Enhancing Reservoir Characterization: Genetic Algorithm-Assisted Correction of Pore Aspect Ratio Using CNN-LSTM in Petrophysical Modeling

Petrophysics primarily focuses on understanding the relationship between rock properties and fluid behavior. However, traditional petrophysical modeling has certain limitations. In the context of the Berryman theory, the aspect ratio of pores is considered in petrophysical modeling. The challenge lies in the inability to directly measure the pore aspect ratio, leading to the use of an empirically fixed value. To address this issue, we propose a method for correcting the pore aspect ratio through genetic algorithms (GAs) in conjunction with the Berryman model. By revising the pore aspect ratio (α), we enhance the accuracy of forward modeling. To incorporate the revised pore aspect ratio into the petrophysical inversion process, we utilize a data-driven deep learning approach to solve this unconventional problem. Specifically, we employ a convolution long short-term memory (CNN-LSTM) network to jointly invert multiple reservoir parameters, including the revised pore aspect ratio. This approach was applied to a tight sandstone reservoir in a specific work area.