Browsing by Author "Ouma, Hassan Masinde"

Now showing 1 - 1 of 1
  • No Thumbnail Available
    Item
    A Hybrid Modflow-Machine Learning Approach for Groundwater Prospecting and Optimal Borehole Siting
    (Busitema University, 2026) Ouma, Hassan Masinde
    This report presents the role of a hybrid MODFLOW-Machine Learning (ML) approach in predicting groundwater potential and optimizing borehole siting in the Awoja Catchment in eastern Uganda. Groundwater remains the primary source of safe water for rural communities in Uganda; however, its exploration and development are often hindered by limited hydrogeological data and the use of conventional methods that inadequately capture subsurface variability. The study integrates the physically based MODFLOW groundwater flow model with data-driven ML algorithms, including Random Forest, Support Vector Machine, Artificial Neural Networks, and XGBoost to form a hybrid framework capable of enhancing groundwater prospecting accuracy. Hydrogeological, geological, soil, and climatic datasets were utilized to simulate aquifer conditions, generate hydraulic parameters, and train predictive models. Model performance was evaluated using statistical indicators such as the Coefficient of Determination (R²), Root Mean Square Error (RMSE), and Nash-Sutcliffe Efficiency (NSE). The hybrid model demonstrates superior predictive accuracy compared to standalone ML approaches, effectively delineating high-yielding aquifer zones and identifying optimal borehole locations. The findings provide a framework that supports efficient groundwater exploration, minimizes drilling failure rates, and promotes sustainable groundwater management. This study directly contributes to Sustainable Development Goal 6 (SDG 6) on clean water and sanitation and aligns with Uganda’s Third National Development Plan (NDPIII), which prioritizes reliable and sustainable groundwater utilization for socio-economic development.