CN111323817A - Carbon dioxide sequestration monitoring method and device based on deep learning - Google Patents
Carbon dioxide sequestration monitoring method and device based on deep learning Download PDFInfo
- Publication number
- CN111323817A CN111323817A CN202010297491.6A CN202010297491A CN111323817A CN 111323817 A CN111323817 A CN 111323817A CN 202010297491 A CN202010297491 A CN 202010297491A CN 111323817 A CN111323817 A CN 111323817A
- Authority
- CN
- China
- Prior art keywords
- carbon dioxide
- seismic data
- target area
- formation
- deep learning
- 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.)
- Granted
Links
- CURLTUGMZLYLDI-UHFFFAOYSA-N Carbon dioxide Chemical compound O=C=O CURLTUGMZLYLDI-UHFFFAOYSA-N 0.000 title claims abstract description 224
- 229910002092 carbon dioxide Inorganic materials 0.000 title claims abstract description 128
- 239000001569 carbon dioxide Substances 0.000 title claims abstract description 112
- 238000000034 method Methods 0.000 title claims abstract description 82
- 238000013135 deep learning Methods 0.000 title claims abstract description 77
- 230000009919 sequestration Effects 0.000 title claims abstract description 38
- 238000012544 monitoring process Methods 0.000 title claims abstract description 27
- 238000013508 migration Methods 0.000 claims abstract description 79
- 230000005012 migration Effects 0.000 claims abstract description 76
- 230000000704 physical effect Effects 0.000 claims abstract description 58
- 238000013507 mapping Methods 0.000 claims abstract description 16
- 238000005755 formation reaction Methods 0.000 claims description 96
- 230000015572 biosynthetic process Effects 0.000 claims description 95
- 238000002347 injection Methods 0.000 claims description 38
- 239000007924 injection Substances 0.000 claims description 38
- 230000006870 function Effects 0.000 claims description 21
- 238000011156 evaluation Methods 0.000 claims description 12
- 238000007789 sealing Methods 0.000 claims description 12
- 238000012806 monitoring device Methods 0.000 claims description 11
- 238000012549 training Methods 0.000 claims description 11
- 238000004590 computer program Methods 0.000 claims description 7
- 230000008569 process Effects 0.000 abstract description 9
- 238000004364 calculation method Methods 0.000 abstract description 8
- 230000000694 effects Effects 0.000 abstract description 5
- 239000000243 solution Substances 0.000 description 7
- 230000008859 change Effects 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 238000004891 communication Methods 0.000 description 3
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000009792 diffusion process Methods 0.000 description 3
- 238000006073 displacement reaction Methods 0.000 description 2
- 230000007480 spreading Effects 0.000 description 2
- 230000001052 transient effect Effects 0.000 description 2
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 description 1
- 235000012206 bottled water Nutrition 0.000 description 1
- 239000012267 brine Substances 0.000 description 1
- 229910052799 carbon Inorganic materials 0.000 description 1
- 238000012217 deletion Methods 0.000 description 1
- 230000037430 deletion Effects 0.000 description 1
- 239000003651 drinking water Substances 0.000 description 1
- 230000005484 gravity Effects 0.000 description 1
- 125000001475 halogen functional group Chemical group 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
- 238000012545 processing Methods 0.000 description 1
- 238000011084 recovery Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000000452 restraining effect Effects 0.000 description 1
- 239000011435 rock Substances 0.000 description 1
- HPALAKNZSZLMCH-UHFFFAOYSA-M sodium;chloride;hydrate Chemical compound O.[Na+].[Cl-] HPALAKNZSZLMCH-UHFFFAOYSA-M 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000001131 transforming effect Effects 0.000 description 1
Images
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
-
- 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
- G01V1/303—Analysis for determining velocity profiles or travel times
-
- 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
- G01V1/306—Analysis for determining physical properties of the subsurface, e.g. impedance, porosity or attenuation profiles
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01V—GEOPHYSICS; GRAVITATIONAL MEASUREMENTS; DETECTING MASSES OR OBJECTS; TAGS
- G01V20/00—Geomodelling in general
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- 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
- G01V2210/62—Physical property of subsurface
- G01V2210/622—Velocity, density or impedance
- G01V2210/6222—Velocity; travel time
-
- 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
- G01V2210/62—Physical property of subsurface
- G01V2210/622—Velocity, density or impedance
- G01V2210/6224—Density
-
- 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
- G01V2210/62—Physical property of subsurface
- G01V2210/624—Reservoir parameters
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Remote Sensing (AREA)
- General Physics & Mathematics (AREA)
- Geophysics (AREA)
- General Life Sciences & Earth Sciences (AREA)
- Geology (AREA)
- Environmental & Geological Engineering (AREA)
- Acoustics & Sound (AREA)
- Theoretical Computer Science (AREA)
- Biophysics (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Molecular Biology (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- General Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- Data Mining & Analysis (AREA)
- Computational Linguistics (AREA)
- Biomedical Technology (AREA)
- Artificial Intelligence (AREA)
- Health & Medical Sciences (AREA)
- Physical Or Chemical Processes And Apparatus (AREA)
Abstract
The invention provides a carbon dioxide sequestration monitoring method and device based on deep learning, which relate to the technical field of carbon dioxide sequestration and comprise the following steps: firstly, acquiring multiple groups of single-shot seismic data of a target area; then inputting a plurality of groups of single-shot seismic data into a preset deep learning network to obtain a plurality of groups of stratum physical property parameters of the target area; and finally, determining the migration information of the carbon dioxide in the target area based on the multiple groups of stratum physical property parameters. The preset deep learning network in the embodiment comprises a nonlinear mapping relation between single shot seismic data and stratum physical parameters, multiple groups of stratum physical parameters of the target area can be quickly obtained by inputting multiple groups of acquired single shot seismic data of the target area into the preset deep learning network, and then migration information of carbon dioxide in the target area is effectively monitored, and the process is not influenced by calculation time and low frequency, so that the technical effects of high efficiency and high precision are achieved.
Description
Technical Field
The invention relates to the technical field of carbon dioxide sequestration, in particular to a carbon dioxide sequestration monitoring method and device based on deep learning.
