High-resolution long-term average groundwater recharge in Africa estimated using random forest regression and residual interpolation

Abstract

Groundwater recharge is a key hydrogeological variable that informs the renewability of groundwater resources. Long-term average (LTA) groundwater recharge provides a measure of replenishment under the prevailing climatic and land-use conditions and is therefore of considerable interest in assessing the sustainability of groundwater withdrawals globally. This study builds on the modelling results by MacDonald et al. (2021), who produced the first LTA groundwater recharge map across Africa using a linear mixed model (LMM) rooted in 134 ground-based studies. Here, continent-wide predictions of groundwater recharge were generated using random forest (RF) regression employing five variables (precipitation, potential evapotranspiration, soil moisture, normalised difference vegetation index (NDVI) and aridity index) at a higher spatial resolution (0.1° resolution) to explore whether an improved model might be achieved through machine learning. Through the development of a series of RF models, we confirm that a RF model is able to generate maps of higher spatial variability than a LMM; the performance of final RF models in terms of the goodness of fit (R2=0.83; 0.88 with residual kriging) is comparable to the LMM (R2=0.86). The higher spatial scale of the predictor data (0.1°) in RF models better preserves small-scale variability from predictor data than the values provided via interpolated LMMs; these may prove useful in testing global- to local-scale models. The RF model remains, nevertheless, constrained by its representation of focused recharge and by the limited range of recharge studies in humid, equatorial Africa, especially in the areas of high precipitation. This confers substantial uncertainty in model estimates.