CN117471537A - High-quality reservoir depicting method based on machine learning - Google Patents
High-quality reservoir depicting method based on machine learning Download PDFInfo
- Publication number
- CN117471537A CN117471537A CN202210858822.8A CN202210858822A CN117471537A CN 117471537 A CN117471537 A CN 117471537A CN 202210858822 A CN202210858822 A CN 202210858822A CN 117471537 A CN117471537 A CN 117471537A
- Authority
- CN
- China
- Prior art keywords
- curve
- logging curve
- research area
- sensitive
- quality 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
- 238000010801 machine learning Methods 0.000 title claims abstract description 37
- 238000000034 method Methods 0.000 title claims abstract description 35
- 238000009826 distribution Methods 0.000 claims abstract description 45
- 229910052500 inorganic mineral Inorganic materials 0.000 claims abstract description 30
- 239000011707 mineral Substances 0.000 claims abstract description 30
- 238000012512 characterization method Methods 0.000 claims abstract description 25
- 238000003860 storage Methods 0.000 claims abstract description 10
- 238000005457 optimization Methods 0.000 claims abstract description 9
- 238000011160 research Methods 0.000 claims description 60
- 239000011435 rock Substances 0.000 claims description 18
- 238000004590 computer program Methods 0.000 claims description 13
- 238000013528 artificial neural network Methods 0.000 claims description 12
- 238000004458 analytical method Methods 0.000 claims description 11
- 238000011835 investigation Methods 0.000 claims description 11
- 238000012706 support-vector machine Methods 0.000 claims description 5
- 238000013211 curve analysis Methods 0.000 claims description 3
- 238000011156 evaluation Methods 0.000 abstract description 2
- 230000000875 corresponding effect Effects 0.000 description 15
- 238000012545 processing Methods 0.000 description 11
- 238000010586 diagram Methods 0.000 description 10
- 230000000704 physical effect Effects 0.000 description 7
- 230000008569 process Effects 0.000 description 7
- 230000006870 function Effects 0.000 description 6
- 239000004576 sand Substances 0.000 description 6
- 238000004891 communication Methods 0.000 description 4
- 230000002093 peripheral effect Effects 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- 238000011161 development Methods 0.000 description 3
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 3
- OYPRJOBELJOOCE-UHFFFAOYSA-N Calcium Chemical compound [Ca] OYPRJOBELJOOCE-UHFFFAOYSA-N 0.000 description 2
- 239000011575 calcium Substances 0.000 description 2
- 229910052791 calcium Inorganic materials 0.000 description 2
- 238000005520 cutting process Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000035945 sensitivity Effects 0.000 description 2
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 238000003556 assay Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 239000007795 chemical reaction product Substances 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 230000008878 coupling Effects 0.000 description 1
- 238000010168 coupling process Methods 0.000 description 1
- 238000005859 coupling reaction Methods 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 229910021389 graphene Inorganic materials 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000011022 operating instruction Methods 0.000 description 1
- 239000011148 porous material Substances 0.000 description 1
- 238000004321 preservation Methods 0.000 description 1
- 239000000047 product Substances 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000001228 spectrum Methods 0.000 description 1
- 238000011269 treatment regimen Methods 0.000 description 1
Classifications
-
- 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
- G01V1/301—Analysis for determining seismic cross-sections or geostructures
-
- 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
- G01V1/36—Effecting static or dynamic corrections on records, e.g. correcting spread; Correlating seismic signals; Eliminating effects of unwanted energy
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01V—GEOPHYSICS; GRAVITATIONAL MEASUREMENTS; DETECTING MASSES OR OBJECTS; TAGS
- G01V1/00—Seismology; Seismic or acoustic prospecting or detecting
- G01V1/40—Seismology; Seismic or acoustic prospecting or detecting specially adapted for well-logging
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01V—GEOPHYSICS; GRAVITATIONAL MEASUREMENTS; DETECTING MASSES OR OBJECTS; TAGS
- G01V2210/00—Details of seismic processing or analysis
- G01V2210/50—Corrections or adjustments related to wave propagation
- G01V2210/51—Migration
- G01V2210/512—Pre-stack
-
- 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
- G01V2210/61—Analysis by combining or comparing a seismic data set with other data
- G01V2210/616—Data from specific type of measurement
- G01V2210/6161—Seismic or acoustic, e.g. land or sea measurements
-
- 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
- G01V2210/61—Analysis by combining or comparing a seismic data set with other data
- G01V2210/616—Data from specific type of measurement
- G01V2210/6169—Data from specific type of measurement using well-logging
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/02—Reliability analysis or reliability optimisation; Failure analysis, e.g. worst case scenario performance, failure mode and effects analysis [FMEA]
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Remote Sensing (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Physics & Mathematics (AREA)
- Acoustics & Sound (AREA)
- Environmental & Geological Engineering (AREA)
- Geology (AREA)
- General Life Sciences & Earth Sciences (AREA)
- Geophysics (AREA)
- Evolutionary Computation (AREA)
- Theoretical Computer Science (AREA)
- Artificial Intelligence (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Computer Hardware Design (AREA)
- Geometry (AREA)
- General Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Geophysics And Detection Of Objects (AREA)
Abstract
The invention provides a machine learning-based high-quality reservoir characterization method, a machine learning-based high-quality reservoir characterization device, a computer-readable storage medium and electronic equipment. The method includes determining a sensitive log for identifying a premium reservoir; on the basis of multi-mineral optimization evaluation, a petrophysical parameter curve is deduced by developing petrophysical modeling, and then an elastic parameter curve is obtained; on the basis of determining the corresponding relation between the elastic parameter curve and the sensitive logging curve through machine learning, analyzing the probability distribution of the sensitive logging curve of the high-quality reservoir; obtaining an elastic parameter body by carrying out prestack statistical inversion under phase control; then, according to the corresponding relation between the elastic parameter curve and the sensitive logging curve, a corresponding sensitive logging curve body is obtained by utilizing the elastic parameter body; and finally, developing the distribution depiction of the high-quality reservoir according to the probability distribution of the sensitive well logging curve of the high-quality reservoir and the sensitive well logging curve body.
