Hybrid deep belief network and fuzzy clustering approach for geothermal prospectivity mapping in northeastern Nigeria using magnetic and landsat data

Nigeria faces persistent energy supply challenges, particularly in its northeastern region, where grid access is limited and dependence on fossil fuels undermines sustainability goals. Although the National Renewable Energy Action Plan (NREAP 2015–2030) outlines ambitious targets for renewable energy integration, it notably lacks specific strategies for geothermal development—leaving a critical gap in policy and resource utilization. This study addresses that gap by developing a scalable, cost-effective geothermal prospectivity mapping framework using remote sensing and aeromagnetic data integrated through a hybrid machine learning model. A novel combination of Deep Belief Networks (DBN) for feature extraction and Fuzzy C-Means (FCM) clustering for spatial classification was employed, with optimization achieved using three metaheuristic algorithms: Genetic Algorithm (GA), Particle Swarm Optimization (PSO), and Simulated Annealing (SA). Among these, the DBN-SA model achieved the best internal validity, with superior Silhouette Score, Davies–Bouldin Index, and cluster compactness, ensuring robust and interpretable prospectivity results. Key geothermal indicators—including land surface temperature, vegetation stress, Curie depth, heat flow, and magnetic source depth—were derived from Landsat and airborne magnetic datasets. The resulting map classifies the study area into low, moderate, and high geothermal potential zones, with validation supported by geological correlation and the presence of known thermal features like the Wikki Warm Spring. Approximately one-third of the area was identified as high-potential, particularly over basement terrains with high heat production and structural permeability. This approach offers both scientific insight and practical direction for decentralized, low-carbon energy deployment in northeastern Nigeria, aligning with broader national renewable energy goals and filling a crucial gap in geothermal resource planning.