Shale gas yield prediction method based on isotopic tracer method and multi-source data fusion

Abstract

The invention discloses a shale gas yield prediction method based on an isotopic tracing method and multi-source data fusion, and the method comprises the following steps: S1, obtaining seismic reflection data, and constructing a reservoir physical model; s2, acquiring a gas sample, and performing isotope analysis to obtain isotope composition; s3, determining a gas source, a flow path and reservoir formation causes according to the isotope composition, and guiding fluid distribution on the reservoir physical model; s4, pressure change conditions of a shaft and a stratum in the fracturing process are obtained, and the fracture network distribution condition of the reservoir physical model after hydraulic fracturing is determined; s5, acquiring change conditions of pressure, temperature and yield in the production process, and updating the reservoir physical model; and S6, fusing the data in the steps S1-S5 to obtain a dynamic three-dimensional reservoir model, establishing a multiphase fluid flow model, solving by adopting numerical simulation, and predicting to obtain the yield of the target shale gas well. The shale gas yield prediction accuracy can be improved.

Description

Technical Field

[0001] The present invention relates to the technical field of shale gas production prediction, and in particular to a shale gas production prediction method based on isotope tracing and multi-source data fusion. Background Art

[0002] As an important unconventional natural gas resource, shale gas extraction technology has become a research hotspot in the global energy field. Traditional shale gas production prediction methods mainly rely on geological models and seepage simulations, but in actual production, the prediction accuracy is often limited due to the complexity of the reservoir and the single data source. In order to improve the accuracy of shale gas production prediction, a comprehensive prediction method that can integrate multiple data sources is urgently needed to more comprehensively analyze the dynamic behavior and production potential of gas reservoirs. Summary of the invention

[0003] In view of the above problems, the present invention aims to provide a shale gas production prediction method based on isotope tracing and multi-source data fusion.

[0004] The technical solution of the present invention is as follows:

[0005] A shale gas production prediction method based on isotope tracing method and multi-source data fusion includes the following steps:

[0006] S1: Acquire seismic reflection data of the reservoir where the target shale gas well is located, and construct a reservoir physical model based on the seismic reflection data;

[0007] S2: Obtaining a gas sample from a target shale gas well, and performing isotope analysis on the gas sample to obtain the isotope composition of the gas sample;

[0008] S3: determining the gas source, flow path and reservoir genesis according to the isotopic composition, and guiding the fluid distribution on the reservoir physical model according to the gas source, flow path and reservoir genesis;

[0009] S4: Obtaining the pressure changes of the wellbore and the formation during the fracturing process of the target shale gas well, and determining the distribution of the fracture network of the reservoir physical model after hydraulic fracturing according to the pressure changes;

[0010] S5: Obtain changes in pressure, temperature and output during the production process of the target shale gas well, and update the reservoir physical model according to the changes;

[0011] S6: Integrate the data of steps S1-S5 to obtain a dynamic three-dimensional reservoir model, and establish a multiphase fluid flow model on the dynamic three-dimensional reservoir model. Use numerical simulation to solve the multiphase fluid flow model to predict the production of the target shale gas well.

[0012] Preferably, in step S2, the isotopic composition includes carbon isotopes 13 C / 12 C. Hydrogen isotopes 2 H / 1 H and oxygen isotopes 18 O / 16 O.

[0013] Preferably, in step S2, if it is during the hydraulic fracturing process, it also includes the step of introducing isotope tracers to monitor the diffusion of the fluid and the formation of the fracture network.

[0014] Preferably, in step S6, the multiphase fluid flow model includes a continuity equation, a momentum equation, an energy equation, a state equation, interactions and relative permeability.

[0015] Preferably, the continuity equation is:

[0016]

[0017] Where: φ is the porosity; ρ i is the density of the i-th phase fluid; S i is the saturation of the i-th phase; t is the time; is the divergence operator; V i is the velocity vector of the i-th phase; q i is the source and sink term of the i-th phase.

[0018] Preferably, the momentum equation is:

[0019]

[0020] Where: is the pressure gradient of the i-th phase; μ i is the fluid viscosity; is the Laplace operator of the velocity field; g is the gravitational acceleration vector.

[0021] Preferably, the energy equation is:

[0022]

[0023] Where: c p,i is the specific heat capacity of the i-th phase; T i is the temperature of the i-th phase; k i is the thermal conductivity of the i-th phase; is the temperature gradient change per unit time; Q i is the source phase of the i-th phase.

