Tadele Bedo Gelete

@haramaya.edu.et

School of Geography and Environmental Science program of Geo-Information Science
Haramaya University

Tadele Bedo Gelete


                  Download Compact PDF  
https://researchid.co/tadelebedo

RESEARCH, TEACHING, or OTHER INTERESTS

Earth and Planetary Sciences, Artificial Intelligence, Forestry, General Decision Sciences
11

Scopus Publications

138

Scholar Citations

6

Scholar h-index

6

Scholar i10-index

Scopus Publications

  • Random forest-based species distribution modeling reveals intensifying multi-species invasion risks of alien plants in Ethiopia under climate change
    Kalid Hassen Yasin, Diriba Tulu, Tadele Bedo Gelete, Beyan Ahmed Yuya, Anteneh Derribew Iguala, Kiya Adare Tadesse, Erana Kebede
    Remote Sensing Applications Society and Environment, 2026
  • Spatiotemporal analysis of urban expansion and its impact on farmlands in the central Ethiopia metropolitan area
    Kalid Hassen Yasin, Anteneh Derribew Iguala, Tadele Bedo Gelete
    Discover Sustainability, 2025
    Urban growth in sub-Saharan Africa presents significant challenges to sustainable development, food security, and environmental conservation. The rapid urban expansion and impact on agricultural land reduction in central Ethiopian metropolitan areas (Addis Ababa and Sheger city) exemplify these issues while simultaneously offering opportunities for sustainable development. This study aims to quantify and characterize the spatiotemporal dynamics of urban expansion in Addis Ababa and the surrounding Sheger city, explicitly focusing on understanding the impact of urban expansion on farmlands. The supervised random forest (RF) classification in the Google Earth Engine platform was used to prepare land use and land cover (LULC) for 1990, 2000, 2010, and 2023. The study employed an analytical framework incorporating multiple methodologies: intensity analysis at interval, categorical, and transitional levels to quantify urban growth trajectories; gradient direction and distance analyses to examine spatial expansion patterns; and Land Expansion Index (LEI) and Landscape Dynamic Typology (LDT) metrics to characterize the urban morphology and spatial dynamics of the study area. The results revealed that edge expansion is the predominant mode of urban development, primarily affecting farmlands in the eastern section. Built-up areas quadrupled between 1990 and 2023, whereas arable land declined. Intensity analysis revealed significant changes, particularly affecting farmlands. Our LDT analysis showed reduction in stable areas and increased in LULC changes from 1990 to 2023. The findings highlight the need for revised urban development strategies in Ethiopia to focus on compact and efficient growth while safeguarding agricultural lands, aligning with SDGs 2, 11, and 15 to promote balanced development that ensures urban and agricultural sustainability.
  • Machine learning predictions of climate change effects on nearly threatened bird species (Crithagra xantholaema) habitat in Ethiopia for conservation strategies
    Tadele Bedo Gelete, Diriba Tulu, Kalid Hassen Yasin, Erana Kebede
    Scientific Reports, 2025
    Endemic and endangered bird species, such as Salvadori serin ( C. xantholaema ), are vulnerable to environmental and anthropogenic changes. Understanding the impact of climate change on ecological niches is essential for effective conservation. This study employed advanced ML algorithms to model the current and future suitability of C. xantholaema under two scenarios (SSP245 and SSP585) for the years 2050 and 2070. The four machine learning models, namely, Maximum Entropy (MaxEnt), Random Forest (RF), Support Vector Machine (SVM), and Extreme Gradient Boost (XGBoost), predicted habitat suitability using 188 presence occurrence data and 15 environmental factors. Model performance was assessed using AUC-ROC, accuracy, precision, sensitivity, specificity, kappa, and F1 score, with ensemble modeling techniques enhancing reliability. The current analysis indicated high predictive accuracy, with XGBoost achieving the highest AUC (0.99), followed by RF (0.98), SVM (0.97), and MaxEnt (0.92). Regarding habitat suitability, 75.3% of Ethiopia’s land was unsuitable for C. xantholaema , with only 3.9% classified as highly suitable. By 2050, 61.82% and 57.14% of areas were projected to be unsuitable under SSP245 and SSP585, respectively. By 2070, unsuitable habitats may increase to 65.24% (SSP245) and 