Background
The current geophysical technology is to monitor carbon dioxide CO2The main technology of migration law comprises the following steps: time-lapse earthquake, controllable source geoacoustic electromagnetic method, transient electromagnetic method, etc. Due to CO2After the injection into the underground, the change of the formation physical parameters (seismic wave propagation velocity, formation density and the like) of the injection area is very small, so that the formation physical parameters cannot be effectively distinguished by the traditional monitoring method, the resolution is limited, and the CO can be qualitatively monitored only to a certain extent2The law of migration. The full-waveform inversion is regarded as the reservoir parameter prediction method with the highest precision by people at present, and is not ideal in practical application due to the reasons of calculation time, low-frequency loss and the like.
Disclosure of Invention
The invention aims to provide a carbon dioxide sequestration monitoring method and device based on deep learning, so as to relieve the influence of calculation time and low-frequency deletion on the traditional monitoring method in the prior art, prevent formation physical property parameters from being effectively distinguished, limit resolution and only qualitatively monitor CO to a certain extent2The migration rule of (2).
In a first aspect, an embodiment of the present invention provides a carbon dioxide sequestration monitoring method based on deep learning, where the method includes: acquiring multiple groups of single-shot seismic data of a target area; the target area comprises a carbon dioxide sequestration area, and different single-shot seismic data correspond to different acquisition time points; inputting the multiple groups of single-shot seismic data into a preset deep learning network to obtain multiple groups of stratum physical property parameters of the target area; the preset deep learning network comprises a nonlinear mapping relation between single-shot seismic data and stratum physical parameters, and the stratum physical parameters corresponding to different single-shot seismic data are different; determining migration information of carbon dioxide in the target area based on the multiple sets of formation physical property parameters; wherein the migration information comprises: migration range and/or migration status.
Further, determining migration information of carbon dioxide within the target zone based on the plurality of sets of formation property parameters comprises: acquiring injection position information of carbon dioxide in the target area; carrying out subtraction operation on the multiple groups of stratum physical property parameters to obtain time shifting information of the stratum physical property parameters; and determining migration information of the carbon dioxide in the target region based on the time shift information of the formation physical property parameters and the injection position information.
Further, after determining the carbon dioxide migration information in the target area, the method further includes: performing security evaluation on the target area based on the migration information to obtain a security evaluation result; wherein the safety evaluation result is used for representing the capability of the target area for sealing carbon dioxide.
Further, the method further comprises: randomly establishing a plurality of geological models; wherein: the geological model has geological model characteristics of at least one of: the number of strata, the thickness of the strata, the physical parameters of the strata, the fluctuation form of the strata, the injection position of carbon dioxide and the migration information of the carbon dioxide; forward modeling is carried out on each geological model to obtain single shot seismic data corresponding to the geological model; and training an initial deep learning network based on the single-shot seismic data and the stratum physical property parameters of the geological model to obtain a preset deep learning network.
Further, the formation relief shape is obtained by transforming according to the following function:
wherein Shift _ Z represents the formation relief pattern,
is a linear operator, z is the depth of the formation, z ismaxλ is a constant, a, b, c, d are random parameters controlling the relief pattern of the formation, the sum of all the formation thicknessesAnd generating a machine function, wherein i represents the ith stratum, and N is the number of the stratums.
Further, the formation property parameters include: formation compressional wave velocity, formation shear wave velocity and formation density, the formation compressional wave velocity comprising the formation compressional wave velocity after carbon dioxide injection:
Vp＝Vp0+Ng×G
wherein Vp is the formation longitudinal wave velocity after the carbon dioxide injection, Vp0Ng is the influence value and G is the influence range of injected carbon dioxide, wherein the influence range is determined by the following formula:
wherein (x, y, z) is injection position information of carbon dioxide.
Further, forward modeling each geological model, and obtaining single shot seismic data corresponding to the geological model comprises: forward modeling is carried out on the geological model by using a staggered network finite difference method to obtain a first forward modeling result; forward modeling is carried out on the stratum physical property parameters of the first layer of the geological model by using a staggered network finite difference method to obtain a second forward modeling result; and carrying out subtraction operation on the first forward result and the second forward result to obtain the single-shot seismic data without the direct waves.
In a second aspect, an embodiment of the present invention provides a carbon dioxide sequestration monitoring device based on deep learning, including: the acquisition unit is used for acquiring multiple groups of single-shot seismic data of a target area; the target area comprises a carbon dioxide sequestration area, and different single-shot seismic data correspond to different acquisition time points; the input unit is used for inputting the multiple groups of single-shot seismic data into a preset deep learning network to obtain multiple groups of stratum physical property parameters of the target area; the preset deep learning network comprises a nonlinear mapping relation between single-shot seismic data and stratum physical parameters, and the stratum physical parameters corresponding to different single-shot seismic data are different; the determining unit is used for determining the migration information of the carbon dioxide in the target area based on the multiple groups of formation physical property parameters; wherein the migration information comprises: migration range and/or migration status.
In a third aspect, an embodiment of the present invention provides an electronic device, including a memory and a processor, where the memory stores a computer program operable on the processor, and the processor executes the computer program to implement the method according to any one of the above first aspects.
In a fourth aspect, the present invention provides a computer-readable medium having non-volatile program code executable by a processor, wherein the program code causes the processor to execute the method according to any one of the above first aspects.
The invention provides a carbon dioxide sequestration monitoring method and device based on deep learning, which comprises the steps of firstly obtaining a plurality of groups of single-shot seismic data of a target area; the target area comprises a carbon dioxide sealing area, and different single-shot seismic data correspond to different acquisition time points; then inputting a plurality of groups of single-shot seismic data into a preset deep learning network to obtain a plurality of groups of stratum physical property parameters of the target area; the preset deep learning network comprises a nonlinear mapping relation between single-shot seismic data and stratum physical parameters, and the stratum physical parameters corresponding to different single-shot seismic data are different; finally, determining the migration information of the carbon dioxide in the target area based on the multiple groups of stratum physical property parameters; wherein the migration information comprises: migration range and/or migration status.
The preset deep learning network in the embodiment comprises a nonlinear mapping relation between single shot seismic data and stratum physical parameters, multiple groups of stratum physical parameters of the target area can be quickly obtained by inputting multiple groups of acquired single shot seismic data of the target area into the preset deep learning network, and then migration information of carbon dioxide in the target area is effectively monitored, and the process is not influenced by calculation time and low frequency, so that the technical effects of high efficiency and high precision are achieved.
