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.

Soil erosion in Ethiopia harms agricultural production, water quality, and overall ecosystem health. Effective soil loss estimation can help minimize these outcomes. The implementation of the Revised Universal Soil Loss Equation (RUSLE) in Ethiopia has not been sufficiently evaluated. Thus, the main objective of this review is to systematically review the comprehensive strengths and limitations of the RUSLE model applications for soil loss estimation. Specifically, it evaluates the specific parameters used, the type of input data, the validation approaches, and the role of GIS and remote sensing in the computation process of the RUSLE Model. An extensive search method was employed to classify suitable research papers about applying the RUSLE model in estimating soil erosion in Ethiopia. The review underscores that different approaches have been used to compute the five parameters of the RUSLE model. Key strengths of the RUSLE model include its widespread acceptance and adaptability to various environmental conditions; however, notable limitations are evident, regarding the validation and calibration processes. This review highlights that the scale of study areas varies widely, from 18.33 to 1,119,683 km². Soil loss estimates across the reviewed studies ranged from 12.94 to 576 t ha⁻¹ yr⁻¹. The findings of this review presented here are critical for using the RUSLE model to estimate soil loss integrating it with other process-based models and the advanced machine learning technologies. Ultimately, this review aids in improving soil resource management and ecological sustainability in Ethiopia.

Ethiopia is currently facing a major environmental problem caused by soil erosion. In order to tackle this problem, it is essential to implement a comprehensive watershed management approach and give priority to conservation efforts depending on the level of severity. Therefore, the objective of this research is to evaluate the mean annual soil erosion and rank the sub-watersheds for conservations in the Ayu watershed, utilizing the Revised Universal Soil Loss Equation (RUSLE) model and the Sub-Watershed Prioritization Tool (SWPT). RUSLE was utilized to predict the annual average soil erosion rate, while SWPT was applied to conduct Weighted Sum Analysis (WSA) for ranking sub-watersheds. Support Vector Machine (SVM) was employed for classifying land use and land cover. The Relative importance of morphometric and topo-hydrologic features in the SWPT was analyzed using a Random Forest model. The Bland-Altman plot and Wilcoxon Signed Rank Test were employed to assess the agreement in prioritizing watersheds between RUSLE results and the SWPT. Furthermore, field observations were conducted to validate the land use classification by collecting ground data. In addition, the study was enhanced with local viewpoints by conducting focus group discussions with agricultural experts and farmers to obtain qualitative insights and validation of resuts. The findings showed that soil loss varied from 0 to 110 t/ha/yr, with an average of 8.95 t/ha/yr, resulting in a total loss of 384365.3 tons annually. The comparison of RUSLE and SWPT showed a moderate positive relationship (r = 0.59). The results of the Bland-Altman plot indicate a consistent agreement between the two methods. However, there is inconsistency among the five sub watersheds. This study enhances the knowledge of soil erosion patterns and offers useful guidance for watershed conservation techniques. It can be also used as a beneficial framework for managing watersheds, with possible uses outside of the Ayu watershed.

Irrigation dams and irrigation suitability analysis is important for optimal water management, crop selection and productivity, water conservation, environmental sustainability, and economic viability in agriculture arena. Thus, the main objectives of this study were to identify a suitable dam site and irrigation area in the Gedeb River, Ethiopia, using Multi-Criteria Decision-Making analysis and 3D Visualization techniques. To identify a suitable dam site, various parametrs such as rainfall, runoff, stream flow, mineral site, faulting areas, landslide site, rock types, elevation points, relief features, soil types were used while to identify a suitable irrigation area, different parametrs such as altitude, slope, soil, geological structure, distance, and land use land cover datasets were used. The necessary dataset which were used to identify a suitable dam site and irrigation area collected from Ethiopian Mapping Authority (EMA), Ethiopian irrigation and energy ministry freely. In addition, for the final irrigation dam site selection and suitable irrigation area in the Gedeb watershed, multi-criteria decision-making method with expert judgment were applied respectively. Based on the study's findings, a suitable irrigation water reservoir dam covering an area of 1886 ha, with a potential water holding capacity of 2,961,145,697 cubic meters was identified. The results also revealed a highly suitable area of 18,362.05 ha, a moderately suitable area of 19,204.05 ha, a marginally suitable area of 2095.25 ha, and a not suitable area of 2.89 ha for the aforementioned purpose. The methodological approach and research findings presented in this study can greatly assist government and non-governmental organization planners and decision-makers in the development of irrigation projects.

Background: Effective management of solid waste, generated as a result of human activities, is crucial. However, improper solid waste management seriously threatens the environment and public health in developing countries including Ethiopia. Objective: This study is aimed at assessing the status of solid waste management practices and identifying key factors in Awi Administrative Zone, Ethiopia. Methods: A community‐based cross‐sectional study design was used to collect the data and then analyze using descriptive statistics and logistic regression modeling. The survey was conducted in select kebeles (wards) (administrative subdivisions) of Injibara, Dangila, and Chagni towns, using two‐stage sampling techniques. Primary and secondary data sources were utilized. The per capita waste generation rate was calculated based on the total solid waste generated in kilograms per total family size of households per year. Results: The per capita per day solid waste generation rates for Injibara, Dangila, and Chagni were 0.443, 0.456, and 0.487 kg/capita/day, respectively. The composition of household solid waste mainly consisted of biodegradable and nonbiodegradable materials. It was concluded that a significant proportion of household solid waste comprised biodegradable organic matter, which could be efficiently recycled or decomposed through microbial activity. Of the households, 40.6% had access to door‐to‐door solid waste collection service, and 35.9% and 26.2% of the households disposed their solid waste on riverside bridge/drainage lines and roadside/open land, respectively. The regression analysis showed that the head of the household’s age, family size, monthly income, solid waste selling practice, solid waste reduction practice, awareness of solid waste disposal rules, frequency of household cleanup campaign participation, and awareness of the impacts of improper solid waste management on the environment and human health were significantly associated with improper solid waste management practices. Conclusion: The study revealed poor performance in solid waste management in the study area, attributed to factors such as inadequate collection system design and schedule, open burning of refuse, substandard condition of the final dumpsite, and lack of community awareness leading to illegal dumping. Recommendations: Based on the findings of the study, we recommend that the town municipality strengthen its door‐to‐door solid waste collection service and distribution of communal bin containers, conduct environmental assessments for better dumpsite selection, and implement a community‐based waste management system to ensure sustainable solutions and continuous education on proper solid waste management practices.