Well-earthquake quantitative description method for delta estuary dam side edge microfacies boundary

Abstract

The invention discloses a delta estuary dam side edge microfacies boundary well-seismic quantitative description method. The method comprises the steps that the geological background, core data, drilling data and seismic data of a target work area are acquired; a high-frequency sequence stratigraphic framework is established, and tracking interpretation of a seismic horizon is completed; the sedimentary microfacies are identified and divided; carrying out resolution analysis and phase conversion on the seismic data volume; through well-seismic calibration, determining seismic response characteristics of the stratum sand body of the target work area, and extracting seismic attributes corresponding to the conventional data body, the-90-degree phase data body and the high-frequency-90-degree phase conversion data body; identifying and explaining a plane sedimentary subphase boundary; the extracted seismic attributes are optimized; predicting the thickness of the sand body through various artificial intelligence algorithms to obtain an artificial intelligence sand body thickness map; and completing the sedimentary microfacies fine description of the delta outer leading edge estuary dam area according to the artificial intelligence sand body thickness map. According to the method, the microfacies boundary of the delta outer leading edge estuary dam area can be depicted finely.

Description

Technical Field

[0001] This invention relates to a well-seismic quantitative characterization method for microfacies boundary on the side of delta estuary dams, belonging to the field of petroleum exploration and development technology. Background Technology

[0002] With prolonged oil and gas exploration in sparsely populated offshore oilfields, identifying effective structural traps of commercial scale is becoming increasingly difficult, making the shift from structural traps to lithological traps inevitable. However, the large well spacing, lower seismic data quality, multiple superimposed large braided channels, and small impedance differences between sandstone and mudstone make it difficult to characterize sedimentary microfacies to meet the needs of lithological trap exploration. Therefore, accurate identification and detailed characterization of deltaic sedimentary microfacies are crucial for achieving lithological trap exploration in sparsely populated offshore areas.

[0003] Currently, the characterization of deltaic sedimentary microfacies often relies on qualitative analysis of sedimentary microfacies using core, well logging, and lithological data. Guided by sedimentary models and considering the distribution patterns of single-well and multi-well sedimentary microfacies, the lateral boundaries of each sedimentary microfacies are determined. However, this method heavily depends on the interpretation and experience of geologists, easily leading to multiple interpretations. It often works well in areas with a certain number of dense well networks, but struggles to accurately characterize deltaic sediments in sparsely populated areas, resulting in limited practicality.

[0004] With the continuous development and improvement of 3D seismic technology, high-precision seismic data can provide more sufficient evidence for the identification and prediction of sand bodies. Seismic attributes are specific parameter values ​​related to seismic wave geometry, dynamics, kinematics, and statistics. Seismic attribute analysis technology is now widely used in oilfield exploration and production. However, the analysis and processing of seismic attributes are still in the stage of qualitative analysis of single attributes. Seismic attributes are often a comprehensive response to multiple complex geological factors, and single attributes have strong ambiguity, which greatly increases the difficulty of fine characterizing sedimentary microfacies and seriously restricts the fine characterization of deltaic sedimentary microfacies.

[0005] In coastal sedimentary settings influenced by multiple hydrodynamic forces, the outer delta front estuary bars and distal sandbars, being relatively isolated sand bodies modified by hydrodynamic forces, are prone to the development of lithological traps. Conversely, the frequent migration and diversion of underwater distributary channels within the delta front makes it difficult to form lithological lateral boundaries, and tectonic traps are typically developed instead. Therefore, accurately characterizing the microfacies boundaries of the outer delta front estuary bar region is an urgent need in the search for lithological traps. Summary of the Invention

[0006] The purpose of this invention is to address the problems existing in the prior art by providing a well-seismic quantitative characterization method for the microfacies boundary of delta estuary dam sidewalls.

