selection of important environmental parameters may sometimes be a better choice than pure machine learning models, particularly where there are incomplete datasets, but perhaps, counterintuitively, this is not always the case.

Cardiovascular diseases (CVDs) have been recognized as the most serious non-carcinogenic detrimental health outcome arising from chronic exposure to arsenic. Drinking arsenic contaminated groundwaters is a critical and common exposure pathway for arsenic, notably in India and other countries in the circum-Himalayan region. Notwithstanding this, there has hitherto been a dearth of data on the likely impacts of this exposure on CVD in India. In this study, CVD mortality risks arising from drinking groundwater with high arsenic (>10 μg/L) in India and its constituent states, territories, and districts were quantified using the population-attributable fraction (PAF) approach. Using a novel pseudo-contouring approach, we estimate that between 58 and 64 million people are exposed to arsenic exceeding 10 μg/L in groundwater-derived drinking water in India. On an all-India basis, we estimate that 0.3–0.6% of CVD mortality is attributable to exposure to high arsenic groundwaters, corresponding to annual avoidable premature CVD-related deaths attributable to chronic exposure to groundwater arsenic in India of between around 6500 and 13,000. Based on the reported reduction in life of 12 to 28 years per death due to heart disease, we calculate value of statistical life (VSL) based annual costs to India of arsenic-attributable CVD mortality of between USD 750 million and USD 3400 million.

Although there are an increasing number of artificial intelligence/machine learning models of various hazardous chemicals (e.g. As, F, U, NO3−, radon) in environmental media (e.g. groundwater, soil), these most commonly use arbitrarily selected cutoff criteria to balance model specificity and sensitivity. This results in models of hazard distribution that, whilst often of considerable interest and utility, are not designed to optimize cost benefits of the mitigation of those hazards. In this case study, building upon recent machine learning modelling of the geographical distribution of groundwater arsenic in India, we show that the use of objective cost-informed criteria not only results in (i) different cutoff values for the classification of areas as of high or low groundwater arsenic hazard but also, more importantly, (ii) a reduction of overall potential (mitigation + testing + health impacts) costs. Further, we show that the change in optimal cutoff values and the reduction in overall costs vary from state to state depending upon locally specific classification-dependent costs, the prevalence of high arsenic groundwaters, the heterogeneity of the distribution of those high arsenic groundwaters, and the extent to which inhabitants are exposed to the hazard. It follows more generally that using cost-optimized criteria will result in different, more objective, and more cost-relevant appropriate balances being made between specificity and sensitivity in modelling environmental hazard distribution in different regions. This indicates also the utility of developing machine learning models at an appropriate local (e.g. country, state, district) scale rather than more global scales in order to better inform local-scale mitigation strategies.