Groundwater is an important resource that contributes significantly to the total annual water supply. The purpose of the present study is to assess and delineate the groundwater recharge zone using geospatial technology through an analytical hierarchal process (AHP) method in to the Muga watershed, Abay Basin. Remote sensing satellite images and the corresponding data are used for the preparation of thematic layers, viz., geology, rainfall, slope, soil, curvature, topography wetness index, elevation, drainage density, land use land cover, and lineament density of the study watershed. All thematic layers are integrated with a multicriteria evaluation technique. Weighted overlay index analysis is carried out to give rank for each parameter. The weight is assigned for each thematic layer depending on the AHP technique. The reliability of the output is checked by the calculated consistency index and consistency ratio which is reasonably acceptable (0.044 < 0.1). Verification is done by considering the groundwater well locations in the validation datasets. The receiver operating characteristic curve and area under curve (=82.9%) are used to explore the prediction accuracy.

Climate extreme events have been observed more frequently since the 1970s throughout Ethiopia, which adversely affects the socio-economic development of the country, as its economy depends on agriculture, which, in turn, relies heavily on annual and seasonal rainfall. Climate extremes studies conducted in Ethiopia are mainly limited to a specific location or watershed, making it difficult to have insights at the national level. The present study thus aims to examine the observed climate extreme events in Ethiopia at both station and agro-ecological zone (AEZ) levels. Daily rainfall and temperature data for 47 and 37 stations, respectively (1986 up to 2020), were obtained from the National Meteorology Agency (NMA). The Modified Mann–Kendall (MMK) trend test and the Theil–Sen slope estimator were employed to estimate the trends in rainfall and temperature extremes. This study examines trends of 13 temperature and 10 rainfall extreme indices using RClimDex in R software. The results revealed that most of the extreme rainfall indices showed a positive trend in the majority of the climate stations. For example, an increase in consecutive dry days (CDD), very heavy rainfall days (R20), number of heavy rainfall days (R10) and consecutive wet days (CWD) were exhibited in most climate stations. In relation to AEZs, the greater number of extreme rainfall indices illustrated an upward trend in cool and sub-humid, cool and humid, and cool and moist AEZs, a declining trend in hot arid AEZ, and equal proportions of increasing and decreasing trends in warm semi-arid AEZs. Concerning extreme temperature indices, the result indicated an increasing trend of warm temperature extreme indices and a downward trend of cold temperature extreme indices in most of the climate stations, indicating the overall warming and dryness trends in the country. With reference to AEZs, an overall warming was exhibited in all AEZs, except in the hot arid AEZ. The observed trends in the rainfall and temperature extremes will have tremendous direct and indirect impacts on agriculture, water resources, health, and other sectors in the country. Therefore, the findings suggest the need for identifying and developing climate change adaptation strategies to minimize the ill effects of these extreme climate events on the social, economic, and developmental sectors.

The change in climate elements such as rainfall and temperature are determinant factors of hydrological components (e.g., streamflow, water yield, evapotranspiration). Thus, understanding the trends of hydro-climate variables are imperative for planning water resources management measures. This study examines the trends of precipitation and temperature (1980–2014) as well as streamflow (1990–2008) changes in the Jemma sub-basin of the Upper Blue Nile (Abbay) Basin. A homogeneity test was performed for pre-processing data to inspect the statistical nature of data homogeneity viz., Pettitt’s, SNHT, Buishand range test, and Von Neumann test (VNT). The Mann–Kendall (MK) test, Modified Mann–Kendall (MMK) test, Sen’s slope estimator, and Innovative trend analysis (ITA) were applied to compute the existence of trend and the magnitude of change at an annual timescale. In a nutshell, the study portrays a change in the trends of hydro-climate variables when using different statistical tests. The result showed that the mean annual temperature in many stations depicted upward trends. There is a significant increasing trend (p < 0.05) by 0.029 °C per year in the mean annual temperature of all climatic stations. Based on Sen’s slope estimator, the annual precipitation and streamflow were increased by 1.781 mm/year and 0.085 m³/s, respectively. But no significant trends were detected in precipitation and streamflow when using Sen’s slope estimator test. The results of this study are worthwhile for evaluating the trends of hydro-climatic variables in other areas of Ethiopia in particular and elsewhere in the world in general, which are fundamental for planning water resource management measures.

Accurate drought prediction is essential for proactive water management and agricultural planning, especially in regions like Ethiopia that are highly susceptible to climate variability. This study investigates the classification of the Palmer Drought Severity Index (PDSI) using machine learning models trained on TerraClimate data, incorporating variables such as precipitation, temperature, soil moisture, and vapor pressure deficit. We employed several classifiers Logistic Regression, Support Vector Machine (SVM), k-Nearest Neighbors (KNN), Decision Tree, Random Forest, Gradient Boosting, Naive Bayes, AdaBoost, and XGBoost with Logistic Regression serving as a baseline statistical approach for comparison. To address data imbalance across drought classes, we applied a hybrid resampling method combining manual upsampling and SMOTE. Hyperparameter tuning was conducted using grid search and cross-validation. Random Forest outperformed all models, achieving an accuracy of 71.18%, F1-score of 0.71, and ROC AUC of 0.9000. Gradient Boosting and SVM also performed well with ROC AUC values of 0.8982 and 0.8681, respectively. SHAP analysis revealed that soil moisture, precipitation, and vapor pressure deficit were the most influential features in predicting drought severity. For benchmarking, an ARIMA (3,1,2) time-series model was applied but yielded poor performance (RMSE = 1.789, R² = −0.077), confirming the advantages of non-linear machine learning techniques for complex climate data. The results highlight the utility of ensemble learning in environmental modelling, offering valuable insights for drought early warning systems and climate resilience planning in Ethiopia. Future work should explore integrating localized predictors and real-time data to enhance prediction robustness.

The Blue Nile basin is one of the hot‐spots of soil erosion areas in Ethiopia. However, the impact of land use changes on soil erosion is poorly understood in the Tagaw watershed. Hence, the objective of the study is to assess the impact of land use changes on soil erosion in Tagaw watershed over the last 31 years. Rainfall, soil, satellite images and topographic data are acquired from field survey and secondary sources. A Revised Universal Soil Loss Equation (RUSLE) model is used to estimate soil erosion. The mean annual and total potential soil losses of the watershed are 19.3, 22.9, 26 and 0.06–503.56, 0.11–516.67, and 0.00–543.5 tons ha⁻¹ yr⁻¹ for 1995, 2006 and 2016 respectively. The highest soil loss is found for bare land. The RUSLE model further showed that the highest soil erosion occurred in 2016 whereas the lowest soil erosion occurred in 1995.