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and claims hereof as well as the appended drawings.
In order to make the aforementioned and other objects, features and advantages of the present invention comprehensible, preferred embodiments accompanied with figures are described in detail below.
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, and it is obvious that the drawings in the following description are some embodiments of the present invention, and other drawings can be obtained by those skilled in the art without creative efforts.
Fig. 1 is a flowchart of a carbon dioxide sequestration monitoring method based on deep learning according to an embodiment of the present invention;
FIG. 2 is a flowchart of step S103 in FIG. 1;
fig. 3 is a flowchart of a second method for monitoring carbon dioxide sequestration based on deep learning according to an embodiment of the present invention;
FIG. 4 is a flowchart of a third method for monitoring carbon dioxide sequestration based on deep learning according to an embodiment of the present invention;
FIG. 5 is a schematic structural diagram of a geological model;
FIG. 6 is a schematic 3D model of formation compressional velocity after carbon dioxide injection;
FIG. 7 is a schematic diagram of a 2D model of formation compressional velocity;
fig. 8 is a schematic structural diagram of a carbon dioxide sequestration monitoring device based on deep learning according to an embodiment of the present invention.
Icon:
11-an acquisition unit; 12-an input unit; 13-determination unit.
Detailed Description
The technical solutions of the present invention will be described clearly and completely with reference to the following embodiments, and it should be understood that the described embodiments are some, but not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
CO2The capture and sequestration (CCS) technology is globally recognized as reducing CO2One of the fast and effective technical means of concentration. Wherein, CO2The oil displacement and gas displacement technology can realize CO2The sealing and storing of the oil and gas can also improve the oil and gas recovery ratio. But how to ensure injection of underground CO2The safe and leak-free underground sealing is a difficult problem at present. How to ensure CO2There was no leakage to the brine layer near the reservoir, near surface potable water layer and surface. Thus, CO2The monitoring of migration information is to ensure that the CO is2The important technical guarantee of safe sealing.
The geophysical technique is to monitor CO2Effective means for migration information mainly comprise technologies such as time-lapse seismic, time-lapse VSP, controllable source geoacoustic electromagnetic method, transient electromagnetic method and the like. Specifically, Alnes predicts CO based on gravity monitoring data2Distribution characteristics of diffusion halo density and temperature; park analyzes CO by using a controllable source geoacoustic electromagnetic method2Sensitivity study of migration monitoring; cavanagh researches CO on the basis of four-dimensional seismic monitoring data2The migration law of (2); ghosh develops CO by utilizing seismic joint inversion and rock physics models2Quantitative prediction of migration information; there are also many scholars who use the time-shifted VSP full waveform inversion method for CO2The gas drive leading edge position was monitored. These methods described above qualitatively monitor CO to some extent2Is in a state of motion, but has limited resolution, i.e. CO2After the injection into the underground, the change/influence on the physical parameters (seismic wave propagation speed, formation density and the like) of the stratum is small, a high-precision method is required for monitoring/predicting the change by some technical means, and no effective technical means exists at present. WhileThe full-waveform inversion is regarded as the reservoir parameter prediction method with the highest precision by people at present, and is not ideal in practical application due to the reasons of calculation time, low-frequency loss and the like.
Based on the above, the embodiment of the invention provides a method and a device for monitoring carbon dioxide sequestration based on deep learning, wherein multiple groups of stratum physical property parameters of a target area can be rapidly obtained by inputting multiple groups of acquired single-shot seismic data of the target area into a preset deep learning network, so that the migration information of carbon dioxide in the target area is effectively monitored, and the process is not influenced by calculation time and low frequency, so that the technical effects of high efficiency and high precision are achieved.
To facilitate understanding of the embodiment, a method for monitoring sequestration of carbon dioxide based on deep learning disclosed in the embodiment of the present invention may be described first.
Example 1:
in accordance with an embodiment of the present invention, there is provided an embodiment of a deep learning based carbon dioxide sequestration monitoring method, it being noted that the steps illustrated in the flowchart of the accompanying figures may be performed in a computer system, such as a set of computer-executable instructions, and that while a logical order is illustrated in the flowchart, in some cases the steps illustrated or described may be performed in an order different than here.
Fig. 1 is a flowchart of a method for monitoring carbon dioxide sequestration based on deep learning according to an embodiment of the present invention, as shown in fig. 1, the method includes the following steps:
s101, acquiring multiple groups of single-shot seismic data of a target area;
in the embodiment of the invention, the target area comprises a carbon dioxide sequestration area, and different single shot seismic data correspond to different acquisition time points. The multiple groups of single-shot seismic data refer to single-shot seismic data of different acquisition time points of the same target area actually acquired in the field.
S102, inputting multiple groups of single-shot seismic data into a preset deep learning network to obtain multiple groups of stratum physical property parameters of a target area;
in the embodiment of the invention, the preset deep learning network comprises a nonlinear mapping relation between single-shot seismic data and stratum physical property parameters, and the stratum physical property parameters corresponding to different single-shot seismic data are different.
For example, a first group of single-shot seismic data of a target area is acquired in 2015, wherein the first group of single-shot seismic data comprises hundreds to thousands of single-shot seismic data; similarly, a second group of single-shot seismic data of the target area is acquired in 2016, and the second group of single-shot seismic data also comprises hundreds to thousands of single-shot seismic data; a third group of single-shot seismic data of the target area is acquired in 2018, and the third group of single-shot seismic data also comprises hundreds to thousands of single-shot seismic data. The three groups of single-shot seismic data are respectively input into a preset deep learning network to obtain a first group of stratum physical property parameters, a second group of stratum physical property parameters and a third group of stratum physical property parameters, and the change condition of the stratum physical property parameters can be determined based on the three groups of stratum physical property parameters in 2015, 2016 and 2018.
S103, determining migration information of carbon dioxide in a target area based on multiple groups of stratum physical property parameters;
in the embodiment of the present invention, the migration information includes: migration range and/or migration status. Migration states can be understood as CO2How far to move from the injection site, which kind of movement is used, wherein the movement includes but is not limited to: a mode of spreading along a line, and a mode of spreading along the center of the sphere to the periphery.
The embodiment of the invention can determine the change condition of the formation physical property parameters, and further determine the migration information of the carbon dioxide in the target area.
