Generating 3D Geothermal Maps in Catalonia, Spain Using a Hybrid Adaptive Multitask Deep Learning Procedure

Mapping the subsurface temperatures can efficiently lead to identifying geothermal distribution heat flow and potential hot spots at different depths. In this paper, an advanced adaptive multitask deep learning procedure for 3D spatial mapping of temperature was proposed. As a result, predictive depths were successfully generated using geolocation 494 exploratory boreholes data in Catalonia (Spain). To increase accuracy achieved results, hybridization with new modified firefly algorithm carried out. Subsequently, uncertainty analysis novel automated ensemble approach predicted maps executed. Comparing performances terms correct classification rate (CCR) area under precision–recall curves validation whole datasets least 4.93% 2.76% improvement indicated superiority hybridized model. According efficiency proposed hybrid characterization enhance understanding predictability is inferred. This implies that applicability cost effectiveness producing high resolution depth dependent locate prospective geothermally hotspot active regions.