CN113393335A - Reservoir oil and gas prediction method and device based on multi-seismic attribute optimization - Google Patents
Reservoir oil and gas prediction method and device based on multi-seismic attribute optimization Download PDFInfo
- Publication number
- CN113393335A CN113393335A CN202010175162.4A CN202010175162A CN113393335A CN 113393335 A CN113393335 A CN 113393335A CN 202010175162 A CN202010175162 A CN 202010175162A CN 113393335 A CN113393335 A CN 113393335A
- Authority
- CN
- China
- Prior art keywords
- seismic attribute
- seismic
- attribute data
- data
- reservoir
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 52
- 238000005457 optimization Methods 0.000 title claims abstract description 32
- 230000009467 reduction Effects 0.000 claims abstract description 39
- 238000011160 research Methods 0.000 claims abstract description 32
- 238000012216 screening Methods 0.000 claims abstract description 26
- 238000005553 drilling Methods 0.000 claims abstract description 25
- 238000013145 classification model Methods 0.000 claims abstract description 10
- 238000010801 machine learning Methods 0.000 claims abstract description 10
- 238000012549 training Methods 0.000 claims abstract description 9
- 238000012545 processing Methods 0.000 claims description 19
- 229930195733 hydrocarbon Natural products 0.000 claims description 16
- 150000002430 hydrocarbons Chemical class 0.000 claims description 16
- 239000004215 Carbon black (E152) Substances 0.000 claims description 15
- 238000004590 computer program Methods 0.000 claims description 14
- 238000003860 storage Methods 0.000 claims description 9
- 238000013528 artificial neural network Methods 0.000 claims description 5
- 230000008901 benefit Effects 0.000 abstract description 10
- 239000007789 gas Substances 0.000 description 64
- 238000005516 engineering process Methods 0.000 description 13
- 238000010586 diagram Methods 0.000 description 11
- 230000008859 change Effects 0.000 description 7
- 239000004576 sand Substances 0.000 description 6
- 230000015572 biosynthetic process Effects 0.000 description 5
- 238000011161 development Methods 0.000 description 4
- 238000001914 filtration Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- VNWKTOKETHGBQD-UHFFFAOYSA-N methane Chemical compound C VNWKTOKETHGBQD-UHFFFAOYSA-N 0.000 description 4
- 239000011435 rock Substances 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 3
- 238000009826 distribution Methods 0.000 description 3
- 238000005755 formation reaction Methods 0.000 description 3
- 238000004519 manufacturing process Methods 0.000 description 3
- 239000002131 composite material Substances 0.000 description 2
- 230000002596 correlated effect Effects 0.000 description 2
- 230000008021 deposition Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 239000003345 natural gas Substances 0.000 description 2
- 230000000704 physical effect Effects 0.000 description 2
- 238000003786 synthesis reaction Methods 0.000 description 2
- 230000002349 favourable effect Effects 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000035699 permeability Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 230000001737 promoting effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/02—Agriculture; Fishing; Forestry; Mining
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01V—GEOPHYSICS; GRAVITATIONAL MEASUREMENTS; DETECTING MASSES OR OBJECTS; TAGS
- G01V1/00—Seismology; Seismic or acoustic prospecting or detecting
- G01V1/28—Processing seismic data, e.g. for interpretation or for event detection
- G01V1/30—Analysis
- G01V1/307—Analysis for determining seismic attributes, e.g. amplitude, instantaneous phase or frequency, reflection strength or polarity
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01V—GEOPHYSICS; GRAVITATIONAL MEASUREMENTS; DETECTING MASSES OR OBJECTS; TAGS
- G01V2210/00—Details of seismic processing or analysis
- G01V2210/60—Analysis
- G01V2210/63—Seismic attributes, e.g. amplitude, polarity, instant phase
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Remote Sensing (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Business, Economics & Management (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Computation (AREA)
- Tourism & Hospitality (AREA)
- Bioinformatics & Cheminformatics (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Biology (AREA)
- Marketing (AREA)
- Marine Sciences & Fisheries (AREA)
- Geology (AREA)
- Primary Health Care (AREA)
- Health & Medical Sciences (AREA)
- Mining & Mineral Resources (AREA)
- Animal Husbandry (AREA)
- Agronomy & Crop Science (AREA)
- Acoustics & Sound (AREA)
- Environmental & Geological Engineering (AREA)
- General Health & Medical Sciences (AREA)
- General Life Sciences & Earth Sciences (AREA)
- Geophysics (AREA)
- Development Economics (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Geophysics And Detection Of Objects (AREA)
Abstract
The invention discloses a reservoir oil gas prediction method and a reservoir oil gas prediction device based on multi-seismic attribute optimization, wherein the method comprises the following steps: obtaining first seismic attribute data for a region of interest, wherein the first seismic attribute data comprises: parametric data for a plurality of seismic attributes; screening second seismic attribute data which accord with preset seismic attribute conditions according to the first seismic attribute data; inputting the second seismic attribute data into a pre-trained classifier, and outputting third seismic attribute data after dimensionality reduction, wherein the classifier is a seismic attribute classification model obtained through machine learning training according to the relation between known well drilling data and seismic attributes; and performing reservoir oil and gas prediction on the research area according to the third seismic attribute data. The method utilizes the longitudinal high resolution of the logging data and the transverse high resolution of the seismic attribute data, combines the advantages of multi-seismic attribute reservoir prediction, can improve the accuracy of reservoir oil gas prediction, and can be suitable for oil gas prediction of a compact sandstone reservoir.