The embodiment of the invention provides a carbon dioxide sequestration monitoring method based on deep learning, which comprises the steps of firstly obtaining a plurality of groups of single-shot seismic data of a target area; the target area comprises a carbon dioxide sealing area, and different single-shot seismic data correspond to different acquisition time points; then inputting a plurality of groups of single-shot seismic data into a preset deep learning network to obtain a plurality of groups of stratum physical property parameters of the target area; the preset deep learning network comprises a nonlinear mapping relation between single-shot seismic data and stratum physical parameters, and the stratum physical parameters corresponding to different single-shot seismic data are different; finally, determining the migration information of the carbon dioxide in the target area based on the multiple groups of stratum physical property parameters; wherein the migration information comprises: migration range and/or migration status. The preset deep learning network in the embodiment comprises a nonlinear mapping relation between single shot seismic data and stratum physical parameters, multiple groups of stratum physical parameters of the target area can be quickly obtained by inputting multiple groups of acquired single shot seismic data of the target area into the preset deep learning network, and then migration information of carbon dioxide in the target area is effectively monitored, and the process is not influenced by calculation time and low frequency, so that the technical effects of high efficiency and high precision are achieved.
In an alternative embodiment, as shown in fig. 2, the step S103 of determining the migration information of carbon dioxide in the target area based on the plurality of sets of formation property parameters includes the following steps:
step S201, acquiring injection position information of carbon dioxide in a target area;
step S202, carrying out subtraction operation on multiple groups of stratum physical property parameters to obtain time shifting information of the stratum physical property parameters;
and step S203, determining migration information of the carbon dioxide in the target area based on the time shift information and the injection position information of the formation physical property parameters.
In the embodiment of the present invention, the injection position information of carbon dioxide acquired in step S201 may be regarded as a three-dimensional region having a volume. When the target region is sufficiently large, the volume of the region is negligible, that is, the injection position information of carbon dioxide can also be regarded as a point. In step S202, a plurality of differences can be obtained by subtracting the formation property parameters at every two adjacent times, and the time shift information of the formation property parameters can be obtained by integrating the plurality of differences. Step S203 may determine the migration range and/or the migration state of carbon dioxide in the target region based on the time shift information and the injection position information of the formation property parameter.
According to the method and the device, the migration information of the carbon dioxide in the target area is determined only by acquiring two information, namely the multiple groups of formation property parameters and the injection position information of the carbon dioxide, and the carbon dioxide is injected into the underground after the injection position is manually set, so that the injection position information of the carbon dioxide can be directly acquired from the carbon dioxide sealed storage data.
In an alternative embodiment, as shown in fig. 3, after determining the carbon dioxide transport information in the target area, the method further comprises:
step S104, performing security evaluation on the target area based on the migration information to obtain a security evaluation result;
in the examples of the invention, CO was obtained2After migration information, the CO can be analyzed2Whether the migration pattern of (a) is as expected, whether geological fractures or faults occur in the target area to allow CO2Migration is the case. Thus, the safety assessment results can be used to characterize the ability of the target area to sequester carbon dioxide.
In an alternative embodiment, referring to fig. 4, the method further comprises:
step S401, randomly establishing a plurality of geological models;
in an embodiment of the invention, the geological model has geological model characteristics of at least one of: the number of the stratums, the thickness of the stratums, the physical parameters of the stratums, the fluctuation forms of the stratums, the injection positions of carbon dioxide and the migration information of the carbon dioxide.
Referring to fig. 5, the geological model is an actual underground stratum, and the physical parameters of the stratum of each layer are different.
According to the actual geological condition, randomly establishing a plurality of geological models (thousands of geological models) which meet the characteristics of the actual geological models as far as possible, wherein the characteristics of the geological models comprise the following random parameters: random number of formations, random thickness of formations, random formation physical parameters, random groundRandom CO with layer relief morphology2Location of injection and CO2Migration information. These random parameters are generated by a random function under certain constraints, such as: the number of the stratums can be set to 10-20]Generated by a first random function, the formation thickness may be set at 1-100]Generated by a second random function. The first random function and the second random function may be the same random function or may refer to different random functions, and the selection of the random function is not particularly limited in the embodiment of the present invention. The structure of the randomly built geological model is shown in fig. 5.
The actual geological features may be approximate ranges of the parameters determined based on geological common knowledge, experience of professionals, and the like, or may be obtained based on known geological data of the target region. The actual geological features aim at limiting the value ranges of the parameters, and because the parameters are randomly generated by adopting a random function, the parameters can be randomly generated within a certain range, and the generation of parameter values which do not accord with the actual parameters is avoided.
Step S402, forward modeling is carried out on each geological model to obtain single shot seismic data corresponding to the geological model;
and S403, training the initial deep learning network based on the single shot seismic data and the stratum physical property parameters of the geological model to obtain a preset deep learning network.
In the step S402, a geological model may be subjected to forward modeling to obtain a batch of single-shot seismic data, and another geological model may be subjected to forward modeling to obtain another batch of single-shot seismic data, so that thousands of geological models may obtain thousands of batches of single-shot seismic data.
Training the initial deep learning network refers to training by using thousands of geological models generated in the step S401 and single shot seismic data corresponding to each model in the step S402 to obtain a preset deep learning network. In the training process, the training parameters of the initial deep learning network are continuously tested and adjusted, and then a sensitive preset deep learning network can be established. The preset deep learning network applies big data and can automatically find the nonlinear mapping relation between single-shot seismic data and stratum physical property parameters.
Therefore, the preset deep learning network used in the embodiment of the invention can establish the nonlinear mapping relation between the single shot seismic data and the stratum physical property parameters, has the advantages of efficiently and accurately determining the stratum physical property parameters, and can further realize CO according to the determined stratum physical property parameters2And (4) sealing and monitoring.
The formation fluctuation form included in the geological model feature may refer to a folding structure of the formation, and is used to represent a vertical fluctuation height difference of the formation. And the number of strata may refer to the number of folded configurations.
In an alternative embodiment, the formation relief pattern is transformed according to the following function:
wherein Shift _ Z represents a formation relief pattern,
is a linear operator, z is the depth of the formation, z ismaxλ is a constant, a, b, c, d are random parameters that control the formation relief pattern, generated by a random function, i denotes the ith formation, and N is the number of formations. Linear operator
The method is used for controlling the fluctuation degree of the stratum in the depth direction, namely, the vertical shear (vertical fluctuation height difference) is increased along with the increase of the depth.