60.17% (SSP585), further decreasing habitat suitability. High-suitability habitats are expected to decline by 80.8% in 2050, covering approximately 8,259.95 km 2 , and by 73.2% in 2070, covering about 11,584.6 km 2 . Precipitation during the driest month (Bio14) was the most crucial predictor of habitat suitability, with importance values ranging from 32.5% (XGBoost) to 100% (SVM and RF), while temperature-related factors, particularly annual mean temperature (Bio1), contributed differently across ML models. According to this study, climate factors impact habitat changes. The findings emphasize the urgent need for conservation strategies to mitigate C. xantholaema habitat loss. Future research should include local data and other human-related factors to enhance the effectiveness of conservation efforts and improve predictions.
  • Advanced geospatial and machine learning models identify groundwater potential and reveal storage dynamics in Ethiopia's abbay river basin
    Kalid Hassen Yasin, Tadele Bedo Gelete, Erana Kebede, Anteneh Derribew Iguala, Mohammed Yusuf Abdo
    Journal of Hydrology Regional Studies, 2025
    The Abbay (Blue Nile) River Basin in Ethiopia is a critical sub-basin of the Nile, facing mounting groundwater management challenges due to its complex hydrogeology, which is compounded by climate change, population growth, and agricultural intensification. We developed a hydrologically validated groundwater potential zone (GWPZ) map using four machine learning algorithms—random forest (RF), extremely randomized trees (EXT), support vector machines (SVM), and extreme gradient boosting (XGBoost)–to capture spatial nonlinearity and hydrogeological complexity. Models were trained on 18 environmental predictors and 7100 well/spring locations, balanced with pseudoabsences generated via target-group background sampling in low-potential geomorphological units > 5 km from known water points. To reduce spatial autocorrelation bias, a 5-fold spatial cross-validation was employed. Model performance was evaluated using accuracy, F1 score, log loss, and AUC, with RF achieving the highest predictive accuracy (91 %) and rainfall as the dominant predictor. Spatial patterns revealed high-potential zones in the northeast and low-potential zones in the northwest and south. The ML-delineated high-potential zones demonstrated remarkable congruence with GRACE/GLDAS-derived groundwater storage trends, revealing significant recharge (+4.41 mm· yr⁻¹, 2003–2023) without dataset integration. This independent validation, emerging from methodologically distinct approaches, robustly confirmed the active recharge dynamics of the basin. By leveraging ML alongside satellite hydrology, we established a scalable framework for resolving hydrogeological complexities in data-scarce regions, with direct implications for evidence-based groundwater governance and regional water security. • Random Forest algorithms achieve 91 % accuracy in groundwater potential mapping. • Rainfall is identified as the key predictor in the model. • GRACE/GLDAS data integration reveals a 2.3 cm/year groundwater storage increase post-2015 infrastructure changes. • Machine learning algorithm enhances prediction accuracy in complex hydrogeological systems.
  • Methodological Integration of Machine Learning and Geospatial Analysis for PM10 Pollution Mapping
    Kalid Hassen Yasin, Muaz Ismael Yasin, Anteneh Derribew Iguala, Tadele Bedo Gelete, Erana Kebede
    Methodsx, 2025
    Air pollution mitigation necessitates accurate spatial modelling to inform public health interventions. Traditional approaches inadequately capture complex predictor-pollutant interactions, whereas machine learning (ML) offers a superior capacity for modelling nonlinear relationships. This study compares three ML Random Forest (RF), K-Nearest Neighbors (KNN), and Naïve Bayes (NB) algorithms using annual PM 10 data from 11 monitoring stations alongside atmospheric, urban, and terrain covariates. The methodological framework employed rigorous preprocessing and cross-validation to classify pollution into three categorical levels. Results demonstrate RF superior performance, achieving 94% balanced accuracy and 97% specificity, significantly outperforming KNN (92%) and NB (89%). RF excelled in capturing spatial heterogeneity and complex variable interactions, while KNN and NB exhibited limitations in managing feature dependencies and localized variability. Despite computational demands, findings substantiate RF reliability for robust air quality monitoring applications. The study contributes valuable insights for implementing scalable pollution prediction systems in resource-constrained urban environments while acknowledging interpretability challenges inherent to complex ML models. • Preprocessing of spatial data from various sources, incorporating the handling of missing/abnormal data, analysis, and normalization • Implementation of the three ML algorithms with rigorous hyperparameter tuning, model validation, and performance assessment • Mapping PM 10 Hotspots on the Gradient Direction and Distance from the City Center
