Horizontal Wells In Tight Reservoirs Research Articles

Machine learning-based fracturing parameter optimization for horizontal wells in Panke field shale oil

In the process of developing tight oil and gas reservoirs, multistage fractured horizontal wells (NFHWs) can greatly increase the production rate, and the optimal design of its fracturing parameters is also an important means to further increase the production rate. Accurate production prediction is essential for the formulation of effective development strategies and development plans before and during project execution. In this study, a novel workflow incorporating machine learning (ML) and particle swarm optimization algorithms (PSO) is proposed to predict the production rate of multi-stage fractured horizontal wells in tight reservoirs and optimize the fracturing parameters. The researchers conducted 10,000 numerical simulation experiments to build a complete training and validation dataset, based on which five machine learning production prediction models were developed. As input variables for yield prediction, eight key factors affecting yield were selected. The results of the study show that among the five models, the random forest (RF) model best establishes the mapping relationship between feature variables and yield. After verifying the validity of the Random Forest-based yield prediction model, the researchers combined it with the particle swarm optimization algorithm to determine the optimal combination of fracturing parameters under the condition of maximizing the net present value. A hybrid model, called ML-PSO, is proposed to overcome the limitations of current production forecasting studies, which are difficult to maximize economic returns and optimize the fracturing scheme based on operator preferences (e.g., target NPV). The designed workflow can not only accurately and efficiently predict the production of multi-stage fractured horizontal wells in real-time, but also be used as a parameter selection tool to optimize the fracture design. This study promotes data-driven decision-making for oil and gas development, and its tight reservoir production forecasts provide the basis for accurate forecasting models for the oil and gas industry.

Production Capacity Variations of Horizontal Wells in Tight Reservoirs Controlled by the Structural Characteristics of Composite Sand Bodies: Fuyu Formation in the Qian’an Area of the Songliao Basin as an Example

In order to improve the combined exploitation efficiency of horizontal and vertical wells, and given the fact that the complex and varied spatial structure of sand bodies in the Fuyu oil layer in the Qian’an area of Songliao Basin leads to significant differences in production characteristics of horizontal wells, the sand body types and internal spatial structure are finely dissected according to the theory of configuration analysis, and the internal spatial structure is divided into three configuration styles: spatial clipping type, overlapping type, and separation type. Then, by comparing the productivity characteristics of horizontal wells with different configurations of sand bodies, combined with the analysis of fluid flow law under horizontal well volume fracturing, a main fracture–fracture network–matrix coupled fluid flow model in a tight reservoir based on composite sand body configuration is established. Combined with the actual volume fracturing the horizontal well area, the productivity curves of each cluster in the horizontal section after numerical simulation of volume fracturing of typical horizontal well groups are extracted, which are divided into four types: high-yield stable type, high-yield two-stage type, high-yield rapid-decline type, and low-yield rapid-decline type, and the coupling relationship between the productivity characteristics of each cluster in the horizontal well volume fracturing and sand body configuration style is established, which provides a theoretical basis for the adjustment of different sand body development methods in subsequent oilfields.

Forward modeling of P- and S-waves response of fractures intersected with horizontal wells in tight reservoirs

Horizontal wells play an important role in expanding the drilling volume of reservoirs and oil production area, and are widely used in unconventional reservoirs. Fractures have a positive effect on reservoir permeability, but fractures can also cause accidents such as casing deformation and inter-well frac-hit. It is of great significance to identify and evaluate fractures intersected with horizontal wells in tight reservoirs. In this paper, a three-dimensional numerical model of horizontal wells and fractures in tight reservoirs is designed. The responses of monopole P-wave and dipole S-wave to fractures with different width, dip angle and filling medium are systematically studied, by using three-dimensional finite difference algorithm. The results show that when the fracture is filled with calcite, the amplitude attenuation of monopole P-wave and dipole S-wave has a monotonic exponential increase with the increase of fracture width and the decrease of fracture dip angle. In the real data processing, the amplitude attenuation of P- and S-waves can be used to jointly evaluate the fracture filled with calcite. When the fracture is filled with water, both P- and S-waves have prominent amplitude attenuation. P wave amplitude attenuation does not have a monotonic variation with the increase of fracture width but it has a monotonic increase with the decrease of fracture dip angle. S wave amplitude attenuation has a monotonic increase with the increase of fracture width and the decrease of fracture dip angle. The amplitude attenuation of P- and S- waves rises significantly when the fracture is filled with natural gas. This study is crucial for better understanding the response of P- and S-waves to fractures intersected with borehole in tight reservoirs, and it provides useful information for the inversion of fracture parameters by using P- and S-waves.