[0007] The technical solution provided by this invention to solve the above-mentioned technical problems is: a well-seismic quantitative characterization method for microfacies boundaries on the side margins of deltaic estuary bar, comprising the following steps:

[0008] Step S10: Obtain the geological background, core data, drilling data, and seismic data of the target work area;

[0009] Step S20: Establish a high-frequency sequence stratigraphic framework and complete the seismic horizon tracking and interpretation;

[0010] Step S30: Identify and classify the sedimentary microfacies;

[0011] Step S40: Perform resolution analysis and phase transformation on the seismic data volume;

[0012] Step S50: Through well-seismic calibration, determine the seismic response characteristics of the sand bodies in the target work area, and extract the corresponding seismic attributes of the conventional data volume, the -90° phase data volume, and the high-frequency -90° phase conversion data volume;

[0013] Step S60: Identification and interpretation of planar sedimentary subfacies boundaries;

[0014] Step S70: Optimize the extracted seismic attributes;

[0015] Step S80: Predict the sand body thickness using multiple artificial intelligence algorithms to obtain an artificial intelligence sand body thickness map;

[0016] Step S90: Based on the artificial intelligence sand body thickness map, complete the fine characterization of sedimentary microfacies in the delta front estuary bar area.

[0017] A further technical solution is that the specific process of step S20 is as follows:

[0018] Step S21: Based on the relevant theories of sequence stratigraphy and the rock electrical characteristics and sedimentary cycle characteristics of drilling data, establish a high-frequency sequence division scheme and carry out sequence division and comparison of single wells and interconnected wells.

[0019] Step S22: Based on the well sequence stratigraphic results, the seismic horizons are marked and interpreted, and finally a high-frequency sequence stratigraphic framework for the entire region is established.

[0020] A further technical solution is that the specific process of step S30 is as follows:

[0021] Step S31: Based on the core data of the target work area, identify the lithology, sedimentary structures and sediment grain size, and establish a sedimentary microfacies division scheme for the target work area;

[0022] Step S32: Based on sedimentary characteristics such as core samples and well logging, establish a rock-electrodeposition microfacies transition chart;

[0023] Step S33: Based on the rock-electrodeposition microfacies transformation chart, conduct single-well and interconnected-well interpretation and comparison of microfacies.

[0024] A further technical solution is that the specific process of step S40 is as follows:

[0025] Step S41: Perform spectral analysis on the target layer to obtain the dominant frequency and seismic wave propagation velocity of the seismic data volume;

[0026] Step S42: Calculate the vertical resolution of the earthquake based on the dominant frequency and seismic wave propagation velocity of the earthquake data volume;

[0027] Step S43: Statistically analyze the thickness of the target layer sand body;

[0028] Step S44: Compare the target layer sand body thickness with the seismic vertical resolution. If the thickness of a single sand body is less than the seismic vertical resolution and 1 / 8 of the wavelength λ, then perform a -90° phase transformation on the original data volume.

[0029] If the thickness of a single sand layer is less than 1 / 8 of the wavelength λ, the relatively high-frequency part of the conventional data volume is extracted and a -90° phase conversion is performed.

[0030] A further technical solution is that the specific process of step S60 is as follows:

[0031] Step S61: Based on the distribution characteristics of the well-connected facies and the sand-soil ratio of the drilled wells in the skeleton profile, the planar sedimentary subfacies boundary is preliminarily determined;

[0032] Step S62: Based on the well seismic calibration results, select conventional seismic attributes to further clarify the subfacies boundaries.

[0033] A further technical solution is that the specific process of step S70 is as follows:

[0034] Step S71: Using the Pearson correlation analysis method, analyze the correlation between the sand body thickness of all well points and the seismic attributes of the well points extracted from each data volume, and select the 6 seismic attributes with the highest correlation from each data volume.

[0035] Step S72: Using the Pearson correlation analysis method, select some well points on the outer edge of the delta using phase control, analyze the correlation between the thickness of the drilled sand body and the seismic attributes of the well points extracted from each data volume, and select the 6 seismic attributes with the highest correlation from each data volume.

