Water quality degradation of freshwater bodies is a concern worldwide, particularly in Africa, where data are scarce and standard water quality monitoring is expensive. This study explored the use of remote sensing imagery and machine learning (ML) algorithms as an alternative to standard field measuring for monitoring water quality in large and remote areas constrained by logistics and finance. Six machine learning (ML) algorithms integrated with Landsat 8 imagery were evaluated for their accuracy in predicting three optically active water quality indicators observed monthly in the period from August 2016 to April 2022: turbidity (TUR), total dissolved solids (TDS) and Chlorophyll a (Chl-a). The six ML algorithms studied were the artificial neural network (ANN), support vector machine regression (SVM), random forest regression (RF), XGBoost regression (XGB), AdaBoost regression (AB), and gradient boosting regression (GB) algorithms. XGB performed best at predicting Chl-a, with an R² of 0.78, Nash–Sutcliffe efficiency (NSE) of 0.78, mean absolute relative error (MARE) of 0.082 and root mean squared error (RMSE) of 9.79 µg/L. RF performed best at predicting TDS (with an R² of 0.79, NSE of 0.80, MARE of 0.082, and RMSE of 12.30 mg/L) and TUR (with an R² of 0.80, NSE of 0.81, and MARE of 0.072 and RMSE of 7.82 NTU). The main challenges were data size, sampling frequency, and sampling resolution. To overcome the data limitation, we used a K-fold cross validation technique that could obtain the most out of the limited data to build a robust model. Furthermore, we also employed stratified sampling techniques to improve the ML modeling for turbidity. Thus, this study shows the possibility of monitoring water quality in large freshwater bodies with limited observed data using remote sensing integrated with ML algorithms, potentially enhancing decision making.

Water hyacinth (Eichhornia crassipes) is a widespread invasive plant in tropical and subtropical regions, creating serious ecological and hydrological problems. Beyond disrupting aquatic ecosystems, it increases unaccounted water loss and alters key physicochemical properties. This study evaluated the evapotranspiration of water hyacinth and its influence on water quality in Lake Tana, Ethiopia’s largest freshwater lake. Two artificial ponds (one control and one covered with water hyacinth), each measuring 1 m × 1 m × 0.94 m, were monitored over three months to quantify water loss. In parallel, water samples were collected from the lake at 0.5 m depth along 2 km intervals, comparing hyacinth infested and open-water sites. The results showed clear differences between conditions. Dissolved oxygen was significantly lower in hyacinth-covered areas (6.65 ± 0.44 mg/L) than in open water (7.93 ± 0.42 mg/L). Similarly, pH decreased under hyacinth cover (5.53 ± 0.53) compared to non-infested sites (6.53 ± 0.40). In contrast, water temperature increased in infested areas (23.70 ± 0.42 °C) relative to open water (22.08 ± 0.33 °C). Total dissolved solids were slightly but significantly lower in hyacinth-covered water. Evapotranspiration from water hyacinth was about 1.6 times higher than evaporation from open water, with an estimated monthly loss of 0.28 m³ per square meter. When scaled to lake conditions, this corresponds to approximately 0.78 to 7.01 million m³ of water loss per month, though actual values may vary due to environmental factors. Overall, water hyacinth substantially affects both water quantity and quality, highlighting its importance for lake management and sustainable water use.