Evaluation of hydraulic fracturing of horizontal wells in tight reservoirs based on the deep neural network with physical constraints

Accurate diagnosis of fracture geometry and conductivity is of great challenge due to the complex morphology of volumetric fracture network. In this study, a DNN (deep neural network) model was proposed to predict fracture parameters for the evaluation of the fracturing effects. Field experience and the law of fracture volume conservation were incorporated as physical constraints to improve the prediction accuracy due to small amount of data. A combined neural network was adopted to input both static geological and dynamic fracturing data. The structure of the DNN was optimized and the model was validated through k-fold cross-validation. Results indicate that this DNN model is capable of predicting the fracture parameters accurately with a low relative error of under 10% and good generalization ability. The adoptions of the combined neural network, physical constraints, and k-fold cross-validation improve the model performance. Specifically, the root-mean-square error (RMSE) of the model decreases by 71.9% and 56% respectively with the combined neural network as the input model and the consideration of physical constraints. The mean square error (MRE) of fracture parameters reduces by 75% because the k-fold cross-validation improves the rationality of data set dividing. The model based on the DNN with physical constraints proposed in this study provides foundations for the optimization of fracturing design and improves the efficiency of fracture diagnosis in tight oil and gas reservoirs.

Numerical investigation of refracturing with/without temporarily plugging diverters in tight reservoirs

Refracturing is an important technique to tap the potential of reservoirs and boost production in depleted oil and gas fields. However, fracture propagation during refracturing, including both conventional refracturing and temporary-plugging refracturing remains poorly understood, especially for cases with non-uniform distribution of formation pressure due to long-term oil production and water injection. Therefore, taking pilot tests of refracturing with sidetracking horizontal wells in tight reservoirs in the Changqing Oilfield, China as an example, we establish a three-dimensional numerical model of conventional refracturing and a numerical model of temporary-plugging refracturing based on the discrete lattice method. Non-uniform distributions of formation pressure are imported in these models. We discuss the effects of key operating parameters such as injection rate, cluster spacing, and number of clusters on the propagation of multi-cluster fractures for conventional refracturing. For temporary-plugging refracturing, we examine the impacts of controlling factors such as the timing and number of temporary plugging on fracture propagation. In addition, we analyze a field case of temporary-plugging refracturing using well P3 in the Changqing Oilfield. The results show that fractures during refracturing tend to propagate preferentially and dominantly in the depleted areas. Improved stimulation effect can be obtained with an optimal injection rate and a critical cluster spacing. The proposed model of temporary-plugging refracturing can well describe the temporary plugging of dominant existing-fractures and the creation of new-fractures after fracturing fluid is forced to divert into other clusters from previous dominant clusters. Multiple temporary plugging can improve the balanced propagation of multi-cluster fractures and obtain the maximum fracture area. The established numerical model and research results provide theoretical guidance for the design and optimization of key operating parameters for refracturing, especially for temporary-plugging refracturing.

Evaluation of Enhanced Oil Recovery Potential using Interfracture Water Flooding in a Tight Oil Reservoir

Abstract The recovery factor of horizontal wells in tight reservoirs after stage fracturing is low. The effect of water huff-puff on enhancing oil recovery is not obvious. Water channeling is serious during interwell water displacement. Conventional EOR (enhance oil recovery) methods are not effective. Scholars have proposed the method of interfracture water flooding after horizontal well fracturing to improve recovery efficiency in tight reservoirs. In order to study the EOR effects of interfracture water flooding and huff-puff in tight reservoirs, three different EOR schemes were designed: interfracture synchronous water flooding (IFSWF), interfracture asynchronous water flooding (IFAWF), and water huff-puff. The experiment results show the following: (1) in the physical simulation experiment of homogeneous cores, after injection of 0.8 PV formation water, the recovery rates of huff-puff, IFAWF, and IFSWF were 25.7%, 33.7%, and 38.6%, respectively. (2) In the simulation of fractured cores, the oil concentration of IFAWF is 2.7 times higher than that of IFSWF. (3) In the simulation of formation energy replenishment by fractured core, the formation pressure increased by IFAWF is 1.9 times higher than the pressure increased by IFSWF. The results of this study show that interfracture asynchronous flooding can increase the utilization efficiency of injected water, overcome heterogeneity, effectively supplement the energy of tight reservoir, increase the swept area, and improve the recovery factor. IFAWF is a more suitable EOR method for tight reservoirs. The findings of this study contribute to a better understanding of how to select methods to enhance tight oil recovery. At the same time, it provides a method and idea for improving oil recovery of shale oil with lower reservoir physical properties.