In an alternative embodiment, the formation property parameters include: formation compressional velocity (as shown in fig. 6 and 7), formation shear velocity and formation density, including formation compressional velocity after carbon dioxide injection:
Vp＝Vp0+Ng×G
wherein Vp is the formation longitudinal wave velocity after carbon dioxide injection, Vp0Formation longitudinal before injection of carbon dioxideThe wave velocity, Ng, is the influence value, G is the influence range of the injected carbon dioxide, which is determined by the following formula:
wherein (x, y, z) is injection position information of carbon dioxide.
The formation property parameters include the following three parameters: formation compressional velocity, formation shear velocity and formation density are all data that must be used to analyze carbon dioxide migration information. Therefore, in the process of training the preset deep learning network, the parameters can be randomly generated in a certain numerical range by using a random function according to the actual underground stratum condition.
For each geological model built in step S401, its carbon dioxide migration information (CO)2Migration case) is controlled by a gaussian function assuming CO, an influence value Ng, and formation constraints2The spherical shape and the spherical center position CO are generated by a Gaussian function in a mode of presenting spherical outward diffusion2The concentration is highest and weakens outwards. The influence value Ng needs to be selected in combination with the geological conditions of the study area, and the formation constraint refers to CO2The sealing is required to exist in the same stratum, and only the migration can be carried out in the same stratum, and the phenomenon of layer crossing cannot occur.
Coordinates (x, y, z) for CO control2The diffusion range of (a) is similar to a sphere in the way it is put into a three-dimensional formation, there is the possibility that the sphere will cross two formations. To prevent spheres from crossing both strata, CO is allowed2The method and the device can be used for restraining the longitudinal wave velocity of the stratum in a mode of controlling coordinates (x, y, z) so as to realize the restraint on the physical property parameters of the stratum.
In an alternative embodiment, the step S402 of forward modeling each geological model to obtain single-shot seismic data corresponding to the geological model includes the following steps:
step 1, forward modeling is carried out on a geological model by using a staggered network finite difference method to obtain a first forward modeling result;
step 2, forward modeling is carried out on the stratum physical property parameters of the first layer of the geological model by using a staggered network finite difference method to obtain a second forward modeling result;
and 3, carrying out subtraction operation on the first forward result and the second forward result to obtain the single-shot seismic data without the direct waves.
In an embodiment of the present invention, the staggered network finite difference method may refer to a 3D finite difference method. According to the embodiment of the invention, different numbers of single-shot records (single-shot seismic data) can be obtained according to the size of the geological model and the parameter setting in the forward modeling. In order to make the reflected wave characteristics clear in the single shot record, the embodiment of the invention removes the direct wave in the single shot record. The removing method is to make a uniform geological model by using the formation physical property parameters of the first formation of the geological model, wherein the first formation refers to the uppermost layer of a plurality of formations, and the number of the formations can be set artificially. And then carrying out subtraction operation on the first forward result and the second forward result to obtain the single-shot seismic data without the direct waves.
The embodiment of the invention provides a carbon dioxide sequestration monitoring method based on deep learning, which comprises the following steps: the method comprises the steps of establishing a random geological model, performing forward modeling on the geological model, and training a deep learning network by using single shot seismic data obtained by the forward modeling and stratum physical property parameters of the geological model to obtain a preset deep learning network, wherein the preset deep learning network comprises a nonlinear mapping relation between the single shot seismic data and the stratum physical property parameters.
Example 2:
on the basis of the foregoing embodiment, an embodiment of the present invention further provides a carbon dioxide sequestration monitoring device based on deep learning, where the carbon dioxide sequestration monitoring device based on deep learning is mainly used for executing the carbon dioxide sequestration monitoring method based on deep learning provided by the embodiment of the present invention, and the following provides a specific description of the carbon dioxide sequestration monitoring device based on deep learning provided by the embodiment of the present invention.
Fig. 8 is a schematic structural diagram of a carbon dioxide sequestration monitoring device based on deep learning according to an embodiment of the present invention. As shown in fig. 8, the carbon dioxide sequestration monitoring device based on deep learning mainly includes: an acquisition unit 11, an input unit 12, and a determination unit 13, wherein:
the acquiring unit 11 is used for acquiring multiple groups of single-shot seismic data of a target area; the target area comprises a carbon dioxide sealing area, and different single-shot seismic data correspond to different acquisition time points;
the input unit 12 is used for inputting multiple groups of single-shot seismic data into a preset deep learning network to obtain multiple groups of stratum physical property parameters of a target area; the preset deep learning network comprises a nonlinear mapping relation between single-shot seismic data and stratum physical parameters, and the stratum physical parameters corresponding to different single-shot seismic data are different;
the determining unit 13 is used for determining the migration information of the carbon dioxide in the target area based on the multiple groups of formation physical property parameters; wherein the migration information comprises: migration range and/or migration status.
The embodiment of the invention provides a carbon dioxide sequestration monitoring device based on deep learning, which comprises the steps of firstly, acquiring multiple groups of single-shot seismic data of a target area by using an acquisition unit 11; the target area comprises a carbon dioxide sealing area, and different single-shot seismic data correspond to different acquisition time points; then, inputting a plurality of groups of single-shot seismic data into a preset deep learning network by using an input unit 12 to obtain a plurality of groups of stratum physical property parameters of the target area; the preset deep learning network comprises a nonlinear mapping relation between single-shot seismic data and stratum physical parameters, and the stratum physical parameters corresponding to different single-shot seismic data are different; finally, determining the migration information of the carbon dioxide in the target area by using the determining unit 13 based on the multiple groups of stratum physical property parameters; wherein the migration information comprises: migration range and/or migration status. The preset deep learning network in the embodiment comprises a nonlinear mapping relation between single shot seismic data and stratum physical parameters, multiple groups of stratum physical parameters of the target area can be quickly obtained by inputting multiple groups of acquired single shot seismic data of the target area into the preset deep learning network, and then migration information of carbon dioxide in the target area is effectively monitored, and the process is not influenced by calculation time and low frequency, so that the technical effects of high efficiency and high precision are achieved.
