A method for quantitatively restoring paleo-water depth based on pre-stack reflection

Abstract

A method for quantitatively restoring paleowater depth based on foreset reflections, belonging to the field of oil and gas field geological exploration, includes: collecting seismic, drilling and logging data in the study area; establishing a high-precision isochronous stratigraphic framework for the target interval, identifying multiple sets of foreset reflection structures on multiple provenance profiles; determining the slope tops and slope toes of the foreset reflection structures, and calculating the apparent thickness H of each foreset body using the segmented accumulation method. s ; Then use the de-compaction correction technology to get the true thickness H z The obtained paleowater depth values are vertically connected to obtain a line graph of paleowater depth changes. A deep interpolation neural network model is constructed and the curve is smoothed to obtain a lake level change curve. This invention uses a piecewise cumulative calculation method to quantitatively and accurately restore the paleowater depth of the lake basin. By constructing a deep neural network model, interpolation calculations and smoothing are performed on a line graph consisting of only a few paleowater depth points to quickly obtain a lake level change curve.

Description

Technical Field

[0001] The present invention relates to the field of oil and gas field geological exploration, and in particular to a method for quantitatively restoring paleo-water depth based on foreset reflection. Background Art

[0002] With the advancement of oil and gas exploration, the industry has gradually come to understand that semi-deep to deep water areas control the development of high-quality source rocks. Therefore, paleowater depth reconstruction is a crucial task in oil and gas geological exploration, providing valuable guidance for studying basin sedimentary evolution, determining sedimentary system types, and evaluating and predicting the conditions of source rocks, reservoirs, and caprocks. Currently, commonly used paleowater depth reconstruction methods can be divided into two categories: qualitative and semi-quantitative-quantitative. Qualitative methods primarily include sediment color, bedding type, geochemical element analysis, and stratigraphic thickness. For example, Patent CN 118296094A discloses a method, apparatus, and storage medium for quantitative characterization of paleogeomorphology. Patent CN 111580183 B discloses a method for quantitatively restoring paleolake water depth. Patent CN 117851748 B discloses a method and system for calculating paleowater depth in low-exploration areas. In 2009, Volume 45, Issue 6, Journal of Lanzhou University (Natural Science Edition), Pang Jungang and Li Wenhou determined the scope of the deep lake area of the basin by combining the sedimentary facies of the Chang 7 Yanchang Formation and the core bedding type analysis. In 2017, Volume 31, Issue 6, Modern Geology, Wang Chenjie et al. used the lithology and sedimentary facies characteristics of the lower section of the second section of the Dongying Formation to restore and correct the ancient water depth of the study area. In 2020, Volume 42, Issue 2, Petroleum Experimental Geology, Xiao Kunze et al. used the correspondence between water depth and stratum thickness to restore the average depth of ancient seawater in the Miocene of the Yinggehai Basin. These methods can qualitatively restore the bottom structure of the basin and clarify the relative heights of different parts, but cannot obtain quantitative ancient water depth data at every point. In addition, these methods are easily restricted by natural conditions and require a large amount of intensive sampling, which is costly. In recent years, geological prospectors have gradually recognized the importance of quantitatively restoring paleowater depth, and new methods have been continuously proposed, including shoreline trajectory methods, Milankovitch cycles combined with Co element analysis, paleontological methods, TOC determination methods, and coarse-grain abundance methods. For example, Patent CN113674806 B discloses a method for restoring paleowater depth in sedimentary lake basins based on trace element and paleontological heterogeneity. Patent CN113687440 A discloses a method and storage medium for quantitative paleowater depth restoration based on Milankovitch cycles. Patent CN114624775B discloses a comprehensive quantitative paleowater depth restoration method for sedimentary lake basins. Patent CN117687113A discloses a quantitative paleowater depth restoration method. Patent CN118133519A discloses a method for quantitatively restoring paleogeomorphology in faulted lake basins based on quantitative paleowater depth calculation. Patent CN104932031 B discloses a quantitative paleowater depth calculation method for lacustrine deposits. In the Journal of Palaeogeography, Vol. 7, No. 3, 2005, Li Shoujun et al. studied the dominant heterogeneity of ostracods. (s)By fitting the relationship between the lacustrine depth D and the paleo-lake depth, the paleo-water depth of the third member of the Paleogene Shahejie Formation in the Dongying Sag was quantitatively restored. In the 2016, Volume 18, Issue 2, Journal of Palaeogeography, Du Qingxiang et al. reconstructed the relative paleo-water depth of the top of the middle sub-member of the first member of the Shahejie Formation in the study area based on variations in Mn / Fe ratios, kerogen types, algal fossils, and the discovery of tubercle-like snails. In the 2024, Volume 42, Issue 1, Acta Sedimentologica Sinica, Wang Changyong et al. quantitatively reconstructed the Early Jurassic paleo-water depth using the La-Co method, TOC method, and Th / U ratio method. These methods can semi-quantitatively or quantitatively restore paleo-water depths and have contributed to the restoration of paleo-water depths in lacustrine and marine sediments. However, these methods also have some challenges in practical application. For example, the shoreline trajectory method is primarily used to restore paleo-water depths in large deltaic sedimentary areas. The calculation process must consider multiple factors such as decompaction, provenance supply rate, and differential tectonic subsidence. This method has high uncertainty, a complex computational process, and poor operability. Paleontological methods require high sample requirements and are limited by the diversity of ostracods and foraminifera, making them suitable only for analyzing sediment depth in shallow lakes. Trace element methods such as TOC and La-Co require extensive trace element testing data for the study area, resulting in high experimental costs. Due to the inherent habitat of coccoliths, coccolith abundance methods are only suitable for paleowater depth reconstruction near coastlines or coastal areas.

