Drilling costs of ultra-deep well is the significant part of development investment, and accurate prediction of drilling costs plays an important role in reasonable budgeting and overall control of development cost. In order to improve the prediction accuracy of ultra-deep well drilling costs, the item and the dominant factors of drilling costs in Tarim oilfield are analyzed. Then, those factors of drilling costs are separated into categorical variables and numerous variables. Finally, a BP neural network model with drilling costs as the output is established, and hyper-parameters (initial weights and bias) of the BP neural network is optimized by genetic algorithm (GA). Through training and validation of the model, a reliable prediction model of ultra-deep well drilling costs is achieved. The average relative error between prediction and actual values is 3.26%. Compared with other models, the root mean square error is reduced by 25.38%. The prediction results of the proposed model are reliable, and the model is efficient, which can provide supporting for the drilling costs control and budget planning of ultra-deep wells.

In the process of fracturing construction in shale gas reservoirs, microseism is a common means and effective method to evaluate the fracturing effect, but it is not suitable for large-scale and large batches due to its high applicability conditions and cost. Therefore, a concise, fast and low-cost post-fracturing effect evaluation method is needed to evaluate the complexity of fractures formed by fracturing in shale gas reservoirs. In this paper, based on the basic theory of the G-function, the free variable μ was introduced to correct the filter loss coefficient with the participation of natural fractures, and thousands of G-function curves were plotted with fracturing data from hundreds of gas wells in the southern Fuling shale gas field in China. Through the feature analysis of the curve morphology, a G-function graphic template conforming to the block was established, which contains four types and eight morphologies. Four characteristic parameters in the G-function curve were selected to establish a productivity evaluation model for shale gas wells. Based on the validation results, it can be seen that the G-function graphic template and productivity evaluation model proposed by the author had a good correlation with the post-fracturing productivity of shale gas wells, which provided a fast, economical and accurate method for the post-fracturing effect evaluation and productivity evaluation of shale gas wells and can effectively provide feedback on the field fracturing effect and guide subsequent fracturing construction.

With the rapid development of computer science and technology, the Chinese petroleum industry has ushered in the era of big data. In this study, by collecting fracturing data from 303 horizontal wells in the Fuling Shale Gas Demonstration Area in China, a series of big data analysis studies was conducted using Pearson’s correlation coefficient, the unweighted pair group with arithmetic means method, and the graphical plate method to determine which is best. The fracturing parameters were determined through a series of big data analysis studies. The big data analysis process is divided into three main steps. The first is data preprocessing to screen out eligible, high-yielding wells. The second is a fracturing parameter correlation clustering analysis to determine the reasonableness of the parameters. The third is a big data panel method analysis of specific fracturing construction parameters to determine the optimal parameter range. The analyses revealed that the current amount of 100 mesh sand in the Fuling area is unreasonable; further, there are different preferred areas for different fracturing construction parameters. We have combined different fracturing parameter schemes by preferring areas. This analysis process is expected to provide new ideas regarding fracturing scheme design for engineers working on the frontline.

Low-permeability conglomerate reservoirs are characterized by complex pore structures and poor sweep efficiency, making the optimization of carbon dioxide-water alternating gas (CO2-WAG) injection critical for enhanced oil recovery. To evaluate the displacement performance of CO2-WAG and determine the lower limit of effectively swept pore throats, this study presents long-core flooding experiments conducted on cores from the KS Formation of the B Oilfield in the Junggar Basin under reservoir conditions (20.1 MPa and 58°C). Continuous CO2 flooding and CO2-WAG schemes with varying cycle numbers and gas-water ratios (GWRs) were systematically compared. In situ online nuclear magnetic resonance (NMR) monitoring was employed to quantitatively characterize the mobilization of microscopic remaining oil during flooding. The results demonstrate that CO2-WAG significantly outperforms continuous CO2 flooding. Among the tested scenarios, three alternating cycles and a GWR of 1:1 yielded the highest oil displacement efficiencies of 64.8% and 66.13%, respectively, representing improvements of 23.6% and 24.53% over water flooding and 4.75% and 6.08% over continuous CO2 flooding. NMR analysis revealed that water flooding primarily mobilizes crude oil in larger pore throats, with an effective sweep limit of approximately 18.2 nm. In contrast, CO2-WAG extends the lower limit of effectively swept pore throats to 9.52 nm, enabling the recovery of oil trapped within mesopores and micro/nano-scale pore systems. Mechanistically, the injected water slugs improve sweep efficiency and suppress gas channeling, while the CO2 slugs reduce crude oil viscosity and enhance displacement within smaller pores. This synergistic combination of macroscopic sweep improvement and microscopic displacement enhancement substantially increases oil recovery.