Reservoir prediction method and system based on multi-source information fusion

Abstract

The invention discloses a reservoir prediction method and system based on multi-source information fusion, and relates to the technical field of reservoir prediction. The method comprises the following steps: performing high-fidelity weak-keeping signal processing on seismic data in combination with seismic geological conditions of a target area; fine well-seismic calibration is carried out by utilizing information such as logging, earthquake and geology and combining domain knowledge; carrying out seismic facies identification by adopting a deep embedded self-organizing mapping network; performing multi-scale breaking joint detection by using the cepstrum analysis enhanced coherent ant body attributes; carrying out wave impedance and porosity inversion by adopting seismic waveform indication inversion; data-driven seismic line analysis, depth domain frequency dispersion analysis and seismic data deep learning are combined to carry out reservoir gas-bearing property detection; and predicting favorable reservoir distribution through results of adaptive weighted fusion seismic facies identification, breaking joint detection, wave impedance and porosity inversion and gas-bearing property detection. The method has the advantage that accurate and reliable prediction of the deep complex oil and gas reservoir can be realized by integrating multi-source, multi-dimensional and multi-attribute data.

Description

Technical Field

[0001] The present invention relates to the technical field of seismic data processing and reservoir prediction, and particularly relates to a reservoir prediction method and system based on multi-source information fusion. Background Art

[0002] The goal of reservoir prediction is to determine the spatial distribution of oil and gas reservoirs and the oil and gas reserves, which is one of the most important links in oil and gas exploration. With the continuous growth of the global demand for oil and gas resources and the continuous deepening of the degree of oil and gas exploration, the objects of oil and gas exploration are gradually changing from shallow layers to middle and deep layers or even deep layers, from single to complex, and from conventional to unconventional. Reservoir prediction has become an effective means to improve the accuracy of reservoir characterization in deep oil and gas reservoirs and reduce exploration risks.

[0003] Reservoir prediction is a comprehensive research work aimed at quantitatively characterizing the spatial distribution, physical property parameters and fluid distribution of underground reservoirs through the integrated analysis of multi-source and multi-scale data. In the current technical system, a single geophysical attribute or a phased independent analysis mode is usually adopted, which is difficult to meet the requirements of fine characterization of deep and complex oil and gas reservoirs. There is an urgent need to develop more effective reservoir prediction methods to achieve the collaborative characterization of reservoir spatial distribution, physical property parameters and fluid properties. Summary of the Invention

[0004] In view of the above deficiencies in the prior art, the present invention provides a reservoir prediction method and system based on multi-source information fusion to solve the problem of collaborative characterization of reservoir spatial distribution, physical property parameters and fluid properties, achieve stable and high-precision prediction of deep and complex reservoirs, and provide a reliable basis for the efficient exploration and development of deep and complex gas reservoirs.

[0005] To achieve the above object and reach the above technical effect, the present invention provides the following technical solutions.

[0006] According to one aspect of the present invention, there is provided a reservoir prediction method based on multi-source information fusion, including the following steps: (1) Obtain data such as logging, coring, seismic and geological data of the target area and perform data analysis and preprocessing; (2) Perform high-fidelity and weak-signal-preserving processing on the seismic data in combination with the seismic geological conditions of the target area to obtain high-fidelity, high-signal-to-noise ratio and high-resolution seismic data; (3) Use information such as logging, seismic and geological information and combine the knowledge in the field of geological geophysics to perform fine well-seismic calibration and accurately calibrate the target layer; (4) Use a depth-embedded self-organizing mapping network that can adaptively consider the change of formation thickness to perform seismic facies visualization analysis, and combine logging and coring data to determine the sedimentary facies types and distribution characteristics of the reservoir; (5) Perform cepstrum analysis on seismic data to enhance the seismic response characteristics of fractures, calculate coherence and ant body attributes by combining the gradient structure tensor algorithm, and conduct multi-scale fracture detection in combination with FMI imaging logging interpretation; (6) Use seismic waveform indicator inversion to obtain parameters closely related to rock porosity, such as density and wave impedance, convert to obtain porosity based on the statistical relationship of well data, and divide a relatively large range of favorable blocks in combination with rock physics analysis; (7) Extract seismic attribute characteristics sensitive to gas-bearing by using data-driven seismic texture analysis, depth-domain dispersion analysis, deep learning of seismic data, etc., and detect the gas-bearing property of the reservoir by fusing the calculated attribute characteristics according to the proportion of the dominant part; (8) Predict the distribution of favorable reservoirs by adaptively weighted fusion of the results of seismic facies identification, multi-scale fault and fracture detection, wave impedance and porosity inversion, and gas-bearing property detection; (9) Analyze and evaluate the distribution results of favorable reservoirs predicted by multi-source, multi-dimensional and multi-attribute data fusion according to the logging interpretation of the drilled wells in the target area, single-well gas testing and production data.