[0003] After analyzing the above existing technologies, the following problems were found: (1) At present, the restoration of paleowater depth is mainly based on qualitative analysis, and the research on quantitative restoration of paleowater depth is still relatively lacking. The predecessors mostly focused on the comprehensive use of paleontological markers, geochemical analysis, trace element testing and other means for semi-quantitative analysis. However, these methods require a large amount of core sample data and analytical test data when restoring paleowater depth, which is costly and is mostly suitable for areas with rich drilling data. (2) Although the shoreline trajectory method for large delta sediments can quantitatively calculate paleowater depth, due to too many influencing factors in the calculation process, the calculation process is complicated and the labor cost is high, which is not suitable for large-scale paleowater depth restoration work. (3) At present, there is no method that can simply and quickly restore paleowater depth quantitatively based on only a small amount of exploration data, and then obtain the lake level change curve to provide guidance for studying the sedimentary filling evolution process of the basin. Summary of the Invention

[0004] The purpose of the present invention is to provide a method for quantitatively restoring paleo-water depth based on foreset reflection, so as to solve the problem in the prior art that paleo-water depth and lake level change curve cannot be quickly and accurately quantitatively restored. This method combines seismic data, core data and logging data, and quantitatively calculates paleo-water depth by identifying the foreset reflection structure on the seismic profile. Not only does it solve the influence of differential compaction of strata on sediment thickness through decompaction correction technology, but it also interpolates and smoothes the line graph composed of only a small number of paleo-water depth value points by constructing a deep neural network model to obtain a lake level change curve. This method requires little data, and the calculation process is simple and fast. It can quickly and quantitatively restore paleo-water depth through simple geometric calculations, and generate a lake level change curve using deep neural network technology. In addition, the trained deep interpolation neural network model can be reused, which reduces operating costs. This method is suitable for paleo-water depth recovery and lake level change curve generation over a large range.

[0005] The technical solution adopted by the present invention is:

[0006] A method for quantitatively restoring paleowater depth based on foreset reflections comprises the following steps:

[0007] Step 1: Collect seismic data, drilling data and logging data in the study area;

[0008] Step 2: Detailed interpretation of the seismic data in the study area to establish a high-precision isochronous stratigraphic framework for the target interval. On multiple provenance-oriented seismic sections, the top surface is flattened to identify deltaic progradational reflection structures. This high-precision isochronous stratigraphic framework is a general term, with no specific standard, but is generally accepted within the industry. It is generally considered high-precision when the stratigraphic framework is constructed using high-quality 2D or 3D seismic data. High precision ensures that the model accurately reflects the geological history and sedimentary environment.

[0009] Step 3: Determine the top and foot of the delta's foreset reflection structure, and use the segmented cumulative summation method to calculate the distance between the top and foot of the slope to determine the apparent thickness of the foreset body; the top refers to the dividing point between the top and bottom layers of the foreset reflection structure, and the bottom refers to the lowest point of the foreset layer on the profile, that is, the dividing point between the foreset layer and the bottom layer.