[0036] A further technical solution is that the specific process of step S80 is as follows:

[0037] Step S81: Use random forest, support vector machine, augmented regression tree and artificial neural network to fuse the six selected attributes;

[0038] Step S82: Establish a comparison of the accuracy of the prediction models, compare the fusion effects of the four methods, select the algorithm with the best fusion effect for artificial intelligence sand body prediction, and obtain the artificial intelligence sand body thickness map.

[0039] A further technical solution is that the specific process of step S90 is as follows:

[0040] Step S91: Based on the calibration of the single-well logging facies interpretation results, and combined with the artificial intelligence sand body thickness map, the sedimentary microfacies are finely characterized;

[0041] Step S92: Combine the oil and water data from the development wells to verify the sedimentary microfacies map, clarify the lateral microfacies boundaries of the delta mouth bar area, and finally obtain the sedimentary microfacies map.

[0042] The beneficial effects of the present invention are that it can precisely characterize the microfacies boundary of the delta front estuary bar region. Attached Figure Description

[0043] Figure 1 This is a flowchart of the present invention;

[0044] Figure 2 This is a logging facies-sedimentary microfacies transition chart;

[0045] Figure 3 The thickness of the sand body above the well is calculated for each well section;

[0046] Figure 4 The results of the seismic data spectrum analysis;

[0047] Figure 5 This is the minimum amplitude diagram;

[0048] Figure 6 Pearson correlation results (all wells);

[0049] Figure 7 This is a map showing the sedimentary facies zones.

[0050] Figure 8 The results show the Pearson correlation (phase control point selection).

[0051] Figure 9 For artificial intelligence to predict sand body thickness maps;

[0052] Figure 10 Comparison chart showing the accuracy of artificial intelligence prediction of sand body thickness;

[0053] Figure 11 This is a detailed sedimentary microfacies map of the estuarine bar side margin area. Detailed Implementation

[0054] The technical solution of the present invention will now be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0055] like Figure 1 As shown, the present invention provides a well-seismic quantitative characterization method for microfacies boundaries on the side of delta estuary bar, comprising the following steps:

[0056] Step S10: Obtain the geological background, core data, drilling data, and seismic data of the target work area;

[0057] Step S20: Establish a high-frequency sequence stratigraphic framework and complete the seismic horizon tracking and interpretation;

[0058] Step S21: Based on the relevant theories of sequence stratigraphy and the rock electrical characteristics and sedimentary cycle characteristics of drilling data, establish a high-frequency sequence division scheme and carry out sequence division and comparison of single wells and interconnected wells.

[0059] In this embodiment, previous researchers have established a three-level sequence stratigraphic framework for the target area based on typical earthquake termination relationships and paleontological data, but its accuracy is no longer sufficient for the exploration of lithological traps. The study area has long been situated in a mid-shelf context characterized by high sediment supply rates, frequent sea-level fluctuations, and relatively flat sedimentary topography. Frequent delta advances and retreats have resulted in a lithological assemblage of relatively isolated sandstone and prodeltaic mudstone interbedded on the outer delta front in the horizontal plane, and interbedded sand and mudstone vertically, which is conducive to the formation of lithological traps.

[0060] With frequent rises and falls in sea level, different levels of flooding surfaces are formed. In this embodiment, a high-frequency sequence stratigraphic framework is established using multi-level flooding surfaces. Flooding interfaces are easily identifiable and interpretable in drilling and seismic data. In drilling, they typically appear as a relatively thick mudstone layer, with GR curves showing high values ​​greater than 120 API, and opposite depositional cycles above and below the interface. In seismic data, they appear as strong, continuous wave peaks with locally identifiable subsurface points on the interface.

[0061] In this embodiment, multiple fourth-order and fifth-order floodplains are identified within a third-order sequence, a single-well composite columnar section is completed, a well-connected framework profile is constructed, high-frequency sequence division and comparison are completed on the well-connected sections, and a high-frequency sequence stratigraphic framework is established.

