The development of unconventional oil and gas resources is becoming increasingly challenging, with artificial intelligence (AI) emerging as a key technology driving technological advancement and industrial upgrading in this field. This paper systematically reviews the current applications and development trends of AI in unconventional oil and gas exploration and development, covering major research achievements in geological exploration; reservoir engineering; production forecasting; hydraulic fracturing; enhanced oil recovery; and health, safety, and environment management. This paper reviews how deep learning helps predict gas distribution and classify rock types. It also explains how machine learning improves reservoir simulation and history matching. Additionally, we discuss the use of LSTM and DNN models in production forecasting, showing how AI has progressed from early experiments to fully integrated solutions. However, challenges such as data quality, model generalization, and interpretability remain significant. Based on existing work, this paper proposes the following future research directions: establishing standardized data sharing and labeling systems; integrating domain knowledge with engineering mechanisms; and advancing interpretable modeling and transfer learning techniques. With next-generation intelligent systems, AI will further improve efficiency and sustainability in unconventional oil and gas development.

High molecular polymers have been widely studied and applied in the field of enhanced oil recovery (EOR). At present, the focus of research has been changed to the design of polymer networks with unique properties such as anti-temperature and anti-salinity, good injection and so on. Supramolecular polymers have high viscoelasticity as well as excellent temperature, salt resistance and injection properties. Can supramolecular polymers become another material choice for polymer flooding to enhance oil recovery? The present review aims to systematically introduce supramolecular polymers, including its design strategy, interactions and rheological properties, and address three main concerns: (1) Why choose supramolecular polymers? (2) How do we synthesize and characterize supramolecular polymers in the field of oilfield chemistry? (3) What has been the application progress of supramolecular polymers in improving oil recovery? The introduction of a supramolecular interaction system provides a new idea for polymer flooding and opens up a new research direction to improve oil recovery. Aiming at the “reversible dynamic” supramolecular polymers, the supramolecular polymers are compared with the conventional covalent macromolecular polymer networks, and the challenges and future research directions of supramolecular polymers in EOR are discussed. Finally, the author’s viewpoints and perspectives in this emerging field are discussed.

The research and application of CO₂ storage and enhanced oil recovery (EOR) have gradually emerged in China. However, the vast unconventional oil and gas resources are stored in reservoir pores ranging from several nanometers to several hundred micrometers in size. Additionally, CO₂ geological sequestration involves the migration of fluids in tight caprock and target layers, which directly alters the transport and phase behavior of reservoir fluids at different scales. Micro- and nanoscale fluidics technology, with their advantages of in situ visualization, high temperature and pressure resistance, and rapid response, have become a new technical approach to investigate gas–liquid interactions in confined domains and an effective supplement to traditional core displacement experiments. The research progress of micro–nano fluidics visualization technology in various aspects, such as CO₂ capture, utilization, and storage, is summarized in this paper, and the future development trends and research directions of micro–nano fluidics technology in the field of carbon capture, utilization, and storage (CCUS) are predicted.

Many factors need to be considered in the evaluation of tight conglomerate reservoirs, including the microscopic pore-throat structure, pore connectivity, lithology, porosity, permeability, and clay mineral content. The contents and types of clay minerals reflect the mineral evolution process during the deposition of the reservoir and can reflect the reservoir’s physical properties to a certain extent. In this study, cores from the Baikouquan Formation in Mahu were used to comprehensively analyze the effects of the clay mineral content on the physical properties of a tight conglomerate reservoir, including field emission scanning electron microscopy (FE-SEM), casting thin section observations, X-ray diffraction (XRD), interface property testing, high-pressure mercury injection, low temperature N₂ adsorption, and nuclear magnetic resonance (NMR)-movable fluid saturation testing. The results revealed that differences in different lithologies lead to differences in clay mineral content and pore structure, which in turn lead to differences in porosity and permeability. The interface electrification, adsorption, and specific surface area of the reservoir are positively correlated with the clay mineral content, which is mainly affected by the smectite content. As the clay mineral content increases, the proportion of nanoscale pore throats increases, and the core becomes denser. The saturation of the movable fluid controlled by the >50 nm pore throats in the tight conglomerate ranges from 8.7% to 33.72%, with an average of 20.24%. The clay mineral content, especially the I/S (mixed layer of Illite and montmorillonite) content, is negatively correlated with the movable fluid. In general, the research results clarified the relationship between the lithology and physical properties of clay minerals and the microscopic pore structure of the tight conglomerate reservoirs in the Baikouquan Formation in the Mahu area.

CO₂ flooding plays a crucial role in enhancing oil recovery and achieving carbon reduction targets, particularly in unconventional reservoirs with complex pore structures. The phase behavior of CO₂ and hydrocarbons at different scales significantly affects oil recovery efficiency, yet its underlying mechanisms remain insufficiently understood. This study improves existing thermodynamic models by introducing Helmholtz free energy as a convergence criterion and incorporating adsorption effects in micro- and nano-scale pores. This study refines existing thermodynamic models by incorporating Helmholtz free energy as a convergence criterion, offering a more accurate representation of confined phase behavior. Unlike conventional Gibbs free energy-based models, this approach effectively accounts for confinement-induced deviations in phase equilibrium, ensuring improved predictive accuracy for nanoscale reservoirs. Additionally, adsorption effects in micro- and nano-scale pores are explicitly integrated to enhance model reliability. A multi-scale thermodynamic model for CO₂-hydrocarbon systems is developed and validated through physical simulations. Key findings indicate that as the scale decreases from bulk to 10 nm, the bubble point pressure shows a deviation of 5% to 23%, while the density of confined fluids increases by approximately 2%. The results also reveal that smaller pores restrict gas expansion, leading to an enhanced CO₂ solubility effect and stronger phase mixing behavior. Through phase diagram analysis, density expansion, multi-stage contact, and differential separation simulations, we further clarify how confinement influences CO₂ injection efficiency. These findings provide new insights into phase behavior changes in confined porous media, improving the accuracy of CO₂ flooding predictions. The proposed model offers a more precise framework for evaluating phase transitions in unconventional reservoirs, aiding in the optimization of CO₂-based enhanced oil recovery strategies.