[0010] Step 4: Combine drilling and logging data to perform decompaction correction on the apparent thickness obtained in step 3 to obtain the true thickness of the foreset body, i.e., paleowater depth;

[0011] Step 5: Repeat steps 3 to 4 to quantitatively calculate the thickness of the progradational body at different periods on the source-oriented seismic profile to obtain the paleo-water depth values at different periods, and connect them vertically to obtain a line graph of paleo-water depth changes;

[0012] Step 6: Construct a deep interpolation neural network model, set model parameters, repeatedly train to obtain the best model, and use the best model to interpolate the paleowater depth calculated in step 5;

[0013] Step 7: Draw the interpolated curve and use the CubicSpline function to smooth the curve to obtain a smooth paleo-water depth change curve, that is, the lake level change curve.

[0014] Furthermore, in step 2, the process of identifying the foreshortened reflection structure includes the following steps:

[0015] S201: Based on sequence stratigraphy theory, a set of coal seams with strong peaks and strong troughs in seismic response in the target interval is identified as the top marker layer, and a set of widely and stably developed black shales is identified as the bottom marker layer;

[0016] S202: Combine well and seismic data to calibrate synthetic seismic records, identify, track and interpret target layer segments, and establish a high-precision isochronous stratigraphic framework;

[0017] S203: On multiple seismic sections following the provenance, flatten the top surface and finely identify and depict the multi-stage foreset bodies of the target interval.

[0018] Furthermore, in step 3, the thickness of the front volume (H s ) method comprises the following steps:

[0019] S301: Based on the drilling data in the study area, select the acoustic time difference logging curve of the well closest to the slope top and which has been calibrated with synthetic seismic records, remove abnormal data values, count the logging curve data of the target layer, and calculate the acoustic wave velocity V corresponding to each depth point according to formula (1) i , where i corresponds to different depth points, i = 1, 2, ... n, n represents the number of depth points;

[0020] S302: Based on the different logging phases of sandstone and mudstone, the acoustic wave velocity of the sandstone section and mudstone section with a thickness of not less than 5m is calculated respectively. The acoustic wave time difference of the mudstone section is higher than that of the sandstone, and the whole section is irregular and sharp.

[0021] S303: Calculate the average acoustic velocity values of different sandstone and mudstone intervals according to formula (2) Where j = 1, 2, ... m represents different interval segments, and m is the number of interval segments;

[0022] S304: Read the time ΔT from the top of the slope to the foot of the slope in segments on the seismic profile j , substitute into formula (3) to calculate the apparent thickness H of the foreshortened volume s ;

[0023]

[0024] Where: V i is the acoustic wave velocity at the i-th depth point, m / us; Δt i is the acoustic time difference value at the i-th depth point, us / m; is the average sound wave velocity of the jth interval, m / us; ΔT j is the time difference of the jth time period read on the seismic profile, ms; n j is the number of depth points in the jth interval.

[0025] The segmented cumulative summation method utilizes acoustic logging velocities rather than directly using seismic logging velocities. This is because the average velocity obtained by acoustic logging represents the true formation velocity, compared to the average formation velocity obtained directly from seismic logging. Furthermore, due to its continuous measurement and small receiving distance, it can finely divide layer velocities, better reflecting the lithologic characteristics of the formation. The results are more accurate and more consistent with practical geological significance. Furthermore, acoustic logging can be performed simultaneously with electrical logging, making it more efficient and convenient.

[0026] In addition, the acoustic time difference logging curve of the well closest to the top of the slope and which has been calibrated with synthetic seismic records is used. Because the distance on the well and the time on the seismic profile can be one-to-one corresponded, the formation velocity and the time of reading the seismic profile can be calculated in sections, and the cumulative sum is used to calculate the pre-deposition volume thickness (H s ).

