Groundwater salinity in the Horn of Africa: Spatial prediction modeling and estimated people at risk.

BACKGROUND: Changes in climate and anthropogenic activities have made water salinization a significant threat worldwide, affecting biodiversity, crop productivity and contributing to water insecurity. The Horn of Africa, which includes eastern Ethiopia, northeast Kenya, Eritrea, Djibouti, and Somalia, has natural characteristics that favor high groundwater salinity. Excess salinity has been linked to infrastructure and health problems, including increased infant mortality. This region has suffered successive droughts that have limited the availability of safe drinking water resources, leading to a humanitarian crisis for which little spatially explicit information about groundwater salinity is available. METHODS: Machine learning (random forest) is used to make spatial predictions of salinity levels at three electrical conductivity (EC) thresholds using data from 8646 boreholes and wells along with environmental predictor variables. Attention is paid to understanding the input data, balancing classes, performing many iterations, specifying cut-off values, employing spatial cross-validation, and identifying spatial uncertainties. RESULTS: Estimates are made for this transboundary region of the population potentially exposed to hazardous salinity levels. The findings indicate that about 11.6 million people (∼7% of the total population), including 400,000 infants and half a million pregnant women, rely on groundwater for drinking and live in areas of high groundwater salinity (EC > 1500 µS/cm). Somalia is the most affected and has the largest number of people potentially exposed. Around 50% of the Somali population (5 million people) may be exposed to unsafe salinity levels in their drinking water. In only five of Somalia's 18 regions are less than 50% of infants potentially exposed to unsafe salinity levels. The main drivers of high salinity include precipitation, groundwater recharge, evaporation, ocean proximity, and fractured rocks. The combined overall accuracy and area under the curve of multiple runs is âˆ¼ 82%. CONCLUSIONS: The modelled groundwater salinity maps for three different salinity thresholds in the Horn of Africa highlight the uneven spatial distribution of salinity in the studied countries and the large area affected, which is mainly arid flat lowlands. The results of this study provide the first detailed mapping of groundwater salinity in the region, providing essential information for water and health scientists along with decision-makers to identify and prioritize areas and populations in need of assistance.

Geogenic manganese and iron in groundwater of Southeast Asia and Bangladesh - Machine learning spatial prediction modeling and comparison with arsenic.

Naturally occurring, geogenic manganese (Mn) and iron (Fe) are frequently found dissolved in groundwater at concentrations that make the water difficult to use (deposits, unpleasant taste) or, in the case of Mn, a potential health hazard. Over 6000 groundwater measurements of Mn and Fe in Southeast Asia and Bangladesh were assembled and statistically examined with other physicochemical parameters. The machine learning methods random forest and generalized boosted regression modeling were used with spatially continuous environmental parameters (climate, geology, soil, topography) to model and map the probability of groundwater Mn > 400 µg/L and Fe > 0.3 mg/L for Southeast Asia and Bangladesh. The modeling indicated that drier climatic conditions are associated with a tendency of elevated Mn concentrations, whereas high Fe concentrations tend to be found in a more humid climate with elevated levels of soil organic carbon. The spatial distribution of Mn > 400 µg/L and Fe > 0.3 mg/L was compared and contrasted with that of the critical geogenic contaminant arsenic (As), confirming that high Fe concentrations are often associated with high As concentrations, whereas areas of high concentrations of Mn and As are frequently found adjacent to each other. The probability maps draw attention to areas prone to elevated concentrations of geogenic Mn and Fe in groundwater and can help direct efforts to mitigate their negative effects. The greatest Mn hazard is found in densely populated northwest Bangladesh and the Mekong, Red and Ma River Deltas of Cambodia and Vietnam. Widespread elevated Fe concentrations and their associated negative effects on water infrastructure pose challenges to water supply. The Mn and Fe prediction maps demonstrate the value of machine learning for the geospatial prediction modeling and mapping of groundwater contaminants as well as the potential for further constituents to be targeted by this novel approach.

Fluoride contamination of groundwater resources in Ghana: Country-wide hazard modeling and estimated population at risk.

Most people in Ghana have no or only basic access to safely managed water. Especially in rural areas, much of the population relies on groundwater for drinking, which can be contaminated with fluoride and lead to dental fluorosis. Children under the age of two are particularly susceptible to the adverse effects of fluoride and can retain 80-90% of a fluoride dose, compared to 60% in adults. Despite numerous local studies, no spatially continuous picture exists of the fluoride contamination across Ghana, nor is there any estimate of what proportion of the population is potentially exposed to unsafe fluoride levels. Here, we spatially model the probability of fluoride concentrations exceeding 1.0 mg/L in groundwater across Ghana to identify risk areas and estimate the number of children and adults exposed to unsafe fluoride levels in drinking water. We use a set of geospatial predictor variables with random forest modeling and evaluate the model performance through spatial cross-validation. We found that approximately 15% of the area of Ghana, mainly in the northeast, has a high probability of fluoride contamination. The total at-risk population is about 920,000 persons, or 3% of the population, with an estimated 240,000 children (0-9 years) in at-risk areas. In some districts, such as Karaga, Gushiegu, Tamale and Mion, 4 out of 10 children are potentially exposed to fluoride poisoning. Geology and high evapotranspiration are the main drivers of fluoride enrichment in groundwater. Consequently, climate change might put even greater pressure on the area's water resources. Our hazard maps should raise awareness and understanding of geogenic fluoride contamination in Ghana and can advise decision making at local levels to avoid or mitigate fluoride-related risks.