Description
Technical Field
The invention relates to the technical field of oil and gas exploration logging, in particular to a high-quality reservoir characterization method, device, computer readable storage medium and electronic equipment based on machine learning, which are suitable for tight sandstone.
Background
For tight sandstone gas reservoirs, high-quality reservoirs are the key of high and stable production of gas wells, so that the distribution of the high-quality reservoirs is clear and is critical to the exploration and development of tight oil and gas reservoirs; however, the compact sandstone has poor overall physical properties, strong heterogeneity and high-quality reservoir characterization difficulty.
The conventional method for describing the high-quality reservoir comprises seismic attribute analysis, wave impedance inversion and the like, wherein the seismic attribute is used for describing the sand body with a certain effect, but the sand body comprises a compact layer with poor physical properties, so the attribute cannot be used for describing the reservoir. The wave impedance inversion is to develop the description of the high-quality reservoir based on the difference of the elastic parameters of the high-quality reservoir and the surrounding rock, so that the differences of mineral components, physical properties and the like of the high-quality reservoir and the surrounding rock of the compact sandstone are often small, and the difference of the elastic parameters is small, so that the high-quality reservoir and the surrounding rock have certain overlapping, even serious overlapping, on an elastic parameter intersection diagram, and the reliability of the description of the high-quality reservoir is to be improved by directly utilizing the parameters.
Aiming at the problems, li Long and the like (2019) develop the prediction of the sand body of the concave water-sinking sand section of the western Liaoning through the reconstruction of the GR curve and the wave impedance curve, and the method can only describe the distribution of sandstone and cannot describe the distribution of high-quality reservoirs in the sandstone. The method comprises the steps of obtaining a wave impedance data volume through well constraint seismic inversion by using a Gangda wary or the like (2020); then, carrying out geostatistical GR inversion to obtain lithology data bodies, and calculating the lithology data bodies and the wave impedance data bodies to eliminate lithology influence; and finally, obtaining a porosity inversion data body by utilizing the relation between the porosity and the wave impedance, and describing whether the sand-temple group compact sandstone reservoir is in the QL area, thick and thin and good or not. In most cases, the dense sandstone porosity and the wave impedance are generally correlated, so that the reliability of the porosity obtained by using the wave impedance antibody is low. The middle petrochemical exploration branch company (2017) develops dense sandstone reservoirs and gas-containing predictions of the river groups of the Jianjia in the northeast areas of Sichuan by a successive approximation and multiple dimension reduction method, firstly, utilizes an impedance inversion body and a GR inversion body to distinguish sandstone and mudstone, and clearly determines sandstone distribution; then, separating a reservoir layer from a compact layer in the sandstone by using elastic parameters such as poisson ratio and impedance or reconstructed parameters; finally, the gas layer and the water layer are separated by elastic parameters such as density, impedance and the like or parameters of partial reconstruction. By analyzing the elastic parameter intersection graph of the sandstone and the mudstone, the reservoir and the compact layer and the air layer and the water layer, the sandstone and the mudstone, the reservoir and the compact layer, and the air layer and the water layer still have certain overlapping, so the reliability of the characterization of the high-quality reservoir by the method needs to be improved.
Disclosure of Invention
In view of the foregoing, embodiments of the present invention provide a method, an apparatus, a computer-readable storage medium, and an electronic device for characterizing a high-quality reservoir based on machine learning.