[0027] Furthermore, in step 4, the de-compaction correction includes the following steps:

[0028] S401: Statistically analyze the measured porosity and corresponding depth values of target layers of different lithologies in multiple wells in the study area, and fit the porosity Φ-burial depth Z relationship curve of different lithologies according to the exponential function distribution:

[0029] Ф=Ф0e -C*Z (4)

[0030] Where: Ф is the porosity at depth Z; Ф0 is the surface porosity; C is the compaction coefficient; Z is the burial depth, m;

[0031] S402: Based on the principle that the volume of the rock skeleton particles remains unchanged before and after compaction, and given the current top boundary depth (Z1) and bottom boundary depth (Z2) of the formation, the rock skeleton thickness integral mathematical model (Formula 5) is used to iteratively calculate the top interface burial depth Z'1 and the bottom interface burial depth Z'2 of the original formation, thereby determining the original formation thickness. The compaction rate t of the target layer section of the single well is then calculated based on the ratio of the original formation thickness to the current formation thickness (Formula 6):

[0032]

[0033] Where: Z1, Z2 are the top and bottom depths of the current stratum, respectively, in meters; Z'1, Z'2 are the top and bottom depths of the original stratum, respectively, in meters; t is the compaction rate;

[0034] S403: Compare the compaction rate of the target layer of the single well corresponding to the different foreset bodies with the apparent thickness H of the foreset body calculated in step 3. s Multiply them to get the true thickness H after de-compaction correction z , that is, the paleowater depth:

[0035] H z =t·H s (7)

[0036] Where: H z is the true thickness of the foreset body (paleowater depth), m; H s is the apparent thickness of the foreset volume, m.

[0037] Furthermore, in step six, the interpolation calculation includes the following steps:

[0038] S601: Extract the depth column and calculate the true thickness H of the pre-integrated volume at each stage z (i.e., ancient water depth);

[0039] S602: Perform normalization preprocessing on the extracted data: Use MinMaxScaler to scale the data to the range of [0, 1] to improve the efficiency and accuracy of neural network training;

[0040] S603: Construct a deep interpolation neural network model: The model includes an input layer, three hidden layers, and an output layer. Each hidden layer contains 32 neurons, and the activation function is ReLU.

[0041] S604: Conduct model training: Use the mean square error (MSE) loss function to train the model and use the Adam optimizer for optimization, where the learning rate is set to 0.01 and the number of training epochs is 2000. When the MSE reaches 0.01, the training is stopped and the optimal deep interpolation model is obtained.

[0042] S605: Perform interpolation calculation using the trained optimal model and plot the interpolation result.

[0043] Beneficial effects of the present invention:

[0044] (1) Based on the identification of foreset reflection structures on seismic sections, the present invention calculates the thickness of the foreset body using the segmented cumulative summation method. Taking into account the impact of differential compaction on stratum thickness, the target layer is decompacted and corrected. The thickness of the foreset body of each period is converted into the original sedimentary thickness, quantitatively characterizing the trend of lake basin level change. The restored results are accurate and reliable.

[0045] (2) Compared with other methods that directly use average formation velocity on seismic sections to calculate the thickness of the progradational body, the segmented cumulative summation method fully considers the differences in formation velocity among different lithologies and is more in line with actual geological significance. Different lithologic intervals are accurately divided according to the logging phase, and the average formation velocity of each interval is calculated. The apparent thickness of the progradational body is then accumulated and calculated, making the calculation results more accurate and the overall operation simpler.

[0046] (3) Compared with previous studies, the calculation of the thickness of the foreset body (paleowater depth) requires a large amount of analytical test data and exploration logging data, and the calculation process is complicated. The present invention only requires a small amount of seismic data, drilling data and the most basic logging curve data (AC, CNL, DEN, GR, SP). The thickness of the foreset body (paleowater depth) in different periods is obtained by the segmented cumulative summation method, and the influence of differential compaction is fully considered. The overall calculation process is simple and fast, the results are more accurate, and it has good promotion and application value.

