Accurate lithofacies identification in deep shale gas reservoirs via an optimized neural network recognition model, Qiongzhusi Formation, southern Sichuan

The Lower Cambrian Qiongzhusi Formation is crucial for exploring deep shale gas in Sichuan, however, challenges in accurately classifying shale lithofacies have hindered its commercialization. To address this, the deep shale reservoirs of the Qiongzhusi Formation were categorized into five lithofacies, five microfacies, and two-sedimentary models utilizing thin sections, scanning electron microscopy, X-ray diffraction (XRD), and petrophysical parameters. Subsequently, various lithofacies identification methods for deep shale gas reservoirs were developed. The recognition performance of triangle and three-dimensional spatial distribution chart methods is poor. The recognition effects of neural network clustering analysis (the testing and validation datasets) are less than 80%, and the training dataset is only 82.6%. On the basis of the trigonometric features, three-dimensional spatial distribution features, and neural network clustering features of the dataset, an optimized neural network lithofacies recognition model was developed. The recognition accuracy of the testing, validation, and training datasets of the ONN model based on the DL principle yielded is greater than 80%. The model achieves a recognition accuracy (training dataset) of 89.9%, with an 85% accuracy rate for blind well lithofacies recognition. This model offers valuable guidance for the exploration and development of deep shale gas in the research area, providing a substantial reference for lithofacies identification in deep shale gas reservoirs of other regions.