A method for predicting open fractures in a reservoir

Abstract

The application provides a reservoir opening fracture prediction method, and belongs to the technical field of fracture prediction, and comprises the following steps: S1, establishing a target layer fracture information standardized data set by using original three-dimensional seismic data, imaging logging data and geological data; S2, discriminating the target layer fracture information standardized data set, reserving the value of the data points consistent with the opening fracture, and establishing an opening fracture quantitative modeling data volume; and S3, combining reservoir seismic inversion, merging the opening fracture quantitative modeling data volume, and obtaining reservoir opening fracture density. The method can effectively determine the development degree of natural effective fractures in sandstone and conglomerate, obtain information such as opening fracture direction and fracture density, and further provide rich fracture information for the research of fracture reservoirs.

Description

TECHNICAL FIELD

[0001] The present application belongs to the technical field of fracture prediction, and particularly relates to a reservoir opening fracture prediction method. BACKGROUND

[0002] With the continuous development of sandstone gas reservoirs, the prediction of natural effective fractures has become an important part of efficient development of sandstone gas reservoirs. In particular, oil and gas in fractured reservoirs will account for an increasingly large proportion of oil and gas reserves. Therefore, fractures are a key factor affecting productivity.

[0003] There are a large number of faults and natural fractures in the study area due to tectonic movement, and these faults are the channels of underground water and acid solution. Through the summary and study of this actual geological law, a geological modeling-based opening fracture prediction technology method is proposed. Accurate prediction of opening fractures can have a great control effect on avoiding drilling engineering risks, improving the drilling rate of reservoirs, and reservoir reconstruction in development links such as fracturing.

[0004] The existing opening fracture prediction methods in the prior art mainly include shear wave splitting, microseismic, core thin section, and FMI imaging logging technology.

[0005] The main reservoir space of sandstone in the study area is opening fractures and dissolution pores, and the corresponding reservoir types are opening fracture type and induced fracture.

[0006] The commonly used natural effective fracture prediction technology at present is the seismic P-wave opening fracture prediction technology.

[0007] The seismic P-wave opening fracture prediction technology can be divided into two types of pre-stack and post-stack seismic data prediction according to the type of seismic data.

[0008] The pre-stack P-wave opening fracture prediction technology uses the mathematical method of pre-stack three-dimensional seismic data to analyze the correlation between seismic traces, quantitatively describes the heterogeneity characteristics of the formation, and predicts the opening fractures. Since the pre-stack P-wave opening fracture prediction technology has a relatively high cost, it is not used at present.

[0009] The post-stack P-wave opening fracture prediction technology mainly studies the lateral discontinuity of seismic traces through seismic attributes and rose diagrams, and studies the fracture-pore dual medium reservoir characteristics caused by faults, small faults, etc.

[0010] In summary, the methods for predicting underground opening fractures using seismic data are all related to pre-stack and post-stack three-dimensional seismic data, but it is difficult to implement these methods for predicting opening fractures, and the operation process is easily affected by various factors such as poor signal-to-noise ratio of seismic data. Specifically, when using conventional post-stack seismic data to predict fractures, it is often difficult to predict micro-fractures due to the influence of stacking averaging. SUMMARY

[0011] In order to solve the above problems in the prior art, the present application provides a reservoir opening fracture prediction method, and the technical problem to be solved by the present application is to provide a method for conveniently, simply and accurately effectively predicting opening fractures.

[0012] In order to solve the above problems, the present application provides a reservoir opening fracture prediction method, comprising the following steps:

[0013] Step S1: using original three-dimensional seismic data, imaging logging data and geological data, establishing a target layer fracture information standardized data set;

[0014] Step S2: discriminating the target layer fracture information standardized data set, retaining the value of the data points consistent with the opening fracture, and establishing an opening fracture quantitative modeling data volume;

[0015] Step S3: combining reservoir seismic inversion, merging the opening fracture quantitative modeling data volume, and obtaining the reservoir opening fracture density.

[0016] Further, the original three-dimensional seismic data volume in step S1 includes three data volumes of fracture similarity attribute, dip angle and strike.

[0017] Further, the fracture similarity attribute data of the original three-dimensional seismic data volume is preprocessed, and when the calculated fracture similarity attribute is left-biased, the preprocessed calculation formula is as follows:

[0018] likelihood=(1-semblance 8 ) 2 (1)

[0019] In the formula, likelihood is the similarity attribute value, and semblance is the skewness.

