The process of determining hydrocarbon potential areas for exploration requires numerous extensive studies of both surface and subsurface structures. Analysis and good understanding of these structures and surface expressions related to hydrocarbon formation provides a basis for identifying petroleum traps. The existence of favorable subsurface conditions for petroleum accumulation is always dependent on surface manifestation of petroleum traps. Identifying these areas prior to exploration allows for proper planning of seismic works so as to focus exploration and resources on relatively small areas. The main objective of this study was to locate and map petroleum potential areas in parts of Turkana by integrating spatial data derived from geology, gravity and remote sensing. Six predictor maps were developed including; alteration, lineament density, residual gravity anomaly, proximity to fault, lithology and regional gravity anomaly. The maps were analyzed using Artificial Neural Network (ANN) model to generate petroleum potential map. The map was further classified to high, moderate and low potential zones. The final petroleum potential map was validated by 9 existing wells that were not used in training. The final map demarcated an area of 8,994.41 Km 2 equivalent to 55.9% of the total study area as high potential.