Description
Technical Field
The invention relates to the field of reservoir oil and gas identification, in particular to a reservoir oil and gas prediction method and device based on multi-seismic attribute optimization.
Background
This section is intended to provide a background or context to the embodiments of the invention that are recited in the claims. The description herein is not admitted to be prior art by inclusion in this section.
With the progress of seismic exploration technology, seismic attribute analysis technology is widely applied to oil and gas development. Seismic attribute analysis can obtain hidden information about lithology and reservoir properties from seismic data so that seismic interpreters can use the information to interpret geological features such as subsurface formations, lithology and hydrocarbons.
The seismic attributes are in complex relation with the physical properties of underground rocks, and the relation between the seismic attributes can be influenced by different regions, lithology and oil reservoir configuration. Because single seismic attributes have multiple resolutions and cannot well represent geological features, dimension reduction processing is carried out on multiple seismic attributes, and richer reservoir geological information can be mined by using the seismic attributes after dimension reduction processing, so that a more accurate reservoir oil and gas prediction result is obtained.
At present, due to the influence of seismic resolution and the like, the prestack inversion technology suitable for reservoir prediction with a thin low deceleration layer and high seismic resolution is not ideal for reservoir prediction results with thick low deceleration layer and low seismic resolution (for example, the oil-gas prediction coincidence rate of compact sandstone reservoirs in ancient kingdom on south threigold of the deldos basin is only sixty percent), and is difficult to meet the increasingly fine oil-gas exploration and development requirements.
Disclosure of Invention
The embodiment of the invention provides a reservoir oil and gas prediction method based on multi-seismic attribute optimization, which is used for solving the technical problems that the existing reservoir oil and gas prediction method based on a prestack inversion technology is influenced by reservoir seismic resolution and is not suitable for tight sandstone reservoir oil and gas prediction, and comprises the following steps: obtaining first seismic attribute data for a region of interest, wherein the first seismic attribute data comprises: parametric data for a plurality of seismic attributes; screening second seismic attribute data which accord with preset seismic attribute conditions according to the first seismic attribute data; inputting the second seismic attribute data into a pre-trained classifier, and outputting third seismic attribute data after dimensionality reduction, wherein the classifier is a seismic attribute classification model obtained through machine learning training according to the relation between known well drilling data and seismic attributes; and performing reservoir oil and gas prediction on the research area according to the third seismic attribute data.
The embodiment of the invention also provides a reservoir oil and gas prediction device based on multi-seismic attribute optimization, which is used for solving the technical problems that the existing reservoir oil and gas prediction method based on the prestack inversion technology is influenced by the seismic resolution of the reservoir and is not suitable for tight sandstone reservoir oil and gas prediction, and the device comprises: a seismic attribute data acquisition module configured to acquire first seismic attribute data of a study area, where the first seismic attribute data includes: parametric data for a plurality of seismic attributes; the earthquake attribute data screening module is used for screening second earthquake attribute data which accord with preset earthquake attribute conditions according to the first earthquake attribute data; the seismic attribute data dimension reduction processing module is used for inputting the second seismic attribute data into a pre-trained classifier and outputting third seismic attribute data after dimension reduction, wherein the classifier is a seismic attribute classification model obtained through machine learning training according to the relation between known well drilling data and seismic attributes; and the reservoir oil gas prediction module is used for performing reservoir oil gas prediction on the research area according to the third seismic attribute data.
The embodiment of the invention also provides computer equipment for solving the technical problems that the existing reservoir oil and gas prediction method based on the pre-stack inversion technology is influenced by the seismic resolution of the reservoir and is not suitable for tight sandstone reservoir oil and gas prediction.
The embodiment of the invention also provides a computer readable storage medium for solving the technical problems that the existing reservoir oil and gas prediction method based on the prestack inversion technology is influenced by the seismic resolution of the reservoir and is not suitable for tight sandstone reservoir oil and gas prediction, and the computer readable storage medium stores a computer program for executing the reservoir oil and gas prediction method based on multi-seismic attribute optimization.
In the embodiment of the invention, after seismic attribute data containing various seismic attributes in a research area are acquired, the seismic attribute data meeting the conditions are screened out according to the preset seismic attribute conditions, the screened seismic attribute data are input into a pre-trained classifier, the seismic attribute data after dimensionality reduction are output, and finally reservoir oil and gas prediction is carried out on the research area according to the seismic attribute data after dimensionality reduction.