[0020] When the calculated fracture similarity attribute is right-biased, the preprocessed calculation formula is as follows:

[0021]

[0022] Further, in step S1, the value range of the dip angle and the strike of the corresponding fracture of the original three-dimensional seismic data volume is searched, the strike and the dip angle of the opening fracture are determined by using the imaging logging data and the geological data, and the target layer fracture information standardized data set is established.

[0023] Further, the value range of the dip angle is 0-180 degrees, and the value range of the strike is -90-90 degrees.

[0024] Further, the dip angle of the fracture of the original three-dimensional seismic data volume is normalized to 0-90 degrees, if the strike is greater than 90 degrees, then the corrected dip angle is used as the normalized dip angle data; if the dip angle is less than 90 degrees, it remains unchanged, and the calculation formula of the corrected dip angle is:

[0025] B = 180°-A

[0026] In the formula, B is the corrected dip angle, °; A is the original dip angle, °;

[0027] The strike of the fracture of the original three-dimensional seismic data volume is normalized to 0-90 degrees, if the strike is less than 0 degrees, then the first corrected strike is used as the normalized strike data; if the strike is greater than 0 degrees, then the second corrected strike is used as the normalized strike data, and the calculation formula of the first and second corrected strikes is as follows:

[0028] C = 90°+E

[0029] In the formula, C is the first corrected strike, °; E is the original strike, °;

[0030] D = 90°-E

[0031] In the formula, D is the second corrected strike, °; E is the original strike, °;

[0032] The dip angle and strike of the fracture of the imaging logging data are normalized to 0-90 degrees, if the dip angle and strike of the opening fracture of the imaging logging data are in different set ranges, then the corresponding data of the fracture information normalized data set is assigned as the opening fracture; otherwise, it is a closed fracture, and the set range is set according to the actual situation of the region. For example, the set range of the dip angle in a certain region is 60-90 degrees, and the set range of the strike is 0-45 degrees, and the set range of other regions is selected according to the actual situation.

[0033] Further, in step S2, the logistic logistic binary machine learning discrimination program is used to discriminate the opening fracture of the target layer fracture information normalized data set.

[0034] Further, in step S3, combined with the reservoir inversion result, the invalid mudstone is filtered, the reservoir opening fracture information is reserved, and the opening fracture quantitative modeling data volume is output.

[0035] Further, when the impedance value is less than or equal to the set value, it is mudstone, and the opening fracture density planar distribution map is output, and the set value is equal to 9500 g.m / (cm 3 .s).

[0036] The method for predicting reservoir open fractures of the present invention can effectively determine the development degree of natural effective fractures in sandstone-containing conglomerate, obtain information such as the direction of open fractures and fracture density, and thus provide rich fracture information for the study of fractured reservoirs.

[0037] The method for predicting reservoir open fractures of the present invention can effectively solve the problem of identifying natural effective fractures in sandy conglomerate and has the following beneficial effects:

[0038] 1. Solve the problem of multiple solutions in the prediction of natural effective fractures in sandy conglomerate;

[0039] 2. Improved the success rate of deployment demonstration pilot wells;

[0040] 3. Improve the accuracy of the main controlling factors and oil and gas properties of Permian conglomerate reservoirs;

[0041] 4. It laid the foundation for the efficient development of Middle and Lower Permian conglomerate oil and gas reservoirs;

[0042] 5. Provide a theoretical basis for the selection of corresponding reserve parameters in reserve declaration;

[0043] 6. The fracture sweet spots predicted by this technology can greatly promote the construction of reserve production capacity. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] Figure 1 This is a flow chart of a reservoir opening fracture prediction method and device of the present invention.

[0045] Figure 2 This is a diagram showing the effect of the fusion of M-well open fracture prediction and seismic profile in a reservoir open fracture prediction method of the present invention.

[0046] Figure 3 It is a planar distribution diagram of the density of open fractures in a reservoir open fracture prediction method according to the present invention. DETAILED DESCRIPTION

[0047] To make the purpose, technical solutions, and advantages of the embodiments of the present invention more clear, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts shall fall within the scope of protection of the present invention.

[0048] Therefore, the following detailed description of the embodiments of the application provided in the drawings is not intended to limit the scope of the application claimed, but merely represents selected embodiments of the application. Based on the embodiments in the application, all other embodiments obtained by those of ordinary skill in the art without creative labor are within the scope of protection of the application.

