This study aims to evaluate changes in the frequency and severity of historical droughts (1980–2018) and then model future droughts occurrences (2019–2099) in the Lepelle River Basin (LRB), using Intergovernmental Panel on Climate Change (IPPC) General Circulation Model (GCM) simulations for two representative concentration pathways (RCP8.5 and RCP4.5). Firstly, the present-day and future hydrology of the LRB are modelled using the weather evaluation and planning (WEAP) model. Mann–Kendall tests are conducted to identify climate trends in the LRB. The reconnaissance drought in-dex (RDI) and the streamflow drought index (SDI) are employed to explore hydro-meteorological droughts in the Lepelle River Basin, South Africa. The RDI and SDI are plotted over time to assess drought magnitude and duration. The simulated temporal evolution of RDI and SDI show a significant decrease in wetting periods and a concomitant increasing trend in the dry periods for both the lower and middle sections of the LRB under RCP4.5 as the 22nd century is approached. Lastly, the Spearman and Pearson correlation matrix is used to determine the degrees of association between the RDI and SDI drought indices. A strong positive correlation of 0.836 is computed for the middle and lower sections of the LRB under the RCP8.5 forcing. Further findings indicate that severe to extreme drought above –2.0 magnitude are expected to hit the all three sec-tions of the LRB between 2080 and 2090 under RCP8.5. In the short term, it is suggested that policy actions for drought be implemented to mitigate possible impacts on human and hydro-ecological systems in the LRB.

Artificial neural network models (ANNs) were used in this study to predict reference evapotranspiration ( ET_o) using climatic data from the meteorological station at the test station in Kafr El-Sheikh Governorate as inputs and reference evaporation values computed using the Penman–Monteith (PM) equation. These datasets were used to train and test seven different ANN models that included different combinations of the five diurnal meteorological variables used in this study, namely, maximum and minimum air temperature ( T_max and T_min), dew point temperature ( T_dw), wind speed ( u), and precipitation (P), how well artificial neural networks could predict ET_o values. A feed- forward multi-layer artificial neural network was used as the optimization algorithm. Using the tansig transfer function, the final architected has a 6-5-1 structure with 6 neurons in the input layer, 5 neurons in the hidden layer, and 1 neuron in the output layer that corresponds to the reference evapotranspiration. The root mean square error ( RMSE) of 0.1295 mm∙day ^–1 and the correlation coefficient ( r) of 0.996 are estimated by artificial neural network ET_o models. When fewer inputs are used, ET_o values are affected. When three separate variables were employed, the RMSE test values were 0.379 and 0.411 mm∙day ^–1 and r values of 0.971 and 0.966, respectively, and when two input variables were used, the RMSE test was 0.595 mm∙day ^–1 and the r of 0.927. The study found that including the time indicator as an input to all groups increases the prediction of ET_o values significantly, and that including the rain factor has no effect on network performance. Then, using the Penman–Monteith method to estimate the missing variables by using the ET_o calculator the normalised root mean squared error ( NRMSE) reached about 30% to predict ET_o if all data except temperature is calculated, while the NRMSE reached about of 13.6% when used ANN to predict ET_o using variables of temperature only.