Physical simulation experiment method of water breakthrough mechanism and plugging effect of horizontal well in tight reservoir

Horizontal wells have become a key technology for the economical and effective development of tight reservoirs. In production, water cut increases rapidly, and even waterflooding is prominent. The mechanism of water breakthrough and the analysis of the water plugging effect are still tricky problems worldwide. Based on the reservoir characteristics of the typical tight oil area in Changqing oilfield, a physical simulation method of water breakthrough and plugging effect of segmented fractured horizontal wells was established based on the parallel connection of double cores and large-scale physical simulation system, and the mechanism of water breakthrough and water plugging effect of horizontal wells were studied. The results show that natural fractures or dynamic fractures are the main factors affecting the characteristics of water breakthrough. The end and waist of staged fractured horizontal wells are the main parts of water breakthrough. Water breakthrough points gradually increase in production, showing multi-direction. The overall water cut decreases after the water-prone area is plugged. Specifically, in this study, water plugging was implemented when the water cut of the horizontal well rose to 91%, and the water cut of a breakthrough part was reduced to about 60% after plugging, which played a good role in controlling the overall water cut. Oil displacement efficiency increased from 32.5% before plugging to 36% after plugging, rising by 4.5 percent. In addition, the duration of oil production increase in horizontal well after water plugging is not long, mainly because of the formation of water injection dominant channel between the injection well and horizontal well fracture before plugging. At this time, the resistance primarily exists in the water-affected area, and the Jamin effect caused by imbibition is the main factor of resistance; then, the swept volume is difficult to expand.

Dominant Channels Identification Method for Multi-Fractured Horizontal Wells in Tight Reservoirs: Progress and Challenges

Dominant Channels Identification Method for Multi-Fractured Horizontal Wells in Tight Reservoirs: Progress and Challenges

Estimated ultimate recovery prediction of fractured horizontal wells in tight oil reservoirs based on deep neural networks

Accurate estimated ultimate recovery prediction of fractured horizontal wells in tight reservoirs is crucial to economic evaluation and oil field development plan formulation. Advances in artificial intelligence and big data have provided a new tool for rapid production prediction of unconventional reservoirs. In this study, the estimated ultimate recovery prediction model based on deep neural networks was established using the data of 58 horizontal wells in Mahu tight oil reservoirs. First, the estimated ultimate recovery of oil wells was calculated based on the stretched exponential production decline model and a five-region flow model. Then, the calculated estimated ultimate recovery, geological attributes, engineering parameters, and production data of each well were used to build a machine learning database. Before the model training, the number of input parameters was reduced from 14 to 9 by feature selection. The prediction accuracy of the model was improved by data normalization, the early stopping technique, and 10-fold cross validation. The optimal activation function, hidden layers, number of neurons in each layer, and learning rate of the deep neural network model were obtained through hyperparameter optimization. The average determination coefficient on the testing set was 0.73. The results indicate that compared with the traditional estimated ultimate recovery prediction methods, the established deep neural network model has the strengths of a simple procedure and low time consumption, and the deep neural network model can be easily updated to improve prediction accuracy when new well information is obtained. Cited as: Luo, S., Ding, C., Cheng, H., Zhang, B., Zhao, Y., Liu, L. Estimated ultimate recovery prediction of fractured horizontal wells in tight oil reservoirs based on deep neural networks. Advances in Geo-Energy Research, 2022, 6(2): 111-122. https://doi.org/10.46690/ager.2022.02.04

Semi-Analytical Rate Decline Solutions for a Refractured Horizontal Well Intercepted by Multiple Reorientation Fractures with Fracture Face Damage in an Anisotropic Tight Reservoir