[0007] Preferably, the data preprocessing in step (1) may include outlier rejection, environmental correction, multi-well consistency correction, etc.

[0008] Preferably, the process of high-fidelity and weak-signal protection processing of seismic data in step (2) may include static correction processing combining tomography static correction and reflection wave residual static correction, wide-band high-fidelity and weak-signal noise suppression processing, pre-stack high-fidelity amplitude compensation and high-resolution processing, etc., and the purpose of weak-signal protection is considered in each step.

[0009] Preferably, the fine well-seismic calibration in step (3) is based on the conventional well-seismic calibration process, and uses prior geological information and knowledge in the field of geological geophysics for constraint to obtain results more in line with the actual geological conditions of the target area, and accurately establish the connection between geological, logging and other information in the depth domain and seismic geophysical information in the time domain.

[0010] Preferably, the depth-embedded self-organizing map network in step (4) is a seismic facies visualization analysis method that simultaneously completes the self-encoding feature extraction process and self-organizing map feature clustering, and improves the stability of the seismic facies classification result by adding sparse constraints, so that the visualization result shows more details.

[0011] Preferably, the cepstrum analysis in step (5) is to perform spectral analysis on the seismic signal, take the logarithm of the spectrum to obtain cepstrum coefficients, and then approximately quantitatively characterize features such as the low-frequency enhancement effect of seismic in-phase axes, and enhance the seismic signal of small fractures.

[0012] Preferably, the seismic waveform indication inversion described in step (6) uses the lateral variation of seismic waveforms to replace the variogram spatial domain interpolation simulation, realizes the inversion under the automatic control of seismic facies, and can overcome the subjectivity caused by the need to artificially give sedimentary facies in advance in traditional phase-controlled inversion. It is a real phase-controlled inversion.

[0013] Preferably, the seismic texture analysis described in step (7) is a seismic data analysis and seismic geological information extraction method that develops from speech feature extraction methods to identify reservoir pore fluid characteristics from seismic signals, and can extract weak seismic response characteristics of reservoir pore fluids.

[0014] Preferably, the dispersion analysis in the depth domain described in step (7) refers to performing seismic dispersion analysis in the depth domain rather than the time domain. The depth domain can better reflect the actual position and content change of gas-bearing properties, including: establishing a high-precision velocity model for the target area, converting the time-domain seismic data from the time domain to the depth domain according to the velocity model, and completing the extraction of seismic dispersion attenuation attributes in the depth domain.

[0015] Preferably, the deep learning of seismic data described in step (7) uses the non-linear representation ability and knowledge discovery ability of deep neural networks to mine and utilize weak and insignificant seismic geological information hidden in seismic data.

[0016] Preferably, the purpose of the adaptive weighted fusion described in step (8) is to unify the obtained multi-source, multi-dimensional, and multi-attribute data fusion to achieve comprehensive prediction of favorable reservoirs.