[0024] Preferably, the gas state equation includes:

[0025] Gas state equation:

[0026] P=ρRT (4)

[0027] Where: P is the pressure of the gas; ρ is the density of the gas; R is the gas constant; T is the temperature of the gas;

[0028] Liquid state equation:

[0029] ρ liq =ρ0(1-β(T liq -T0)) (5)

[0030] Where: liq is the density of the liquid; ρ0 is the density of the liquid at the reference temperature T0; β is the volume expansion coefficient; T liq is the temperature of the liquid.

[0031] Preferably, the interaction and relative permeability include relative permeability, capillary pressure, adsorption and desorption processes;

[0032] The relative permeability is calculated by the following formula:

[0033]

[0034] Where: K r,gas and K r,liquid are the relative permeabilities of the gas phase and the liquid phase, respectively; S gas and S liquid are the saturation of gas phase and liquid phase respectively; S gas,min and S liquid,min are the minimum saturation of gas phase and liquid phase respectively; S gas,Sat and S liquid,Sat are the upper limits of saturation of gas phase and liquid phase respectively; k gas and k liquid are the absolute permeabilities of gas and liquid phases, respectively; k is the calibration factor;

[0035] The capillary pressure is calculated by the following formula:

[0036]

[0037] Where: P c is the capillary pressure; σ is the surface tension of the liquid; θ is the contact angle between the liquid and the solid surface; r is the pore radius or the equivalent radius of curvature;

[0038] The adsorption and desorption processes are calculated by the following formula:

[0039]

[0040]

[0041] Where: q is the adsorption amount; q max is the maximum adsorption amount; b is the adsorption isotherm model constant, which indicates the adsorption strength of gas and solid; P is the gas pressure; θ′ is the desorption amount of gas; P0 is the initial desorption pressure of gas.

[0042] As an advantage, the method further comprises the following steps:

[0043] S7: Change the parameters of the multiphase fluid flow model, conduct sensitivity analysis, evaluate the uncertainty of production prediction, and then use different reservoir models and production scenarios to conduct multiple simulation comparisons and select the prediction model with higher accuracy;

[0044] S8: Use the prediction model with higher accuracy to predict the production of the target shale gas well.

[0045] The beneficial effects of the present invention are:

[0046] 1. The present invention obtains data such as the gas properties and genesis of shale gas through the isotope tracer method, and then integrates seismic data, pressure data and long-term dynamic reservoir data to construct a dynamically changing three-dimensional reservoir formation model. On this basis, a multiphase fluid flow model is constructed to describe the movement path and flow of gas in the formation, and shale gas production is predicted using numerical simulation solutions. The isotope tracer data is used for guidance in constructing the multiphase fluid flow model, which can improve the accuracy of the prediction.

[0047] 2. The present invention can dynamically predict the shale gas production in different wells and reservoirs, obtain the shale gas production distribution, and provide a theoretical basis and support for subsequent shale gas exploitation. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0049] Figure 1 It is a schematic flow chart of a shale gas production prediction method based on isotope tracing method and multi-source data fusion of the present invention;

[0050] Figure 2 It is a schematic diagram of the production history matching results of some wells in a specific embodiment;

[0051] Figure 3A schematic diagram of the structure of a reservoir physical model in a specific embodiment;

[0052] Figure 4 This is a schematic diagram of the distribution results of high-yield areas and low-yield areas in a specific embodiment;

[0053] Figure 5 It is a schematic diagram of the comparison results between the predicted value and the actual value of shale gas production of a single well in a specific embodiment. DETAILED DESCRIPTION

[0054] The present invention is further described below in conjunction with the accompanying drawings and embodiments. It should be noted that, in the absence of conflict, the embodiments in this application and the technical features in the embodiments can be combined with each other. It should be noted that, unless otherwise specified, all technical and scientific terms used in this application have the same meanings as those generally understood by those of ordinary skill in the art to which this application belongs. The words "including" or "comprising" and the like used in the disclosure of the present invention mean that the elements or objects appearing before the word cover the elements or objects listed after the word and their equivalents, without excluding other elements or objects.

[0055] like Figure 1 As shown, the present invention provides a shale gas production prediction method based on isotope tracing method and multi-source data fusion, comprising the following steps:

[0056] S1: Acquire seismic reflection data of a reservoir where a target shale gas well is located, and construct a reservoir physical model based on the seismic reflection data.