[0062] Step S22: Based on the well sequence stratigraphic results, the seismic horizons are marked and interpreted, and finally a high-frequency sequence stratigraphic framework for the entire region is established;

[0063] Based on the well-ground division results, a synthetic seismic record is produced, and well-seismic calibration is performed on the seismic horizons. At the same time, the seismic facies changes and typical termination relationships at the interfaces can also be used as identification markers for sequence boundaries and transgression boundaries.

[0064] Sequence boundaries often exhibit seismic response characteristics of medium amplitude and poor continuity. Sandstone is developed above and below the boundary, with the lithology mainly being medium to fine sandstone. The sandstone content is higher below the boundary and lower above it. In contrast, marine transgressive boundaries often correspond to a stable set of mudstone of varying thickness. The seismic phase axes at the boundary generally show medium to strong amplitude and good continuity, with an under-contact relationship visible above the boundary. Seismic horizons are interpreted on the seismic framework profile, and then the horizons are interpreted and traced throughout the region, ultimately establishing a high-frequency sequence stratigraphic framework for the entire region.

[0065] Step S30: Identify and classify the sedimentary microfacies;

[0066] Step S31: Based on the core data of the target work area, identify the lithology, sedimentary structures and sediment grain size, and establish a sedimentary microfacies division scheme for the target work area;

[0067] Deltas are influenced by various forces—rivers, waves, and tides—resulting in complex sedimentary systems. Since the development of the delta in the target study area is significantly affected by sea-level changes, during periods of sea-level decline, river activity is pronounced, with tributary channels extending continuously over long distances into the sea. During periods of sea-level rise, early-formed tributary channels and estuary bars are hydrodynamically modified, resulting in altered sand bodies distributed discontinuously in a southwest-trending pattern.

[0068] Therefore, the delta front is subdivided into the inner delta front and the outer delta front. The inner delta front mainly develops continuously distributed underwater distributary channels, inter-distributary bays, and mouth bars, while the outer delta front mainly develops discontinuous mouth bars, distal bars, distal bar flanks, and sheet sands.

[0069] Step S32: Based on sedimentary characteristics such as core samples and well logging, establish a rock-electrodeposition microfacies transition chart;

[0070] Four subfacies and seven main sedimentary microfacies were identified, including the inner delta front (mainly underwater distributary channels), the outer delta front (mouth bars, distal bars and distal bar flanks), the prodelta (sheet sands and prodelta mud), and the shallow marine shelf (shelf sand ridges and shallow marine mud). A corresponding core facies-logging facies-sedimentary microfacies transformation chart was also established.

[0071] Step S33: Based on the rock-electrodeposition microfacies transition chart, conduct single-well and interconnected-well interpretation and comparison of microfacies.

[0072] Step S40: Perform resolution analysis and phase transformation on the seismic data volume;

[0073] Step S41: Perform spectral analysis on the target layer to obtain the dominant frequency and seismic wave propagation velocity of the seismic data volume;

[0074] To clarify the fundamental frequency band information of the seismic data volume, the dominant frequency of the seismic data volume was determined to be approximately 35 Hz, with a frequency band range of 12 Hz to 56 Hz.

[0075] Step S42: Calculate the vertical resolution of the earthquake based on the dominant frequency f and the propagation velocity v of the earthquake data volume; where the vertical resolution is λ / 4, and the wavelength λ = v / f;

[0076] In this embodiment, the dominant frequency of the seismic data is approximately 35 Hz, the propagation velocity of the seismic wave at the target layer is approximately 3600 m / s, and the vertical resolution of the seismic data is approximately 26 m.

[0077] Step S43: Statistically analyze the thickness of the target layer sand body;

[0078] The thickness of the target layer sand body was statistically analyzed. The results showed that the sand body thickness in the X1 well area was relatively thick, about 10-12m, while the sand body thickness in the X2 and X3 well areas was relatively thin, about 4-10m, with most being 6-9m. In the H1 well area, the sand body thickness varied greatly, ranging from 0-10m, and the lithology was mainly fine siltstone.