Further, the determination unit 13 includes:
the acquisition module is used for acquiring injection position information of carbon dioxide in a target area;
the subtraction module is used for carrying out subtraction on the multiple groups of stratum physical property parameters to obtain time shift information of the stratum physical property parameters;
and the determining module is used for determining the migration information of the carbon dioxide in the target region based on the time shift information and the injection position information of the formation physical property parameters.
Further, this carbon dioxide sequestration monitoring devices based on deep learning still includes the security evaluation unit, wherein:
the safety evaluation unit is used for evaluating the safety of the target area based on the migration information to obtain a safety evaluation result; and the safety evaluation result is used for representing the capability of the target area for sealing carbon dioxide.
Further, the carbon dioxide sequestration monitoring devices based on deep learning still includes the following unit:
the building unit is used for building a plurality of geological models at random; wherein: the geological model has geological model characteristics of at least one of: the number of strata, the thickness of the strata, the physical parameters of the strata, the fluctuation form of the strata, the injection position of carbon dioxide and the migration information of the carbon dioxide;
the forward modeling unit is used for forward modeling each geological model to obtain single shot seismic data corresponding to the geological model;
and the training unit is used for training the initial deep learning network based on the single-shot seismic data and the stratum physical property parameters of the geological model to obtain a preset deep learning network.
Further, the formation relief pattern is transformed according to the following function:
wherein Shift _ Z represents a formation relief pattern,
is a linear operator, z is the depth of the formation, z ismaxλ is a constant, a, b, c, d are random parameters that control the formation relief pattern, generated by a random function, i denotes the ith formation, and N is the number of formations.
Further, the formation property parameters include: formation compressional wave velocity, formation shear wave velocity and formation density, the formation compressional wave velocity including the formation compressional wave velocity after carbon dioxide injection:
Vp＝Vp0+Ng×G
wherein Vp is the formation longitudinal wave velocity after carbon dioxide injection, Vp0The longitudinal wave velocity of the stratum before the carbon dioxide is injected, Ng is an influence value, G is an influence range of the injected carbon dioxide, and the influence range is determined by the following formula:
wherein (x, y, z) is injection position information of carbon dioxide.
Further, the forward unit includes: the device comprises a first forward modeling module, a second forward modeling module and a subtraction operation module;
the first forward modeling module is used for forward modeling the geological model by using a staggered network finite difference method to obtain a first forward modeling result;
the second forward modeling module is used for forward modeling the formation physical property parameters of the first layer of the geological model by using a staggered network finite difference method to obtain a second forward modeling result;
and the subtraction operation module is used for carrying out subtraction operation on the first forward result and the second forward result to obtain the single-shot seismic data without the direct waves.
Further, the present embodiment also provides an electronic device, which includes a memory and a processor, where the memory stores a computer program that is executable on the processor, and when the processor executes the computer program, the processor executes the steps of the method provided in the foregoing method embodiment.
Further, the present embodiment also provides a computer readable medium having a non-volatile program code executable by a processor, the program code causing the processor to perform the steps of the method provided by the foregoing method embodiment.
It is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described apparatuses and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
The computer program product of the carbon dioxide sequestration monitoring method based on deep learning provided by the embodiment of the present invention includes a computer-readable storage medium storing a program code, and instructions included in the program code may be used to execute the method described in the method embodiment, and specific implementation may refer to the method embodiment, and will not be described herein again. Furthermore, the terms "first," "second," and "third" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance.
In the several embodiments provided in this embodiment, it should be understood that the disclosed apparatus and method may be implemented in other manners. The above-described embodiments of the apparatus are merely illustrative, and for example, the division of the units is only one logical division, and there may be other divisions when actually implemented, and for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection of devices or units through some communication interfaces, and may be in an electrical, mechanical or other form.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit.
The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a non-volatile computer-readable storage medium executable by a processor. Based on such understanding, the technical solution of the present embodiment or parts of the technical solution may be essentially implemented in the form of a software product stored in a storage medium and including instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
Finally, it should be noted that: the above-mentioned embodiments are only specific embodiments of the present invention, which are used for illustrating the technical solutions of the present invention and not for limiting the same, and the protection scope of the present invention is not limited thereto, although the present invention is described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: any person skilled in the art can modify or easily conceive the technical solutions described in the foregoing embodiments or equivalent substitutes for some technical features within the technical scope of the present disclosure; such modifications, changes or substitutions do not depart from the spirit and scope of the embodiments of the present invention, and they should be construed as being included therein.
Claims (10)
1. A carbon dioxide sequestration monitoring method based on deep learning is characterized by comprising the following steps:
acquiring multiple groups of single-shot seismic data of a target area; the target area comprises a carbon dioxide sequestration area, and different single-shot seismic data correspond to different acquisition time points;
inputting the multiple groups of single-shot seismic data into a preset deep learning network to obtain multiple groups of stratum physical property parameters of the target area; the preset deep learning network comprises a nonlinear mapping relation between single-shot seismic data and stratum physical parameters, and the stratum physical parameters corresponding to different single-shot seismic data are different;
determining migration information of carbon dioxide in the target area based on the multiple sets of formation physical property parameters; wherein the migration information comprises: migration range and/or migration status.
2. The method of claim 1, wherein determining migration information of carbon dioxide within the target region based on the plurality of sets of formation property parameters comprises:
acquiring injection position information of carbon dioxide in the target area;
carrying out subtraction operation on the multiple groups of stratum physical property parameters to obtain time shifting information of the stratum physical property parameters;
and determining migration information of the carbon dioxide in the target region based on the time shift information of the formation physical property parameters and the injection position information.
3. The method of claim 1, after determining carbon dioxide transport information within the target area, further comprising:
performing security evaluation on the target area based on the migration information to obtain a security evaluation result; wherein the safety evaluation result is used for representing the capability of the target area for sealing carbon dioxide.
4. The method of claim 1, further comprising:
randomly establishing a plurality of geological models; wherein: the geological model has geological model characteristics of at least one of: the number of strata, the thickness of the strata, the physical parameters of the strata, the fluctuation form of the strata, the injection position of carbon dioxide and the migration information of the carbon dioxide;
forward modeling is carried out on each geological model to obtain single shot seismic data corresponding to the geological model;
and training an initial deep learning network based on the single-shot seismic data and the stratum physical property parameters of the geological model to obtain a preset deep learning network.