According to the embodiment of the invention, the seismic attribute dimension reduction processing is realized based on the drilling control, and then the seismic attribute data after dimension reduction is utilized to predict the reservoir oil gas, the longitudinal high resolution of the logging data and the transverse high resolution of the seismic attribute data can be utilized, the advantages of multi-seismic attribute reservoir prediction are combined, the accuracy of reservoir oil gas prediction can be improved, and the method and the device can be suitable for oil gas prediction of a compact sandstone reservoir.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts. In the drawings:
FIG. 1 is a flow chart of a reservoir hydrocarbon prediction method based on multi-seismic attribute optimization according to an embodiment of the present invention;
FIG. 2 is a plan view of a minimum Poisson's ratio of 8 sections of the cassette provided in an embodiment of the present invention;
FIG. 3 is a cross plot of the box 8 segment minimum Poisson's ratio versus effective reservoir thickness provided in an embodiment of the present invention;
FIG. 4 is a planar deployment diagram of seismic attributes after box 8 segments have been reduced in dimension, as provided in an embodiment of the present invention;
FIG. 5 is a cross plot of seismic attributes and effective reservoir thickness after box 8-segment dimensionality reduction provided in an embodiment of the present invention;
FIG. 6 is a schematic diagram of a reservoir hydrocarbon prediction apparatus based on multi-seismic attribute optimization according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the embodiments of the present invention are further described in detail below with reference to the accompanying drawings. The exemplary embodiments and descriptions of the present invention are provided to explain the present invention, but not to limit the present invention.
In the description of the present specification, the terms "comprising," "including," "having," "containing," and the like are used in an open-ended fashion, i.e., to mean including, but not limited to. Reference to the description of the terms "one embodiment," "a particular embodiment," "some embodiments," "for example," etc., means that a particular feature, structure, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the application. In this specification, the schematic representations of the terms used above do not necessarily refer to the same embodiment or example. Furthermore, the particular features, structures, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. The sequence of steps involved in the embodiments is for illustrative purposes to illustrate the implementation of the present application, and the sequence of steps is not limited and can be adjusted as needed.
The embodiment of the invention provides a reservoir oil and gas prediction method based on multi-seismic attribute optimization, and FIG. 1 is a flow chart of the reservoir oil and gas prediction method based on multi-seismic attribute optimization, as shown in FIG. 1, the method comprises the following steps:
s101, first seismic attribute data of a research area are obtained, wherein the first seismic attribute data comprise: parametric data for a plurality of seismic attributes.
It should be noted that the seismic attributes are the specific measurement contents of geometric, kinematic and dynamic characteristics generated from the seismic data volume, and have a connection with underground rock physical properties in thousands of lines, and the connection between the seismic attributes is influenced by different regions, different lithologies and different reservoir configurations. However, due to the fact that single seismic attribute is high in multi-solution performance and cannot well represent geological features, seismic attribute data of a research area containing multiple seismic attributes are obtained to conduct reservoir oil and gas prediction on the research area. Alternatively, the first seismic attribute data acquired in S101 may be parameter data of a plurality of seismic attributes extracted from seismic data. It should be noted that hundreds of seismic attribute parameter data can be extracted from the seismic data.
In the embodiments of the present invention, the reservoir in the research area may be, but is not limited to, a tight sandstone reservoir, and the following embodiments are described by taking the reservoir in the south of surlygar of the berdos basin as an example.
The south of Su-Li Ge of Ordos basin has complex earth surface, thick low velocity reduction layer and low seismic data frequency; the reservoir stratum in the ancient world has the advantages of rapid transverse change, thin single sand body, low porosity, low permeability and low abundance, and belongs to a typical 'three-low gas reservoir'. Because the impedance difference between the reservoir stratum and the surrounding rock in the region is small, the reservoir stratum and the effective reservoir stratum are difficult to identify through longitudinal wave impedance; the method is suitable for the pre-stack inversion technology of an area with a thin low-deceleration layer and high seismic resolution, the oil-gas prediction effect of the area is not ideal due to the influence of the seismic resolution, the prediction coincidence rate only reaches sixty percent, and the increasingly fine exploration and development requirements are difficult to meet.
And S102, screening second seismic attribute data meeting preset seismic attribute conditions according to the first seismic attribute data.
It should be noted that, because there are usually hundreds of seismic attributes extracted from seismic data, how to select a suitable dominant seismic attribute is a primary problem, and the selection of the dominant seismic attribute in the embodiment of the present invention is mainly based on the following three principles: the first is whether the correlation of the seismic attribute with the actual drilling reservoir data is greater than a certain threshold (e.g., 50%); secondly, whether the plane spread of the seismic attributes accords with geological rules or not (reservoir spread characteristics can be preliminarily determined through analysis of early-stage drilling data and application of an inversion technology); third is whether the correlation between seismic attributes is within some preset range (e.g., greater than 60% and less than 80%).