[0017] According to another aspect of the present invention, there is provided a reservoir prediction system based on multi-source information fusion. The system includes a processor and a memory. The memory stores a computer program that can run on the processor. When the processor executes the computer program, it implements a reservoir prediction method based on multi-source information fusion. The system includes: A data acquisition module for acquiring data such as logging, coring, seismic, and geological data, and performing data analysis and preprocessing; A high-fidelity and weak-signal preservation processing module for performing high-fidelity and weak-signal processing on seismic data according to the seismic geological conditions of the target area; A well-seismic fine calibration module for performing fine well-seismic calibration according to information such as logging, seismic, and geological data and combining domain knowledge; A seismic facies analysis module for performing seismic facies visualization analysis of depth-embedded self-organizing mapping on seismic data, and determining the sedimentary facies types and distribution characteristics of reservoirs in combination with logging and coring data; The fracture detection module is used to perform cepstrum analysis on seismic data to enhance the seismic response characteristics of fractures, calculate coherence and ant body attributes by combining the gradient structure tensor algorithm, and perform multi-scale fracture detection by combining FMI imaging logging interpretation; The porosity inversion module is used to perform seismic waveform indication inversion on seismic data to obtain parameters closely related to rock porosity such as density and wave impedance, convert to obtain porosity based on the statistical relationship of well data, and divide a relatively large range of favorable blocks by combining rock physics analysis; The gas-bearing property detection module is used to perform data-driven seismic texture analysis, depth-domain dispersion analysis, deep learning of seismic data, etc. on seismic data to extract seismic attribute characteristics sensitive to gas-bearing, and detect the gas-bearing property of the reservoir by fusing the calculated attribute characteristics according to the proportion of the dominant part; The reservoir comprehensive prediction module is used to adaptively and weightedly fuse the results of seismic facies identification, multi-scale fault and fracture detection, wave impedance and porosity inversion, and gas-bearing property detection to predict the distribution of favorable reservoirs; The prediction result evaluation module is used to analyze and evaluate the favorable reservoir distribution results obtained by multi-source, multi-dimensional and multi-attribute data fusion prediction according to the logging interpretation of the drilled wells in the target area and the single-well gas testing and production data.

[0018] Compared with the prior art, the beneficial effects of the present invention are as follows: Based on high-fidelity and weak-signal processing of seismic data and fine well-seismic calibration, the present invention organically combines seismic facies visualization analysis that can adaptively consider the change of formation thickness, multi-scale fracture detection of coherence and ant body attributes enhanced by cepstrum analysis, wave impedance and porosity inversion by seismic waveform indication inversion, and multi-dimensional reservoir gas-bearing property detection combining seismic texture analysis, depth-domain dispersion analysis, and deep learning of seismic data, forming a reservoir prediction method of "phase determining zone - porosity determining reservoir - gas determining reservoir", which can overcome the limitation of the current technical system that usually uses a single geophysical attribute or a phased independent analysis mode for reservoir prediction, realize the collaborative characterization of the spatial distribution of the reservoir, physical property parameters and fluid properties, and provide a reliable basis for guiding the subsequent development of the reservoir. Description of the Drawings

[0019] Figure 1 It is a flowchart of a reservoir prediction method based on multi-source information fusion provided by an embodiment of the present application; Figure 2 It is a structural schematic diagram of a reservoir prediction system based on multi-source information fusion provided by an embodiment of the present application; Figure 3 It is a prediction result map of the distribution of favorable reservoirs in a certain target area provided by an embodiment of the present application. Detailed Embodiments

[0020] To enable those skilled in the art to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of this specification. Obviously, the described embodiments are only a part of the embodiments of the specification, rather than all the embodiments.

[0021] An embodiment of the present invention provides a reservoir prediction method based on multi-source information fusion. As Figure 1 shown, in some embodiments, the method includes the following steps: Step 101, obtain data materials including logging, coring, seismic, and geological data of the target area and perform data analysis and preprocessing; It should be noted that in some embodiments, the data preprocessing in Step 101 may include outlier removal, environmental correction, multi-well consistency correction, etc.

[0022] Step 102, perform high-fidelity and weak-signal-preserving processing on the seismic data in combination with the seismic geological conditions of the target area to obtain high-fidelity, high-signal-to-noise ratio, and high-resolution seismic data; It should be noted that in some embodiments, the process of high-fidelity and weak-signal-preserving processing of the seismic data in Step 102 may include steps such as static correction processing combining tomography static correction and reflection wave residual static correction, wide-band high-fidelity and weak-signal-preserving signal noise suppression processing, pre-stack high-fidelity amplitude compensation, and high-resolution processing. The purpose of weak-signal protection is considered in each step.

[0023] Step 103, use information such as logging, seismic, and geological data and combine geological and geophysical knowledge to perform fine well-seismic calibration and accurately calibrate the target layer; It should be noted that in some embodiments, the fine well-seismic calibration in Step 103 is based on the conventional well-seismic calibration process, and prior geological information and geological and geophysical knowledge are used for constraint to obtain results that are more in line with the actual geological conditions of the target area, and accurately establish the connection between geological, logging, etc. information in the depth domain and seismic and geophysical information in the time domain.