5. The method of claim 4, wherein the formation relief pattern is transformed according to the function:
wherein Shift _ Z represents the formation relief pattern,
is a linear operator, z is the depth of the formation, z ismaxλ is a constant, a, b, c, d are random parameters that control the formation relief pattern, generated by a random function, i denotes the ith formation, and N is the number of formations.
6. The method of claim 4, wherein the formation property parameters comprise: formation compressional wave velocity, formation shear wave velocity and formation density, the formation compressional wave velocity comprising the formation compressional wave velocity after carbon dioxide injection:
Vp＝Vp0+Ng×G
wherein Vp is the formation longitudinal wave velocity after the carbon dioxide injection, Vp0Ng is the influence value and G is the influence range of injected carbon dioxide, wherein the influence range is determined by the following formula:
wherein (x, y, z) is injection position information of carbon dioxide.
7. The method of claim 4, wherein forward modeling each of the geological models to obtain single shot seismic data corresponding to the geological model comprises:
forward modeling is carried out on the geological model by using a staggered network finite difference method to obtain a first forward modeling result;
forward modeling is carried out on the stratum physical property parameters of the first layer of the geological model by using a staggered network finite difference method to obtain a second forward modeling result;
and carrying out subtraction operation on the first forward result and the second forward result to obtain the single-shot seismic data without the direct waves.
8. The utility model provides a carbon dioxide sequestration monitoring devices based on deep learning which characterized in that includes:
the acquisition unit is used for acquiring multiple groups of single-shot seismic data of a target area; the target area comprises a carbon dioxide sequestration area, and different single-shot seismic data correspond to different acquisition time points;
the input unit is used for inputting the multiple groups of single-shot seismic data into a preset deep learning network to obtain multiple groups of stratum physical property parameters of the target area; the preset deep learning network comprises a nonlinear mapping relation between single-shot seismic data and stratum physical parameters, and the stratum physical parameters corresponding to different single-shot seismic data are different;
the determining unit is used for determining the migration information of the carbon dioxide in the target area based on the multiple groups of formation physical property parameters; wherein the migration information comprises: migration range and/or migration status.
9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the method according to any one of claims 1 to 7 when executing the computer program.
10. A computer-readable medium having non-volatile program code executable by a processor, the program code causing the processor to perform the method of any of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010297491.6A CN111323817B (en) | 2020-04-15 | 2020-04-15 | Carbon dioxide sequestration monitoring method and device based on deep learning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010297491.6A CN111323817B (en) | 2020-04-15 | 2020-04-15 | Carbon dioxide sequestration monitoring method and device based on deep learning |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111323817A true CN111323817A (en) | 2020-06-23 |
| CN111323817B CN111323817B (en) | 2021-02-02 |
Family
ID=71171941
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010297491.6A Active CN111323817B (en) | 2020-04-15 | 2020-04-15 | Carbon dioxide sequestration monitoring method and device based on deep learning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111323817B (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112925012A (en) * | 2021-01-26 | 2021-06-08 | 中国矿业大学(北京) | Seismic full-waveform inversion method and device |
| CN114563820A (en) * | 2022-03-07 | 2022-05-31 | 中国矿业大学(北京) | Geophysical monitoring method, device and system |
| CN114994759A (en) * | 2022-08-02 | 2022-09-02 | 中国科学院地质与地球物理研究所 | Intelligent carbon seal storage box identification method and system based on GAN network |
| CN115616660A (en) * | 2022-12-20 | 2023-01-17 | 广州海洋地质调查局三亚南海地质研究所 | Monitoring of sea carbon sequestration project CO using diffraction waves 2 Method and device for leakage condition |
| CN116679572A (en) * | 2023-08-03 | 2023-09-01 | 北京绿能碳宝科技发展有限公司 | Carbon dioxide trapping self-learning method based on deep Q learning network |
| CN117219180A (en) * | 2023-09-19 | 2023-12-12 | 中国矿业大学 | Method and system for monitoring, evaluating and dynamically regulating and enhancing mineralization effect of carbon dioxide |
| US11933691B2 (en) | 2021-12-15 | 2024-03-19 | Institute Of Geology And Geophysics, Chinese Academy Of Sciences | CO2 storage state networking monitoring device, system and method with multi-information fusion |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100312480A1 (en) * | 2009-04-24 | 2010-12-09 | Hansteen Fredrik | Method for monitoring fluid flow in a multi-layered system |
| CN103245966A (en) * | 2013-05-24 | 2013-08-14 | 成都理工大学 | Earthquake early warning method based on Internet of Things multi-sensor information fusion and neutral network technology |
| CN103544361A (en) * | 2013-11-04 | 2014-01-29 | 西北大学 | Evaluation method of CO2 geological sequestration potential in oil-gas field development |
| CN105243463A (en) * | 2014-07-09 | 2016-01-13 | 中国石油化工股份有限公司 | River channel sand oiliness evaluation method |
| CN105527660A (en) * | 2016-01-11 | 2016-04-27 | 中国石油大学(华东) | High-over mature stage out-of-source disperse dissoluble organic matter gas generation quantitative evaluation method |
| WO2016160964A1 (en) * | 2015-04-01 | 2016-10-06 | Schlumberger Technology Corporation | Cross-well seismic monitoring of carbon dioxide injection |
| US20160298447A1 (en) * | 2015-04-07 | 2016-10-13 | West Virginia University | Leakage detection using smart field technology |
| CN106842326A (en) * | 2015-12-04 | 2017-06-13 | 中国石油化工股份有限公司 | Sand and mud interstratification CO2 geological storages time-lapse seismic the Forward Modeling during without Shear Wave Velocity Well Logging |
| US20190277988A1 (en) * | 2018-01-23 | 2019-09-12 | Saudi Arabian Oil Company | Generating target-oriented acquisition-imprint-free prestack angle gathers using common focus point operators |
