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.

The accurate understanding of the origin of overpressure is the basis of formation pressure research and the core work of determining the distribution of formation pore pressure in drilling design. The deep water area of Baiyun Sag in the Pearl River Mouth Basin in the northern margin of the South China Sea has been proved to be a hydrocarbon rich depression. In recent years, overpressure has been encountered in the middle and deep layers, but the geological origin of the overpressure in the deep water area are still unclear. Therefore, the pore pressure profile of the Baiyun Sag was evaluated using the data of drilling and seismic velocity, and the relationship between overpressure and the generation mechanism was established. Most of the surrounding and shallow strata of Baiyun Sag show normal pressure, while the middle and deep strata generally show overpressure, with the maximum pressure coefficient up to 1.55. The overpressure zone mainly develops from the middle of Zhujiang Formation to the upper member of Enping Formation. The mudstone resistivity and density values of the two typical Wells deviated from the normal trend. The density showed a constant trend with the increase of depth, while the resistivity showed a certain degree of reversal. The upper layer of the overpressure zone showed abnormally high resistivity values, corresponding to the overgland and transition zone formed by high carbonate content. There is no obvious increase of porosity in the overpressured sandstone strata of Baiyun sag, which does not have the characteristics of undercompaction. The velocity in the overpressure section of the two Wells varies greatly, and the density is basically unchanged or slightly decreased. It is concluded that the overpressure is caused by fluid expansion from hydrocarbon-generation. The large-scale and long-term fluid expansion caused by hydrocarbon generation and expulsion of source rocks provides the power source for the formation of overpressure in Baiyun sag. The distribution of effective source rocks has a controlling effect on the distribution range of overpressure. The tight sandstone strata in the Zhuhai, Wenchang and Enping formations become the cover layer of the overpressure system in the longitudinal direction.

An intelligent safety risk assessment model is proposed by integrating the λ-fuzzy measure, Choquet integral, and triangular fuzzy numbers. It addresses the limitations of conventional methods like AHP that neglect nonlinear interactions among risk factors. The framework quantifies expert linguistic judgments to capture synergistic and substitutive relationships. Validation using two Sinopec seismic projects shows a 23.3% reduction in assessment time and an 18.1% accuracy improvement. Computed λ values (HB: −0.999997; SC: −0.999821) confirm strong substitutive interactions. Sensitivity analysis demonstrates robustness, with ±10% fuzzy measure variation causing <±3% output change. The model provides a computationally efficient, reliable tool for seismic acquisition and other complex industrial systems.

In order to further understand the complex spatial distribution caused by the extremely strong heterogeneity of buried hill reservoirs, this paper proposes a new method for predicting the development pattern of buried hill reservoirs based on the traditional pre-drilling prediction and post-drilling evaluation methods that mainly rely on seismic, logging, and core data, which are difficult to meet the timeliness and accuracy of drilling operations. Firstly, the box method and normalization formula are used to process and normalize the abnormal data of element logging and engineering logging, and then the stepwise regression analysis method is used to optimize the sensitive parameters of element logging and engineering logging. The Light Gradient Boosting Machine (LightGBM) algorithm, deep neural network (DNN), and support vector machine (SVM) are used to establish a new method for predicting the development pattern of buried hill reservoirs. Lastly, a comprehensive evaluation index F1 score for the model is established to evaluate the prediction model for the development pattern of buried hill reservoirs. The F1 score value obtained from this model’s comprehensive evaluation index indicates that the LightGBM model achieves the highest accuracy, with 96.7% accuracy in identifying weathered zones and 95.8% accuracy in identifying interior zones. The practical application demonstrates that this method can rapidly and accurately predict the development mode of buried hill reservoirs while providing a new approach for efficient on-site exploration and decision-making in oil and gas field developments. Consequently, it effectively promotes exploration activities as well as enhances the overall process of oil and gas reservoir exploration.

The current gas logging electric degasser is susceptible to various factors, such as drilling fluid displacement, drilling fluid level height, motor speed, and drilling fluid properties. Consequently, the degassing efficiency varies, and quantification is poor. The gas chromatographic analysis time is lengthy, the gas path structure is complex, and the operation process is intricate. These factors distort gas measurement data and compromise the accuracy of hydrocarbon discovery and interpretation. To address these issues associated with traditional logging equipment, a novel gas logging instrument based on semipermeable film degasser and infrared spectroscopy has been developed. This instrument utilizes the principle of quantitative separation of gas and liquid through a semipermeable membrane combined with rapid and highly sensitive infrared spectroscopic analysis for precise gas characterization. Laboratory and field tests demonstrate excellent repeatability and stability of this instrument while meeting the detection range requirements for alkane gas concentration in oil fields. Comparison between the hydrocarbon curves obtained from both electric degasser and membrane degassing reveals similar trends; however, the latter provides more comprehensive information.

The Ordovician thick dolostone in Shuntogol area of the Tarim Basin has the potential to form a large-scale reservoir, but its genesis and reservoir development model are still unclear. Starting from a sedimentary sequence, this study takes a batch of dolostone samples obtained from new drilling cores in recent years as the research object. On the basis of core observation and thin section identification, trace elements, cathodoluminescence, carbon and oxygen isotopes, rare earth elements, and X-ray diffraction order degree tests were carried out to discuss the origin of the dolomite and summarize the development model of the dolostone reservoir. The analysis results show that the Ordovician dolomite in the study area had a good crystalline shape, large thickness, high Fe and Mn values, and mostly showed bright red light or bright orange–red light under cathode rays. The ratio of δ¹⁸O values to seawater values at the same time showed a negative bias; the δCe values were negative anomalies, the δEu values were positive anomalies, and the order degree was high. This indicates that the dolomitization process occurred in a relatively closed diagenetic environment. The Ordovician carbonate rocks in the study area were low-lying during the sedimentary period, and with the rise of sea level, the open platform facies continued to develop. When the Middle and Lower Ordovician series entered the burial stage, the main hydrocarbon source rocks of the lower Cambrian Series entered the oil generation peak, and the resulting formation overpressure provided the dynamic source for the upward migration of the lower magnesium-rich fluid, and the dolomitization fluid entered the karst pore system in the target layer to produce all the dolomitization. This set of dolostone reservoirs is large in scale and can be used as a favorable substitute area for deep carbonate exploration for continuous study.