[0057] Seismic reflection data of reservoirs are obtained through 3D seismic exploration to identify reservoir structures, faults, fracture networks and gas reservoir distribution. During hydraulic fracturing, microseismic monitoring technology can also be used to monitor tiny seismic events in the formation in real time, thereby locating and characterizing the fractures generated by hydraulic fracturing and their extension range. Combining microseismic monitoring data with seismic data can analyze the fracture network formed by hydraulic fracturing and its impact on reservoir permeability.

[0058] S2: Obtain a gas sample from a target shale gas well, and perform isotope analysis on the gas sample to obtain the isotope composition of the gas sample.

[0059] In a specific embodiment, an isotope mass spectrometer or the like is used to analyze the isotope composition in the gas sample. Optionally, the isotope composition includes carbon isotopes. 13 C / 12 C. Hydrogen isotopes 2 H / 1 H and oxygen isotopes 18 O / 16 O.

[0060] In a specific embodiment, during the hydraulic fracturing process, the method further includes introducing isotope tracers (such as radioactive or stable isotopes) to monitor the diffusion of the fluid and the formation of the fracture network.

[0061] S3: Determine the gas source, flow path and reservoir genesis according to the isotope composition, and guide the fluid distribution on the reservoir physical model according to the gas source, flow path and reservoir genesis.

[0062] In this step, isotope data can be used to identify the source and origin of gas in different strata, determine the maturity and type of natural gas (such as biogenic or thermal origin), and then combine isotope data from multiple wells and layers to analyze the degree of mixing of gases from different sources in the reservoir and identify the gas components contributed by each layer.

[0063] S4: Obtain the pressure changes of the wellbore and the formation during the fracturing process of the target shale gas well, and determine the distribution of the fracture network of the reservoir physical model after hydraulic fracturing according to the pressure changes.

[0064] In this step, by combining the fracturing monitoring data and microseismic data at different reservoir stages in the wellbore, the fracture volume and extension range can be evaluated, and the gas seepage paths in different areas can be determined. Then, the Tracer fluid tracing technology (such as chemical tracers, isotope tracers) can be used to monitor the distribution and mixing of the injected fluid in different layers, identify the main flow paths and flow rates of the fluid in the reservoir, determine high-yield and low-yield areas, and record the gas production data of each wellhead.

[0065] S5: Obtain changes in pressure, temperature and output during the production process of the target shale gas well, and update the reservoir physical model according to the changes.

[0066] In this step, the dynamic behavior and exhaustion process of the gas reservoir can be understood by monitoring the changes in temperature and pressure data, and the gas production data at the wellhead can be recorded to provide data support for the subsequent analysis of the production dynamics of the gas reservoir in combination with other data. In combination with long-term pressure monitoring and gas production data, the exhaustion mode and gas desorption behavior of the reservoir can be analyzed, and the three-dimensional reservoir model can be updated using dynamic data, and the reservoir characteristics (such as permeability, porosity) and fracture model can be adjusted to optimize the prediction model.

[0067] S6: Integrate the data of steps S1-S5 to obtain a dynamic three-dimensional reservoir model, and establish a multiphase fluid flow model on the dynamic three-dimensional reservoir model. Use numerical simulation to solve the multiphase fluid flow model to predict the production of the target shale gas well.

[0068] In this step, the data of fusion steps S1-S5 mainly refers to the use of the constructed reservoir physical model to fuse the isotope data with other data to guide the multiphase fluid flow model, so as to simulate the interaction, flow and distribution of gas (shale gas), water (such as fracturing fluid or natural water in the reservoir), and other possible phases (such as oil or solid mineral particles) in the reservoir. After identifying the different gas properties and sources of the gas through isotope data, the initial conditions and boundary conditions in the model are adjusted. For example, if the isotope data shows that part of the gas comes from the deep reservoir, the initial pressure, temperature and fluid composition of the model may need to be adjusted accordingly.

[0069] In a specific embodiment, the multiphase fluid flow model includes continuity equation, momentum equation, energy equation, state equation, interaction and relative permeability.

[0070] The continuity equation is:

[0071]

[0072] Where: φ is the porosity; ρ i is the density of the i-th phase fluid; S i is the saturation of the i-th phase; t is the time; is the divergence operator; V i is the velocity vector of the i-th phase; q i is the source and sink term of the i-th phase.

[0073] The momentum equation is:

[0074]

[0075] Where: is the pressure gradient of the i-th phase; μ i is the fluid viscosity; is the Laplace operator of the velocity field; g is the gravitational acceleration vector.