In a first aspect, an embodiment of the present invention provides a method for characterizing a high-quality reservoir based on machine learning, including:
s100, acquiring a pre-stack seismic trace set of a research area;
s200, acquiring a logging curve of a research area, and determining a sensitive logging curve which can be used for identifying a high-quality reservoir of the research area by analyzing intersection conditions of the logging curve;
s300, determining the mineral composition and the content of the mineral composition of a research area, and obtaining an elastic parameter curve of the research area based on a petrophysical parameter curve of a forward research area through petrophysical modeling based on the mineral composition and the content of the mineral composition;
s400, establishing a corresponding relation between the sensitive well logging curve and the elastic parameter curve by using a deep neural network algorithm, calculating a corresponding sensitive well logging curve from the rock physical parameter curve of the well drilled in the research area based on the corresponding relation, and determining probability distribution of the sensitive well logging curve of the high-quality reservoir by analyzing intersection conditions of the sensitive well logging curve;
s500, acquiring an elastic parameter body of a research area by utilizing a pre-stack seismic trace set of the research area through pre-stack statistical inversion under phase control, and inverting the sensitive well logging curve body by utilizing the elastic parameter body based on the corresponding relation between the sensitive well logging curve and the elastic parameter curve;
and S600, judging whether each position on the sensitive well logging curve body is a high-quality reservoir according to probability distribution of the sensitive well logging curve of the high-quality reservoir, so as to determine the distribution condition of the high-quality reservoir in the research area.
According to an embodiment of the present invention, in the step S100 described above, after acquiring the pre-stack seismic trace set of the investigation region and before utilizing the pre-stack seismic trace set of the investigation region, the quality of the pre-stack seismic trace set is optimized.
In accordance with an embodiment of the present invention, in the step S200 described above, the sensitive logs that can be used to identify good quality reservoirs of the investigation region are natural Gamma (GR) logs and deep lateral Resistivity (RD) logs.
According to an embodiment of the present invention, in the step S300, the determining the composition of the mineral components of the investigation region and the content thereof includes:
and establishing a multi-mineral optimization model of the research area, and determining the mineral composition and the content of the mineral composition of the research area by using the multi-mineral optimization model.
In the step S300, the elastic parameter curves include longitudinal wave velocity, transverse wave velocity, vp/Vs, pull Mei Jishu and poisson' S ratio elastic parameter curves.
In the step S400, the deep neural network algorithm includes a FVR-based support vector machine deep neural network algorithm; the probability distribution of the sensitive logging curve of the high-quality reservoir is Bayesian probability distribution.
According to an embodiment of the present invention, in the step S500, the obtaining, by using the pre-stack seismic trace set of the investigation region, the elastic parameter body of the investigation region through the phase-controlled pre-stack statistical inversion includes:
determining sand-ground ratio distribution by utilizing a pre-stack seismic trace set of a research area and a sedimentary microphase map and a pre-stack deterministic inversion longitudinal wave impedance plane map of a well sand-ground ratio machine learning geological sketch;
and carrying out prestack statistical inversion under the constraint condition of sand-ground ratio distribution to obtain the elastic parameter body of the research area.
In a second aspect, the present invention further provides a machine learning-based high-quality reservoir characterization and identification device, which is characterized by comprising:
the pre-stack data acquisition module is used for acquiring a pre-stack seismic trace set of the research area;
the logging curve analysis module is used for acquiring a logging curve of the research area and determining a sensitive logging curve which can be used for identifying a high-quality reservoir of the research area by analyzing intersection conditions of the logging curve;
the elastic parameter deduction module is used for determining the composition and the content of mineral components in the research area, based on the composition and the content of the mineral components, forward modeling a petrophysical parameter curve of the research area through petrophysical modeling, and obtaining an elastic parameter curve of the research area based on the petrophysical parameter curve;
the reservoir probability analysis module is used for establishing a corresponding relation between the sensitive well logging curve and the elastic parameter curve by using a deep neural network algorithm, calculating a corresponding sensitive well logging curve from the rock physical parameter curve of the well drilled in the research area based on the corresponding relation, and determining probability distribution of the sensitive well logging curve of the high-quality reservoir by analyzing intersection conditions of the sensitive well logging curve;
the sensitive well logging curve inversion module is used for obtaining an elastic parameter body of the research area through prestack statistics inversion under phase control by utilizing a prestack seismic trace set of the research area, and inverting the sensitive well logging curve body by utilizing the elastic parameter body based on the corresponding relation between the sensitive well logging curve and the elastic parameter curve;
and the reservoir distribution determining module is used for judging whether each position on the sensitive well logging curve body is a high-quality reservoir according to probability distribution of the sensitive well logging curve of the high-quality reservoir, so as to determine the distribution condition of the high-quality reservoir in the research area.
In a third aspect, an embodiment of the present invention provides a computer-readable storage medium, on which a computer program is stored, which program, when executed by a processor, implements a method for machine learning based quality reservoir characterization as described in the first aspect above.
In a fourth aspect, an embodiment of the present invention provides an electronic device, including:
a processor;
a memory for storing the processor-executable instructions;
wherein the processor is configured to execute the instructions to implement a machine learning based quality reservoir characterization method as described in the first aspect.
