Application of machine learning techniques to predict groundwater quality in the Nabogo Basin, Northern Ghana.

The main objective of this study was to map the quality of groundwater for domestic use in the Nabogo Basin, a sub-catchment of the White Volta Basin in Ghana, by applying machine learning techniques. The study was conducted by applying the Random Forest (RF) machine learning algorithm to predict groundwater quality, by utilizing factors that influence groundwater occurrence and quality such as Elevation, Topographical Wetness Index (TWI), Slope length (LS), Lithology, Soil type, Normalize Different Vegetation Index (NDVI), Rainfall, Aspect, Slope, Plan Curvature (PLC), Profile Curvature (PRC), Lineament density, Distance to faults, and Drainage density. The groundwater quality of the area was predicted by building a Random Forest model based on computed Arithmetic Water Quality Indices (WQI) (as dependent variable) of existing boreholes, to serve as an indicator of the groundwater quality. The predicted WQI of groundwater in the study area shows that it ranges from 9.51 to 69.99%. This implied that 21.97 %, 74.40 %, and 3.63 % of the study area had respectively the likelihood of excellent. The models were found to perform much better with an RMSE of 23.03 and an R2 value of 0.82. The study conducted highlighted an essential understanding of the groundwater quality in the study area, paving the way for further studies and policy development for groundwater management.

Nitrate contamination and source apportionment in surface and groundwater in Ghana using dual isotopes (15N and 18O-NO3) and a Bayesian isotope mixing model.

The rising food production to meet the growing human population has led to increased anthropogenic inputs of nutrients such as NO3- in groundwater and aquatic environments. Nitrate concentrations, hydrochemistry, and isotope data (δ18O-H2O, δ2H-H2O, 15N-NO3, and δ18O-NO3) from boreholes (BH), hand dug wells (HDW), and surface water (SW) were analyzed. The objectives of the study were to identify potential nitrate sources and their proportional contributions using an isotope mixing model (SIAR). The results showed that NO3- concentrations in the BH, HDW, and SW were heterogeneous and controlled by localized anthropogenic activities. The hydrochemistry and dual isotope (15N-NO3 and 18O-NO3) identified manure/sewage as the dominant source of NO3- in the groundwater, while the SW showed a complex signature overlapping in the areas of manure/septic, chemical fertilizer, and soil nitrogen. The SIAR analysis showed that sewage/manure contributed about 66%, 68%, and 55% of NO3- in the BH, HDW, and SW, respectively. In the study area, the NO3- source contribution based on the mean probable estimate (MPE) were in the order S&M > SN > CF > P. Shortcomings and the uncertainties associated with the SIAR to guide future studies have also been discussed. The study also highlighted the use of hydrochemistry, environmental isotopes, and Bayesian isotope mixing models for NO3- source identification and apportionment. This is to enable effective planning, farming practices, and sewage disposals to safeguard groundwater quality and control the eutrophication in rivers to meet safe drinking water demand.

Nitrate contamination of groundwater in the Lower Volta River Basin of Ghana: Sources and related human health risks.

A significant population within the Lower Volta River Basin of Ghana relies solely on untreated groundwater (GW) and surface water (SW) for various purposes. However, negative practices associated with increasing human activities pose threats to particularly GW quality in the basin. Using NO3- as a proxy, this study mainly focused on the status of GW contamination, origins of NO3- and potential human health risks through integrated hydrochemistry, correlation analysis, isotopes (15N, δ18O), Bayesian and USEPA human health risk models. Slightly acidic to alkaline GW and SW environments were observed. Electrical conductivity (EC) values above 1000 µS/cm were recorded in 45% of the GW with a maximum of 19370 µS/cm. NO3- in GW ranged from 0.12 to 733 mg/L with average 59.6 mg/L and positively correlated with K+, Ca2+, Mg2+, Cl-, Na+ and EC. In SW, a maximum of 5.3 mg/L of NO3- was observed. Largely, 75% of the GW exceeded local background NO3- value of 2.1 mg/L, while 35% were above the WHO recommended value of 50 mg/L. Bivariate and correlation relationships elucidated human contributions to sources of NO3-, Cl-, SO42- and K+ to GW in the basin. From NO3-/Cl- ratio, 43% of the GW and 21% of SW were affected by effluents and agrochemicals. Values for δ15N-NO3- and δ18O-NO3- ranged from +4.2‰ to +27.5‰ and +4.5‰ to +19.9‰ for GW, and from +3.8‰ to +14.0‰ and +10.7‰ to +25.2‰ for SW. Manure, septic effluents and mineralized fertilizers are sources of NO3- contamination of water in the basin. The Bayesian model apportioned 80% of GW NO3- contamination to sewage/manure. Hazard index indicated 70%, 50% and 48% medium to high-risk levels for infants, children and adults respectively, with 79% high-risk of SW NO2- contamination to infants. Immediate measures for GW and SW quality protection are recommended.

