Development of a large language model-driven intelligent agent for predicting relative permeability in oil and gas reservoirs

To address the challenges and difficulties in predicting the relative permeability of reservoirs using traditional physics-driven and data-driven approaches, this paper proposes a collaborative analysis intelligent agent for the relative permeability of oil and gas reservoirs based on a large model. By constructing a multiagent collaborative workflow, integrated collaboration of data, models, and analysis results is achieved. The intelligent agent automatically completes data preprocessing, feature extraction, parameter calibration, small model calling, and output and evaluation of prediction results based on preset task dependencies. At the same time, by introducing deep learning-based embedding of physical information, the analysis efficiency and accuracy are significantly improved. The results show that compared with traditional physical analysis methods, this method improves the accuracy of reservoir relative permeability prediction by 10%, has a computational efficiency 10 times higher than traditional deep learning algorithms, and a computational speed 100–1000 times higher than conventional physical models. This study further enhances the efficiency and intelligence of physical property analysis of oil and gas reservoirs, providing a new research direction for the intelligent development of oil and gas digitization.