It should be noted that on the basis of the first principle and the second principle, 12 attributes such as root mean square amplitude, instantaneous frequency, amplitude slope, amplitude arithmetic mean, quality factor, target layer peak density, AVO change rate, smooth reflection intensity, minimum velocity ratio, texture attribute, highlight body, arc length attribute and the like can be selected, and the attributes are intersected with each other to calculate the correlation, if the correlation between the two seismic attributes is less than 60%, it is indicated that one of the seismic attributes cannot reflect the geological rule; if the correlation degree between the two seismic attributes is greater than 80%, the two seismic attributes are too similar, and one of the two seismic attributes is selected.
As an alternative implementation, the above S102 may be implemented by the following steps: screening seismic attribute data with the correlation degree higher than a preset threshold value from the first seismic attribute data according to the correlation degree of the single seismic attribute data and the well drilling data; screening seismic attribute data which accord with reservoir geological feature information of a research area from the seismic attribute data with the correlation degree higher than a preset threshold value; and screening second seismic attribute data from the seismic attribute data which accord with reservoir geological feature information of the research area according to the correlation degree between the seismic attributes.
Optionally, before the seismic attribute data with the correlation degree higher than the preset threshold value is screened from the first seismic attribute data according to the correlation degree of the single seismic attribute data and the well drilling data, the reservoir hydrocarbon prediction method based on multi-seismic attribute optimization provided in the embodiment of the present invention may further include the following steps: acquiring drilling data of a research area; the parametric data for the single seismic attribute is intersected with well data for the area of interest to determine a correlation of the single seismic attribute data with the well data.
Optionally, before the seismic attribute data meeting the reservoir geological feature information of the research area is screened from the seismic attribute data with the correlation degree higher than the preset threshold, the reservoir hydrocarbon prediction method based on multi-seismic attribute optimization provided in the embodiment of the present invention may further include the following steps: and acquiring reservoir geological feature information of the research area.
Optionally, before screening the second seismic attribute data from the seismic attribute data conforming to the reservoir geological feature information of the research area according to the correlation between the seismic attributes, the reservoir hydrocarbon prediction method based on multi-seismic attribute optimization provided in the embodiment of the present invention may further include the following steps: and intersecting the parameter data of different seismic attributes to determine the correlation between the data of different seismic attributes.
And S103, inputting the second seismic attribute data into a pre-trained classifier, and outputting the third seismic attribute data after dimensionality reduction, wherein the classifier is a seismic attribute classification model obtained through machine learning training according to the relation between the known well drilling data and the seismic attributes.
It should be noted that, a single seismic attribute represents geological features from a certain aspect and includes information of many non-geological features, and therefore, it is necessary to perform dimension reduction processing on multiple seismic attributes to achieve the purpose of removing false and truly representing geological features comprehensively and truly.
The embodiment of the invention carries out dimension reduction processing (well control dominant attribute dimension reduction technology for short) on the selected dominant seismic attribute under the control of well drilling, utilizes actual well drilling data as known sample data, designs a classifier according to the condition of the known sample data, for example, the classifier is designed by utilizing the change rate of the sample data by taking sandstone thickness, porosity and the like as the sample data, divides the classification according to the change rate, establishes the relation between the well drilling data and the seismic attribute based on a neural network algorithm, so as to classify unknown samples, and enable the samples of the same class to have certain similarity and the samples of different classes to show certain difference, thereby achieving the purpose of the dimension reduction processing of the seismic attribute.
Therefore, the well control advantage attribute dimension reduction technology provided by the embodiment of the invention can well realize oil and gas prediction of a reservoir by well utilizing the existing well drilling data, utilizing the longitudinal high resolution of logging data and the transverse high resolution of seismic attribute data and combining the advantages of seismic multi-attribute reservoir prediction, and is particularly suitable for tight sandstone reservoirs.
Furthermore, the relation between the drilling data and the seismic attributes is established based on a neural network algorithm, and a classifier is designed by using an inflection point method, so that a good application effect can be obtained.
Alternatively, the classifier may be a seismic attribute classification model obtained through machine learning training based on a neural network algorithm.
And S104, performing reservoir oil and gas prediction on the research area according to the third seismic attribute data.
It should be noted that, because the seismic attribute data after the dimensionality reduction (i.e., the third seismic attribute data) can retain information of a plurality of seismic attributes before dimensionality reduction, the reservoir oil and gas prediction can be performed on the research area by using the seismic attribute data after the dimensionality reduction, so that abundant geological information can be mined, and the reservoir oil and gas distribution can be accurately identified and predicted.
As can be seen from the above, in the reservoir oil and gas prediction method based on multi-seismic attribute optimization provided in the embodiment of the present invention, after seismic attribute data including multiple seismic attributes in a research area are acquired, seismic attribute data meeting conditions are screened out according to preset seismic attribute conditions, the screened seismic attribute data are input into a pre-trained classifier, the seismic attribute data after dimensionality reduction are output, and finally, reservoir oil and gas prediction is performed on the research area according to the seismic attribute data after dimensionality reduction.
By the reservoir oil and gas prediction method based on multi-seismic attribute optimization, provided by the embodiment of the invention, the seismic attribute dimension reduction processing is realized based on the drilling control, the reservoir oil and gas is predicted by using the seismic attribute data after dimension reduction, the longitudinal high resolution of logging data and the transverse high resolution of the seismic attribute data can be utilized, the advantages of multi-seismic attribute reservoir prediction are combined, the accuracy of reservoir oil and gas prediction can be improved, and the method can be suitable for oil and gas prediction of a tight sandstone reservoir.
Taking the compact sandstone gas prediction of the ancient world in Su Li Ge south of Ordos basin as an example, the Su Li Ge south block is positioned in the west of slope of Yi shan, the main reservoir of the ancient world is 8-1 sections of a two-tier system box, the gas reservoir enrichment rule is controlled by the deposition environment of late ancient generations and the structural evolution of later stages, the reservoir formation geological condition is favorable, and the reservoir formation geological condition has exploration potential of a certain scale. The section 8 to the section 1 of the box are from delta plain to front edge deposition, and the single sand body has small scale and is mostly in a lens shape; the composite sand body has large scale and is longitudinally stacked in multiple layers. The effective reservoir is a coarse rock phase in riverway sandstone and is mainly distributed at the intersection of the lower part of riverway filling and the riverway. The effective reservoir has large transverse change and is in an isolated shape or a small-range connected shape. The thickness of the sand layer of the single river channel sand body is 3-5 meters, and the thickness of the sand layer of the composite river channel is 10-20 meters. In general, ancient reservoirs in the south of the surigran are characterized by small reservoir thickness, thin effective reservoir thickness, strong heterogeneity, and difficult reservoir and gas bearing prediction.
According to the reservoir oil and gas prediction method based on multi-seismic attribute optimization, the distribution of the high-quality sandstone reservoir is predicted based on seismic multi-attribute change synthesis, a matched seismic prediction method is formed, and reliable guarantee is provided for well position optimization.
FIGS. 2 and 3 are effective reservoir prediction results based on prestack inversion, where FIG. 2 is a box 8-segment minimum Poisson's ratio plan; FIG. 3 is a plot of box 8 section minimum Poisson's ratio versus effective reservoir thickness; as can be seen from the cross-plot, the minimum Poisson ratio is roughly negatively correlated with the effective reservoir thickness of the box 8, but the correlation degree is only 63.57 percent
FIG. 4 is a planar layout after dimension reduction processing of seismic attributes for 8 segments of the box, for characterizing the effective reservoir thickness of 8 segments of the box;
FIG. 5 is a cross plot of seismic attributes and effective reservoir thickness after box 8-segment dimensionality reduction; it can be seen from the cross plot that the seismic attributes are positively correlated with the effective reservoir thickness of the box 8, and the correlation reaches 86.7%.
As can be seen by comparing fig. 2 and fig. 4, the minimum poisson ratio is substantially similar to the overall spread form of the seismic attribute, which indicates that the thickness of the effective reservoir of the box 8 sections predicted by using the prestack inversion and the seismic attribute has higher reliability, and the actual production can be guided. As can be seen by comparing the images in the figures 3 and 5, the correlation degree of the seismic attribute after the dimensionality reduction treatment and the effective reservoir thickness is higher, the effective reservoir can be well predicted, the actual production can be guided, and the drilling coincidence rate can be improved.
Based on the same inventive concept, the embodiment of the invention also provides a reservoir hydrocarbon prediction device based on multi-seismic attribute optimization, and the device is described in the following embodiment. Because the principle of solving the problems of the embodiment of the device is similar to the reservoir oil and gas prediction method based on multi-seismic attribute optimization, the implementation of the embodiment of the device can refer to the implementation of the method, and repeated parts are not repeated.
Fig. 6 is a schematic diagram of a reservoir hydrocarbon prediction apparatus optimized based on multiple seismic attributes according to an embodiment of the present invention, and as shown in fig. 6, the apparatus may include: the system comprises a seismic attribute data acquisition module 61, a seismic attribute data screening module 62, a seismic attribute data dimension reduction processing module 63 and a reservoir oil and gas prediction module 64.
The seismic attribute data obtaining module 61 is configured to obtain first seismic attribute data of a research area, where the first seismic attribute data includes: parametric data for a plurality of seismic attributes; the seismic attribute data screening module 62 is configured to screen second seismic attribute data meeting a preset seismic attribute condition according to the first seismic attribute data; the seismic attribute data dimension reduction processing module 63 is configured to input the second seismic attribute data into a pre-trained classifier, and output third seismic attribute data after dimension reduction, where the classifier is a seismic attribute classification model obtained through machine learning training according to a relationship between known well drilling data and seismic attributes; and the reservoir oil and gas prediction module 64 is used for performing reservoir oil and gas prediction on the research area according to the third seismic attribute data.