[0049] It should be noted that similar reference numerals and letters represent similar items in the following drawings, and therefore, once an item is defined in one drawing, it need not be further defined and explained in subsequent drawings.

[0050] In the present application, unless otherwise explicitly specified and limited, the terms "mounting", "connection", "connecting", "fixing" and the like should be understood broadly, for example, can be fixed connection, or detachable connection, or integral; can be directly connected, or indirectly connected through an intermediate medium, can be internal communication of two elements or interaction relationship between two elements. For those of ordinary skill in the art, the specific meaning of the above terms in the present application can be understood according to the specific circumstances.

[0051] In order to better understand the purpose, structure and function of the present application, the reservoir opening fracture prediction method of the present application is further described in detail below in combination with the drawings.

[0052] Example 1:

[0053] As shown in the figure, the reservoir opening fracture prediction method of the present application comprises the following steps: Figure 1 Step S1: using original three-dimensional seismic data body, imaging logging data and geological data, establishing a target layer fracture information standardized data set;

[0054] Step S2: discriminating the target layer fracture information standardized data set, retaining the value of the data points consistent with the opening fracture, and establishing an opening fracture quantitative modeling data body;

[0055] Step S3: combining reservoir seismic inversion, merging the opening fracture quantitative modeling data body, and obtaining reservoir opening fracture density.

[0056] Example 2:

[0057] As shown in the figure, the reservoir opening fracture prediction method of the present application comprises the following steps:

[0058] Figure 1 Step S1: using original three-dimensional seismic data body, imaging logging data and geological data, establishing a target layer fracture information standardized data set;

[0059] Step S1: using original three-dimensional seismic data body, imaging logging data and geological data, establishing a target layer fracture information standardized data set;

[0060] ​Step S2: using a logistic logic binary machine learning discrimination program to discriminate the target layer opening fracture data body, retaining the value of the data points consistent with the opening fracture, and establishing an opening fracture quantitative modeling data body;

[0061] Step S3: combining the reservoir seismic inversion, merging the opening fracture quantitative modeling data body, and obtaining the opening fracture density.

[0062] The difference between this embodiment and the first embodiment is that:

[0063] In the step S1, the value range of the dip and strike corresponding to the original three-dimensional seismic data body is searched, the imaging logging data and the geological data are used to determine the strike and dip of the opening fracture, and a standardization data set of all fracture information of the target layer is established.

[0064] In the step S1, the original three-dimensional seismic data body includes the semblance attribute, the dip and the strike.

[0065] In the step S1, the original three-dimensional seismic data body is subjected to a fracture identification algorithm, that is, an analysis window of an analysis point is defined, the window can be theoretically any shape, and for convenience of calculation, it is usually a regular window (such as 3x3) with the analysis point as the center, and the skewness is estimated according to the calculation semblance, and when the calculated fracture semblance attribute is left-skewed, the pre-processing calculation formula is as follows:

[0066] likelihood=(1-semblance 8 ) 2 (1)

[0067] In the formula, likelihood is the semblance attribute value, and semblance is the skewness.

[0068] When the calculated fracture semblance attribute is right-skewed, the pre-processing calculation formula is as follows:

[0069]

[0070] Because the fracture semblance attribute value domain calculated by different three-dimensional data bodies is all 0-1, but the skewness is different, standardization processing is needed to ensure the uniformity of the output drawings.

[0071] That is, the calculated semblance values are all normal distribution, otherwise the final fracture planar graph display is inconsistent.

[0072] In the step S1, according to the value range of the fracture dip and strike of each sampling point of the original three-dimensional seismic data body, the discrimination statement is used to determine the specific value of the dip and strike of the fracture response according to the logging data. The following method is used:

[0073] IFC(dip < 90°, dip, 180° - dip)

[0074] IFC(strike >= 0°, 90° - strike, strike + 90°)

[0075] Finally, the data with dip angle of -90°-90° in the original 3D seismic data volume is normalized to the dip angle data of 0°-90°, and the data with strike of 0°-180° is normalized to the strike data of 0°-90°.

[0076] In the step S1, the three normalized data (dip angle, strike, and similarity attribute) of the sampling point are output, and the input data format is as follows:

[0077] The format is: dip angle (x, y, data value); strike (x, y, data value); and similarity attribute (x, y, data value).

