The core of the exploration and development of unconventional oil and gas resources, such as shale oil, lies in the effective identification and scale utilization of the sweet spot. Oil saturation is an important parameter in evaluating the sweet spot. Aiming to solve the many current problems of oil saturation logging evaluations of shale oil reservoirs, this study outlines the research progress of oil saturation logging evaluations of shale oil from the three aspects, namely, the electrical method, non-electrical method, and machine learning, through researching the literature and practical applications. At the same time, several typical saturation models are applied to shale oil reservoirs in the Qingshankou Formation of the Gulong Depression, and applicability analyses are conducted. Lastly, the advantages and disadvantages of each oil saturation calculation model are summarized, and suggestions are given for conducting research using each type of method. This study has certain significance in the selection of oil saturation logging evaluation methods for shale oil reservoirs and provides directions for improvement.

Total organic carbon (TOC) content is a key indicator for determining the hydrocarbon content of shale. The current model for calculating the TOC content of shale is relatively simplistic, the modeling process is cumbersome, and the parameters involved are influenced by subjective factors, which have certain shortcomings. To address this problem, a time-domain convolutional neural network (TCN) model for predicting total organic carbon content based on logging sequence information was established by starting from logging sequence information, conducting logging parameter sensitivity analysis experiments, prioritizing logging-sensitive parameters as model feature vectors, and constructing a TCN network. Meanwhile, to overcome the problem of an insufficient sample size, a five-fold cross-validation method was used to train the TCN model and obtain the weight matrix with the minimum error, and then a shale reservoir TOC content prediction model based on the TCN model was established. The model was applied to evaluate the TOC logging of the Lianggaoshan Formation in the Sichuan Basin, China, and the predicted results were compared with the traditional ΔlogR model. The results indicate that the TCN model predicts the TOC content more accurately than the traditional model, as demonstrated by laboratory tests. This leads to a better application effect. Additionally, the model fully explores the relationship between the logging curve and the total organic carbon content, resulting in improved accuracy of the shale TOC logging evaluation.

Shale oil stands as a critical growth engine for global unconventional hydrocarbon exploration and production. Sandstone interlayers within shale successions have become the primary reservoir units and key development intervals for interbedded shale oil plays due to their superior storage and seepage capacity relative to the shale matrix. Nevertheless, conventional petrophysical cutoff standards for effective reservoirs are mostly derived from independent conventional sandstone reservoirs, largely ignoring the controlling effect of source–reservoir configuration on hydrocarbon charging. This has resulted in a widespread paradox in production practices and severely constrained accurate resource assessment and efficient sweet spot delineation. To cover this gap, this study integrates thin section analysis, organic geochemical experiments, core petrophysical measurements, and geophysical logging data to systematically characterize the geochemical features of source rocks and the petrophysical properties of sandstone reservoirs. Then, a quantitative source–reservoir coupling index is established by integrating key controlling factors, including total organic carbon content, free hydrocarbon content, vitrinite reflectance, source–reservoir pressure difference, source–reservoir distance, and configuration relationship. According to the index, source–reservoir coupling relationships are categorized into strong, moderate, and weak grades. The corresponding petrophysical lower limits for effective sandstone reservoirs are determined hierarchically. The results indicate that threshold values increase with decreasing coupling intensity: strongly coupled systems have lower limits of 6.5% porosity and 0.12 mD permeability, while moderately coupled systems require higher thresholds of 8.5% porosity and 0.23 mD permeability. This study breaks through the limitations of traditional empirical methods that define reservoir cutoffs solely by porosity and permeability. A method and corresponding criteria for evaluating the petrophysical cutoffs of sandstone reservoirs were established for the study area. This enables effective identification of relatively low-quality sandstone reservoirs that can still form commercial oil accumulations under robust hydrocarbon supply conditions. This also significantly improves the accuracy of effective reservoir recognition and sweet spot prediction in interbedded shale oil systems.