Jin Feng

A growing number of large data sets have created challenges for the oil and gas industry in predicting reservoir parameters and assessing well productivity through efficient and cost-effective techniques. The design of drilling plans for a high-pressure tight-sand reservoir requires accurate estimations of pore pressure (P_p) and reservoir parameters. The objective of this study is to predict and compare the P_p of Huizhou Sag, Pearl River Mouth Basin, China, using conventional techniques and machine learning (ML) algorithms. We investigated the characteristics of low-permeability reservoirs by observing well-logging data sets and cores and examining thin sections under a microscope. In the reservoir zone, the average hydrocarbon saturation is 55%, and the average effective porosity is 11%. The tight sandstone reservoirs consist of fine- to extremely fine-grained argillaceous feldspathic sandstone. The mean absolute error for reservoir property prediction is 1.3%, 2.2%, and 4.8%, respectively, for effective porosity, shale volume, and water saturation. Moreover, the ML algorithm was employed to cross-check the validity of the prediction of P_p. Combining conventional and ML techniques with the core data demonstrates a correlation coefficient (R²) of 0.9587, indicating that ML techniques are the most effective in testing well data. This study shows that ML can effectively predict P_p at subsequent depths in adjacent geologically similar locations. Compared to conventional methods, a substantial data set and ML algorithms improve the precision of P_p predictions.

The accurate identification of [ ] nonhydrocarbon gas layers plays an important role in the exploration and development of natural gas reservoirs. The logging response characteristics of layers containing nonhydrocarbon gas and hydrocarbon gas are very similar because there are gas fluids in both kinds of layers, which leads to the uncertainty in the interpretation results of gas types. We have developed a comprehensive method for the identification of [ ] nonhydrocarbon gas layers by using [ ]-relative content and apparent porosity. First, based on the formation component bulk volume model of the coexisting reservoir of the [ ] nonhydrocarbon gas layers and the hydrocarbon gas layers, we develop an optimization algorithm to quantitatively calculate the [ ] relative content in the reservoir. Second, by analyzing and determining the logging response value of the [ ] nonhydrocarbon gas under the formation temperature and pressure conditions, we establish a qualitative identification chart using the difference between the calculated value of the apparent porosity of [ ] and the hydrocarbon gas. Finally, we were able to accurately identify the [ ] nonhydrocarbon gas layers by comprehensively analyzing the calculation results of the [ ] relative content in the reservoir and the identification results of the [ ] apparent porosity identification chart. We apply the above workflow in the Baiyun deep-water area in the eastern South China Sea, and it shows high efficiency in the identification of [ ] nonhydrocarbon gas layers.