[0079] Step S44: Compare the target layer sand body thickness with the seismic vertical resolution. If the thickness of a single sand body is less than the seismic vertical resolution and 1 / 8 of the wavelength λ, then perform a -90° phase transformation on the original data volume.

[0080] If the thickness of a single sand layer is less than 1 / 8 of the wavelength λ, the relatively high-frequency part of the conventional data volume is extracted and a -90° phase conversion is performed.

[0081] Step S50: Through well-seismic calibration, determine the seismic response characteristics of the sand bodies in the target work area, and extract various seismic attributes such as amplitude, waveform, frequency and statistical categories corresponding to the conventional data volume, -90° phase data volume and high-frequency -90° phase conversion data volume;

[0082] Based on the interpreted horizon of the target layer, 17 seismic attributes in 4 categories—amplitude, waveform, frequency, and statistics—are extracted from its conventional data volume, -90° phase data volume, and high-frequency -90° phase conversion data volume.

[0083] Step S60: Identification and interpretation of planar sedimentary subfacies boundaries;

[0084] Step S61: Based on the distribution characteristics of the well-connected facies and the sand-soil ratio of the drilled wells in the skeleton profile, the planar sedimentary subfacies boundary is preliminarily determined;

[0085] Based on the microfacies profiles of the skeletal wells along and across the source direction, the planar distribution characteristics of the sedimentary microfacies were preliminarily determined. In the embodiment, the underwater distributary channel at the inner delta front, extending to between wells X81 and X31, can be identified on the well-connected profiles along the source direction and the seismic profiles, while relatively isolated dams develop at the outer delta front at the far end.

[0086] Step S62: Based on the well seismic calibration results, select conventional seismic attributes to further clarify the subfacies boundaries;

[0087] In this embodiment, the troughs in the -90° phase data volume correspond to sandy deposits, while the peaks correspond to muddy deposits. Therefore, the minimum amplitude is selected to characterize it. Based on the well calibration, strong amplitude represents underwater distributary channel sand bodies, and weak amplitude represents muddy sand bodies. Therefore, the boundary between strong and weak amplitudes is selected as the subfacies boundary.

[0088] Step S70: Optimize the extracted seismic attributes;

[0089] Step S71: Using the Pearson correlation analysis method, analyze the correlation between the sand body thickness of all well points and the seismic attributes of the well points extracted from each data volume, and select the 6 seismic attributes with the highest correlation from each data volume.

[0090] Correlation analysis was performed on the 17 seismic attributes of each of the three extracted data volumes with the statistical sand body thickness of all drilled wells, and the six seismic attributes with the best correlation were selected.

[0091] Step S72: Using the Pearson correlation analysis method, select some well points in the outer edge of the delta using phase control, analyze the correlation between the thickness of the drilled sand body and the seismic attributes of the well points extracted from each data volume, and select the 6 seismic attributes with the highest correlation from each data volume.

[0092] Statistical analysis of sand body thickness revealed significant variations in thickness across the plane. Sand bodies were thicker at the deltaic front, while their thickness decreased markedly at the deltaic front mouth bar and its lateral edges. The sand bodies within the prodeltaic facies zone were even thinner, by approximately 2-6 meters. This substantial difference in sand body thickness across the plane can introduce significant errors into the correlation results.

[0093] Therefore, based on the drawn sedimentary pattern or sedimentary subfacies diagram, wells were screened by facies control constraints, and areas from the outer delta front to the development of isolated sandbars in the predelta region (i.e. key lithological trap exploration areas) were selected. 21 wells were selected from all 34 wells, and correlation analysis was performed with 17 seismic attributes extracted from each of the 3 data volumes. The 6 attributes with the best correlation were selected.