Compared with the prior art, the technical scheme of the invention has the following beneficial effects:
1) According to the high-quality reservoir characterization method based on machine learning, parameters for distinguishing the high-quality reservoir of the tight sandstone from surrounding rocks are expanded through the sensitive logging curve of the machine learning, and the characterization precision of the high-quality reservoir of the tight sandstone is improved;
2) According to the high-quality reservoir depicting method based on machine learning, sand bodies do not need to be depicted first, and then the reservoirs are depicted in the sand bodies, so that sensitive logging curves and elastic parameters of the high-quality reservoirs can be directly determined, and distribution of the sensitive logging curves and elastic parameters of the high-quality reservoirs can be depicted;
3) The method for describing the high-quality reservoir based on machine learning provided by the invention not only can accurately describe the high-quality reservoir, but also can directly describe the distribution of the gas layer on the basis of determining the sensitive logging curve and the elastic parameter of the gas layer, and has wide application.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a workflow diagram of a method for machine learning based characterization of a premium reservoir according to an embodiment of the present invention;
fig. 2 is a schematic diagram of the composition structure of an electronic device according to a fifth embodiment of the present invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are some embodiments of the present invention, but not all embodiments of the present invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Example 1
In consideration of the problem that elastic parameters are difficult to accurately distinguish high-quality reservoirs and surrounding rocks in tight sandstone, the invention obtains a reservoir sensitive logging curve through elastic parameter machine learning, and combines the sensitive logging curve and the elastic parameters to distinguish the reservoirs and the surrounding rocks, so as to accurately describe high-quality reservoir distribution. Can be popularized and applied to exploration and development of tight oil and gas reservoirs.
As shown in FIG. 1, the machine learning-based high-quality reservoir characterization method provided by the embodiment of the invention mainly comprises the following steps of adopting a support vector machine (FVR) deep neural network algorithm, expanding parameters for identifying a high-quality reservoir of tight sandstone, and improving the reservoir characterization precision.
The invention is realized by the following steps:
based on the quality analysis of the pre-stack seismic trace set, a targeted optimization processing technology is adopted to improve the quality of the pre-stack seismic trace set.
And step two, clearly distinguishing sensitive logging curves of the high-quality reservoir and the surrounding rock through intersection analysis of the high-quality reservoir and the surrounding rock logging curves.
Step three, a multi-mineral optimization model is established, and the mineral composition and the content of the compact sandstone are defined; on the basis, rock physical modeling is carried out, rock physical parameters such as longitudinal wave speed, transverse wave speed, density and the like of a single well are accurately and positively performed, and then various elastic parameters are obtained.
Step four, a deep neural network algorithm based on a support vector machine is adopted to establish a nonlinear relation between a sensitive logging curve (determined by the step two) and an elastic parameter curve (obtained by the step three); according to the relation, a sensitive logging curve is calculated from the drilled petrophysical parameter curve, and the Bayesian probability distribution of the high-quality reservoir is determined through intersection analysis of the sensitive logging curves of the high-quality reservoir and the surrounding rock.
Fifthly, determining sand-ground ratio distribution through a sedimentary microphase map and a prestack deterministic inversion longitudinal wave impedance plane map of the sand-ground ratio machine learning geological sketch; carrying out prestack statistical inversion under the constraint of a sand-ground ratio graph to obtain elastic parameter bodies such as longitudinal wave impedance, transverse wave impedance, density and the like; and (3) calculating a high-quality reservoir sensitive logging curve body according to the nonlinear relation between the sensitive logging curve and the elastic parameter determined in the step four.
And step six, judging whether each position on the sensitive logging curve body of the high-quality reservoir is the high-quality reservoir according to the Bayesian probability distribution of the high-quality reservoir obtained in the step four, and further describing the high-quality reservoir distribution.
Example two
The three sections of the river group of the must family in the YB area are a set of calcium cuttings sandstone and conglomerate, and the porosity is mainly distributed between 1% and 3% according to the physical property data of the rock core, so that the river group is a low-pore low-permeability reservoir. The medium and coarse-grain calcium cuttings sandstone, sandy fine conglomerate and sandy fine conglomerate have good physical properties, are high-quality reservoirs, but are thin and difficult to describe. The method develops the high-quality reservoir characterization through the following process, and achieves a good effect.
Analyzing amplitude, phase and energy consistency of superimposed data and pure wave data of signal to noise ratio, multiple waves and full offset distance, effective incidence angle, frequency spectrum and amplitude preservation of the pre-stack CRP gather AVO characteristics in the YB area, clearly researching two problems of spindle-shaped energy distribution and partial remote motion correction deficiency of the pre-stack gather in the area, formulating an optimization treatment strategy of AVO rule compensation, automatic leveling and denoising filtering, and effectively improving the quality of the pre-stack gather.
And secondly, in the three-stage development of the river group of the research area, the multiple sandstone types such as sandy fine conglomerate, medium and coarse-grain calcium-chip sandstone, fine-grain calcium-chip sandstone, siltstone and the like are contained, wherein the sandy fine conglomerate, the medium and coarse-grain calcium-chip sandstone have good physical properties, and the reservoir is of high quality. According to the core sheet of the coring well and physical property assay analysis data, the logging curve values of the sandstone types and the corresponding depths identified by 13 core sheets are counted, various logging curve intersection diagrams are manufactured according to the sandstone, and GR and RD curves can be clearly identified to better identify three sections of high-quality reservoirs.