[0078] In the step S1, the three data (dip angle (dip), strike (strike), and similarity attribute (likelihood)) of the original 3D seismic data volume are combined into a comma-separated data file for storage and loading according to the 3D seismic data volume with Gaussian Kriging geodetic coordinates (without sign), and the specific file format is as follows:

[0079] The format is: (x, y, dip angle, strike, similarity), that is, fracture_dip_strike.csv.

[0080] X, Y, dip, strike, likelihood

[0081] 334314, 4980831.5, 79.761, 28.97, 1

[0082] 334314, 4980856.5, 61.828, 21.77, 1

[0083] 334314, 4980881.5, 80.477, 57.543, 1

[0084] 334314, 4980906.5, 53.818, 56.328, 0.499

[0085] 334314, 4980931.5, 41.929, 43.257, 0.501

[0086] 334314, 4980956.5, 62.898, 21.77, 0.498

[0087] 334339，4980806.5，57.193，，36.057，，0.499

[0088] 334339，4980831.5，53.532，，14.287，，0.5

[0089] 334339，4980856.5，44.425，，48.569，，0.501

[0090] 334339，4980881.5，39.046，，64.63，，1

[0091] 334339，4980906.5，81.986，，57.543，，0.5

[0092] 334339，4980931.5，88.622，，57.827，，0.501

[0093] 334339，4980956.5，65.209，，21.77，，0.5

[0094] 334339，4980981.5，58.359，，21.77，，0.499

[0095] 334339，4981006.5，81.061，，7.483，，0.499

[0096] 334339，4981031.5，89.988，，0，，0.498

[0097] 334339，4981056.5，57.206，，36.057，，0.494

[0098] 334339，4981081.5，57.586，，36.057，，0.496

[0099] 334339，4981106.5，65.87，，75.595，，0.496

[0100] 334339，4981131.5，66.87，，21.77，，0.781

[0101] 334339，4981156.5，66.463，，7.483，，0.493

[0102] 334339，4981181.5，47.309，，0，，0.491

[0103] 334339, 4981206.5, 50.483,, 0,, 0.491

[0104] 334339, 4981231.5, 89.859,, 36.057,, 0.491

[0105] 334339, 4981256.5, 65.744,, 50.343,, 0.492

[0106] 334339, 4981281.5, 44.293,, 50.343,, 0.492

[0107] 334339, 4981306.5, 45.758,, 50.343,, 0.989

[0108] 334339, 4981331.5, 42.997,, 56.828,, 0.495

[0109] In the step S1, the imaging logging data and the geological data are used to determine the strike and dip of the open fracture, and the following python statement is used for judgment:

[0110] Import pandas as pd

[0111] data = pd.read_csv("logfracture_dip_strike.csv')

[0112] df = pd.DataFrame(data)

[0113] print(df.columns, df.shape)

[0114] / / Input three data with Gaussian Kriging three-dimensional seismic data body with coordinates (not including with number).

[0115] Import pandas as pd

[0116] Import matplotlib.pyplot as plt

[0117] data = pd.read_csv("fracture_dip_strike.csv')

[0118] df = pd.DataFrame(data)

[0119] color = []

[0120] for i in df['class'][0:100]:

[0121] if i == 'open':

[0122] color.append('red')

[0123] else:

[0124] color.append('blue')

[0125] plt.scatter(df['dip'][0:100], df['strike'][0:100], color=color)

[0126] plt.xlabel('dip')

[0127] plt.ylabel('strike')

[0128] plt.show()

[0129] The above python statement is to compare the dip and strike of three data of three-dimensional seismic data volume with imaging logging data and geological data. The dip and strike of open fractures identified by imaging logging data are used as the sampling point information of open fractures of seismic data volume. The specific determination method is to determine whether the dip and strike are within a certain range by the above python statement. If yes, it is an open fracture; if not, it is a closed fracture.

[0130] In step S2, the input logistic binary machine learning discrimination program (python statement) is as follows: input the data of the whole fracture data volume of the target layer into the program to discriminate the seismic open fracture data.