Refracturing treatment is an economical way to improve the productivity of poorly or damaged fractured horizontal wells in tight reservoirs. Fracture reorientation and fracture face damage may occur during refracturing treatment. At present, there is still no report on the rate decline solution for refractured horizontal wells in tight reservoirs. In this work, by taking a semi-analytical method, traditional rate decline and Blasingame-type rate decline solutions were derived for a refractured horizontal well intercepted by multiple reorientation fractures with fracture face damage in an anisotropic tight reservoir. The accuracy and reliability of the traditional rate decline solution were verified and validated by comparing it with a classic case in the literature and a numerical simulation case. The effects of fracture reorientation and fracture face damage on the rate decline were investigated in depth. These investigations demonstrate that fracture face damage is not conducive to increasing well productivity during the early flow period and there is an optimal matching relationship between the principal fracture section angle and permeability anisotropy, particularly for the reservoirs with strong permeability anisotropy. The fracture length ratio and fracture spacing have a weak effect on the production rate and cumulative production while the fracture number shows a strong influence on the rate decline. Furthermore, multifactor sensitivity analysis indicates that fracture conductivity has a more sensitive effect on well productivity than fracture face damage, implying the importance of improving fracture conductivity. Finally, a series of Blasingame-type rate decline curves were presented, and type curve fitting and parameter estimations for a field case were conducted too. This work deepens our understanding of the production performance of refractured horizontal wells, which helps to identify reorientation fracture properties and evaluate post-fracturing performance.

Flow mechanism of production decline during natural depletion after hydraulic fracturing of horizontal wells in tight oil reservoirs

Currently, there are problems regarding decreasing production rates and low recovery factors in the field test during depletion development of staged fractured horizontal wells in tight reservoirs. However, the production decline mechanism during the depletion development process is not clear at present; so, it is necessary to further explore the pressure distribution law and production decline mechanism in order to guide subsequent tight reservoir exploitation and to improve the recovery factor. In this study, a multi-point pressure measurement physical simulation experiment system, a pressure distribution mathematic model, and a mathematic productivity model were developed. After fitting the model with the experimental data, the production decline mechanism during depletion development of tight oil reservoirs was analyzed from four aspects. The results show that in lower permeability tight reservoir facies, the pressure propagation distance is shorter. The pressure gradient of tight oil reservoirs during depletion development is four times higher than that of low permeability reservoirs. As the permeability decreases, the seepage resistance coefficient increases exponentially. The seepage resistance in tight oil reservoirs is nearly six times higher than that in low permeability reservoirs. Compared with traditional enhanced oil recovery (EOR) techniques, inter-fracture flooding has obvious mechanism advantages in the EOR of tight reservoirs.

Prediction of Refracturing Timing of Horizontal Wells in Tight Oil Reservoirs Based on an Integrated Learning Algorithm

Refracturing technology can effectively improve the EUR of horizontal wells in tight reservoirs, and the determination of refracturing time is the key to ensuring the effects of refracturing measures. In view of different types of tight oil reservoirs in the Songliao Basin, a library of 1896 sets of learning samples, with 11 geological and engineering parameters and corresponding refracturing times as characteristic variables, was constructed by combining numerical simulation with field statistics. After a performance comparison and analysis of an artificial neural network, support vector machine and XGBoost algorithm, the support vector machine and XGBoost algorithm were chosen as the base model and fused by the stacking method of integrated learning. Then, a prediction method of refracturing timing of tight oil horizontal wells was established on the basis of an ensemble learning algorithm. Through the prediction and analysis of the refracturing timing corresponding to 257 groups of test data, the prediction results were in good agreement with the real value, and the correlation coefficient R2 was 0.945. The established prediction method can quickly and accurately predict the refracturing time, and effectively guide refracturing practices in the tight oil test area of the Songliao basin.

Experimental study on physical modeling of flow mechanism in volumetric fracturing of tight oil reservoir

This paper investigates the characteristics of oil–water two-phase flow after volumetric fracturing of horizontal wells in tight reservoirs. Based on a large-scale high-pressure, high-temperature experimental system for modeling horizontal well injection and production, the characteristics of the pressure distribution, cumulative liquid production, recovery factor, and liquid production rate of a matrix model and fractured model during the waterflooding process are compared and analyzed. The results show that, for both types of reservoirs, the fluid forms a high-pressure zone and a low-pressure zone during water injection. As the development progresses, the high-pressure zone continuously moves forward. There is a pressure step between the high-pressure zone and the low-pressure zone, which gradually decreases in magnitude as the pressure wave reaches the well. By this time, the main resistance before water breakthrough is the pressure step at the waterflooding front. The ultimate recovery is found to be 26.71% for the matrix model and 28.48% for the fractured model. Without an effective displacement system, the resistance of the horizontal well during waterflooding mainly acts on the oil–water interface. After the establishment of an effective displacement scheme, the resistance gradually expands to both sides of the water-swept zone. At this point, the formation of a dominant channel greatly weakens the displacement performance. Thus, it is necessary to rely on imbibition or surfactants in the later stages to improve the recovery factor.

Study on the Production Mode of Horizontal Well from Water Huff and Puff to Segmented Injection and Production in Tight Reservoir

Water huff and puff in horizontal wells in tight reservoirs has achieved good results in replenishing formation energy. However, after multiple rounds of treatment, a rapid decrease in formation pressure takes place making it difficult to maintain stable production. To improve the oil recovery rate of tight reservoirs, it is imminent to change the development mode. In this work, the stress distribution characteristics at fracture tips were analyzed based on Irwin theory and elastic theory. A model of propagation and closure length of fractures was established based on the propagation mechanism of water injection-induced natural fracture and the energy balance principle of fracture mechanics. Surfactant imbibition experiments were carried out according to the imbibition principle of surfactant system, and the propagation law of natural fractures was described with numerical simulation to analyze the seepage characteristics of dynamic fracture network. On the basis of the above works, alternating water huff and puff into segmented injection and production was proposed according to the distribution law of dynamic fracture network. The developing process of an actual well case by these two developing modes was simulated to predict 18 years of cumulative recovery, pressure distribution, and recovery rate. Results showed that when stress intensity factor exceeds the fracture toughness, the natural fractures will extend along their original directions and get connected, forming an irregular fracture network. The lengths of fractures after propagation and closure will not bring about water channeling for they are far shorter than well and interval spacing. Surfactant could diminish the resistance of boundary layer by reducing the wetting contact angle, ending up with an improvement in imbibition efficiency. Radial displacement and dynamic imbibition occur simultaneously in a dynamic fracture network during the early stage of water injection, while static imbibition mainly occurs during injection shutdown period and well soaking. According to comparison, the swept area of segmented injection and production was larger, ending up with a continuous increase of simulated recovery rate and cumulative recovery. The findings of this study show alternating water huff and puff after to segmented injection and production in fractured tight reservoir can allow full play of dynamic fracture network’s potential and achieve effective enhancement in oil recovery rate.

Optimization of horizontal well fracturing mode in Gaotaizi tight reservoirs of L26 well block in Daqing Oilfield

The tight reservoir of the Gaotaizi oil layer in the L26 well area of Daqing Oilfield is a typical sand sheet deposit, with complex geological conditions. It is difficult to evaluate the production of horizontal wells in tight reservoirs with different well layout and fracturing operation scales, and the reasonable fracturing mode is unclear. Based on the study of reservoir characteristics and fracturing parameters in the area, multi-scale and multi-media well group models of sand sheet facies deposition in the Gaotaizi reservoir were established, and the reasonable well spacing under the mode of parallel and staggered fracture distribution was studied by numerical simulation. The results show that the production of horizontal wells with staggered fractures is slightly higher than that with parallel fractures. The well spacing of wells with parallel fractures is 600m, and the optimal well spacing under staggered fracturing is 500m. The results provide a basis for the optimal design of tight oil horizontal wells in the Gaotaizi reservoir of Daqing.

The characteristics of unconventional tight oil reservoir and its modification technology and productivity prediction

The zonal productivity prediction model of volume fractured horizontal wells in tight reservoirs is established in this study based on the physical model of volume fractured horizontal wells to study the near-well seepage law of volume fractured horizontal wells in unconventional tight reservoirs. The conformal transformation and iteration method are used to solve the problem. Compared with Fan Zifei's and Ning Zhengfu's method, the optimization of fractured horizontal wells' production parameters is studied. The effects of starting pressure gradient and fracture cluster number on horizontal wells' productivity with volume fracturing are analyzed. Multivariate regression analysis is used to rank the importance of influencing factors. The results show that the starting pressure gradient has the most significant impact on capacity. The application example of volume fractured horizontal wells in Lucaogou tight reservoir shows that the zonal productivity model established in this study can be used to predict the initial productivity of volume fractured horizontal wells. Thus, through theoretical analysis and numerical simulation, the productivity prediction model of horizontal wells with volume fracturing has certain guiding significance for the effective development of tight reservoirs.