Tracking nitrate sources in groundwater and associated health risk for rural communities in the White Volta River basin of Ghana using isotopic approach (δ15N, δ18ONO3 and 3H).

In this study, we present a first attempt on the use of integrated hydro-chemical and isotopic technique to trace the sources of groundwater nitrate contamination in the Upper East Region of Ghana to aid the sustainable management of this vital resource. The objectives of the study are (1) assess the present status and spatial distribution of the nitrate contamination (2) identify and distinguish the most likely sources of nitrate , (3) identify the relationship between 3H and NO3- and F-, and (4) ascertain the potential human risk from exposure to nitrate contamination. The results showed that, nitrate concentrations varied from 0.42 to 431.17, 0.83 to 143.94, 0.03 to 28.94mg/l with mean values of 36.09, 21.54 and 5.01mg/l for boreholes, hand dug wells and the surface water respectively. These values showed that, about 95% of boreholes and hand dug wells and 45% of the surface water have nitrate concentration above the baseline value in the area. The NO3-/Cl- ratio showed that, 98.4%, 95% and 64% of the NO3- in the borehole, hand dug wells and the surface water are from anthropogenic activities. The δ15NNO3 and δ18ONO3- data confirmed that NO3- in the samples was predominantly derived from manure (human and animal waste) and denitrification occurring in some areas. The isotopic data further affirms the hydro-chemical interpretation that, chemical fertilizer and atmospheric deposition are unlikely sources of NO3- in the area. The relationship between 3H and NO3- concentrations showed that, higher NO3- values are associated with younger waters. Non carcinogenic health risk for adults and children posed by oral ingestion of the NO3- contaminated water revealed some degree of health risk, especially to children whose risk is about 72% higher. The study provides a conceptual model of the NO3- dynamics and some recommendation for groundwater management in the area.

Analysis of climate and anthropogenic impacts on runoff in the Lower Pra River Basin of Ghana.

The Lower Pra River Basin (LPRB), located in the forest zone of southern Ghana has experienced changes due to variability in precipitation and diverse anthropogenic activities. Therefore, to maintain the functions of the ecosystem for water resources management, planning and sustainable development, it is important to differentiate the impacts of precipitation variability and anthropogenic activities on stream flow changes. We investigated the variability in runoff and quantified the contributions of precipitation and anthropogenic activities on runoff at the LPRB. Analysis of the precipitation-runoff for the period 1970-2010 revealed breakpoints in 1986, 2000, 2004 and 2010 in the LPRB. The periods influenced by anthropogenic activities were categorized into three periods 1987-2000, 2001-2004 and 2005-2010, revealing a decrease in runoff during 1987-2000 and an increase in runoff during 2001-2004 and 2005-2010. Assessment of monthly, seasonal and annual runoff depicted a significant increasing trend in the runoff time series during the dry season. Generally, runoff increased at a rate of 9.98 × 107m3yr-1, with precipitation variability and human activities contributing 17.4% and 82.3% respectively. The dominant small scale alluvial gold mining activity significantly contributes to the net runoff variability in LPRB.