Groundwater Potential Mapping Using Remote Sensing and Random Forest Machine Learning Model: A Case Study from Lower Part of Wadi Yalamlam, Western Saudi Arabia

Groundwater storage is influenced by many geo-environmental factors. Most of these factors are prepared in the form categorical data. The present study utilized raster satellite data instead and a Random Forest machine learning model to identify groundwater potential zones at downstream parts Wadi Yalamlam, western Saudi Arabia. Eighteen groundwater-influenced variables continuous format from ASTER GDEM, TRMM, SPOT-5 (RF) trained using (70%) target variable validated rest (30%). accuracy, sensitivity, F1-score all generated evaluate performance. SPOT band 3, 4, rainfall most important for mapping contributing 11%, 7%, 8% during prediction stage. GDEM elevation contributed 6% slope scored 1%. main conclusions are: (1) RF algorithm successfully identified three with an accuracy 96%. (2) high, moderate, low covered 11.5%, 59.9%, 28.6% area respectively. (3) Majority high moderate lie within pumping rate range between 10 20 m3/day. (4) approach developed this can be applied any other wadis having same conditions help authorities decision-makers planning development projects.