[0076] The energy equation is:

[0077]

[0078] Where: c p,i is the specific heat capacity of the i-th phase; T i is the temperature of the i-th phase; k i is the thermal conductivity of the i-th phase; is the temperature gradient change per unit time; Q i is the source phase of the i-th phase.

[0079] The gas state equation includes:

[0080] Gas state equation:

[0081] P=ρRT (4)

[0082] Where: P is the pressure of the gas; ρ is the density of the gas; R is the gas constant; T is the temperature of the gas;

[0083] Liquid state equation:

[0084] ρ liq =ρ0(1-β(T liq -T0)) (5)

[0085] Where: liq is the density of the liquid; ρ0 is the density of the liquid at the reference temperature T0; β is the volume expansion coefficient; T liq is the temperature of the liquid.

[0086] The interaction and relative permeability include relative permeability, capillary pressure, adsorption and desorption processes, and the relative permeability is calculated by the following formula:

[0087]

[0088] Where: K r,gas and K r,liquid are the relative permeabilities of the gas phase and the liquid phase, respectively; S gas and S liquid are the saturation of gas phase and liquid phase respectively; S gas,min and S liquid,min are the minimum saturation of gas phase and liquid phase respectively; S gas,Sat and S liquid,Sat are the upper limits of saturation of gas phase and liquid phase respectively; k gas and k liquid are the absolute permeabilities of gas and liquid phases, respectively; k is the calibration factor;

[0089] The capillary pressure is calculated by the following formula:

[0090]

[0091] Where: P c is the capillary pressure; σ is the surface tension of the liquid; θ is the contact angle between the liquid and the solid surface; r is the pore radius or the equivalent radius of curvature;

[0092] The adsorption and desorption processes are calculated by the following formula:

[0093]

[0094]

[0095] Where: q is the adsorption amount; qmax is the maximum adsorption amount; b is the adsorption isotherm model constant, which indicates the adsorption strength of gas and solid; P is the gas pressure; θ′ is the desorption amount of gas; P0 is the initial desorption pressure of gas.

[0096] In a specific embodiment, the open source software OpenFOAM is used to perform numerical simulation and solve the problem. The basic steps include: first, discretizing the flow equation, then building a suitable network, then setting initial conditions and boundary conditions, and then solving the nonlinear equation using a step-by-step method.

[0097] In a specific embodiment, the shale gas production prediction method based on isotope tracing and multi-source data fusion of the present invention further includes the following steps:

[0098] S7: Change the parameters of the multiphase fluid flow model, perform sensitivity analysis, evaluate the uncertainty of production prediction, and then use different reservoir models and production scenarios to perform multiple simulation comparisons and select the prediction model with higher accuracy.

[0099] In a specific embodiment, permeability and porosity are first selected as parameters, and then a local sensitivity analysis is performed, in which the porosity is fixed, the permeability is gradually increased and decreased (10%), and the change in gas production for each simulation is recorded. Finally, a global sensitivity analysis is performed, and random combinations of permeability and porosity are generated using Monte Carlo simulation. The gas production of different combinations is recorded in the random simulation, and the results are statistically analyzed to evaluate the overall impact of permeability and porosity on gas production, optimize the model parameter settings, and make adjustments to improve prediction accuracy.

[0100] S8: Use the prediction model with higher accuracy to predict the production of the target shale gas well.

[0101] In a specific embodiment, taking the shale gas wells in the bottom layer of southern Sichuan and the Malonxi Formation as an example, the shale gas production prediction method based on isotope tracing method and multi-source data fusion of the present invention is used to predict its production, which specifically includes the following steps:

[0102] (1) Collecting isotope data: Collecting gas samples from shale gas wells and analyzing their isotope composition (e.g. carbon isotope 13 C / 12 C. Hydrogen isotopes 2 H / 1 H. Oxygen isotopes 18 O / 16 O), using the results to determine the origin (e.g., thermal or microbial) of the gas and its maturity, and during the hydraulic fracturing process, introducing artificial isotope tracers (e.g., radioactive or stable isotopes) to monitor the diffusion of the fluid and the formation of the fracture network.

[0103] In this embodiment, 10765 sets of daily production data of eight wells 1HF, 1.2HF, 1.3HF, 1.4HF, 5.1HF, 5.2HF, 6.2HF, and 6.3HF were collected through field measurements. The production history fitting results of some wells are shown in the following figure. Figure 2 As shown, isotope mass spectrometer and other equipment are then used to analyze the isotope composition. The isotope data are used to identify the source and origin of the gas in different strata, and to determine the maturity and type (such as biogenic or thermal) of the natural gas in the eight wells. The isotope data from multiple wells and multiple layers are then combined to analyze the degree of mixing of gases from different sources in the reservoir, and to identify the gas components contributed by each layer. The eight wells are hydraulically fractured, and artificial isotope tracers (such as radioactive or stable isotopes) are introduced to monitor the diffusion of the fluid and the formation of the fracture network.