  • Predictive machine learning and geospatial modeling reveal PM10 hotspots and guide targeted air pollution interventions in Addis Ababa, Ethiopia
    Kalid Hassen Yasin, Muaz Ismael Yasin, Anteneh Derribew Iguala, Tadele Bedo Gelete, Diriba Tulu, Erana Kebede
    Discover Applied Sciences, 2025
    Air pollution is a critical twenty-first century environmental and public health challenge that is linked to millions of deaths and ecological harm. Accurate prediction of pollutants such as PM10 is vital for mitigation and urban sustainability. This study combines geospatial modeling with three machine learning algorithms (MLAs), Random Forest (RF), K-Nearest Neighbor (KNN), and Naïve Bayes (NB), to identify PM10 hotspots in Addis Ababa, Ethiopia. PM10 data from 11 stations (August 2021–August 2023) were analyzed alongside 25 atmospheric, climatic, anthropogenic, and pollution source predictors. A concentric zonal approach was used to assess spatial variability across radial distances and directional sectors and was supported by 30 m-resolution satellite imagery, climate data, and local geospatial repositories. The model accuracies were 0.95 (KNN), 0.93 (RF), and 0.88 (NB), with distinct performance trade-offs: RF predicted the largest “Good” PM10 zones (78.98 km2), KNN highlighted the most “UnHealSen” areas (279 km2), and NB predict “Moderate” coverage (311 km2). High PM10 concentrations clustered in eastern and northwestern sectors, aligning with industrial zones and traffic density. The results demonstrate the efficacy of MLAs and geospatial integration in producing high-resolution pollution maps. We advocate for targeted emission controls in hotspots, expanding public transit to reduce vehicular emissions, and incorporating air quality metrics into urban planning. This study advances air quality assessment methods for rapidly urbanizing regions, providing data-driven strategies to combat pollution and enhance ecological resilience in African cities.
  • Optimal interpolation approach for groundwater depth estimation
    Kalid Hassen Yasin, Tadele Bedo Gelete, Anteneh Derribew Iguala, Erana Kebede
    Methodsx, 2024
    ).
  • Monocropping vs mixed cropping systems under a changing climate: Smallholder farmers' perceptions and farm profitability in Eastern Rwanda
    Hashakimana Léonidas, Tessema Toru, Niyitanga Fidèle, Mulugeta D. Watabaji, Tadele Bedo Gelete, Hirwa Hubert
    Environmental and Sustainability Indicators, 2024
    Traditionally, mixed cropping (MxC) has been Rwanda’s smallholder farming technology used to sustainably manage farmlands for family subsistence while forming dynamic and climate-resilient agroecosystems. Yet, its significance is overlooked over monocropping (MnC) adopted at dissent since the inception of Crop Intensification Program (CIP) in Rwanda. Thus, this study sought to analyze and compare MnC and MxC systems based on farmers’ perceptions and farm profitability in drought-prone areas of Kayonza district in Eastern Province of Rwanda. The farmers' perceptions were assessed using questionnaires, focus group discussions (FGDs), and in-depth group interviews (IDGIs). The farm profitability was assessed using revenue-cost ratio (RCR) analysis. Purposive and multi-stage random sampling techniques were used for selecting sample households (n = 196). The data were analyzed using IBM SPSS software (version 25). Thematic content analysis method and Pearson correlations were used to analyze farmers’ perceptions. The binomial logit model was used to determine the effect of the selected determinants on adopting either MxC or MnC. The results show that the majority of the respondents were more involved in MxC during short-rainy and dry seasons (98%) than MnC. Household heads’ sex, family size, access to credit services, access to weather and