[0047] (4) The present invention proposes an interpolation calculation method based on a deep neural network model, which interpolates and smoothes a line graph composed of a small number of paleowater depth value points to obtain a smooth lake level change curve. Compared with the traditional one-time interpolation method, the interpolation technology based on deep learning can achieve better interpolation effects through the optimization of model parameters and repeated training. This method is particularly suitable for processing the interpolation calculation of discrete data points such as paleowater depth, thereby generating a more accurate and smoother interpolation curve. The lake level change curve after smoothing can better reflect the trend of basin sedimentary evolution, and provides new research ideas and technical means for the study of the sedimentary evolution process of paleolakes and the prediction of multi-type lake-phase high-quality reservoirs. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] Figure 1 It is a flowchart of the method of the present invention;

[0049] Figure 2 This is a schematic diagram of the research area and the source seismic survey line of the present invention;

[0050] Figure 3 This is a schematic diagram of a high-precision isochronous stratigraphic framework established by the present invention using the A-A' seismic profile as an example;

[0051] Figure 4 This is a schematic diagram of the present invention's restoration of paleo-water depth based on the foreset reflection structure;

[0052] Figure 5 This is a schematic diagram of the porosity-depth relationship of sandstone and mudstone fitted in the decompaction correction of the present invention;

[0053] Figure 6 The sand and mudstone structure model and compaction rate calculation of each single well in the present invention;

[0054] Figure 7 This is a flow chart of the deep interpolation neural network algorithm of the present invention;

[0055] Figure 8 This is a structural diagram of the deep interpolation neural network model of the present invention;

[0056] Figure 9 paleo-bathymetric maps restored for this invention;

[0057] Figure 10 This is the lake level change curve restored by the present invention. DETAILED DESCRIPTION

[0058] In this example, through the systematic analysis of the three-dimensional seismic data in the Qingcheng area of the Ordos Basin, a high-precision isochronous stratigraphic framework of the Yanchang Group was established to identify the foreset reflection structure and determine the top and foot of each foreset body. The apparent thickness of the foreset body was then calculated using the segmented cumulative summation method, and the original sedimentary thickness was restored using the decompaction correction technology, converting the apparent thickness into the true thickness (i.e., paleowater depth). Finally, a deep neural network model was constructed to interpolate a small number of paleowater depth values to obtain a smooth lake level change curve. Based on the identification of the delta proset reflection structure, the present invention only requires a small amount of data to quickly and quantitatively calculate the paleowater depth, and takes into account the influence of differential compaction of the strata, resulting in higher accuracy. In addition, in view of the characteristics of the small number of paleowater depth numerical points and the unevenness of the resulting curve, an interpolation calculation method based on a deep neural network model is proposed. Specifically, the following steps are included, such as Figure 1 As shown:

[0059] Step 1: Collect 3D seismic data, drilling data, and logging data in the Qingcheng area of the Ordos Basin.

[0060] Step 2: Detailed interpretation of 3D seismic data to establish a high-precision isochronous stratigraphic framework for the Yan9-Chang7 segment. On multiple provenance-oriented seismic sections, the top surface is flattened to identify the delta progradational reflection structure, including the following steps:

[0061] 1) According to sequence stratigraphy theory, multiple coal seams are extensively developed between Yan 7 and Yan 9, exhibiting a response characteristic of a combination of strong peaks and strong troughs on the seismic profile. Therefore, Yan 9 is designated as the top marker. The Chang 7 shale exhibits a seismic response characteristic of "one black, two red, one peak, two troughs," so Chang 7 is designated as the bottom marker.

[0062] 2) Combined well-seismic calibration of synthetic seismic records, and calibration of main seismic reflection interfaces y9, Tj, C1, C2, C3, and C7 顶 、C7 底 and C8 identification, tracking and interpretation to establish a high-precision isochronous stratigraphic framework.

[0063] 3) Combined with the well location distribution in the 3D work area, five seismic profiles A-A', B-B', C-C', D-D', and E-E' were made along the source direction (southwest) (see Figure 2 ), flatten the top surface marker layer Yan9, and finely identify and depict the foreset body. Taking the A-A' seismic profile as an example, the six foreset bodies F1 to F6 were identified (see Figure 3 ).

[0064] Step 3: Determine the top and foot of each foreset reflection structure, and calculate the distance between the top and foot using the segmented cumulative summation method to determine the apparent thickness of each foreset body. See the model diagram for details. Figure 4 As shown, the specific steps are:

[0065] 1) Based on the drilling data in the study area, the acoustic time difference logging curve of the well (X1) closest to the slope top of the foreset body F1 is selected and the abnormal data values are eliminated. The logging curve data of the target layer is counted and the acoustic velocity V corresponding to each depth point is calculated according to formula (1). i , where i corresponds to different depth points;

