Accurate prediction of monthly oil and gas production is essential for oil enterprises to make reasonable production plans, avoid blind investment and realize sustainable development. Traditional oil well production trend prediction methods are based on years of oil field production experience and expertise, and the application conditions are very demanding. With the rapid development of artificial intelligence technology, big data analysis methods are gradually applied in various sub-fields of the oil and gas reservoir development. Based on the data-driven artificial intelligence algorithm Gradient Boosting Decision Tree (GBDT), this paper predicts the initial single-layer production by considering geological data, fluid PVT data and well data. The results show that the GBDT algorithm prediction model has great accuracy, significantly improving efficiency and strong universal applicability. The GBDT method trained in this paper can predict production, which is helpful for well site optimization, perforation layer optimization and engineering parameter optimization and has guiding significance for oilfield development.

Unstable water injection can effectively improve the recovery ratio of reservoirs with strong heterogeneity. However, the oil displacement mechanism and the determination method of unstable water injection parameters still need to be clarified, especially for complex fracture reservoirs, which greatly restrict the popularization and development of unstable water injection technology. This paper studies unstable water injection technology in highly heterogeneous reservoirs from the core and reservoir scales, utilizing many displacement experiments and numerical simulations. The differences in oil displacement efficiency, remaining oil distribution, pressure field, and streamlines between continuous water injection and unstable water injection are compared and evaluated. Five flow stages of unstable injection and production are precisely divided, and the microscopic and macroscopic displacement mechanism is clarified. A numerical model of two injection wells and one production is established to determine the best time to implement unstable water injection technology. Based on the principle of pressure superposition, the expression of pressure field distribution between injection and production well in each period of unstable water injection is analytically solved. This formula has provided a new development parameter optimization method aiming at the maximum pressure fluctuation range and optimized the development technology parameters in the water injection process. The results show that precise control injection and production parameters can expand water swept volume, effectively improve the degree of reserve utilization, and improve the recovery of complex reservoirs by 3–7%, which provides a reliable basis for the practical implementation of unstable water injection technology.

The volume fracturing technique has been widely used to improve the productivity of ultralow-permeability reservoirs. This paper presents a new semianalytical model to simulate the pressure transient and production behaviour of finite conductivity vertical fractured wells with stimulated reservoir volume (SRV) in heterogeneous reservoirs. The model is based on the five-linear flow model, the Warren-Root model, and fracture conductivity influence function. The model is validated by comparing its results with a numerical model. One novelty of this model is its consideration of three different kinds of production prediction models. Constant rate, constant pressure, and compound working systems are taken into account. This paper illustrates the effects of the SRV size and shape, mobility ratio, initial flow rate, limiting wellbore pressure, and hydraulic fracture parameters under different working systems. Results show that the SRV and parameters of fractures have a significant influence on long-term well performance. Moreover, the initial rate can extend the constant rate period by 418%, and limiting wellbore pressure can effectively improve the cumulative recovery rate by 23%. Therefore, this model can predict long-term wells’ behaviour and provide practical guiding significance for hydraulic fracturing design.

Multiple-thermal-fluid (MTF) stimulation technology has been successfully applied in heavy-oil reservoir development, resulting in the significant enhancement of oil production. However, the underlying mechanism of multi-component coupling remains unclear. This paper constructs a coupling model for MTF stimulation, investigates the coupling mechanism of different media in various zones during multiple-cycle stimulation operations, and compares the implementation effect with field results. The findings reveal that (1) based on media distribution, the area from near-wellbore to far well locations can be divided into four zones: high-temperature oil-viscosity-reduction zones, compound action zones, energy-replenishment zones, and unaffected zones. (2) In the high-temperature oil-viscosity-reduction zone, the latent heat of vaporization is released by steam, and ultra-heavy oil absorbs heat and reduces its viscosity, which plays a dominant role in the production of MTF. In the compound action zone, hot water, CO₂, and N₂ exhibit a synergistic effect which enhances overall performance. In the energy-replenishment zone, a small amount of N₂ provides pressure maintenance and an additional energy supply. (3) As more cycles of stimulation are conducted, the compound action zone expands, while the energy-replenishment zone contracts. Simultaneously, there is a decrease in contribution rate from the high-temperature viscosity-reduction zone to oil production but an increase from both the compound action zone and energy-replenishment zone up to 30%. Based on the dynamic law of representative wells, this paper proposes a multi-media zonal coupling mechanism, providing a reference for subsequent research on MTF stimulation mechanisms and the adjustment of production measures.