While drilling formation pressure monitoring is an important basis for ensuring drilling safety and oil and gas discovery, the calculation of existing pressure monitoring methods is complicated and the accuracy is difficult to improve. Taking the actual well data of well area X in Yinggehai Basin as the object, correlation analysis was first carried out to select and standardize the data features, and relevant effective parameters were extracted. Two kinds of neural networks, back-propagation network BP and back-propagation network GA-BP optimized by genetic algorithm, were used to establish artificial intelligence monitoring models of formation pressure based on 10 kinds of measuring and logging data, respectively. The application effect of the model was evaluated based on the results of monitoring the pressure while drilling. The results show that the monitoring accuracy of the BP neural network model is 91.25%, and that of the GA-BP neural network model is 92.89%. The latter has a better monitoring effect on formation pore pressure. In formation pressure monitoring in areas with a high degree of well control, the introduction of artificial intelligence technology has the advantages of simplicity, speed and high precision, and can provide a reference for other areas of pressure monitoring while drilling.

Carbon isotope logging technology can obtain timely and accurate hydrocarbon fluid and reservoir geological information and has great application potential in oil–gas body property analysis, the comprehensive study of source rocks, and fault-sealing evaluation. Since 2014, real-time methane isotope logging technology has been applied in the western South China Sea. Based on the on-site, real-time, continuous, and accurate detection of methane carbon isotopes, combined with the rapid comprehensive analysis and evaluation of logging gas measurement data, the application effect in ultra-high-temperature and high-pressure wells in the western South China Sea has been remarkable. Taking the Ledong 10 Area of Yinggehai Basin as an example, real-time carbon isotope logging data can be used to quickly identify gas origins, source rock maturity, and gas source type and help judge the sealing quality of overburdened mudstone caps. This knowledge can serve as a reference for ascertaining the popularity of isotope-logging technology in other areas.

A large number of low-resistivity and low-permeability reservoirs have been discovered in the deep Paleogene strata of the Wenchang Sag. These reservoirs are characterized by complex porosity–permeability relationships and difficulties in fluid property identification, which restrict the progress of exploration and development operations. However, existing reservoir studies mostly focus on either low-permeability or low-resistivity reservoirs, with relatively few investigations targeting this specific type. Using petrological analysis and physical property testing as the main methods, combined with sedimentary and diagenetic studies, this paper examines the characteristics and genesis of low-resistivity and low-permeability reservoirs in the Paleogene of the Wenchang Sag. The results show that the Paleogene reservoirs are dominated by lithic quartz sandstones, with secondary pores as the main reservoir space, consisting of medium–small pores and fine throats. Samples of the same grain size exhibit a favorable porosity–permeability correlation. Based on capillary pressure curve morphology, the reservoirs can be classified into three types: high mercury intrusion saturation with low displacement pressure, medium mercury intrusion saturation with medium displacement pressure, and medium mercury intrusion saturation with medium–high displacement pressure. The low porosity and permeability are mainly attributed to the fact that the reservoir rocks are primarily deposited in near-source braided fluvial delta underwater distributary channels, resulting in low compositional and textural maturity of sandstones. Strong compaction resistance leads to a significant reduction in primary pores during burial, and intergranular cement filling further deteriorates physical properties. On the other hand, rapid lithological changes and complex pore structures give rise to abundant isolated pores and poor connectivity, leading to high irreducible water saturation. Coupled with high formation water salinity, these factors collectively give rise to low-resistivity reservoirs in the study area. This study clarifies the formation mechanism of low-permeability and low-resistivity reservoirs in the Paleogene of the Wenchang Sag, providing guidance for reservoir evaluation in subsequent oil and gas exploration and serving as a reference for analogous areas.

Overpressure is widely developed in the Enping Formation of the Baiyun Sag, Pearl River Mouth Basin, yet its origin has long remained controversial. Previous studies, based on the acoustic velocity-effective stress crossplot, concluded that undercompaction is the dominant overpressure mechanism in this area; however, the significant influence of high total organic carbon (TOC) in the thick mudstone intervals on sonic transit time was not effectively eliminated. In this paper, geochemical logging data are used to perform TOC correction on the sonic transit time of Well BY-X1. Combined with log-curve assemblages and the effective-stress crossplot, the overpressure origin is re-identified, and the development characteristics and quantitative patterns of overpressure are clarified. The results show that the maximum TOC of mudstones in the overpressure intervals of the Enping Formation in the Baiyun Sag reaches 5.8%, exhibiting a strong positive correlation with sonic transit time. After TOC correction, the reduction in sonic transit time ranges from 6.8% to 29.8%, with an average reduction of 16.8% in the lower Enping Formation. Before correction, data points fall within the loading curve region, leading to a potential misinterpretation of undercompaction as the dominant mechanism; after correction, all data points plot along the unloading curve. Combined with the absence of significant shifts in density logs, the maximum formation pressure coefficient of 1.53, and the lack of anomalously high porosity, it is confirmed that the dominant origin of overpressure in this area is fluid expansion driven by hydrocarbon generation, rather than undercompaction. The sonic transit-time correction method for organic-rich mudstones established in this study can significantly improve the accuracy of formation-pressure prediction, providing a quantitative reference for the study of overpressure mechanisms in source-rock systems with high heat flow and hydrocarbon-rich sags.