[0024] Step 104, perform seismic facies visualization analysis using a depth-embedded self-organizing mapping network that can adaptively consider the change in formation thickness, and combine mud logging and coring data to determine the sedimentary facies type and distribution characteristics of the reservoir; It should be noted that in some embodiments, the depth-embedded self-organizing mapping network in Step 104 is a seismic facies visualization analysis method that simultaneously completes the self-encoding feature extraction process and self-organizing mapping feature clustering, and improves the stability of the seismic facies classification result by adding sparse constraints, so that more details are shown in the visualization result.

[0025] Step 105: Perform cepstrum analysis on seismic data to enhance the seismic response characteristics of fractures, calculate coherence and ant body attributes by combining the gradient structure tensor algorithm, and conduct multi-scale fracture detection in combination with FMI imaging logging interpretation; It should be noted that in some embodiments, the cepstrum analysis described in Step 105 is to perform spectral analysis on seismic signals, take the logarithm of the spectrum to obtain cepstrum coefficients, and then approximately quantitatively characterize features such as the low-frequency enhancement effect of seismic event axes, enhancing the seismic signals of small fractures.

[0026] Step 106: Use seismic waveform indicator inversion to obtain parameters closely related to rock porosity, such as density and wave impedance, convert to obtain porosity based on the statistical relationship of well data, and divide a relatively large favorable block in combination with rock physics analysis; It should be noted that in some embodiments, the seismic waveform indicator inversion described in Step 106 uses the lateral variation of seismic waveforms to replace the variogram spatial domain interpolation simulation, realizing inversion under the automatic control of seismic facies, and can overcome the subjectivity caused by the need to artificially give sedimentary facies in advance in traditional phase-controlled inversion, which is a true phase-controlled inversion.

[0027] Step 107: Extract gas-bearing sensitive seismic attribute features by using data-driven seismic texture analysis, depth-domain dispersion analysis, deep learning of seismic data, etc., and conduct reservoir gas-bearing detection by fusing the calculated attribute features according to the proportion of the dominant part; It should be noted that in some embodiments, the seismic texture analysis described in Step 107 is a seismic data analysis and seismic geological information extraction method that develops from speech feature extraction methods to identify reservoir pore fluid features from seismic signals, and can extract weak seismic response features of reservoir pore fluids.

[0028] It should be noted that in some embodiments, the depth-domain dispersion analysis described in Step 107 refers to conducting seismic dispersion analysis in the depth domain rather than the time domain. The depth domain can better reflect the actual location and content change of gas-bearing properties, including: establishing a high-precision velocity model for the target area, converting time-domain seismic data from the time domain to the depth domain according to the velocity model, and completing the extraction of seismic dispersion attenuation attributes in the depth domain.

[0029] It should be noted that in some embodiments, the deep learning of seismic data described in Step 107 uses the nonlinear representation ability and knowledge discovery ability of deep neural networks to mine and utilize weak and insignificant seismic geological information hidden in seismic data.

[0030] Step 108: Predict the distribution of favorable reservoirs by adaptively weighted fusion of the results of seismic facies identification, multi-scale fracture and fault detection, wave impedance and porosity inversion, and gas-bearing detection; It should be noted that in some embodiments, the purpose of the adaptive weighted fusion described in step 108 is to unify the obtained multi-source, multi-dimensional, and multi-attribute data to achieve comprehensive prediction of favorable reservoirs.

[0031] Step 109: Analyze and evaluate the distribution results of favorable reservoirs obtained by fusing and predicting multi-source, multi-dimensional, and multi-attribute data based on the well logging interpretation, single-well gas testing, and production data of the drilled wells in the target area.