[0066] 2) According to the difference in logging phases between sandstone and mudstone, the acoustic velocity of sandstone and mudstone sections with a thickness of not less than 5m was calculated respectively; the acoustic time difference of mudstone section was higher than that of sandstone, and the whole section was irregular and sharp (see Figure 6 );

[0067] 3) Calculate the average acoustic velocity values of different sandstone and mudstone intervals according to formula (2): Where j = 1, 2, ... m represents different intervals, and m is the number of intervals (see Table 1)

[0068] 4) Read the time ΔT from the top of the slope to the foot of the slope in sections on the seismic profile j , substituted into formula (3) to calculate the apparent thickness Hs of the foreset (see Table 1);

[0069] Table 1 Apparent thickness of the forebody F1 obtained by the segmented cumulative summation method

[0070]

[0071] Step 4: Combine drilling and logging data to perform de-compaction correction on the apparent thickness obtained in step 3. Specific steps:

[0072] 1) The measured porosity and corresponding depth values of sandstone and mudstone in Chang 3 to Chang 7 sections of 6 wells in Qingcheng work area were counted, and the porosity Φ-burial depth Z relationship curves of sandstone and mudstone were fitted according to the exponential function distribution (see Figure 5 ).

[0073] The fitted relationship equation between the porosity Φ of sand and mudstone and the burial depth Z is as follows:

[0074] Sandstone: Ф = 46.5121e -0.00079Z (8)

[0075] Mudstone: Ф = 62.9984e -0.00099Z (9)

[0076] 2) Based on the principle that the volume of the rock skeleton particles remains unchanged before and after compaction, and given the current top depth (Z1) and bottom depth (Z2) of the formation, the original top depth (Z'1) and bottom depth (Z'2) of the sandstone and mudstone sections of the Chang 3 to Chang 7 sections of well X1 were iteratively calculated using the rock skeleton thickness integral mathematical model (Formula 4). The compaction rate (t) of Chang 3 to Chang 7 of well X1 was then calculated based on the ratio of the original formation thickness to the current formation thickness to be 1.19 (see Figure 6 ).

[0077] 3) Compare the compaction rate 1.19 of the single well X1 corresponding to the foreset F1 with its apparent thickness (H s )186.47m to obtain the true thickness after de-compaction correction (H z ) is 221.89m, which is the ancient water depth.

[0078] H z =t·H s =1.19×186.47=221.89m

[0079] Where: t is the compaction rate; H z is the true thickness of the foreset body (paleowater depth); H s is the apparent thickness of the foreset volume;

[0080] Step 5: Repeat steps 3 to 4 to quantitatively calculate the thickness of the progradation body at different stages on each seismic section along the provenance direction, and obtain the paleowater depth values (H) at different stages. z )(see Table 2), vertical connection to obtain the paleo-water depth change line graph (see Figure 9 ).

Claims

1. A method for quantitatively restoring paleo-water depth based on foreset reflection, characterized in that: The following steps are involved: Step 1: Collect seismic data, drilling data and logging data in the study area; Step 2: Detailed interpretation of seismic data in the study area to establish a high-precision isochronous stratigraphic framework for the target interval. On multiple provenance-oriented seismic sections, the top surface is flattened to identify the delta progradational reflection structure. Step 3: Determine the top and foot of the delta progradation reflection structure, and calculate the distance between the top and foot using the segmented cumulative summation method to determine the apparent thickness of the progradation body; Step 4: Combine drilling and logging data to perform decompaction correction on the apparent thickness obtained in step 3 to obtain the true thickness of the foreset body, i.e., paleowater depth; Step 5: Repeat steps 3 to 4 to quantitatively calculate the thickness of the progradational body at different periods on the source-oriented seismic profile to obtain the paleo-water depth values at different periods, and connect them vertically to obtain a line graph of paleo-water depth changes; Step 6: Construct a deep interpolation neural network model, set model parameters, repeatedly train to obtain the best model, and use the best model to interpolate the paleowater depth calculated in step 5; Step 7: Draw the interpolated curve and use the CubicSpline function to smooth the curve to obtain a smooth paleo-water depth change curve, that is, the lake level change curve.