As can be seen from the above, the reservoir oil and gas prediction device based on multi-seismic attribute optimization provided by the embodiment of the invention obtains seismic attribute data including multiple seismic attributes in a research area through the seismic attribute data obtaining module 61; screening out the seismic attribute data which meet the conditions through a seismic attribute data screening module 62 according to preset seismic attribute conditions; inputting the screened seismic attribute data into a pre-trained classifier through a seismic attribute data dimension reduction processing module 63, and outputting the dimension-reduced seismic attribute data; and performing reservoir oil and gas prediction on the research area through a reservoir oil and gas prediction module 64 according to the seismic attribute data after dimensionality reduction.
By the reservoir oil and gas prediction device based on multi-seismic attribute optimization, the seismic attribute dimension reduction processing is realized based on the drilling control, the reservoir oil and gas is predicted by using the seismic attribute data after dimension reduction, the longitudinal high resolution of logging data and the transverse high resolution of the seismic attribute data can be utilized, the advantages of multi-seismic attribute reservoir prediction are combined, the accuracy of reservoir oil and gas prediction can be improved, and the device can be suitable for oil and gas prediction of tight sandstone reservoirs.
Optionally, the reservoir hydrocarbon prediction device optimized based on multiple seismic attributes provided by the embodiment of the invention can be used for, but is not limited to, hydrocarbon prediction of tight sandstone reservoirs.
In one embodiment, the seismic attribute data filtering module 62 may be further configured to perform the following steps: screening seismic attribute data with the correlation degree higher than a preset threshold value from the first seismic attribute data according to the correlation degree of the single seismic attribute data and the well drilling data; screening seismic attribute data which accord with reservoir geological feature information of a research area from the seismic attribute data with the correlation degree higher than a preset threshold value; and screening second seismic attribute data from the seismic attribute data which accord with reservoir geological feature information of the research area according to the correlation degree between the seismic attributes.
Further, the seismic attribute data filtering module 62 may be further configured to perform the following steps: acquiring drilling data of a research area; the parametric data for the single seismic attribute is intersected with well data for the area of interest to determine a correlation of the single seismic attribute data with the well data.
Further, the seismic attribute data filtering module 62 may be further configured to perform the following steps: and acquiring reservoir geological feature information of the research area.
Further, the seismic attribute data filtering module 62 may be further configured to perform the following steps: and intersecting the parameter data of different seismic attributes to determine the correlation between the data of different seismic attributes.
Optionally, the classifier adopted by the seismic attribute data dimension reduction processing module 63 may be a seismic attribute classification model obtained through machine learning training based on a neural network algorithm.
Based on the same inventive concept, the embodiment of the invention also provides computer equipment for solving the technical problems that the existing reservoir oil and gas prediction method based on the pre-stack inversion technology is influenced by the reservoir seismic resolution and is not suitable for tight sandstone reservoir oil and gas prediction, the computer equipment comprises a memory, a processor and a computer program which is stored on the memory and can be operated on the processor, and the processor realizes the reservoir oil and gas prediction method based on multi-seismic attribute optimization according to any one of the claims when executing the computer program.
The embodiment of the invention also provides a computer readable storage medium for solving the technical problems that the existing reservoir oil and gas prediction method based on the pre-stack inversion technology is influenced by the seismic resolution of the reservoir and is not suitable for tight sandstone reservoir oil and gas prediction, and the computer readable storage medium stores a computer program for executing any one of the reservoir oil and gas prediction methods based on multi-seismic attribute optimization.
In summary, embodiments of the present invention provide a reservoir hydrocarbon prediction method, a device, a computer device, and a computer readable storage medium based on multi-seismic attribute optimization, which combine the longitudinal high resolution of log data with the lateral high resolution of seismic attribute data by using existing well data, and simultaneously predict reservoir hydrocarbon distribution based on seismic multi-attribute change synthesis, so that reservoir hydrocarbon prediction can be better performed on tight sandstone, a matching seismic prediction method is formed, and reliable guarantee can be provided for well location optimization.
The reservoir oil and gas prediction method based on multi-seismic attribute optimization, which is provided by the embodiment of the invention, is applied to natural gas exploration of compact sandstone thin reservoirs in ancient China in the Weldos basin Suligong region, 40 well positions are preferably developed and 30 wells are drilled in total from 1 month in 2018 to 12 months in 2018, wherein 26 wells of I + II wells account for 86.7 percent. And 2 wells obtain million high-yield industrial gas flows, and compared with pre-stack inversion prediction, the yield is improved by 23.13%. Therefore, the reservoir oil gas prediction method based on multi-seismic attribute optimization provided by the embodiment of the invention can greatly boost the well position optimization success rate, bring huge economic benefits for oil field development and has important significance for promoting dense sandstone exploration and searching natural gas exploration and succession fields.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
The above-mentioned embodiments are intended to illustrate the objects, technical solutions and advantages of the present invention in further detail, and it should be understood that the above-mentioned embodiments are only exemplary embodiments of the present invention, and are not intended to limit the scope of the present invention, and any modifications, equivalent substitutions, improvements and the like made within the spirit and principle of the present invention should be included in the scope of the present invention.