[0032] Corresponding to the above reservoir prediction method based on multi-source information fusion, an embodiment of the present invention provides a reservoir prediction system based on multi-source information fusion, as Figure 2 shown. In some embodiments, the prediction system includes a processor and a memory. The memory stores a computer program that can run on the processor. When the processor executes the computer program, it implements the above reservoir prediction method based on multi-source information fusion. The system includes: A data acquisition module 201, configured to acquire data such as well logging, coring, seismic, and geological data, and perform data analysis and preprocessing; A fidelity and attenuation preservation processing module 202, configured to perform high-fidelity and attenuation preservation signal processing on seismic data according to the seismic geological conditions of the target area; A well-seismic fine calibration module 203, configured to perform fine well-seismic calibration according to well logging, seismic, and geological information and combined with domain knowledge; A seismic facies analysis module 204, configured to perform visual analysis of seismic facies of depth-embedded self-organizing mapping on seismic data, and determine the sedimentary facies types and distribution characteristics of reservoirs in combination with logging and coring data; A fracture detection module 205, configured to perform cepstrum analysis on seismic data to enhance the seismic response characteristics of fractures, calculate coherence and ant body attributes in combination with the gradient structure tensor algorithm, and perform multi-scale fracture detection in combination with FMI imaging well logging interpretation; A porosity inversion module 206, configured to perform seismic waveform indication inversion on seismic data to obtain parameters such as density and wave impedance that are closely related to rock porosity, convert to obtain porosity based on the statistical relationship of well data, and divide a relatively large range of favorable blocks in combination with rock physics analysis; A gas-bearing property detection module 207, configured to perform data-driven seismic texture analysis, depth-domain dispersion analysis, deep learning of seismic data, etc. on seismic data to extract gas-bearing sensitive seismic attribute characteristics, and perform reservoir gas-bearing property detection by fusing the calculated attribute characteristics according to the proportion of the dominant part; A reservoir comprehensive prediction module 208, configured to perform favorable reservoir distribution prediction by adaptively weighted fusion of the results of seismic facies identification, multi-scale fracture detection, wave impedance and porosity inversion, and gas-bearing property detection; The prediction result evaluation module 209 is used to analyze and evaluate the favorable reservoir distribution result obtained by multi-source multi-dimensional multi-attribute data fusion according to the logging interpretation of the drilled wells in the target area and the single-well gas test and production data.

[0033] Figure 3 It is the favorable reservoir distribution prediction result of a certain target area obtained by using this technology. It can be seen from the figure that the prediction result conforms to the geological law of the target area, can reflect the distribution of favorable reservoirs, and is basically consistent with the actual drilling results of the later drilling well positions that were not used for calculation. Overall, it has high accuracy and credibility.

[0034] Those skilled in the art should understand that the above embodiments are only used to exemplarily illustrate the beneficial effects of the present invention and are not exhaustive. Any modifications, equivalent changes, improvements, etc. made without departing from the scope and spirit of the illustrated embodiments should not be excluded from the protection scope of the present invention.

Claims

1. A reservoir prediction method based on multi-source information fusion, characterized in that, It includes the following steps: (1) Obtain data such as logging, coring, seismic, and geological data in the target area, and perform data analysis and preprocessing; (2) Combine the seismic and geological conditions of the target area to perform high-fidelity and weak-signal processing on the seismic data to obtain high-fidelity, high-signal-to-noise ratio, and high-resolution seismic data; (3) Use information such as logging, seismic, and geological data, and combine the knowledge in the field of geological geophysics to perform fine well-seismic calibration to accurately calibrate the target layer; (4) Use a depth-embedded self-organizing mapping network that can adaptively consider the change in formation thickness for seismic facies visualization analysis, and combine logging and coring data to determine the sedimentary facies types and distribution characteristics of the reservoir; (5) Perform cepstrum analysis on the seismic data to enhance the seismic response characteristics of fractures, calculate coherence and ant body attributes in combination with the gradient structure tensor algorithm, and perform multi-scale fracture detection in combination with FMI imaging logging interpretation; (6) Use seismic waveform indication inversion to obtain parameters such as density and wave impedance that are closely related to rock porosity, convert to obtain porosity based on the statistical relationship of well data, and divide a relatively large range of favorable blocks in combination with rock physics analysis; (7) Use data-driven seismic texture analysis, depth-domain dispersion analysis, deep learning of seismic data, etc. to extract gas-sensitive seismic attribute characteristics, and fuse the calculated attribute characteristics according to the proportion of the dominant part to detect the gas-bearing property of the reservoir; (8) Predict the distribution of favorable reservoirs by adaptively weighted fusion of the results of seismic facies identification, multi-scale fault and fracture detection, wave impedance and porosity inversion, and gas-bearing property detection; (9) Analyze and evaluate the distribution results of favorable reservoirs obtained by multi-source, multi-dimensional, and multi-attribute data fusion prediction based on the logging interpretation of the drilled wells in the target area, single-well gas testing, and production data.