Step three, establishing a multi-mineral optimization model, and definitely defining the mineral composition of three sections of compact sandstone; on the basis, an Xu-White model is selected, and curves such as the longitudinal wave speed, the transverse wave speed, the density and the like of the drilled well are just shown, so that the consistency with the actually measured curves is better. From the analysis of the intersection of various petrophysical parameters of different types of sandstones, it can be found that a good quality reservoir cannot be well distinguished by only petrophysical parameters.
Constructing a formula for calculating GR and RD curves by using a petrophysical parameter curve by adopting multiple regression and multiple machine learning methods, further calculating the GR and RD curves, and optimizing the nonlinear relation of a sensitive logging curve and 5 elastic parameter curves of longitudinal wave speed, transverse wave speed, longitudinal and transverse wave speed ratio (Vp/Vs), pull Mei Jishu and Poisson ratio, which are established by a support vector machine depth neural network algorithm based on FVR, through evaluation of the coincidence degree of the calculated GR and RD and the measured curve; accordingly, GR and RD curves are calculated from the drilled petrophysical parameter curves, and the Bayesian probability distribution of GR and RD of the high-quality reservoir is determined through intersection analysis of GR-RD curves of the high-quality reservoir and surrounding rock.
Fifthly, determining sand-ground ratio distribution through a sedimentary microphase map and a prestack deterministic inversion longitudinal wave impedance plane map of the sand-ground ratio machine learning geological sketch; carrying out prestack statistical inversion under the constraint of sand-ground ratio to obtain longitudinal wave impedance, transverse wave impedance and density body; and (3) inverting GR and RD logging curve bodies according to the nonlinear relation between the sensitivity curve and the elastic parameter obtained in the step (4).
Step six, judging whether each position on the GR and RD curve body is a high-quality reservoir according to the Bayesian probability distribution of the high-quality reservoir obtained in the step 4, and further determining the high-quality reservoir distribution.
GR and RD can better discern the three sections of high-quality reservoirs of the must family river group in YB area, so these two log curves are chosen to invert. The sensitivity curve of the high-quality reservoir in other areas may be different from that in the YB area, and a proper curve (parameter) can be selected as an object of machine learning according to the situation, so that the high-quality reservoir is characterized.
The invention expands the parameters for identifying the high-quality reservoir and surrounding rock of the tight sandstone, improves the precision of the depiction of the high-quality reservoir in the tight sandstone, and has the coincidence rate of 86 percent with the high-quality reservoir explained by 72 well logging in a research area. The thickness of the inversion high-quality reservoir layer of different layer segments is basically consistent with the thickness of the uphole high-quality reservoir layer.
Example III
The following are examples of the apparatus of the present invention that may be used to perform the method embodiments of the present invention. For details not disclosed in the embodiments of the apparatus of the present invention, please refer to the embodiments of the method of the present invention.
The embodiment provides a high-quality reservoir characterization device based on machine learning, includes:
the pre-stack data acquisition module is used for acquiring a pre-stack seismic trace set of the research area;
the logging curve analysis module is used for acquiring a logging curve of the research area and determining a sensitive logging curve which can be used for identifying a high-quality reservoir of the research area by analyzing intersection conditions of the logging curve;
the elastic parameter deduction module is used for determining the composition and the content of mineral components in the research area, based on the composition and the content of the mineral components, forward modeling a petrophysical parameter curve of the research area through petrophysical modeling, and obtaining an elastic parameter curve of the research area based on the petrophysical parameter curve;
the reservoir probability analysis module is used for establishing a corresponding relation between the sensitive well logging curve and the elastic parameter curve by using a deep neural network algorithm, calculating a corresponding sensitive well logging curve from the rock physical parameter curve of the well drilled in the research area based on the corresponding relation, and determining probability distribution of the sensitive well logging curve of the high-quality reservoir by analyzing intersection conditions of the sensitive well logging curve;
the sensitive well logging curve inversion module is used for obtaining an elastic parameter body of the research area through prestack statistics inversion under phase control by utilizing a prestack seismic trace set of the research area, and inverting the sensitive well logging curve body by utilizing the elastic parameter body based on the corresponding relation between the sensitive well logging curve and the elastic parameter curve;
and the reservoir distribution determining module is used for judging whether each position on the sensitive well logging curve body is a high-quality reservoir according to probability distribution of the sensitive well logging curve of the high-quality reservoir, so as to describe the distribution condition of the high-quality reservoir in the research area.
Example IV
The present embodiment provides a computer-readable medium having stored thereon a computer program which, when executed by a processor, implements the steps of a machine learning based quality reservoir characterization method as described in the above embodiments.