Claims (10)
1. A reservoir oil and gas prediction method based on multi-seismic attribute optimization is characterized by comprising the following steps:
obtaining first seismic attribute data for a region of interest, wherein the first seismic attribute data comprises: parametric data for a plurality of seismic attributes;
screening second seismic attribute data which accord with preset seismic attribute conditions according to the first seismic attribute data;
inputting the second seismic attribute data into a pre-trained classifier, and outputting third seismic attribute data after dimensionality reduction, wherein the classifier is a seismic attribute classification model obtained through machine learning training according to the relation between known well drilling data and seismic attributes;
and performing reservoir oil and gas prediction on the research area according to the third seismic attribute data.
2. The method of claim 1, wherein screening second seismic attribute data that meet a predetermined seismic attribute condition based on the first seismic attribute data comprises:
screening seismic attribute data with the correlation degree higher than a preset threshold value from the first seismic attribute data according to the correlation degree of the single seismic attribute data and the well drilling data;
screening seismic attribute data which accord with reservoir geological feature information of the research area from the seismic attribute data with the correlation degree higher than a preset threshold value;
and screening the second seismic attribute data from the seismic attribute data which accord with the reservoir geological feature information of the research area according to the correlation degree between the seismic attributes.
3. The method of claim 2, wherein prior to screening seismic attribute data from the first seismic attribute data for a correlation above a predetermined threshold based on a correlation of the single seismic attribute data with well data, the method further comprises:
acquiring drilling data for the region of interest;
the parametric data for the single seismic attribute is intersected with the well data for the study area to determine a correlation of the single seismic attribute data with the well data.
4. The method of claim 1, wherein prior to screening seismic attribute data that corresponds to reservoir geologic profile information for the study area from seismic attribute data having a correlation above a predetermined threshold, the method further comprises:
and acquiring reservoir geological feature information of the research area.
5. The method of claim 1, wherein prior to screening the second seismic attribute data from seismic attribute data that corresponds to reservoir geologic feature information for the study region based on a correlation between seismic attributes, the method further comprises:
and intersecting the parameter data of different seismic attributes to determine the correlation between the data of different seismic attributes.
6. The method of claim 1, wherein the classifier is a seismic attribute classification model trained by machine learning based on neural network algorithms.
7. The method of any one of claims 1 to 6, wherein the reservoir of the study area is a tight sandstone reservoir.
8. A reservoir hydrocarbon prediction device based on multiple seismic attribute optimization, comprising:
a seismic attribute data acquisition module configured to acquire first seismic attribute data of a study area, where the first seismic attribute data includes: parametric data for a plurality of seismic attributes;
the seismic attribute data screening module is used for screening second seismic attribute data which accord with a preset seismic attribute condition according to the first seismic attribute data;
the seismic attribute data dimension reduction processing module is used for inputting the second seismic attribute data into a pre-trained classifier and outputting third seismic attribute data after dimension reduction, wherein the classifier is a seismic attribute classification model obtained through machine learning training according to the relation between known well drilling data and seismic attributes;
and the reservoir oil and gas prediction module is used for performing reservoir oil and gas prediction on the research area according to the third seismic attribute data.
9. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor when executing the computer program implements the method for reservoir hydrocarbon prediction optimized based on multiple seismic attributes of any of claims 1 to 7.
10. A computer readable storage medium storing a computer program for executing the method for reservoir hydrocarbon prediction based on multiple seismic attribute optimization according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010175162.4A CN113393335A (en) | 2020-03-13 | 2020-03-13 | Reservoir oil and gas prediction method and device based on multi-seismic attribute optimization |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010175162.4A CN113393335A (en) | 2020-03-13 | 2020-03-13 | Reservoir oil and gas prediction method and device based on multi-seismic attribute optimization |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113393335A true CN113393335A (en) | 2021-09-14 |
Family
ID=77615922
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010175162.4A Pending CN113393335A (en) | 2020-03-13 | 2020-03-13 | Reservoir oil and gas prediction method and device based on multi-seismic attribute optimization |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113393335A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20220187484A1 (en) * | 2020-12-11 | 2022-06-16 | Landmark Graphics Corporation | Subsurface fluid-type likelihood using explainable machine learning |
