Development of PROMETHEE-Entropy data mining model for groundwater potentiality modeling: a case study of multifaceted geologic settings in south-western Nigeria

This work looks at developing an object-driven decision support system (DSS) model with the goal of improving the prediction accuracy of the present expert-driven DSS model in assessing groundwater potentiality. The database of remote sensing, geological, and geophysical information was constructed using the technological efficiency of GIS, data mining, and programming tools. Groundwater potential conditioning factors (GPCF) extracted from the datasets include lithology (Li), hydraulic conductivity ( K ), lineament density (Ld), transmissivity ( T ), and transverse resistance (TR) for groundwater potentiality mapping in a typical hard rock multifaceted geologic setting in south-western Nigeria. A Python-based entropy approach was used to objectively weight these factors. The weightage findings determined that the greatest and lowest given values for Ld and K were 0.6 and 0.03, respectively. The produced Python-based PROMETHEE-Entropy model algorithm was born through combining the weight findings with the Python-based PROMETHEE-II method. The groundwater potentiality model (GPM) map of the area was created using the model algorithm's outputs on the gridded raster of GPCF themes. Based on the suggested approach, the validated results of the created GPM maps using the Receiver Operating Characteristic (ROC) curve technique yielded an accuracy of 86%. An object-driven DSS model was created using the approaches that were used. The created object-driven model is a viable alternative to existing approaches in groundwater hydrology and aids in the automation of groundwater resource management in the research region.