-
2020
- 2020-04-15 CN CN202010297491.6A patent/CN111323817B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100312480A1 (en) * | 2009-04-24 | 2010-12-09 | Hansteen Fredrik | Method for monitoring fluid flow in a multi-layered system |
| CN103245966A (en) * | 2013-05-24 | 2013-08-14 | 成都理工大学 | Earthquake early warning method based on Internet of Things multi-sensor information fusion and neutral network technology |
| CN103544361A (en) * | 2013-11-04 | 2014-01-29 | 西北大学 | Evaluation method of CO2 geological sequestration potential in oil-gas field development |
| CN105243463A (en) * | 2014-07-09 | 2016-01-13 | 中国石油化工股份有限公司 | River channel sand oiliness evaluation method |
| WO2016160964A1 (en) * | 2015-04-01 | 2016-10-06 | Schlumberger Technology Corporation | Cross-well seismic monitoring of carbon dioxide injection |
| US20160298447A1 (en) * | 2015-04-07 | 2016-10-13 | West Virginia University | Leakage detection using smart field technology |
| CN106842326A (en) * | 2015-12-04 | 2017-06-13 | 中国石油化工股份有限公司 | Sand and mud interstratification CO2 geological storages time-lapse seismic the Forward Modeling during without Shear Wave Velocity Well Logging |
| CN105527660A (en) * | 2016-01-11 | 2016-04-27 | 中国石油大学(华东) | High-over mature stage out-of-source disperse dissoluble organic matter gas generation quantitative evaluation method |
| US20190277988A1 (en) * | 2018-01-23 | 2019-09-12 | Saudi Arabian Oil Company | Generating target-oriented acquisition-imprint-free prestack angle gathers using common focus point operators |
Non-Patent Citations (2)
| Title |
|---|
| 任妹娟: ""深部咸水层二氧化碳地质储存监测技术应用研究"", 《中国优秀硕士学位论文全文数据库-工程科技I辑》 * |
| 吴冲龙 等: ""油气运移和聚集的人工神经网络模拟"", 《石油实验地质》 * |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112925012A (en) * | 2021-01-26 | 2021-06-08 | 中国矿业大学(北京) | Seismic full-waveform inversion method and device |
| US11933691B2 (en) | 2021-12-15 | 2024-03-19 | Institute Of Geology And Geophysics, Chinese Academy Of Sciences | CO2 storage state networking monitoring device, system and method with multi-information fusion |
| CN114563820A (en) * | 2022-03-07 | 2022-05-31 | 中国矿业大学(北京) | Geophysical monitoring method, device and system |
| CN114994759A (en) * | 2022-08-02 | 2022-09-02 | 中国科学院地质与地球物理研究所 | Intelligent carbon seal storage box identification method and system based on GAN network |
| CN114994759B (en) * | 2022-08-02 | 2022-12-02 | 中国科学院地质与地球物理研究所 | Intelligent carbon seal storage box identification method and system based on GAN network |
| CN115616660A (en) * | 2022-12-20 | 2023-01-17 | 广州海洋地质调查局三亚南海地质研究所 | Monitoring of sea carbon sequestration project CO using diffraction waves 2 Method and device for leakage condition |
| CN115616660B (en) * | 2022-12-20 | 2023-05-19 | 广州海洋地质调查局三亚南海地质研究所 | Method and device for monitoring carbon dioxide leakage condition of sea area carbon sealing project by using diffraction waves |
| CN116679572A (en) * | 2023-08-03 | 2023-09-01 | 北京绿能碳宝科技发展有限公司 | Carbon dioxide trapping self-learning method based on deep Q learning network |
| CN116679572B (en) * | 2023-08-03 | 2023-09-29 | 北京绿能碳宝科技发展有限公司 | Carbon dioxide trapping self-learning method based on deep Q learning network |
| CN117219180A (en) * | 2023-09-19 | 2023-12-12 | 中国矿业大学 | Method and system for monitoring, evaluating and dynamically regulating and enhancing mineralization effect of carbon dioxide |
| CN117219180B (en) * | 2023-09-19 | 2024-02-27 | 中国矿业大学 | Method and system for monitoring, evaluating and dynamically regulating and enhancing mineralization effect of carbon dioxide |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111323817B (en) | 2021-02-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111323817B (en) | Carbon dioxide sequestration monitoring method and device based on deep learning | |
| US12117582B2 (en) | Model for coupled porous flow and geomechanics for subsurface simulation | |
| Smith et al. | Carbon dioxide storage risk assessment: Analysis of caprock fracture network connectivity | |
| Wang et al. | Heterogeneous fluid flow in fractured layered carbonates and its implication for generation of incipient karst | |
| CN102749647B (en) | Quantitative method for space of holes in reservoir | |
| Harris et al. | Predicting the three-dimensional population characteristics of fault zones: a study using stochastic models | |
| CN114563820B (en) | Geophysical monitoring method, device and system | |
| Cameron et al. | Use of above-zone pressure data to locate and quantify leaks during carbon storage operations | |
| Anyosa et al. | Assessing the value of seismic monitoring of CO2 storage using simulations and statistical analysis | |
| US8718992B2 (en) | Method for history matching of a geological model comprising a sub-seismic fault network | |
| CN117852416A (en) | Multimode grouting precontrolled analysis method and system based on digital geological model | |
| Lagos et al. | Very fast simulated annealing and particle swarm optimization for microseismic event location | |
| Farahmand et al. | Effect of fracture dilation angle on stress-dependent permeability tensor of fractured rock | |
| Chen | Equivalent permeability distribution for fractured porous rocks: correlating fracture aperture and length | |
| Berg | Methods for Estimating Fracture Abundance and Size From Borehole Observations (includes associated erratum) | |
| EP3749986B1 (en) | 4d seismic as a method for characterizing fracture network and fluid distribution in unconventional reservoir | |
| Maciel et al. | Effectiveness of embedded discontinuities technique in capturing geomechanical behavior in naturally fractured reservoirs | |
| Sun et al. | An Integrated Geology-to-Geomechanics Workflow to Assess Geomechanical Risk of CO2 Geological Storage | |
| Noroozi et al. | 3D stochastic rock fracture modeling related to strike-slip faults | |
| Zeidouni et al. | Interpretation of above‐zone pressure influence time to characterize CO2 leakage | |
| Leines Artieda | Discrete fracture network modeling and simulation using EDFM | |
| Zirczy et al. | Quantitative seismic reservoir modeling–optimizing field development value through early and continuous data integration | |
| Elston et al. | A New Method to Invert for Interseismic Deep Slip Along Closely Spaced Faults using Surface Velocities and Subsurface Stressing-Rate Tensors | |
| Dai et al. | Recognize the Spatial Extent and Properties of the Hydraulic Fracture Network with Multiple Data | |
| CN113031056B (en) | Fault closure analysis method and device under construction constraint |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |