Accurate well productivity prediction plays a significant role in formulating reservoir development plans. However, traditional well productivity prediction methods lack accuracy in tight gas reservoirs; therefore, this paper quantitatively evaluates the correlations between absolute open flow and the critical parameters for Linxing tight gas reservoirs through statistical analysis. Dominant control factors are obtained by considering reservoir engineering theories, and a novel machine learning-based well productivity prediction method is proposed for tight gas reservoirs. The adaptability of the productivity prediction model is assessed through machine learning and field data analysis. Combined with the typical decline curve analysis, the estimated ultimate recovery (EUR) of a single well in the tight gas reservoir is forecasted in an appropriate range. The results of the study include 10 parameters (such as gas saturation) identified as the dominant controlling factors for well productivity and geological factors that impact the productivity in this area compared to fracturing parameters. According to the prediction results of the three models, the R² of Support Vector Regression (SVR), Back Propagation (BP), and Random Forest (RF) models are 0.72, 0.87, and 0.91, respectively. The results indicate that RF has a more accurate prediction. In addition, the RF model is more suitable for medium and high-production wells based on the actual field data. Based on this model, it is verified that the productivity of low-producing wells is affected by water production. This study confirms the model’s reliability and application value by predicting recoverable reserves for a single well.

With the deepening of exploration and development of tight sandstone gas reservoirs, the remaining recoverable reservoirs gradually become thinner with the vertical stratigraphic structure. The geomechanical properties become complex, and development based on conventional hydraulic fracturing methods often leads to serious problems, such as difficult control of fracture height, penetrating interlayers, too short fracture length, and inadequate proppant filling. In view of the above problems, we conducted a numerical investigation on a hydraulic fracturing scheme in a multi-layered and thin tight sandstone gas reservoir. According to the dataset from wells in a real gas reservoir in China’s Ordos Basin, the relevant geomechanical characteristics of the gas layers, together with the interlayers in the main production interval, were obtained, based on which, a fine numerical model was developed. By using the PL3D fracture propagation algorithm, a 3D hydraulic fracture propagation model was produced, and then using microseismic monitoring and production data matching, a high-precision hydraulic fracture model of the multi-layered and thin tight sandstone gas reservoir was obtained. On this basis, the influence of different geomechanical parameters and fracturing operational parameters on hydraulic fracture propagation was analyzed. Finally, an optimized hydraulic fracturing scheme that fitted the characteristics of the multi-layered and thin tight sandstone gas reservoir was proposed. Using a typical reservoir example, the optimized scheme enabled control of the fracture height in thin layers and the creation of long fractures with better proppant filling, so that the productivity of the fracture was significantly improved.

Utilizing the discrete fracture model (DFM), a transient flow model is established for fractured horizontal wells in tight oil reservoirs, accounting for threshold pressure gradient (TPG), stress sensitivity effect, hydraulic fracture parameters, and fracture distribution pattern. This model is solved using the finite-volume method (FVM), and an important sensitivity analysis is conducted. The findings reveal that the models incorporated by the threshold pressure gradient result in an upward trend in the pressure-derivative curve. As the threshold pressure gradient increases, this upward trend becomes more pronounced, rendering the distinction between flow regimes more challenging. The stress sensitivity effect predominantly impacts the pressure-derivative curve during the later flow period. Additionally, as the fracture half-length increases, the pressure performance of both fracture radial flow and formation radial flow becomes more difficult. Fracture conductivity has a significant influence during the early flow period, facilitating the identification of flow regimes with the trend of increasing fracture conductivity.

Well pattern infilling optimization is a crucial measure to enhance gas recovery, especially in tight gas reservoirs with low permeability and small-scale sand bodies. Traditional methods of determining well pattern density rely on qualitative analysis from the perspective of gas blocks. However, these methods are challenging to apply to sand bodies with different properties, and there have been no studies conducted on infilling time, which significantly impacts production increment. In response to this situation, this paper establishes a series of evaluation indexes and proposes a numerical simulation of economic well pattern density and infilling time based on real parameters obtained from the Linxing–Shenfu gas field. To quantitatively determine the economic well pattern density and infilling time based on fine characterization of sand bodies, a sensitivity analysis is conducted, considering various permeability levels and reserve abundance. Two intersection charts of economic well pattern density and infilling time, relating to reserve abundance and permeability, are then drawn. Furthermore, a real well site is selected as an example, and the infilling effect analysis confirms the reliability of the charts. The new method of determining economic well pattern density and infilling time presented in this article can provide theoretical support for the economic and efficient development of the Linxing–Shenfu gas field, serving as a useful reference for the beneficial development of similar gas reservoirs.

Spontaneous counter-current imbibition is a crucial recovery mechanism in water-wet fractured reservoirs, especially in unconventional formations like tight and shale reservoirs. The geometric characteristics of microscale fractures require further clarification regarding their impact on imbibition. In this paper, the numerical simulation method is used to study the influence of fracture aperture, length, density, and relative position between fracture and imbibition open face on the counter-current imbibition process of a matrix block. For fractures perpendicular to the imbibition surface and in contact with water, the embedded discrete fracture model is utilized to simulate the impact of varying fracture apertures on counter-current imbibition. For fractures parallel to the imbibition surface, considering the impact of fracture on the capillary discontinuity of the matrix, the effects of varying fracture lengths and densities on counter-current imbibition are simulated. The results show that when fractures are perpendicular to the imbibition surface and in contact with water, the imbibition rate can be increased, and as the fracture aperture decreases, the imbibition rate first increases and then decreases. On the other hand, fractures parallel to the imbibition surface inhibit the imbibition process, with the imbibition rate decreasing as fracture length or density increases. This paper proposes an empirical shape factor considering the geometric characteristics of fractures, which can effectively characterize the influence of microfractures on matrix block imbibition, thus improving the dual-medium numerical simulation model.