[0131] The python statement is as follows:

[0132] import numpy as np

[0133] import pandas as pd

[0134] data = pd.read_csv('fracture_dip_strike.csv')

[0135] df = pd.DataFrame(data)

[0136] label = []

[0137] for I in df['fracture'][0:400]: / / For example: input the first 400 sample points for training

[0138] if i == 'dip':

[0139] Label.append(θ)

[0140] Else:

[0141] Label.append(1)

[0142] X1=df['dip'][0:400]

[0143] X2=df['strike'][0:400]

[0144] Train_data=list(zip(x1,x2,label))

[0145] Class Logistic_Regression: / / python statement package, logistic binary discrimination Def_init_(self,traindata,alpha=0.01,circle=10,batchlength=20)

[0146] Self.traindata = traindata / / training data set

[0147] Self.alpha = alpha / / learning rate is 0.01

[0148] Self.circle = circle / / The number of learning times is 10

[0149] Self.batchlength = batchlength / / Divide 400 data into 20 parts, 20 data in each part

[0150] Self.w=np.random.normal(size=(3,1)) / / Randomly initialize parameter w

[0151] Def data_process(self) / / Random gradient descent, disrupt the data order, and divide all data into several batches

[0152] Np.random.shuffle(self.traindata)

[0153] Data=[self.traindata[i:i+self.batchlength]]

[0154] For I in range(0,len(self.traindata),self.batchlength)]

[0155] Return data

[0156] Def train1(self):

[0157] Def train1(self):

[0158] / / Perform stochastic gradient descent based on loss function 1

[0159] For I in range(self.circle):

[0160] Batches = self.data_process()

[0161] Print('the{}epoch'.format(i))

[0162] For batch in batches:

[0163] D_w = np.zeros(shape+(3,1))

[0164] For j in batch:

[0165] X0=np.mat(x0).T

[0166] Y=j[2]

[0167] Dw=(self.sigmoid(self.wT*x)-y)[0,0]*x

[0168] D_w+=dw

[0169] Self.w-=self.alpha*d_w / self.batchlength

[0170] Gradient descent solution of root mean square loss function

[0171] Def train2(self):

[0172] For I in range(self.circle):

[0173] Batchs = self.data_process()

[0174] Print('the {} epoch'.format(i))

[0175] For batch in batches:

[0176] D_w = np.zeros(shape=(3, 1)

[0177] For j in batch:

[0178] X0 = np.r_[j[0:2], 1]

[0179] X = np.mat(x0).T

[0180] Y = j[2]

[0181] Dw = ((self.sigmoid(self.w.T * x) - y) * self.sigmoid(self.w.T * x) * (1 - self.sigmoid(self.w.T * x)))[0.0] * x

[0182] D_w += dw

[0183] Self.w -= self.alpha * d_w / self.batchlength

[0184] Def sigmoid(self, x):

[0185] Return 1 / (1 + np.exp(-x))

[0186] Def predict(self, x):

[0187] S = self.sigmoid(self.w.T * x)

[0188] If s >= 0.5:

[0189] Return 1

[0190] Elif s < 0.5:

[0191] Return o

[0192] If __name__ == '__main__':

[0193] Regr = Logistic_Regression(traindata = train_data)

[0194] Regr.train1()

[0195] If fracture = 1

[0196] Return fracture

[0197] Return fracture

[0198] Elif fracture = 0:

[0199] Return o

[0200] In the step S3, according to the reservoir inversion result, invalid mudstone is filtered, and the information of the reservoir opening fracture is reserved.

[0201] The mudstone can be filtered in the following manner:

[0202] if (sand_IMP > 11500)

[0203] { fracture = fracture;}

[0204] else

[0205] { fracture = 0;}

[0206] Impedance value greater than 11500 g.m / (cm 3 .s) is sandy conglomerate, otherwise, it is mudstone.

[0207] Example 3

[0208] As shown in Figure 2 and Figure 3 , the application is well applied in the M well area of a certain place, and the specific content includes:

[0209] First, from the 3D seismic data body SEGY file, the 32-bit floating point format of 12 channel head is outputted, and the amplitude-preserved and stacked 3D seismic data body is obtained.

[0210] The seismic data is processed by using the dip imaging enhancement, and a high-resolution data body is generated according to the large-mesoscale fault of the seismic level;

[0211] The dip angle, strike and similarity attribute of the high-resolution data body are extracted, and three seismic structural fracture attribute data bodies are obtained.

[0212] Second, under the control of the explained horizon, the target layer time window (dip angle, strike and similarity attribute) is extracted and output as the target layer fracture information standardized data set.

[0213] Third, according to the strike and dip angle of the open fracture determined according to the imaging logging data and geological data, the similarity attribute of the open fracture in the whole fracture information standardized data set is retained under the python statement logistic binary discriminant program, and the rest is filtered, so as to establish the target layer open fracture quantitative modeling data body.