[0094] Step S80: Predict the sand body thickness using multiple artificial intelligence algorithms to obtain an artificial intelligence sand body thickness map;

[0095] Step S81: Use random forest, support vector machine, augmented regression tree and artificial neural network to fuse the six selected attributes;

[0096] Seismic attribute fusion, as the most effective and widely used multi-attribute analysis method, is extensively applied in oil and gas exploration and development. Machine learning algorithms can automatically learn the correlations and weights between seismic attributes, thus enabling more accurate fusion of multiple seismic attributes. This study selects four mainstream machine learning algorithms—Random Forest (RF), Support Vector Machine (SVM), Augmented Regression Tree (BRT), and Artificial Neural Network (ANN)—to fuse the optimal attributes.

[0097] Step S82: Establish a comparison of the accuracy of the prediction models, compare the fusion effects of the four methods, select the algorithm with the best fusion effect for artificial intelligence sand body prediction, and obtain the artificial intelligence sand body thickness map.

[0098] Based on various data volumes, four machine learning methods were used to fuse seismic attributes, and a comparison of the accuracy of prediction models was established to evaluate the fusion effects of the four methods. Among the four methods, BRT showed the best fusion effect, with the fused thickness exhibiting the highest correlation R between the actual wellpoint thickness and the actual thickness. 2 The maximum value can reach 0.89, and the sand body prediction results are relatively accurate. At the same time, the planar sand body morphology also conforms to sedimentological laws.

[0099] Step S90: Complete the detailed characterization of sedimentary microfacies in the delta front estuary bar area based on the artificial intelligence sand body thickness map;

[0100] Step S91: Based on the calibration of the single-well logging facies interpretation results, and combined with the artificial intelligence sand body thickness map, the sedimentary microfacies are finely characterized;

[0101] Based on the above method, seismic attributes extracted from the -90° phase high-frequency data volume were used to predict sand body thickness using artificial intelligence. The sand body thickness map obtained by the BRT method showed the highest correlation, and the planar map also better conformed to deltaic sedimentary patterns. The sand body thickness map was then used to finely characterize sedimentary microfacies in the delta front mouth bar and lateral margin areas to meet the needs of lithological trap exploration.

[0102] Step S92: Combine the oil and water data from the development wells to verify the sedimentary microfacies map, clarify the lateral microfacies boundaries of the delta mouth bar area, and finally obtain the sedimentary microfacies map.

[0103] The above description is not intended to limit the present invention in any way. Although the present invention has been disclosed through the above embodiments, it is not intended to limit the present invention. Any person skilled in the art can make some changes or modifications to the above-disclosed technical content to create equivalent embodiments without departing from the scope of the present invention. Any simple modifications, equivalent changes and modifications made to the above embodiments based on the technical essence of the present invention without departing from the scope of the present invention shall fall within the scope of the present invention.

Claims

1. A well-seismic quantitative characterization method for microfacies boundaries on the side margins of deltaic estuary bar, characterized in that, Includes the following steps: Step S10: Obtain the geological background, core data, drilling data, and seismic data of the target work area; Step S20: Establish a high-frequency sequence stratigraphic framework and complete the seismic horizon tracking and interpretation; Step S30: Identify and classify the sedimentary microfacies; Step S40: Perform resolution analysis and phase transformation on the seismic data volume; Step S50: Through well-seismic calibration, determine the seismic response characteristics of the sand bodies in the target work area, and extract the corresponding seismic attributes of the conventional data volume, the -90° phase data volume, and the high-frequency -90° phase conversion data volume; Step S60: Identification and interpretation of planar sedimentary subfacies boundaries; Step S70: Optimize the extracted seismic attributes; Step S80: Predict the sand body thickness using multiple artificial intelligence algorithms to obtain an artificial intelligence sand body thickness map; Step S90: Based on the artificial intelligence sand body thickness map, complete the fine characterization of sedimentary microfacies in the delta front estuary bar area.