It should be noted that, all or part of the flow of the method of the above embodiment may be implemented by a computer program, which may be stored in a computer readable storage medium and which, when executed by a processor, implements the steps of the method embodiments described above. Wherein the computer program comprises computer program code which may be in source code form, object code form, executable file or some intermediate form etc. The computer readable medium may include: any entity or device capable of carrying the computer program code, a recording medium, a U disk, a removable hard disk, a magnetic disk, an optical disk, a computer Memory, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), an electrical carrier signal, a telecommunications signal, a software distribution medium, and so forth. Of course, there are other ways of readable storage medium, such as quantum memory, graphene memory, etc. It should be noted that the computer readable medium contains content that can be appropriately scaled according to the requirements of jurisdictions in which such content is subject to legislation and patent practice, such as in certain jurisdictions in which such content is subject to legislation and patent practice, the computer readable medium does not include electrical carrier signals and telecommunication signals.
Example five
Fig. 2 is a schematic structural view of an electronic device according to an embodiment of the present invention. As shown in fig. 2, at the hardware level, the electronic device comprises a processor, optionally together with an internal bus, a network interface, a memory. The Memory may include a Memory, such as a Random-Access Memory (RAM), and may further include a non-volatile Memory (non-volatile Memory), such as at least 1 disk Memory. Of course, the electronic device may also include hardware required for other services.
The processor, network interface, and memory may be interconnected by an internal bus, which may be an ISA (Industry Standard Architecture ) bus, a PCI (PeripheralComponent Interconnect, peripheral component interconnect standard) bus, or EISA (Extended Industry StandardArchitecture ) bus, among others. The buses may be classified as address buses, data buses, control buses, etc. For ease of illustration, the figures are shown with only line segments, but not with only one bus or one type of bus.
And the memory is used for storing programs. In particular, the program may include program code including computer-operating instructions. The memory may include memory and non-volatile storage and provide instructions and data to the processor. The processor reads the corresponding computer program from the non-volatile memory into the memory and then runs. The processor executes the program stored in the memory to perform all of the steps in a machine learning based method for characterizing a good quality reservoir.
The communication bus mentioned by the above devices may be a peripheral component interconnect standard (Peripheral Component Interconnect, PCI) bus or an extended industry standard architecture (Extended Industry Standard Architecture, EISA) bus, etc. The communication bus may be classified as an address bus, a data bus, a control bus, or the like. For ease of illustration, the figures are shown with only one bold line, but not with only one bus or one type of bus. The communication interface is used for communication between the electronic device and other devices.
The bus includes hardware, software, or both for coupling the above components to each other. For example, the bus may include an Accelerated Graphics Port (AGP) or other graphics bus, an Enhanced Industry Standard Architecture (EISA) bus, a Front Side Bus (FSB), a HyperTransport (HT) interconnect, an Industry Standard Architecture (ISA) bus, an infiniband interconnect, a Low Pin Count (LPC) bus, a memory bus, a micro channel architecture (MCa) bus, a Peripheral Component Interconnect (PCI) bus, a PCI-Express (PCI-X) bus, a Serial Advanced Technology Attachment (SATA) bus, a video electronics standards association local (VLB) bus, or other suitable bus, or a combination of two or more of the above. The bus may include one or more buses, where appropriate. Although embodiments of the invention have been described and illustrated with respect to a particular bus, the invention contemplates any suitable bus or interconnect.
The Memory may include random access Memory (Random Access Memory, RAM) or may include Non-Volatile Memory (NVM), such as at least one disk Memory. Optionally, the memory may also be at least one memory device located remotely from the aforementioned processor.
The memory may include mass storage for data or instructions. By way of example, and not limitation, the memory may comprise a Hard Disk Drive (HDD), floppy Disk Drive, flash memory, optical Disk, magneto-optical Disk, magnetic tape, or universal serial bus (Universal Serial Bus, USB) Drive, or a combination of two or more of the foregoing. The memory may include removable or non-removable (or fixed) media, where appropriate. In a particular embodiment, the memory is a non-volatile solid state memory. In a particular embodiment, the memory includes Read Only Memory (ROM). The ROM may be mask programmed ROM, programmable ROM (PROM), erasable PROM (EPROM), electrically Erasable PROM (EEPROM), electrically rewritable ROM (EAROM), or flash memory, or a combination of two or more of these, where appropriate.
The processor may be a general-purpose processor, including a central processing unit (Central Processing Unit, CPU), a network processor (Network Processor, NP), etc.; but also digital signal processors (Digital Signal Processing, DSP), application specific integrated circuits (Application Specific Integrated Circuit, ASIC), field programmable gate arrays (Field-Programmable Gate Array, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.
It should be noted that, for convenience and brevity of description, only the above-described division of the functional units and modules is illustrated, and in practical application, the above-described functional allocation may be performed by different functional units and modules according to needs, that is, the internal structure of the apparatus is divided into different functional units or modules to perform all or part of the functions described above. The functional units and modules in the embodiment may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit, where the integrated units may be implemented in a form of hardware or a form of a software functional unit. In addition, the specific names of the functional units and modules are only for distinguishing from each other, and are not used for limiting the protection scope of the present invention. The specific working process of the units and modules in the above system may refer to the corresponding process in the foregoing method embodiment, which is not described herein again.
