Lithofacies and sandstone reservoir characterization for geothermal assessment through artificial intelligence

• Machine learning-based workflow was used for better lithofacies identification. • Seismic inversion and permeability were employed to quantify underground heat production and radiogenic heat sources. • This study used DFFNN to predict accurate geothermal reservoir properties. • The finding indicated radiogenic materials acting as significant subsurface heat sources, emphasizing the lithology's geothermal importance. • The integrated study performed better results in harnessing subsurface geothermal resources. Pakistan has potential for geothermal energy within the subsurface, but these resources are still unexplored due to limited research. The present study prime aims to utilize seismic and well data to explore the geothermal potential of the sandstone reservoir. Facies analysis was performed based on well data through machine learning, demonstrating that the major facies present are sandstone and shale in the target Formation. It has been inferred in the current assessment that the presence of radioactive elements in these lithologies is an active source of heat in the subsurface. Deep Feed Forward Neural Network (DFFNN) techniques were employed to populate geothermal reservoir parameters into the seismic section. DFFNN can enhance the integration of seismic and well data for reservoir characterization by estimating rock properties obtained from seismic inversion methods. DFFNN approach achieved correlation values from 88.60–93 % for geothermal properties at the well position. This study is novel due to its combination of statistical methods and an artificial intelligence approach that enables the identification of geothermal perspective maps (heat production and radiogenic heat production) on seismic sections that are typically not studied before. The outcomes of subsurface geothermal reservoir parameters average values derived from well logs data: average porosity (18 %), volume of shale (22.67 %), heat production (0.988 µW/m 3 ), radiogenic heat production (0.847 µW/m 3 ), and permeability (17.74 mD) are quite promising which indicates that the current study region is favorable for geothermal resources. It has been concluded that the current study approaches have improved the prediction accuracy of geothermal reservoir properties.