climate information, access to extension services, social group membership, and farm income were highlighted to motivate farmers to adopt MxC systems. The latter was, therefore, shown to be more socio-economically and ecologically beneficial to farmers than MnC under drought conditions as it was chosen and adopted by most smallholder farmers and provided higher on-farm benefits (RCR>4). • Surveys and revenue-cost ratio approaches adopted to gather insights from farmers. • Farmers perceived climate change (99%); more, 80% didn’t access weather statistics . • Smallholder farmers involved more in mixed cropping (98%, n=196) than monocropping. • On-farm profits (RCR> 4) perceived among major drivers for adopting mixed cropping. • Therefore, mixed cropping should be modernized to be aesthetic to decision-makers.
  • Integrated machine learning and geospatial analysis enhanced gully erosion susceptibility modeling in the Erer watershed in Eastern Ethiopia
    Tadele Bedo Gelete, Pernaidu Pasala, Nigus Gebremedhn Abay, Gezahegn Weldu Woldemariam, Kalid Hassen Yasin, Erana Kebede, Ibsa Aliyi
    Frontiers in Environmental Science, 2024
    Land degradation from gully erosion poses a significant threat to the Erer watershed in Eastern Ethiopia, particularly due to agricultural activities and resource exploitation. Identifying erosion-prone areas and underlying factors using advanced machine learning algorithms (MLAs) and geospatial analysis is crucial for addressing this problem and prioritizing adaptive and mitigating strategies. However, previous studies have not leveraged machine learning (ML) and GIS-based approaches to generate susceptibility maps identifying these areas and conditioning factors, hindering sustainable watershed management solutions. This study aimed to predict gully erosion susceptibility (GES) and identify underlying areas and factors in the Erer watershed. Four ML models, namely, XGBoost, random forest (RF), support vector machine (SVM), and artificial neural network (ANN), were integrated with geospatial analysis using 22 geoenvironmental predictors and 1,200 inventory points (70% used for training and 30% for testing). Model performance and robustness were validated through the area under the curve (AUC), accuracy, precision, sensitivity, specificity, kappa coefficient, F1 score, and logarithmic loss. The relative slope position is most influential, with 100% importance in SVM and RF and 95% importance in XGBoost, while annual rainfall (AR) dominated ANN (100% importance). Notably, XGBoost demonstrated robustness and superior prediction/mapping, achieving an AUC of 0.97, 91% accuracy, 92% precision, and 81% kappa while maintaining a low logloss (0.0394). However, SVM excelled in classifying gully resistant/susceptible areas (97% sensitivity, 98% specificity, and 91% F1 score). The ANN model predicted the most areas with very high gully susceptibility (13.74%), followed by the SVM (11.69%), XGBoost (10.65%), and RF (7.85%) models, while XGBoost identified the most areas with very low susceptibility (70.19%). The ensemble technique was employed to further enhance GES modeling, and it outperformed the individual models, achieving an AUC of 0.99, 93.5% accuracy, 92.5% precision, 97.5% sensitivity, 95.4% specificity, 85.8% kappa, and 94.9% F1 score. This technique also classified the GES of the watershed as 36.48% very low, 26.51% low, 16.24% moderate, 11.55% high, and 9.22% very high. Furthermore, district-level analyses revealed the most susceptible areas, including the Babile, Fedis, Harar, and Meyumuluke districts, with high GES areas of 32.4%, 21.3%, 14.3%, and 13.6%, respectively. This study offers robust and flexible ML models with comprehensive validation metrics to enhance GES modeling and identify gully prone areas and factors, thereby supporting decision-making for sustainable watershed conservation and land degradation prevention.
  • Abattoir Site Suitability Modeling Using a Geographic Information System and Multi-Criteria Evaluation–A Case Study of Dire Dawa City, Ethiopia
    Kalid Hassen Yasin, Elias Cherenet Weldemariam, Gezahegn Weldu Woldemariam, Tadele Bedo Gelete, Iman Abdella Yuya
    Kn Journal of Cartography and Geographic Information, 2023
  • Machine-learning algorithms for land use dynamics in Lake Haramaya Watershed, Ethiopia
    Gezahegn Weldu Woldemariam, Degefie Tibebe, Tesfamariam Engida Mengesha, Tadele Bedo Gelete
    Modeling Earth Systems and Environment, 2022

