The continued threat from climate change and human impacts on water resources demands high-resolution and continuous hydrological data accessibility for predicting trends and availability. This study proposes a novel threefold downscaling method based on machine learning (ML) which integrates: data normalization; interaction of hydrometeorological variables; and the application of a time series split for cross-validation that produces a high spatial resolution groundwater storage anomaly (GWSA) dataset from the Gravity Recovery and Climate Experiment (GRACE) and its successor mission, GRACE Follow-On (GRACE-FO). In the study, the relationship between the terrestrial water storage anomaly (TWSA) from GRACE and other land surface and hydrometeorological variables (e.g., vegetation coverage, land surface temperature, precipitation, and in situ groundwater level data) is leveraged to downscale the GWSA. The predicted downscaled GWSA datasets were tested using monthly in situ groundwater level observations, and the results showed that the model satisfactorily reproduced the spatial and temporal variations in the GWSA in the study area, with Nash-Sutcliffe efficiency (NSE) correlation coefficient values of 0.8674 (random forest) and 0.7909 (XGBoost), respectively. Evapotranspiration was the most influential predictor variable in the random forest model, whereas it was rainfall in the XGBoost model. In particular, the random forest model excelled in aligning closely with the observed groundwater storage patterns, as evidenced by its high positive correlations and lower error metrics (Mean Absolute Error (MAE) of 54.78 mm; R-squared (R²) of 0.8674). The downscaled 5 km GWSA data (based on random forest) showed a decreasing trend in storage associated with variability in the rainfall pattern. An increase in drought severity during El Niño lengthened the full recovery time of groundwater based on historical storage trends. Furthermore, the time lag between the occurrence of precipitation and recharge was likely controlled by the drought intensity and the spatial recharge characteristics of the aquifer. Projected increases in drought severity could further increase groundwater recovery times in response to droughts in a changing climate, resetting storage to a new tipping condition. Therefore, climate change adaptation strategies must recognise that less groundwater will be available to supplement the surface water supply during droughts.

Radar and Optical based satellite sensors were used in the study of the Mumbwa flood of December 2020. The Synthetic Aperture Radar (SAR) based Sentinel-1B was processed in Google Earth Engine (GEE) and utilized to generate an image mosaic from December 2020 to May 2021 to delineate flood extent. A local water histogram threshold change detection approach by image ratio was utilized to determine the flood extent with an intensity value of 1.26 dB as it fitted the study area uniquely as opposed to the global value of 1.25 dB. After extracting the initial flood water extent, it was necessary to filter out regions which inundated during the flood period. This was carried out using the following datasets and parameters: The HydroSHEDS Digital Elevation Model (DEM) was used to filter out regions with a slope value of greater than 7% and the Global Surface Water Layer was used to clip out regions with existing permanent surface water. Once the flooded areas were identified, the Optical based Sentinel-2 was used in the production of a Land Use Land Cover (LULC) Map for August 2020 in order to superimpose the flooded areas with existing land features over the study area. The map also under went pre and post processing in GEE using the Random Forest Classification Algorithm that achieved an Overall Accuracy and Kappa Coefficient of 0.957 and 0.91519 respectively. Thereafter the flood analysis and damage assessment were carried out. The quantitative damages to Landcover were found to be: Wetland 6,338.97 Ha (33.27%), Shrubland 5,117.75 Ha (26.89%), Biochar Soil 3,660.47 Ha (19.21%), Trees 3,466.37 Ha (18.19%), Bare soil 273.47 Ha (1.44%), Crop Fields 190.69 Ha (1%) and Built-Up 4.13 Ha (0.02%). Therefore the use of SAR by local histogram threshold approach with Optical datasets for LULC map production proved successful in the study of flood damage.