http://ir.bdu.edu.et/handle/123456789/1990 2026-09-12T05:03:22Z http://ir.bdu.edu.et/handle/123456789/17093 A Machine Learning Based Approach to Estimate Surface Soil Moisture Using Optical and Microwave Remote Sensing Data for Crop Monitoring In Koga Watershed, Ethiopia. Amare, Dessalew Surface soil moisture (SSM) plays a pivotal role in agriculture, hydrology, and environmental monitoring, yet conventional measurement methods are limited in spatial coverage and operational efficiency. This study aims to estimate high-resolution surface soil moisture in the Koga Watershed, Ethiopia, by integrating optical and microwave remote sensing products with machine learning techniques for improved crop planning and water management. The research utilizes Sentinel-1A Synthetic Aperture Radar (SAR) for backscatter coefficients and surface roughness, and Sentinel-2 MSI imagery to derive vegetation and moisture indices such as NDVI, SAVI, NDWI, MNDWI, NDRE, and NDTI. Prior to modeling, extensive preprocessing, including calibration, multi-looking, and atmospheric correction of satellite data, was conducted. Field soil samples were collected near the Koga irrigation scheme and analyzed using the gravimetric method to obtain reference soil moisture values. These ground-truth data were synchronized with satellite overpass times to ensure temporal consistency. A Random Forest (RF) model was trained using a variety of predictor variables from both SAR and optical datasets, and their performance was evaluated through statistical metrics such as R², RMSE, and MAE. The result of the study revealed that combining SAR and Sentinel-2 MSI data enabled accurate, high-resolution surface soil moisture prediction in the Koga watershed, with values ranging from 30.01% to 52.07% across February to April 2025. VV and VH backscatter, surface roughness, and vegetation indices like NDVI and NDWI were key predictors, with SAR variables more influential in drier months and optical indices gaining importance as vegetation increased. The Random Forest model achieved the highest accuracy (R² = 0.94), and effectively capturing the spatial patterns such as higher soil moisture in low-lying, vegetated, or irrigated areas, confirming the model’s reliability for seasonal crop monitoring and water management. The study concludes that integrating multi sensor data significantly enhances soil moisture estimation accuracy and provides timely, spatially explicit information essential for crop monitoring and water resource management. It is recommended to adopt seasonally adaptive modeling strategies, expand in-situ validation networks, and incorporate surface roughness and land use data to further improve model robustness and decision support in agricultural planning. 2025-06-01T00:00:00Z http://ir.bdu.edu.et/handle/123456789/17083 Geo-Information Science Program Developing an Earth Observation-Derived Combined Drought Index for Agricultural Drought Monitoring In Amhara Region, Ethiopia Banchayehu, Molla Drought is one of the most devastating natural disasters in the world, affecting millions of people in various ways. Effective monitoring and assessment are therefore essential. This study aimed to develop an Earth observation-derived combined agricultural drought index (CADI) for agricultural drought monitoring in the Amhara Region. The development of CADI for the entire study period, that is, from 2000 to 2021, was constructed using a substantial machine learning (ML) algorithm, i.e., Random Forest (RF), by using SPI data calculated from selected fifty-one stations of the study area for each summer month. SPI values of each month were used to train the RF model and test the model; thus, 70% of the value of SPI was utilized for training the RF algorithms, and 30% of the value of SPI was utilized for testing. For the entire study period (2000 to 2021), remote sensing-based input parameters, which are Land Surface Temperature (LST), Temperature Condition Index (TCI), Evapotranspiration (ET), Normalized Difference Vegetation Index (NDVI), Vegetation Condition Index (VCI), Enhanced Vegetation Index (EVI), Precipitation Condition Index (PCI), and Soil Moisture Condition Index (SMCI), in addition to these, three topographic variables (Elevation, Slope, and Aspect) were utilized to develop CADI on a monthly scale for the entire study period (2000 to 2021). Crop yield and the Emergency Events Database (EM-DAT) drought periods were utilized to assess the effectiveness of the Combined Agricultural Drought Index. The result of CADI indicated that temporal and spatial variations of agricultural drought records have been observed in the study period with different severity levels. Hence, during the 22 years, 14, 16, 12, & 13 in June, July, August, and September were affected by droughts of different severity levels, respectively. Particularly, the CADI-derived maps depict that 2002, 2009, and 2015 were the years most affected by drought in terms of area coverage and severity levels (severe-to-extreme drought cases) in the Amhara region, Ethiopia. During these years, drought has affected about 77.14%, 83.04%, and 86.93% of the study area in 2002, 2009, and 2015, respectively, and 2007 was the wettest year during the entire study period as well as seasonally. The correlation coefficient results between the combined agricultural drought index and crop yield were very good, ranging from r = 0.51 to 0.95, indicating the index's utility for agricultural drought monitoring. From these, the highest correlation was observed in the East Gojam Zone and the lowest in the Wag Himra Zone. Overall, the combined agricultural drought index performed well in capturing the spatiotemporal patterns of the historic agricultural drought occurrences. CADI also performed well in distinguishing between drought and non-drought years, with higher sensitivity and spatial resolution than traditional drought indices. Thus, to mitigate the negative effects of drought in the region, the model can be used to develop an early warning system and agricultural drought monitoring. The CADI-based spatial analysis confirms its utility as a reliable tool for detecting and managing agricultural drought, aiding policymakers and stakeholders in developing region-specific drought preparedness and mitigation strategies. As a conclusion, this study confirms that CADI is a robust and adaptable index that enhances early warning capabilities and supports informed decision-making for agricultural drought risk management. 