The apparatus, device, system, module or unit described in the above embodiments may be implemented in particular by a computer chip or entity or by a product having a certain function. One typical implementation is a computer. In particular, the computer may be, for example, a personal computer, a laptop computer, a car-mounted human-computer interaction device, a cellular telephone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.
Although the invention provides method operational steps as described in the examples or flowcharts, more or fewer operational steps may be included based on conventional or non-inventive means. The order of steps recited in the embodiments is merely one way of performing the order of steps and does not represent a unique order of execution. When implemented in an actual device or end product, the instructions may be executed sequentially or in parallel (e.g., in a parallel processor or multi-threaded processing environment, or even in a distributed data processing environment) as illustrated by the embodiments or by the figures.
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 flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations 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.
It should be noted that in this document relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
In this specification, each embodiment is described in a related manner, and identical and similar parts of each embodiment are all referred to each other, and each embodiment mainly describes differences from other embodiments. In particular, for apparatus, electronic devices, and readable storage medium embodiments, since they are substantially similar to method embodiments, the description is relatively simple, and references to parts of the description of method embodiments are only required.
The foregoing description is only of the preferred embodiments of the present invention and is not intended to limit the scope of the present invention. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention are included in the protection scope of the present invention.
Claims (10)
1. The high-quality reservoir depicting method based on machine learning is characterized by comprising the following steps of:
s100, acquiring a pre-stack seismic trace set of a research area;
s200, acquiring a logging curve of a research area, analyzing the difference between a high-quality reservoir logging curve and a non-reservoir logging curve through intersection of the logging curves, and determining a sensitive logging curve of the high-quality reservoir which can be used for identifying the research area;
s300, determining the mineral composition and the content of the mineral composition of a research area, and obtaining an elastic parameter curve of the research area based on a petrophysical parameter curve of a forward research area through petrophysical modeling based on the mineral composition and the content of the mineral composition;
s400, establishing a corresponding relation between the sensitive well logging curve and the elastic parameter curve by using a deep neural network algorithm, calculating a corresponding sensitive well logging curve from the elastic parameter curve of the well drilled in the research area based on the corresponding relation, and determining probability distribution of the sensitive well logging curve of the high-quality reservoir by intersection analysis of the calculated sensitive well logging curve;
s500, acquiring an elastic parameter body of a research area by utilizing a pre-stack seismic trace set of the research area through pre-stack statistical inversion under phase control, and inverting the sensitive well logging curve body by utilizing the elastic parameter body based on the corresponding relation between the sensitive well logging curve and the elastic parameter curve;
and S600, judging whether each position on the sensitive well logging curve body is a high-quality reservoir according to probability distribution of the sensitive well logging curve of the high-quality reservoir, so as to determine the distribution condition of the high-quality reservoir in the research area.
2. The machine learning based quality reservoir characterization method of claim 1 wherein in step S100, the quality of the pre-stack seismic trace set is optimized after acquiring the pre-stack seismic trace set of the investigation region and before utilizing the pre-stack seismic trace set of the investigation region.
3. The machine learning based premium reservoir characterization method of claim 1 wherein in step S200 the sensitive logs that can be used to identify premium reservoirs for a study area are natural Gamma (GR) logs and deep lateral Resistivity (RD) logs.
4. The machine learning based quality reservoir characterization method of claim 1, wherein in step S300, the determining the mineral composition of the investigation region and its content comprises:
and establishing a multi-mineral optimization model of the research area, and determining the mineral composition and the content of the mineral composition of the research area by using the multi-mineral optimization model.
5. The machine learning based quality reservoir characterization method of claim 1, wherein in step S300, the elastic parameter curves include longitudinal wave velocity, transverse wave velocity, longitudinal-to-transverse wave velocity ratio, pull Mei Jishu, and poisson' S ratio elastic parameter curves.
6. The machine learning based quality reservoir characterization method of claim 1, wherein in step S400, the deep neural network algorithm comprises a support vector machine based deep neural network algorithm; the probability distribution of the sensitive logging curve of the high-quality reservoir is Bayesian probability distribution.
7. The machine learning based quality reservoir characterization method according to claim 1, wherein in step S500, the obtaining elastic parameter volumes of the investigation region by phase-controlled prestack statistical inversion using the prestack seismic trace sets of the investigation region comprises:
determining sand-ground ratio distribution by utilizing a pre-stack seismic trace set of a research area and a sedimentary microphase map and a pre-stack deterministic inversion longitudinal wave impedance plane map of a well sand-ground ratio machine learning geological sketch;
and carrying out prestack statistical inversion under the constraint condition of sand-ground ratio distribution to obtain the elastic parameter body of the research area.