[0214] According to the sand and mudstone impedance volume of the Permian Fengcheng Formation in the research area, greater than 10500g.m / (cm 3 .s) can be judged as sandstone, less than 9500g.m / (cm3.s) can be judged as mudstone, and the present study is aimed at the sandstone with impedance greater than 10500g.m / (cm3.s) for open fracture simulation.

[0215] When the well site is demonstrated, there is only one exploratory well CP24 in the Permian Fengcheng Formation in the area, and the fractures are developed, the open fracture dip angle is 65-90 degrees and the strike is 0-40 degrees according to the logging interpretation; the open fracture is developed in the seismic. After the above steps, the open fracture density of the sandstone in the area is predicted, and the results are shown in Figure 3 Fig. 3, and the three favorable targets with greater open fracture density of SP3, SP4 and SP5 are selected for drilling. The drilling results show that the three wells are located in the position where the open fracture is developed, and have good oil and gas show, and obtain industrial oil flow. This method of predicting the open fracture of deep reservoirs provides important technical support for providing drilling targets and optimizing well sites.

[0216] The above only describes the preferred embodiments of the present application and is not used to limit the present application. For those skilled in the art, the present application can have various modifications and changes. Any modification, equivalent replacement, improvement, etc. within the spirit and principles of the present application is included in the protection scope of the present application.

Claims

1. A method for predicting reservoir crack opening, characterized in that The method comprises the following steps: Step S1: using original three-dimensional seismic data, imaging logging data and geological data to establish a standard data set of fracture information of the target layer; The original three-dimensional seismic data in step S1 comprises three data sets of fracture similarity attribute, dip angle and strike; in step S1, the value range of the dip angle and strike of the fracture corresponding to the original three-dimensional seismic data is searched, the imaging logging data and the geological data are used to determine the strike and dip angle of the open fracture, and the standard data set of fracture information of the target layer is established; the value range of the dip angle is 0-180 degrees, and the value range of the strike is -90-90 degrees; the dip angle of the fracture of the original three-dimensional seismic data is standardized to 0-90 degrees, if the strike is greater than 90 degrees, then the corrected dip angle is used as the standardized dip angle data; if the dip angle is less than 90 degrees, it remains unchanged, and the calculation formula of the corrected dip angle is as follows: B = 180°-A In the formula, B is the corrected dip angle, °; A is the original dip angle, °; The strike of the fracture of the original three-dimensional seismic data is standardized to 0-90 degrees, if the strike is less than 0 degrees, then the first corrected strike is used as the standardized strike data; if the strike is greater than 0 degrees, then the second corrected strike is used as the standardized strike data, and the calculation formulas of the first corrected strike and the second corrected strike are as follows: C = 90°+E In the formula, C is the first corrected strike, °; E is the original strike, °; D = 90°-E In the formula, D is the second corrected strike, °; E is the original strike, °; The dip angle and strike of the fracture of the imaging logging data are standardized to 0-90 degrees, if the dip angle and strike of the open fracture of the imaging logging data are in different set ranges, then the corresponding data in the fracture information standardization data set is assigned as the open fracture; otherwise, it is a closed fracture, and the set range is set according to the actual situation of the region; The fracture similarity attribute data of the original three-dimensional seismic data is preprocessed, when the calculated fracture similarity attribute is left-biased, the calculation formula of the preprocessing is as follows: likelihood = (1 - semblance 8 ) 2 (1) In the formula, likelihood is the similarity attribute value, semblance is the skewness; When the calculated fracture similarity attribute is right-biased, the calculation formula of the preprocessing is as follows: Step S2: discriminating the standard data set of fracture information of the target layer, retaining the value of the data point consistent with the open fracture, and establishing a quantitative modeling data set of the open fracture; Step S3: combining reservoir seismic inversion, merging the quantitative modeling data set of the open fracture, and obtaining the open fracture density of the reservoir.

2. The reservoir opening fracture prediction method of claim 1, wherein, In step S2, the logistic logistic binary machine learning discrimination program is used to discriminate the open fracture of the standard data set of fracture information of the target layer.

3. The reservoir opening fracture prediction method of claim 1, wherein, In step S3, the reservoir inversion result is combined to filter invalid mudstone, retain the open fracture information of the reservoir, and output the quantitative modeling data set of the open fracture.

4. The reservoir opening fracture prediction method of claim 3, wherein, The impedance value less than or equal to the set value is mudstone, and the open fracture density plane distribution map is output.

Images