Background: Rainfall variability exceedingly affects agriculture in Ethiopia, particularly in the eastern region where rainfall is relatively scarce. Hence, understanding the spatiotemporal variability of rainfall is indispensable for planning mitigation measures during high and low rainfall seasons. This study examined the spatiotemporal variability and trends of rainfall in the West Harerge Zone, eastern Ethiopia. Method: The coefficient of variation (CV) and standardized anomaly index (SAI) were used to analyze rainfall variability while Mann-Kendall (MK) trend test and Sen’s slop estimator were employed to examine the trend and magnitude of the rainfall changes, respectively. The association between rainfall and Pacific Ocean Sea Surface Temperature (SST) was also evaluated by Pearson correlation coefficient (r). Results: The annual rainfall CV during 1983–2019 periods is between 12 and 19.36% while the seasonal rainfall CV extends from 15–28.49%, 24–35.58%, and 38–75.9% for average Kiremt (June–September), Belg (February–May), and Bega (October–January) seasons, respectively (1983–2019). On the monthly basis, the trends of rainfall decreased in all months except in July, October, and November. However, the trends were not statistically significant (α = 0.05), unlike in November. On a seasonal basis, the trends of mean Kiremt and Belg seasons rainfall decreased while it increased in Bega season although it is not statistically significant. Moreover, the annual rainfall showed a non-significant decreasing trend. The findings also revealed that the correlation between rainfall and Pacific Ocean SST was negative for Kiremt while positive for Belg and Bega seasons. Besides, annual rainfall and Pacific Ocean SST was negatively correlated. Conclusions: High spatial and temporal rainfall variability was observed at the monthly, seasonal, and annual time scales. Seasonal rainfall has high inter-annual variability in the dry season (Bega) than other seasons. The trends in rainfall were decreased in most of the months. Besides, the trend of rainfall decreased in the annual, Belg and Kiremt season while increased in the Bega season. The study also indicated that the occurrence of droughts in the study area was associated with ENSO events like most other parts of Ethiopia and East Africa.

Lake Tana is Ethiopia’s largest lake and is infested with invasive water hyacinth (E. crassipes), which endangers the lake’s biodiversity and habitat. Using appropriate remote sensing detection methods and determining the seasonal distribution of the weed is important for decision-making, water resource management, and environmental protection. As the demand for the reliable estimation of E. crassipes mapping from satellite data grows, comparing the performance of different machine learning algorithms could help in identifying the most effective method for E. crassipes detection in the lake. Therefore, this study aimed to examine the ability of random forest (RF), support vector machine (SVM), and classification and regression tree (CART) machine learning algorithms to detect E. crassipes and estimating seasonal spatial coverage of the weed on the Google Earth Engine (GEE) platform using Landsat 8 and Sentinel 2 images. Cloud-masked monthly median composite Landsat 8 and Sentinel 2 data from October 2021 and 2022, January 2022 and 2023, March 2022, and June 2022 were used to represent autumn, winter, spring, and summer, respectively. Four spectral indices were derived and used in combination with spectral bands to improve the E. crassipes detection accuracy. All methods achieved greater than 95% and 90% overall accuracy when using Sentinel 2 and Landsat 8 images, respectively. Using both data sets, all methods achieved a greater than 93% F1 score for E. crassipes detection. Though the difference in performance between the methods was small, the RF was the most accurate, while the SVM and CART methods had the same accuracy. The maximum E. crassipes coverage area was observed in autumn (22.4 km²), while the minimum (2.2 km²) was observed in summer. Based on Sentinel 2 data, the E. crassipes area coverage decreased significantly by 62.5% from winter to spring and increased significantly by 81.7% from summer to autumn. The findings suggested that the RF classifier was the most accurate E. crassipes detection algorithm, and autumn was an appropriate season for E. crassipes detection in Lake Tana.

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.

Drought is a serious threat to agriculture in Ethiopia. This study examined the spatiotemporal variability of agricultural drought and its association with climatic variables in the Upper Awash basin. Mann–Kendall (MK) trend test was employed to examine the drought trend while Sen’s slop estimator and pixel-based linear regression model were used to analyze the magnitude of drought changes. The association between agricultural drought and climatic variables was evaluated by the Pearson correlation coefficient (r). High spatiotemporal variability of drought was observed in Kiremit (June–September) and Belg (February–May) seasons. The Belg season spatial average vegetation condition index (VCI) trends were decreased insignificantly from 2001 to 2019 at a 5% significant level, whereas the spatial average VCI trends of Kiremit season were increased insignificantly. The return period of severe droughts during the Belg season was less frequent than the Kiremt season severe drought. The correlation between spatial average VCI and precipitation was positive for Belg and Kiremit seasons. Likewise, the correlation between average VCI and land surface temperature (LST) was negative in Belg and positive in Kiremit season. Moreover, the correlation between mean VCI and Pacific Ocean Sea Surface Temperature (SST) was positive for Belg and Kiremit seasons. The influencing factor of precipitation and LST on VCI during Belg season was higher than Kiremit season. The findings of this study are vital for decision-making systems and preparing plans to adjust sowing time, select drought-resistant crops, practice in situ water conservation, practice small-scale irrigation and diversify the income of smallholder farmers.