[0104] (2) Collecting seismic data: Seismic reflection data of reservoirs are obtained through three-dimensional seismic exploration to identify reservoir structures, faults, fracture networks and gas reservoir distribution. During the hydraulic fracturing process, microseismic monitoring technology is used to monitor small seismic events in the formation in real time, so as to locate and characterize the fractures generated by hydraulic fracturing and their extension range, and construct the obtained reservoir physical model such as Figure 3 shown.

[0105] (3) Collecting fracturing formation pressure data: By real-time monitoring of the pressure changes in the wellbore and formation during the fracturing process, we can help understand the expansion behavior of the fractures and the injection of fluids. We can also use Tracer fluid tracing technology (such as chemical tracers and isotope tracers) to monitor the distribution and mixing of injected fluids in different layers. In this example, the distribution of high-yield and low-yield areas is as follows: Figure 4 shown.

[0106] (4) Collect reservoir dynamic data and historical shale gas production data: Collect data on long-term monitoring of reservoir pressure and temperature changes to understand the dynamic behavior and depletion process of the gas reservoir. Review historical data on relevant wellheads to collect gas production data at the wellheads to provide data support for subsequent analysis of the production dynamics of the gas reservoir in combination with other data.

[0107] (5) Constructing a multiphase fluid flow model: The above data are integrated and a dynamic three-dimensional reservoir model is constructed. Multiphase fluid flow simulation is performed to predict the flow behavior and production of gas in different production stages. In the flow simulation, the isotope data are combined to analyze the gas contribution from different layers and sources, optimize the overall production prediction of the gas reservoir, and then the model is solved using numerical simulation.

[0108] (6) Debugging the model: Change model parameters (such as permeability, fracture extension, pressure, etc.), conduct sensitivity analysis, evaluate the uncertainty of production prediction, and then use different reservoir models and production scenarios to conduct multiple simulation comparisons to select the most appropriate prediction model.

[0109] (7) Use the most appropriate prediction model selected in step (6) to predict the production of the target shale gas well. In this embodiment, the comparison between the predicted value and the actual value of the production of a single shale gas well is as follows: Figure 5 As shown. Figure 5 It can be seen that the present invention can accurately predict the production of shale gas wells.

[0110] In summary, firstly, a three-dimensional formation model is constructed through seismic reflection data to define the geometric shape of the reservoir, layer division, and main fractures and faults; secondly, isotope data identifies the gas source, flow path, and reservoir genesis, and further guides the distribution of fluids on the three-dimensional formation model; then, the fracturing pressure detection data helps determine the approximate distribution of the fracture network after hydraulic fracturing; then, the model parameters such as reservoir characteristic permeability are updated through long-term pressure detection data; finally, a multiphase fluid flow model is constructed and numerical simulation is used to accurately predict the shale gas production. Compared with the prior art, the present invention has significant progress.

[0111] The above description is only a preferred embodiment of the present invention and does not constitute any form of limitation to the present invention. Although the present invention has been disclosed as a preferred embodiment as above, it is not intended to limit the present invention. Any technician familiar with the profession can make some changes or modifications to equivalent embodiments of equivalent changes using the technical contents disclosed above without departing from the scope of the technical solution of the present invention. However, any simple modification, equivalent change and modification made to the above embodiments based on the technical essence of the present invention without departing from the content of the technical solution of the present invention still falls within the scope of the technical solution of the present invention.

Claims

1. A shale gas production prediction method based on isotope tracing and multi-source data fusion, characterized in that: The following steps are involved: S1: Acquire seismic reflection data of the reservoir where the target shale gas well is located, and construct a reservoir physical model based on the seismic reflection data; S2: Obtaining a gas sample from a target shale gas well, and performing isotope analysis on the gas sample to obtain the isotope composition of the gas sample; S3: determining the gas source, flow path and reservoir genesis according to the isotopic composition, and guiding the fluid distribution on the reservoir physical model according to the gas source, flow path and reservoir genesis; S4: Obtaining the pressure changes of the wellbore and the formation during the fracturing process of the target shale gas well, and determining the distribution of the fracture network of the reservoir physical model after hydraulic fracturing according to the pressure changes; S5: Obtain changes in pressure, temperature and output during the production process of the target shale gas well, and update the reservoir physical model according to the changes; S6: Integrate the data of steps S1-S5 to obtain a dynamic three-dimensional reservoir model, and establish a multiphase fluid flow model on the dynamic three-dimensional reservoir model. Use numerical simulation to solve the multiphase fluid flow model to predict the production of the target shale gas well.