| CN115657132A (en) * | 2022-12-29 | 2023-01-31 | 成都捷科思石油天然气技术发展有限公司 | Reservoir prediction method and system based on machine learning |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102798892A (en) * | 2011-05-27 | 2012-11-28 | 中国石油天然气集团公司 | Method for extracting and analyzing effective reservoirs by utilizing converted wave attributes |
| CN106707340A (en) * | 2016-12-13 | 2017-05-24 | 中国石油天然气股份有限公司大港油田分公司 | Method for predicting volcanic rock facies |
| CN108732620A (en) * | 2018-03-09 | 2018-11-02 | 山东科技大学 | A kind of non-supervisory multi-wave seismic oil and gas reservoir prediction technique under supervised learning |
| CN108830421A (en) * | 2018-06-21 | 2018-11-16 | 中国石油大学(北京) | The gas distribution prediction method and device of tight sandstone reservoir |
| CN109425900A (en) * | 2017-09-05 | 2019-03-05 | 中国石油化工股份有限公司 | A kind of Seismic Reservoir Prediction method |
| CN110824563A (en) * | 2019-10-21 | 2020-02-21 | 中国海洋石油集团有限公司 | Reservoir lithology prediction method based on Xgboost algorithm |
-
2020
- 2020-03-13 CN CN202010175162.4A patent/CN113393335A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102798892A (en) * | 2011-05-27 | 2012-11-28 | 中国石油天然气集团公司 | Method for extracting and analyzing effective reservoirs by utilizing converted wave attributes |
| CN106707340A (en) * | 2016-12-13 | 2017-05-24 | 中国石油天然气股份有限公司大港油田分公司 | Method for predicting volcanic rock facies |
| CN109425900A (en) * | 2017-09-05 | 2019-03-05 | 中国石油化工股份有限公司 | A kind of Seismic Reservoir Prediction method |
| CN108732620A (en) * | 2018-03-09 | 2018-11-02 | 山东科技大学 | A kind of non-supervisory multi-wave seismic oil and gas reservoir prediction technique under supervised learning |
| CN108830421A (en) * | 2018-06-21 | 2018-11-16 | 中国石油大学(北京) | The gas distribution prediction method and device of tight sandstone reservoir |
| CN110824563A (en) * | 2019-10-21 | 2020-02-21 | 中国海洋石油集团有限公司 | Reservoir lithology prediction method based on Xgboost algorithm |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20220187484A1 (en) * | 2020-12-11 | 2022-06-16 | Landmark Graphics Corporation | Subsurface fluid-type likelihood using explainable machine learning |
| US11630224B2 (en) * | 2020-12-11 | 2023-04-18 | Landmark Graphics Corporation | Subsurface fluid-type likelihood using explainable machine learning |
| CN115657132A (en) * | 2022-12-29 | 2023-01-31 | 成都捷科思石油天然气技术发展有限公司 | Reservoir prediction method and system based on machine learning |
| CN115657132B (en) * | 2022-12-29 | 2023-03-10 | 成都捷科思石油天然气技术发展有限公司 | Reservoir prediction method and system based on machine learning |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Raeesi et al. | Classification and identification of hydrocarbon reservoir lithofacies and their heterogeneity using seismic attributes, logs data and artificial neural networks | |
| CN106842307B (en) | Reservoir stratum fine prediction method based on waveform classification and retrieval under forward constraint | |
| CN106556866B (en) | A method of using rock physics template to reservoir quantitative interpretation | |
| Yasin et al. | Estimation of petrophysical parameters from seismic inversion by combining particle swarm optimization and multilayer linear calculator | |
| Chehrazi et al. | Pore-facies as a tool for incorporation of small-scale dynamic information in integrated reservoir studies | |
| CN105005097A (en) | Method for comprehensive recognition of igneous rocks by employing gravity, magnetism, electromagnetism, and earthquake data | |
| CN105116449B (en) | A kind of recognition methods of weak reflection reservoir | |
| CN106597543A (en) | Stratigraphic sedimentary facies division method | |
| CN105842733A (en) | Shale reservoir earthquake identification method | |
| CN113393335A (en) | Reservoir oil and gas prediction method and device based on multi-seismic attribute optimization | |
| CN109270578A (en) | Beach shallow sea law quality reservoirs rolling development method | |
| Imam et al. | Mapping the geological structures in the Ras El Ush field (Gulf of Suez, Egypt), based on seismic interpretation and 3D modeling techniques | |
| CN112505754A (en) | Method for collaborative partitioning sedimentary microfacies by well-seismic based on high-precision sequence grid model | |
| CN107132574A (en) | A kind of Forecasting Methodology of marine bed clastic rock lithology combination | |
| Iltaf et al. | Facies and petrophysical modeling of Triassic Chang 6 tight sandstone reservoir, Heshui oil field, Ordos basin, China | |
| Liu et al. | Geostatistical modeling for fine reservoir description of Wei2 block of Weicheng oilfield, Dongpu depression, China | |
| CN103278852B (en) | Utilize the method for seismic data volume waveform configuration characteristic model predicting oil/gas | |
| Jika et al. | Application of geostatistics in facies modeling of Reservoir-E,“Hatch Field” offshore Niger Delta Basin, Nigeria | |
| Zhang et al. | Architecture characteristics and characterization methods of fault-controlled karst reservoirs: A case study of the Shunbei 5 fault zone in the Tarim Basin, China | |
| Dai et al. | Stratigraphic automatic correlation using SegNet semantic segmentation model | |
| CN112379435A (en) | Phase-controlled karst type seam hole aggregate carving method and device | |
| CN115880455A (en) | Three-dimensional intelligent interpolation method based on deep learning | |
| Abdolahi et al. | Improving the 3D facies model with the seismic-derived log volumes: a case study from the Asmari Formation in the Hendijan Field, southwest Iran | |
| CN109581489B (en) | Nested seismic facies extraction method and system | |
| Shi et al. | Improved Unet in lithology identification of coal measure Strata |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |