Geothermal investigation of sandstone reservoirs using a probabilistic neural network with 2D seismic and borehole data: insights into structural and reservoir characteristics

One form of renewable energy that is gaining attention globally is geothermal energy resources. Geothermal energy potential exists in Pakistan; however, these resources have not yet been fully tapped because of a lack of research. The present study aims to utilize 2D seismic and well data to explore the geothermal potential of the Lower Indus Basin, specifically in the Sanghar Block, and the target was the Lower Goru Formation sandstone reservoir. The 2D seismic structural interpretation confirms that the area has normal faulting with the horst and graben structure, indicating extension tectonics. A seismic attributes analysis was performed on 2D seismic data, such as spectral decomposition, similarity variance, trace envelop, and instantaneous frequency. It also confirms the presence of geothermal anomalies, such as high frequency and reflectance, at the Lower Goru Formation. Two wells, Sono-2 and Sono-5, were utilised for studies in which heat production, formation temperature, average porosity, shale volume, and permeability were computed. Seismic inversion was performed to assess the impedance in the overall study block. Model-based seismic inversion analysis results indicated that 98 % and 92 % correlation were achieved at the Sono-2 and Sono-5 wells, respectively. Probabilistic Neural Network (PNN) techniques were employed for geothermal reservoir properties and interpolated in the seismic section to assess geothermal potential. The outcomes obtained from geothermal properties via PNN indicated excellent correlation values of 94.50–98.80 % around the well location. The findings of the study suggested the presence of geothermal resources in the study region.