2025-06-01T00:00:00Z http://ir.bdu.edu.et/handle/123456789/17060 Assessment of the Effect of Land Use Land Cover Change On Local Thermal Variability and Human Well-Being Using Gis and Remote Sensing in Bahir Dar City, Ethiopia Melkamie, Belachew Rapid urbanization drives land use and land cover (LULC) change that intensifies Land Surface Temperature (LST), effects, and thermal stress on urban populations. In Bahir Dar City, Ethiopia, three decades of urban expansion have altered the local thermal environment, yet its integrated effects on thermal variability and human well-being remain poorly understood. This study examined these effects using multi-temporal Landsat imagery (for 1995 and 2005, land sat 5 and for 2015, and 2025 Landsat 8 and 9) classified with the Random Forest algorithm via Google Earth Engine. Spectral indices (NDVI, NDBI, and MNDWI), LST, UHI, and the Urban Thermal Field Variance Index (UTFVI) were analyzed, a CA-Markov model predicted LULC and LST for 2045, and a household survey assessed resident’s thermal well-being. Built-up areas expanded by 349% (9.53% to 42.80%) between 1995 and 2025, while agricultural land declined by 66.4% and water bodies by 47.7%. LST rose by 3–4.22°C, from 1995 to 2025, concentrated in built-up zones. UTFVI results indicate poor-to-worst thermal quality across most of the city. NDVI and MNDWI correlated negatively with LST, while NDBI showed a strong positive correlation. CA-Markov projections confirm continued expansion and rising LST through 2045. Classification accuracy reached 95.55% (Kappa: 93.86%) in 2025. Survey findings showed that rising temperatures caused thermal discomfort, disturbed sleep, and reduced productivity. Working-age adults (31–45 years, M = 3.86) and labour workers (M = 3.82) were most affected. Urbanization is the primary driver of thermal climate variability in Bahir Dar City. Expanded green infrastructure, water body conservation, and climate-sensitive urban planning are recommended to mitigate heat stress and safeguard human well-being. 2026-05-01T00:00:00Z http://ir.bdu.edu.et/handle/123456789/17055 The Interplay of Urban Expansion, Climate Governance, and Peri- Urban Livelihood: The Case of Bahir Dar City, Northwest Ethiopia Mastawal, Melese Rapid urbanization and climate change are converging challenges in the Global South, creating a complex nexus of environmental stress, institutional failure, and human vulnerability. In emerging regional capitals like Bahir Dar, Ethiopia, this dynamic is particularly acute, yet a comprehensive understanding of the linkages between the city's physical transformation, the capacity of its governance systems, and the impacts on frontline communities is critically lacking. This study, therefore, conducted a multi-dimensional, integrated analysis of the interplay between urban expansion, climate governance, and the livelihood vulnerability of peri-urban communities in Bahir Dar. The study employed a convergent mixed-methods design, integrating remote sensing and geospatial analysis, the development of composite Relative Importance Indices (RII) from expert surveys, one-way ANOVA to test for perceptual gaps, Structural Equation Modeling (SEM), and the Livelihood Vulnerability Index (LVI) framework. The findings reveal a clear and damaging causal chain. First, the analysis of a 40-year period (1984-2024) demonstrated that Bahir Dar’s designation as a regional capital catalyzed an accelerated urban expansion, leading to a 366% increase in built-up areas. This rapid land use and land cover change, characterized by the significant loss of vegetation and agricultural land, directly resulted in the intensification of the Urban Heat Island effect, with a mean Land Surface Temperature of urbanized zones increasing by 6°C over the 40 year study period (1984-2024). Second, the investigation into the institutional response found the city's Urban Climate Governance (UCG) framework to be demonstrably ineffective, with an overall index score (0.489) falling below the functionality threshold 0.50. The evaluation across seven core governance dimensions revealed a system characterized by a single, fragile strength amidst pervasive weakness. While Accountability (RII=0.639) emerged as the sole dimension to surpass the 0.50 effectiveness threshold, it was an isolated strength. All other dimensions, including Participation, Equity, Institutional Capacity, and Adaptability, were found to be critically weak, with Climate Change Law and Enforcement (RII=0.400) representing the most severe point of failure. The ANOVA specifically validated this structural disconnect by identifying a significant perceptual gap in awareness-raising efforts between regional policymakers and local-level implementers. The subsequent diagnostic analysis confirmed that this overall ineffectiveness is primarily driven by a triad of interconnected institutional constraints; a severe deficit in human and institutional capacity, a weak and poorly enforced policy framework, and a lack of sustained political will and leadership. Consequently, the assessment of the human impact showed that peri-urban farming households are in a state of moderate livelihood vulnerability. This condition is defined by high sensitivity, resulting from their dependence on a shrinking agricultural land base, and severely constrained adaptive capacity, stemming from critical deficits in their physical and financial capital. This vulnerability is not an isolated condition but is actively intensified by the unchecked urban expansion and the systemic governance failures identified in the analyses. Collectively, this study concludes that the unmanaged physical expansion of Bahir Dar, enabled by an impaired governance system, is systematically dismantling the resilience of its peri-urban communities. The study recommends a fundamental shift away from isolated policy interventions towards an integrated approach that combines climate-sensitive land-use planning, targeted institutional strengthening, and robust livelihood support programs to build genuine and equitable urban climate resilience. 2026-05-01T00:00:00Z