2. The method for quantitatively restoring paleo-water depth based on foreset reflection according to claim 1, characterized in that: In step 2, the process of identifying the foreset reflection structure includes the following steps: S201: Based on sequence stratigraphy theory, a set of coal seams with strong peaks and strong troughs in seismic response in the target interval is identified as the top marker layer, and a set of widely and stably developed black shales is identified as the bottom marker layer; S202: Combine well and seismic data to calibrate synthetic seismic records, identify, track and interpret target layer segments, and establish a high-precision isochronous stratigraphic framework; S203: On multiple seismic sections following the provenance, flatten the top surface and finely identify and depict the multi-stage foreset bodies of the target interval.

3. The method for quantitatively restoring paleo-water depth based on foreset reflection according to claim 1, characterized in that: In step 3, the method for determining the foreshortened volume thickness includes the following steps: S301: Based on the drilling data in the study area, select the acoustic time difference logging curve of the well closest to the slope top and which has been calibrated with synthetic seismic records, remove abnormal data values, count the logging curve data of the target layer, and calculate the acoustic wave velocity V corresponding to each depth point according to formula (1) i , where i corresponds to different depth points, i = 1, 2, ... n, n represents the number of depth points; S302: Based on the different logging phases of sandstone and mudstone, the acoustic wave velocity of the sandstone section and mudstone section with a thickness of not less than 5m is calculated respectively. The acoustic wave time difference of the mudstone section is higher than that of the sandstone, and the whole section is irregular and sharp. S303: Calculate the average acoustic velocity values of different sandstone and mudstone intervals according to formula (2) Where j = 1, 2, ... m represents different interval segments, and m is the number of interval segments; S304: Read the time ΔT from the top of the slope to the foot of the slope in segments on the seismic profile j , substitute into formula (3) to calculate the apparent thickness H of the foreshortened volume s ; Where: V i is the acoustic wave velocity at the i-th depth point, m / us; Δt i is the acoustic time difference value at the i-th depth point, us / m; is the average sound wave velocity of the jth interval, m / us; ΔT j is the time difference of the jth time period read on the seismic profile, ms; n j is the number of depth points in the jth interval.

4. The method for quantitatively restoring paleo-water depth based on foreset reflection according to claim 1, characterized in that: In step 4, the de-compaction correction includes the following steps: S401: Statistically analyze the measured porosity and corresponding depth values of target layers of different lithologies in multiple wells in the study area, and fit the porosity Φ-burial depth Z relationship curve of different lithologies according to the exponential function distribution: F=F0e -C*Z (4) Where: Ф is the porosity at depth Z; Ф0 is the surface porosity; C is the compaction coefficient; Z is the burial depth, m; S402: Based on the principle that the volume of the rock skeleton particles remains unchanged before and after compaction, and given the current top and bottom boundary depths of the formation, the rock skeleton thickness integral mathematical model is used to iteratively calculate the top boundary depth Z'1 and the bottom boundary depth Z'2 of the original formation, thereby determining the original formation thickness. The compaction rate t of the target layer section of a single well is then calculated based on the ratio of the original formation thickness to the current formation thickness: Where: Z1, Z2 are the top and bottom depths of the current stratum, respectively, in meters; Z'1, Z'2 are the top and bottom depths of the original stratum, respectively, in meters; t is the compaction rate; S403: Compare the compaction rate of the target layer of the single well corresponding to the different foreset bodies with the apparent thickness H of the foreset body calculated in step 3. s Multiply them to get the true thickness H after de-compaction correction z , that is, the paleowater depth: H z =t·H s (7) Where: H z is the true thickness of the foreset body, m; H s is the apparent thickness of the foreset volume, m.

5. The method for quantitatively restoring paleo-water depth based on foreset reflection according to claim 1, characterized in that: In step six, the interpolation calculation includes the following steps: S601: Extract the depth column and calculate the true thickness H of the pre-integrated volume at each stage z ; S602: Perform normalization preprocessing on the extracted data: use MinMaxScaler to scale the data to the range of [0, 1]; S603: Construct a deep interpolation neural network model: The model includes an input layer, three hidden layers, and an output layer. Each hidden layer contains 32 neurons, and the activation function is ReLU. S604: Conduct model training: Use the mean square error loss function to train the model and use the Adam optimizer for optimization, where the learning rate is set to 0.01 and the number of training rounds is 2000; stop training when the MSE reaches 0.01, and obtain the optimal deep interpolation model; S605: Perform interpolation calculation using the trained optimal model and plot the interpolation result.

Images