Groundwater (GW) is a key source of drinking water and irrigation to combat growing food insecurity and for improved water access in rural sub-Saharan Africa. However, there are limited studies due to data scarcity in the region. New modeling techniques such as Machine learning (ML) are found robust and promising tools to assess GW recharge with less expensive data. The study utilized ML technique in GW recharge prediction for selected locations to assess sustainability of GW resources in Ghana. Two artificial neural networks (ANN) models namely Feedforward Neural Network with Multilayer Perceptron (FNN-MLP) and Extreme Learning Machine (FNN-ELM) were used for the prediction of GW using 58 years (1960–2018) of GW data. Model evaluation between FNN-MLP and FNN-ELM showed that the former approach was better in predicting GW with R² ranging from 0.97 to 0.99 while the latter has an R² between 0.42 to 0.68. The overall performance of both models was acceptable and suggests that ANN is a useful forecasting tool for GW assessment. The outcomes from this study will add value to the current methods of GW assessment and development, which is one of the pillars of the sustainable development goals (SDG 6).

In the Eastern Region of Ghana, 95 % of residents have access to boreholes. However, approximately 30 % of these boreholes are characterized by unpleasurable taste, odour, oily scum and particulate matter. Thus, this study aimed to assess water quality, predict the sources of groundwater contaminants, evaluate the human health risk and to generate spatial distribution and health risk maps. In achieving this, the water quality of 136 boreholes in the region was evaluated through Water Quality Index (WQI) and Groundwater Pollution Index (GPI) analyses. Multivariate statistical procedures, namely, principal component and correlation analyses were employed to define the major groundwater pollutants and their possible sources. Non-carcinogenic health risk to infants, children and adults through nitrates, iron, manganese and fluorides ingestion was also assessed. The results revealed that groundwater in the region is generally slightly acidic with a mean pH of 6.30. WQI analysis grouped 68 % of the groundwater samples under the ‘excellent’ and ‘good’ water types with the remaining percent categorized under ‘poor’, ‘very poor’ and ‘unsafe’ drinking water types. GPI analysis classified 95 %, 2.21 % and 2.79 % of the boreholes as ‘insignificant’, ‘low’ and ‘highly’ polluted zones. From the multivariate analyses, the dominant pollutants were iron, manganese, chlorides, sodium, fluorides, potassium, turbidity, total suspended and dissolved solids, hardness, alkalinity, sulphates, nitrates and phosphates. The sources of these contaminants are primarily from rock-water interactions and fertilizers. Health risk assessment for nitrates, fluorides, iron and manganese ingestion revealed that 23, 17 and 15 boreholes in the region are likely to pose non-carcinogenic health risk to infants, children and adults respectively. Health risk maps indicated that the most vulnerable districts were Atiwa East, Fanteakwa North, Achiase, Birim South, Akwapim, Suhum and Ayensuano. From these findings, it is imperative that appropriate groundwater remediation measures are implemented in the region to protect public health.

The uncertainties and biases associated with Global Climate Models (GCMs) ascend from global to regional and local scales which delimits the applicability and suitability of GCMs in site-specific impact assessment research. The study downscaled two GCMs to evaluate effects of climate change (CC) in the Black Volta Basin (BVB) using Statistical DownScaling Model (SDSM) and 40-year ground station data. The study employed Taylor diagrams, dimensionless, dimensioned, and goodness of fit statistics to evaluate model performance. SDSM produced good performance in downscaling daily precipitation, maximum and minimum temperature in the basin. Future projections of precipitation by HadCM3 and CanESM2 indicated decreasing trend as revealed by the delta statistics and ITA plots. Both models projected near- to far-future increases in temperature and decreases in precipitation by 2.05-23.89, 5.41–46.35, and 5.84–35.33% in the near, mid, and far future respectively. Therefore, BVB is expected to become hotter and drier by 2100. As such, climate actions to combat detrimental effects on the BVB must be revamped since the basin hosts one of the largest hydropower dams in Ghana. The study is expected to support the integration of CC mitigation into local, national, and international policies, and support knowledge and capacity building to meet CC challenges.