2. The well-seismic quantitative characterization method for microfacies boundaries on the side of a delta estuary bar according to claim 1, characterized in that, The specific process of step S20 is as follows: Step S21: Based on the relevant theories of sequence stratigraphy and the rock electrical characteristics and sedimentary cycle characteristics of drilling data, establish a high-frequency sequence division scheme and carry out sequence division and comparison of single wells and interconnected wells. Step S22: Based on the well sequence stratigraphic results, the seismic horizons are marked and interpreted, and finally a high-frequency sequence stratigraphic framework for the entire region is established.

3. The well-seismic quantitative characterization method for microfacies boundaries on the side of a delta estuary bar according to claim 1, characterized in that, The specific process of step S30 is as follows: Step S31: Based on the core data of the target work area, identify the lithology, sedimentary structures and sediment grain size, and establish a sedimentary microfacies division scheme for the target work area; Step S32: Based on sedimentary characteristics such as core samples and well logging, establish a rock-electrodeposition microfacies transition chart; Step S33: Based on the rock-electrodeposition microfacies transformation chart, conduct single-well and interconnected-well interpretation and comparison of microfacies.

4. The well-seismic quantitative characterization method for microfacies boundaries on the side of a delta estuary bar according to claim 1, characterized in that, The specific process of step S40 is as follows: Step S41: Perform spectral analysis on the target layer to obtain the dominant frequency and seismic wave propagation velocity of the seismic data volume; Step S42: Calculate the vertical resolution of the earthquake based on the dominant frequency and seismic wave propagation velocity of the earthquake data volume; Step S43: Statistically analyze the thickness of the target layer sand body; Step S44: Compare the target layer sand body thickness with the seismic vertical resolution. If the thickness of a single sand body is less than the seismic vertical resolution and 1 / 8 of the wavelength λ, then perform a -90° phase transformation on the original data volume. If the thickness of a single sand layer is less than 1 / 8 of the wavelength λ, the relatively high-frequency part of the conventional data volume is extracted and a -90° phase conversion is performed.

5. The well-seismic quantitative characterization method for microfacies boundaries on the side of a delta estuary bar according to claim 1, characterized in that, The specific process of step S60 is as follows: Step S61: Based on the distribution characteristics of the well-connected facies and the sand-soil ratio of the drilled wells in the skeleton profile, the planar sedimentary subfacies boundary is preliminarily determined; Step S62: Based on the well seismic calibration results, select conventional seismic attributes to further clarify the subfacies boundaries.

6. The well-seismic quantitative characterization method for microfacies boundaries on the side of a delta estuary bar according to claim 1, characterized in that, The specific process of step S70 is as follows: Step S71: Using the Pearson correlation analysis method, analyze the correlation between the sand body thickness of all well points and the seismic attributes of the well points extracted from each data volume, and select the 6 seismic attributes with the highest correlation from each data volume. Step S72: Using the Pearson correlation analysis method, select some well points on the outer edge of the delta using phase control, analyze the correlation between the thickness of the drilled sand body and the seismic attributes of the well points extracted from each data volume, and select the 6 seismic attributes with the highest correlation from each data volume.

7. The well-seismic quantitative characterization method for microfacies boundaries on the side of a delta estuary bar according to claim 1, characterized in that, The specific process of step S80 is as follows: Step S81: Use random forest, support vector machine, augmented regression tree and artificial neural network to fuse the six selected attributes; Step S82: Establish a comparison of the accuracy of the prediction models, compare the fusion effects of the four methods, select the algorithm with the best fusion effect for artificial intelligence sand body prediction, and obtain the artificial intelligence sand body thickness map.

8. The well-seismic quantitative characterization method for microfacies boundaries on the side of a delta estuary bar according to claim 1, characterized in that, The specific process of step S90 is as follows: Step S91: Based on the calibration of the single-well logging facies interpretation results, and combined with the artificial intelligence sand body thickness map, the sedimentary microfacies are finely characterized; Step S92: Combine the oil and water data from the development wells to verify the sedimentary microfacies map, clarify the lateral microfacies boundaries of the delta mouth bar area, and finally obtain the sedimentary microfacies map.

Images