8. A machine learning-based high quality reservoir characterization device, comprising:
the pre-stack data acquisition module is used for acquiring a pre-stack seismic trace set of the research area;
the logging curve analysis module is used for acquiring a logging curve of the research area and determining a sensitive logging curve which can be used for identifying a high-quality reservoir of the research area by analyzing intersection conditions of the logging curve;
the elastic parameter deduction module is used for determining the composition and the content of mineral components in the research area, based on the composition and the content of the mineral components, forward modeling a petrophysical parameter curve of the research area through petrophysical modeling, and obtaining an elastic parameter curve of the research area based on the petrophysical parameter curve;
the reservoir probability analysis module is used for establishing a corresponding relation between the sensitive well logging curve and the elastic parameter curve by using a deep neural network algorithm, calculating a corresponding sensitive well logging curve from the rock physical parameter curve of the well drilled in the research area based on the corresponding relation, and determining probability distribution of the sensitive well logging curve of the high-quality reservoir by analyzing intersection conditions of the sensitive well logging curve;
the sensitive well logging curve inversion module is used for obtaining an elastic parameter body of the research area through prestack statistics inversion under phase control by utilizing a prestack seismic trace set of the research area, and inverting the sensitive well logging curve body by utilizing the elastic parameter body based on the corresponding relation between the sensitive well logging curve and the elastic parameter curve;
and the reservoir distribution determining module is used for judging whether each position on the sensitive well logging curve body is a high-quality reservoir according to probability distribution of the sensitive well logging curve of the high-quality reservoir, so as to describe the distribution condition of the high-quality reservoir in the research area.
9. A computer-readable storage medium, on which a computer program is stored which, when executed by a processor, implements a machine learning based quality reservoir characterization method as claimed in any one of claims 1 to 7.
10. An electronic device, comprising:
a processor;
a memory for storing the processor-executable instructions;
wherein the processor is configured to execute the instructions to implement a machine learning based quality reservoir characterization method as claimed in any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210858822.8A CN117471537A (en) | 2022-07-20 | 2022-07-20 | High-quality reservoir depicting method based on machine learning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210858822.8A CN117471537A (en) | 2022-07-20 | 2022-07-20 | High-quality reservoir depicting method based on machine learning |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117471537A true CN117471537A (en) | 2024-01-30 |
Family
ID=89622522
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210858822.8A Pending CN117471537A (en) | 2022-07-20 | 2022-07-20 | High-quality reservoir depicting method based on machine learning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117471537A (en) |
-
2022
- 2022-07-20 CN CN202210858822.8A patent/CN117471537A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106154323B (en) | The thin method for predicting reservoir of phased stochastic inverse of frequency processing is opened up based on earthquake | |
| CN110318745B (en) | Particle size lithology logging evaluation method under deposition microphase constraint | |
| Carlson et al. | Submarine fan environment inferred from turbidite thickness distributions | |
| CN111323844A (en) | Lithology identification method and system of complex gravel rock mass based on curve reconstruction | |
| EP3394647B1 (en) | A methodology for building realistic numerical forward stratigraphic models in data sparse environment | |
| CN110887772B (en) | Carbonate reservoir permeability identification method, system and device | |
| CN108957532B (en) | Reservoir stratum prediction method and device | |
| CN112698399A (en) | Gravel well seismic-logging linkage constraint efficient reservoir quantitative prediction method and system | |
| CN111812716A (en) | Pre-stack quantitative prediction method, device and equipment for total organic carbon content of shale gas reservoir | |
| CN110727027B (en) | Fine carving method for multi-period river sand | |
| CN117471537A (en) | High-quality reservoir depicting method based on machine learning | |
| CN112541523B (en) | Method and device for calculating mud content | |
| CN115522912A (en) | Cable adsorption card risk quantitative evaluation method, system and medium based on big data | |
| CN111679318A (en) | Method and system for identifying fracture system in reservoir | |
| Ren et al. | Data assimilation for surface wave method by ensemble Kalman filter with random field modeling | |
| CN113109875A (en) | Inversion method of carbonate rock reservoir under full waveform velocity field constraint | |
| CN112782780A (en) | Reservoir evaluation method, device and equipment based on rock physical facies | |
| CN114755740A (en) | Rock distribution determination method, device, equipment and medium | |
| CN113075747B (en) | Reservoir fracture development area prediction method and device | |
| CN114428365A (en) | Gas-containing characteristic-based tight sandstone gas reservoir logging identification method and device | |
| CN112505761A (en) | Reservoir gas-containing property detection method and device | |
| Zhang et al. | Characteristics, Main Controlling Factors and Prediction of Complex Fracture–Cavity Reservoirs of Buried Carbonate Hills in the Weixinan Depression, Western South China Sea | |
| CN117784227A (en) | Multistage phased constraint modeling method and device | |
| CN117150183B (en) | Seabed sediment porosity calculation method and device, electronic equipment and medium | |
| CN117784231A (en) | Pre-stack inversion initial model establishment method based on seismic layer velocity |
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 |