RECENT SCHOLAR PUBLICATIONS

  • Random Forest-Based Species Distribution Modeling Reveals Intensifying Multi-Species Invasion Risks of Alien Plants in Ethiopia Under Climate Change
    KH Yasin, D Tulu, TB Gelete, BA Yuya, AD Iguala, KA Tadesse, E Kebede
    Remote Sensing Applications: Society and Environment, 101869 , 2026
    2026
    Citations: 1
  • Machine learning predictions of climate change effects on nearly threatened bird species ( Crithagra xantholaema) habitat in Ethiopia for conservation strategies
    TB Gelete, D Tulu, KH Yasin, E Kebede
    Scientific Reports 15 (1), 36972 , 2025
    2025
    Citations: 2
  • Advanced geospatial and machine learning models identify groundwater potential and reveal storage dynamics in Ethiopia’s Abbay River basin
    KH Yasin, TB Gelete, E Kebede, AD Iguala, MY Abdo
    Journal of Hydrology: Regional Studies 61, 102762 , 2025
    2025
    Citations: 2
  • Methodological integration of machine learning and Geospatial analysis for PM10 pollution mapping
    KH Yasin, MI Yasin, AD Iguala, TB Gelete, E Kebede
    MethodsX 14, 103322 , 2025
    2025
    Citations: 5
  • Predictive machine learning and geospatial modeling reveal PM 10 hotspots and guide targeted air pollution interventions in Addis Ababa, Ethiopia
    KH Yasin, MI Yasin, AD Iguala, TB Gelete, D Tulu, E Kebede
    Discover Applied Sciences 7 (4), 263 , 2025
    2025
    Citations: 11
  • Spatiotemporal analysis of urban expansion and its impact on farmlands in the central Ethiopia metropolitan area
    KH Yasin, AD Iguala, TB Gelete
    Discover Sustainability 6 (1), 36 , 2025
    2025
    Citations: 19
  • Monocropping vs mixed cropping systems under a changing climate: Smallholder farmers' perceptions and farm profitability in Eastern Rwanda
    H Léonidas, T Toru, N Fidèle, MD Watabaji, TB Gelete, H Hubert
    Environmental and Sustainability Indicators 24, 100527 , 2024
    2024
    Citations: 14
  • Optimal interpolation approach for groundwater depth estimation
    KH Yasin, TB Gelete, AD Iguala, E Kebede
    MethodsX 13, 102916 , 2024
    2024
    Citations: 19
  • Integrated machine learning and geospatial analysis enhanced gully erosion susceptibility modeling in the Erer watershed in Eastern Ethiopia
    TB Gelete, P Pasala, NG Abay, GW Woldemariam, KH Yasin, E Kebede, ...
    Frontiers in Environmental Science 12, 1410741 , 2024
    2024
    Citations: 27
  • Abattoir site suitability modeling using a geographic information system and multi-criteria evaluation–a case study of Dire Dawa City, Ethiopia
    KH Yasin, EC Weldemariam, GW Woldemariam, TB Gelete, IA Yuya
    KN-Journal of Cartography and Geographic Information 73 (2), 161-178 , 2023
    2023
    Citations: 3
  • Machine-learning algorithms for land use dynamics in Lake Haramaya Watershed, Ethiopia
    GW Woldemariam, D Tibebe, TE Mengesha, TB Gelete
    Modeling Earth Systems and Environment 8 (3), 3719-3736 , 2022
    2022
    Citations: 35
  • ArcGIS 10x PRACTICAL MANUAL
    WWM Gezahegn, TB Gelete
    2015

MOST CITED SCHOLAR PUBLICATIONS

  • Machine-learning algorithms for land use dynamics in Lake Haramaya Watershed, Ethiopia
    GW Woldemariam, D Tibebe, TE Mengesha, TB Gelete
    Modeling Earth Systems and Environment 8 (3), 3719-3736 , 2022
    2022
    Citations: 35
  • Integrated machine learning and geospatial analysis enhanced gully erosion susceptibility modeling in the Erer watershed in Eastern Ethiopia
    TB Gelete, P Pasala, NG Abay, GW Woldemariam, KH Yasin, E Kebede, ...
    Frontiers in Environmental Science 12, 1410741 , 2024
    2024
    Citations: 27
  • Spatiotemporal analysis of urban expansion and its impact on farmlands in the central Ethiopia metropolitan area
    KH Yasin, AD Iguala, TB Gelete
    Discover Sustainability 6 (1), 36 , 2025
    2025
    Citations: 19
  • Optimal interpolation approach for groundwater depth estimation
    KH Yasin, TB Gelete, AD Iguala, E Kebede
    MethodsX 13, 102916 , 2024
    2024
    Citations: 19
  • Monocropping vs mixed cropping systems under a changing climate: Smallholder farmers' perceptions and farm profitability in Eastern Rwanda
    H Léonidas, T Toru, N Fidèle, MD Watabaji, TB Gelete, H Hubert
    Environmental and Sustainability Indicators 24, 100527 , 2024
    2024
    Citations: 14
  • Predictive machine learning and geospatial modeling reveal PM 10 hotspots and guide targeted air pollution interventions in Addis Ababa, Ethiopia
    KH Yasin, MI Yasin, AD Iguala, TB Gelete, D Tulu, E Kebede
    Discover Applied Sciences 7 (4), 263 , 2025
    2025
    Citations: 11
  • Methodological integration of machine learning and Geospatial analysis for PM10 pollution mapping
    KH Yasin, MI Yasin, AD Iguala, TB Gelete, E Kebede
    MethodsX 14, 103322 , 2025
    2025
    Citations: 5
  • Abattoir site suitability modeling using a geographic information system and multi-criteria evaluation–a case study of Dire Dawa City, Ethiopia
    KH Yasin, EC Weldemariam, GW Woldemariam, TB Gelete, IA Yuya
    KN-Journal of Cartography and Geographic Information 73 (2), 161-178 , 2023
    2023
    Citations: 3
  • Machine learning predictions of climate change effects on nearly threatened bird species ( Crithagra xantholaema) habitat in Ethiopia for conservation strategies
    TB Gelete, D Tulu, KH Yasin, E Kebede
    Scientific Reports 15 (1), 36972 , 2025
    2025
    Citations: 2
  • Advanced geospatial and machine learning models identify groundwater potential and reveal storage dynamics in Ethiopia’s Abbay River basin
    KH Yasin, TB Gelete, E Kebede, AD Iguala, MY Abdo
    Journal of Hydrology: Regional Studies 61, 102762 , 2025
    2025
    Citations: 2
  • Random Forest-Based Species Distribution Modeling Reveals Intensifying Multi-Species Invasion Risks of Alien Plants in Ethiopia Under Climate Change
    KH Yasin, D Tulu, TB Gelete, BA Yuya, AD Iguala, KA Tadesse, E Kebede
    Remote Sensing Applications: Society and Environment, 101869 , 2026
    2026
    Citations: 1
  • ArcGIS 10x PRACTICAL MANUAL
    WWM Gezahegn, TB Gelete
    2015