2. The reservoir prediction method based on multi-source information fusion according to claim 1, wherein: The process of high-fidelity and weak-signal processing of the seismic data described in step (2) may include steps such as static correction processing combining tomography static correction and reflection wave residual static correction, wide-band high-fidelity and weak-signal noise suppression processing, pre-stack high-fidelity amplitude compensation, and high-resolution processing, and the purpose of weak-signal protection is considered in each step.

3. A reservoir prediction method based on multi-source information fusion according to claim 1, characterized in that: The fine well-seismic calibration described in step (3) is based on the conventional well-seismic calibration process, and uses prior geological information and knowledge in the field of geological geophysics for constraint to obtain results that are more in line with the actual geological conditions of the target area, and accurately establish the connection between geological, logging, etc. information in the depth domain and seismic geophysical information in the time domain.

4. A reservoir prediction method based on multi-source information fusion according to claim 1, characterized in that: The depth-embedded self-organizing mapping network described in step (4) is a seismic facies visualization analysis method that simultaneously completes the self-encoding feature extraction process and self-organizing mapping feature clustering, and improves the stability of the seismic facies classification results by adding sparse constraints, so that more details are shown in the visualization results.

5. A reservoir prediction method based on multi-source information fusion according to claim 1, characterized in that: The cepstrum analysis described in step (5) is to perform spectral analysis on the seismic signal, take the logarithm of the spectrum to obtain cepstrum coefficients, and then approximately quantitatively characterize features such as the low-frequency enhancement effect of seismic event axes, enhancing the seismic signal of small fractures.

6. A reservoir prediction method based on multi-source information fusion according to claim 1, characterized in that: The seismic texture analysis described in step (7) is a seismic data analysis and seismic geological information extraction method for identifying reservoir pore fluid characteristics from seismic signals, developed by drawing on speech feature extraction methods, and can extract weak seismic response characteristics of reservoir pore fluids.

7. A reservoir prediction method based on multi-source information fusion according to claim 1, characterized in that: The dispersion analysis in the depth domain described in step (7) refers to performing seismic dispersion analysis in the depth domain rather than the time domain. The depth domain can better reflect the actual location and content changes of gas-bearing properties, including: establishing a high-precision velocity model for the target area, converting time-domain seismic data from the time domain to the depth domain according to the velocity model, and completing the extraction of seismic dispersion attributes in the depth domain.

8. A reservoir prediction system based on multi-source information fusion, characterized in that, The system includes a processor and a memory. The memory stores a computer program that can run on the processor. When the processor executes the computer program, the following steps are implemented: Data acquisition, which is used to acquire data such as logging, coring, seismic, and geological data, and perform data analysis and preprocessing; High-fidelity and weak-signal preservation processing, which is used to perform high-fidelity and weak-signal processing on seismic data according to the seismic geological conditions of the target area; Fine well-seismic calibration, which is used to perform fine well-seismic calibration based on information such as logging, seismic, and geological data and combined with domain knowledge; Seismic facies analysis, which is used to perform seismic facies visualization analysis of depth-embedded self-organizing mapping on seismic data, and determine the sedimentary facies types and distribution characteristics of reservoirs in combination with logging and coring data; Fracture detection, which is used to enhance the seismic response characteristics of fractures by performing cepstrum analysis on seismic data, calculate coherence and ant body attributes in combination with the gradient structure tensor algorithm, and perform multi-scale fracture detection in combination with FMI imaging logging interpretation; Porosity inversion, which is used to perform seismic waveform indication inversion on seismic data to obtain parameters closely related to rock porosity, such as density and wave impedance, convert to obtain porosity according to the statistical relationship of well data, and divide a relatively large range of favorable blocks in combination with rock physics analysis; Gas-bearing property detection, which is used to extract gas-sensitive seismic attribute characteristics from seismic data through data-driven seismic texture analysis, depth-domain dispersion analysis, deep learning of seismic data, etc., and perform reservoir gas-bearing property detection by fusing the calculated attribute characteristics according to the proportion of the dominant part; Reservoir comprehensive prediction, which is used to adaptively and weightedly fuse the results of seismic facies identification, multi-scale fault and fracture detection, wave impedance and porosity inversion, and gas-bearing property detection to predict the distribution of favorable reservoirs; Prediction result evaluation, which is used to analyze and evaluate the favorable reservoir distribution results obtained by multi-source, multi-dimensional, and multi-attribute data fusion prediction based on the logging interpretation of drilled wells and single-well gas testing and production data in the target area.

Images