Research on integrative multi-media modelling and simulation method for tight formation horizontal well development

Tight formations usually have large area of coverage. There is large areal heterogeneity for reservoir petrophysics, rock facies, formation thickness, physical properties and oil saturations, in different reservoir blocks, in area between different wells, and also in different segments of a single well. Tight reservoirs have different scales of natural fracture development. Hydraulic fracturing also forms different scales of complex hydraulic fracture network, which has large macroscopic heterogeneity with prominent multi-scale features. Unconventional tight reservoirs consist of different scales of porous media from nano-sized to nano-micron to micron-sized. There is large difference for compositions and quantity distributions in pore spaces with different scales. Different scales of pores present discrete discontinuous distribution in space, with large heterogeneity in spatial distribution. There is large difference for geometric parameters and physical properties in different scales of porous media. Different scales of pores present large microscopic heterogeneity and multiple porous media features. All of these features make conventional reservoir modelling and numerical simulation theory and technology not applicable in this scenario. In this paper, a new multimedia modelling and simulation method for volume fracturing of horizontal wells in tight reservoirs is introduced in detail by using the unconventional reservoir modelling software Untog, taking a single well as an example.

Transient Pressure Analysis of Volume-Fractured Horizontal Wells Considering Complex Fracture Networks and Stress Sensitivity in Tight Reservoirs.

Tight reservoirs, as an important alternative for conventional energy resources, have been successfully exploited with the aid of hydraulic fracturing technologies. Because of the inherent ultralow permeability and porosity, tight oil reservoirs generally suffer from the effects of stress sensitivity. Both hydraulic fractures with complex geometries and a high-permeability area known as stimulated reservoir volume (SRV) may be generated by the massive hydraulic fracturing operations. All these bring huge challenges in transient pressure analysis of tight reservoirs. Up till now, although many research studies have been carried out on the transient pressure analysis of volume-fractured horizontal wells in tight reservoirs, unfortunately, there is still a lack of research studies that have taken stress sensitivity, complex fracture networks, and the SRV into consideration, simultaneously. To fill up this gap, this paper first idealizes the reservoir after hydraulic fracturing as two radial composite regions, that is, the unstimulated outer region and the inner SRV. The stress sensitivity is characterized by the variable permeability depending on the pore pressure. A linear source with consideration of the stress sensitivity in the composite reservoir is obtained by the perturbation technique, Laplace transformation, and the flow coupling of two regions. Second, the complex fracture networks are discretized into segments to capture their geometries. A semi-analytical model is finally established and validated by the comparison with previous models. On the basis of our model, six flow stages of volume-fractured horizontal well are identified and special features of each regime are analyzed. The stress sensitivity has a great impact on the later stage of production. The mobility ratio and the SRV radius mainly affect SRV pseudo-steady-state flow period and interporosity flow period in the outer region. Fracture number mainly affects the linear flow in the SRV. Fracture geometries mainly affect linear flow and interporosity flow in the SRV. This study has some significance for well test interpretation and production performance analysis of tight reservoirs.

Analysis of production decline factors of fracturing horizontal wells in tight reservoirs and study of decline law

Horizontal well fracturing technology has been applied in tight oil reservoirs, and most horizontal wells show decline after high production period. In order to define the change law of horizontal well production based on the geological and engineering factors on the influence of the horizontal well production change, the paper uses Daqing region A block of the horizontal well production data in view of the analysis of the regressive method. Based on the analysis of each decline method, it is considered that the horizontal well production in this block is the exponential decline, which lays a foundation for the prediction of horizontal well production and the adjustment of the later development system.

Semianalytical Coupled Model of Transient Pressure Behavior for Horizontal Well with Complex Fracture Networks in Tight Oil Reservoirs

Due to a large number of natural fractures in tight oil reservoir, many complex fracture networks are generated during fracturing operation. There are five kinds of flow media in the reservoir: “matrix, natural fracture, hydraulic fracture network, perforation hole, and horizontal wellbore”. How to establish the seepage model of liquid in multiscale medium is a challenging problem. Firstly, this paper establishes the dual medium seepage model based on source function theory, principle of superposition, and Laplace transformation and then uses the “star-triangle” transform method to establish the transient pressure behavior model in the complex fracture network. After that, perforating seepage model and variable mass flow in horizontal wellbore were established. Finally, continuous condition was used to couple the seepage model of dual medium seepage model, transient pressure behavior model in the complex fracture network, perforation seepage model, and the variable mass seepage model in horizontal wellbore, to establish a semianalytical coupled seepage model for horizontal well in tight reservoir. This paper provides theoretical basis for field application of horizontal well with complex fracture networks.