This article focuses on the study of identifying the quality of tight sandstone reservoirs based on machine learning. The machine learning method – Gradient Boosting Decision Tree (GBDT) algorithm is used to design and classify reservoir quality. First, it is based on logging data, core observation, cast thin section, and reservoir physical statistics. The permeability, porosity, resistivity, mud content, sand-to-ground ratio, and sand thickness were preferred as reservoir evaluation criteria in the area, and the gray correlation method was used to obtain reservoir quality categories and construct training datasets. The machine learning GBDT algorithm is used to train and test the obtained dataset. It is found that the recognition accuracy of the GBDT model is 95% by confusion matrix analysis. In addition, it is compared with four commonly used reservoir prediction methods (Bayesian discriminant method, random forest, support vector machine, and artificial neural network) for verifying the reliability of the GBDT model. Finally, the GBDT model is used to identify the reservoir quality of the study area, and it is well verified in the production data. The research results show that the GBDT model can become an important tool for rapid and real-time tight sandstone reservoir evaluation.

After primary and secondary recovery of tight reservoirs, it becomes increasingly challenging to recover the remaining oil. Therefore, improving the recovery of the remaining oil is of great importance. Herein, molecular dynamics simulation (MD) of residual oil droplet movement behavior under CO₂ displacement was conducted in a silica nanopores model. In this research, the movement behavior of CO₂ in contact with residual oil droplets under different temperatures was analyzed, and the distribution of molecules number of CO₂ and residual oil droplets was investigated. Then, the changes in pressure, kinetic energy, potential energy, van der Waals' force, Coulomb energy, long-range Coulomb potential, bond energy, and angular energy with time in the system after the contact between CO₂ and residual oil droplets were studied. At last, the g(r) distribution of CO₂–CO₂, CO₂-oil molecules, and oil molecules-oil molecules at different temperatures was deliberated. According to the results, the diffusion of CO₂ can destroy residual oil droplets formed by the n-nonane and simultaneously peel off the n-nonane molecules that attach to SiO₂ and graphene nanosheets (GN). The cutoff radius r of the CO₂–CO₂ is approximately 0.255 nm and that of the C–CO₂ is 0.285 nm. The atomic force between CO₂ and CO₂ is relatively stronger. There is little effect caused by changing temperature on the radius where the maximum peak occurs in the radial distribution function (RDF)-g(r) of CO₂–CO₂ and C–CO₂. The maximum peak of g(r) distribution of the CO₂–CO₂ in the system declines first and then rises with increasing temperature, while that of g(r) distribution of C–CO₂ changes in the opposite way. At different temperatures, after the peak of g(r), its curve decreases with the increase in radius. The coordination number around C₉H₂₀ decreases, and the distribution of C₉H₂₀ becomes loose.

It is necessary to carry out experiments on cores with different degrees of crack development when studying the seepage law of cracked reservoirs and evaluating cracks. The seepage experiment in the laboratory requires cores with different degrees of microcrack development; cores obtained via conventional drilling cannot meet the requirements, and the efficacies and evaluation methods of geological parameters used for artificial cracks are not perfect. In this study, cores are loaded using a triaxial gripper, and cracks are produced by changing the difference of stress; the relationship between the increased rate of permeability and the change in stress concentration is used to evaluate the degree of development of the crack in real time. The angle between the cracks and the maximum principal stress direction, calculated using the Mohr–Coulomb failure criterion, is 20–27.5°, which provides theoretical support for the process of crack creation. The experimental results show that the permeability variation curve shows two obvious turning points, which divide the whole zone into a reduction zone, a slow increase zone, and a rapid increase zone. Through the obtained experimental and evaluation results, a complete system for crack creation and evaluation is established, which can provide strong support for the study of cracked reservoirs.

Stress sensitivity occurs throughout the reservoir development process, especially in the study of low permeability tight reservoir, considering the influence of stress sensitivity is particularly important. When studying stress sensitivity, the current main experimental methods are variable confining pressure and variable fluid pressure methods, but they cannot simulate the stress sensitivity during water injection development. Therefore, in this paper, an experimental stress sensitivity method that can be used to study the depletion mining and water injection development processes is established. In addition, the influence of different degrees of microcrack development on the stress sensitivity of the reservoir is investigated. The results of this study show that under the experimental conditions described in this article, the loading of axial compression plays a role of preloading stress and realizes the whole process of stress sensitivity under the condition that the fluid pressure is lower than the confining pressure. In the experiment, the permeability growth rate of matrix cores does not exceed 20%. For cores containing microcracks, when the axial pressure was less than 30 MPa, the permeability slowly increased with increasing fluid pressure. When the axial pressure was 30 MPa, the permeability changes are mainly divided into two stages. In the first stage, the microcracks are closed under compressive stress. At this time, the microcracks have a limited impact on the seepage capacity. The permeability increases slowly with increasing fluid pressure. In the second stage, the permeability rapidly increases after the microcracks open. These two stages can be described by two straight lines. The slope of the first line has nothing to do with the development of microcracks; the higher the degree of microcrack development, the greater the slope of the straight line of the second stage. For all of the cores, the permeability decreases as the axial pressure increases.

In the context of the “dual-carbon” strategy and the escalating challenges posed by ultra-high water-cut reservoirs, the development of green and intelligent profile control gels (PCGs) has become essential for balancing enhanced oil recovery (EOR) efficiency with environmental sustainability. In this study, a green performance evaluation framework integrating the Environmental Toxicity Index (ETI) and Carbon Footprint Intensity (CFI) is established to quantitatively assess the environmental friendliness of polymer gel systems. Representative gel types—including conventional chromium(III)–polyacrylamide(Cr(III)–PAM), citric acid–chitosan, and pH-responsive nanogels—are evaluated to reveal their structure–environment interactions. Comparative analysis shows that the Cr(III)–PAM system exhibits strong plugging capability but imposes the highest environmental burden (ETI = 1.45; CFI = 9.1 kg CO₂e/kg), whereas the citric acid–chitosan system significantly reduces both toxicity (ETI = 0.42) and carbon footprint (CFI = 2.1). Meanwhile, pH-responsive nanogels demonstrate superior reservoir stability and sustainability under harsh conditions. The proposed ETI–CFI evaluation framework not only enables quantitative benchmarking of green performance but also provides a unified criterion for molecular design, material screening, and engineering application of intelligent green gels. This framework offers practical guidance for the low-carbon transformation of oilfield chemical systems, aligning innovation with sustainability objectives and supporting the realization of dual-carbon goals.