2. The shale gas production prediction method based on isotope tracing method and multi-source data fusion according to claim 1 is characterized in that: In step S2, the isotopic composition includes carbon isotopes 13 C / 12 C. Hydrogen isotopes 2 H / 1 H and oxygen isotopes 18 O / 16 O.

3. The shale gas production prediction method based on isotope tracing method and multi-source data fusion according to claim 1 is characterized in that: In step S2, if it is during the hydraulic fracturing process, it also includes the step of introducing isotope tracers to monitor the diffusion of fluid and the formation of fracture networks.

4. The shale gas production prediction method based on isotope tracing and multi-source data fusion according to claim 1 is characterized in that: In step S6, the multiphase fluid flow model includes continuity equation, momentum equation, energy equation, state equation, interaction and relative permeability.

5. The shale gas production prediction method based on isotope tracing method and multi-source data fusion according to claim 4 is characterized in that: The continuity equation is: Where: φ is the porosity; ρ i is the density of the i-th phase fluid; S i is the saturation of the i-th phase; t is the time; ▽· is the divergence operator; V i is the velocity vector of the i-th phase; q i is the source and sink term of the i-th phase.

6. The shale gas production prediction method based on isotope tracing and multi-source data fusion according to claim 4 is characterized in that: The momentum equation is: Where: ▽P i is the pressure gradient of the i-th phase; μ i is the fluid viscosity; 2 V i is the Laplace operator of the velocity field; g is the gravitational acceleration vector.

7. The shale gas production prediction method based on isotope tracing and multi-source data fusion according to claim 4 is characterized in that: The energy equation is: Where: c p,i is the specific heat capacity of the i-th phase; T i is the temperature of the i-th phase; k i is the thermal conductivity of the i-th phase; ▽T i is the temperature gradient change per unit time; Q i is the source phase of the i-th phase.

8. The shale gas production prediction method based on isotope tracing and multi-source data fusion according to claim 4 is characterized in that: The gas state equation includes: Gas state equation: P=ρRT (4) Where: P is the pressure of the gas; ρ is the density of the gas; R is the gas constant; T is the temperature of the gas; Liquid state equation: r liq =ρ0(1-β(T liq -T0)) (5) Where: liq is the density of the liquid; ρ0 is the density of the liquid at the reference temperature T0; β is the volume expansion coefficient; T liq is the temperature of the liquid.

9. The shale gas production prediction method based on isotope tracing and multi-source data fusion according to claim 4, characterized in that: The interactions and relative permeability include relative permeability, capillary pressure, adsorption and desorption processes; The relative permeability is calculated by the following formula: Where: K r,gas and K r,liquid are the relative permeabilities of the gas phase and the liquid phase, respectively; S gas and S liquid are the saturation of gas phase and liquid phase respectively; S gas,min and S liquid,min are the minimum saturation of gas phase and liquid phase respectively; S gas,Sat and S liquid,Sat are the upper limits of saturation of gas phase and liquid phase respectively; k gas and k liquid are the absolute permeabilities of gas and liquid phases, respectively; k is the calibration factor; The capillary pressure is calculated by the following formula: Where: P c is the capillary pressure; σ is the surface tension of the liquid; θ is the contact angle between the liquid and the solid surface; r is the pore radius or the equivalent radius of curvature; The adsorption and desorption processes are calculated by the following formula: Where: q is the adsorption amount; q max is the maximum adsorption amount; b is the adsorption isotherm model constant, which indicates the adsorption strength of gas and solid; P is the gas pressure; θ′ is the desorption amount of gas; P0 is the initial desorption pressure of gas.

10. The shale gas production prediction method based on isotope tracing and multi-source data fusion according to any one of claims 1 to 9, characterized in that: The following steps are also included: S7: Change the parameters of the multiphase fluid flow model, conduct sensitivity analysis, evaluate the uncertainty of production prediction, and then use different reservoir models and production scenarios to conduct multiple simulation comparisons and select the prediction model with higher accuracy; S8: Use the prediction model with higher accuracy to predict the production of the target shale gas well.

Images