CN113034638B - Site pollutant depicting method and system based on directional smooth constraint inversion - Google Patents
Site pollutant depicting method and system based on directional smooth constraint inversion Download PDFInfo
- Publication number
- CN113034638B CN113034638B CN202110299494.8A CN202110299494A CN113034638B CN 113034638 B CN113034638 B CN 113034638B CN 202110299494 A CN202110299494 A CN 202110299494A CN 113034638 B CN113034638 B CN 113034638B
- Authority
- CN
- China
- Prior art keywords
- resistivity
- tensor
- representing
- difference interface
- eigenvector
- 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.)
- Active
Links
- 239000003344 environmental pollutant Substances 0.000 title claims abstract description 43
- 231100000719 pollutant Toxicity 0.000 title claims abstract description 43
- 238000000034 method Methods 0.000 title claims abstract description 30
- 238000009792 diffusion process Methods 0.000 claims abstract description 86
- 238000009499 grossing Methods 0.000 claims abstract description 65
- 239000011159 matrix material Substances 0.000 claims abstract description 38
- 238000005259 measurement Methods 0.000 claims abstract description 21
- 238000009826 distribution Methods 0.000 claims abstract description 18
- 238000005553 drilling Methods 0.000 claims abstract description 18
- 238000012512 characterization method Methods 0.000 claims description 11
- 238000012216 screening Methods 0.000 claims description 9
- 238000004364 calculation method Methods 0.000 claims description 4
- 238000012545 processing Methods 0.000 claims description 4
- 239000000356 contaminant Substances 0.000 claims description 3
- 238000013139 quantization Methods 0.000 claims description 3
- 239000013598 vector Substances 0.000 claims description 3
- 238000010276 construction Methods 0.000 claims description 2
- 238000005516 engineering process Methods 0.000 claims description 2
- 238000006467 substitution reaction Methods 0.000 claims description 2
- 239000000126 substance Substances 0.000 claims 1
- 238000010586 diagram Methods 0.000 description 5
- 238000011835 investigation Methods 0.000 description 5
- 230000004323 axial length Effects 0.000 description 3
- 230000015572 biosynthetic process Effects 0.000 description 3
- 101150064138 MAP1 gene Proteins 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000000295 complement effect Effects 0.000 description 1
- 150000001875 compounds Chemical class 0.000 description 1
- 238000011109 contamination Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 229910001385 heavy metal Inorganic materials 0.000 description 1
- 229930195733 hydrocarbon Natural products 0.000 description 1
- 150000002430 hydrocarbons Chemical class 0.000 description 1
- 238000009776 industrial production Methods 0.000 description 1
- 239000000575 pesticide Substances 0.000 description 1
- 239000003208 petroleum Substances 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000005067 remediation Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 239000002904 solvent Substances 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 231100000331 toxic Toxicity 0.000 description 1
- 230000002588 toxic effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T11/00—2D [Two Dimensional] image generation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/16—Matrix or vector computation, e.g. matrix-matrix or matrix-vector multiplication, matrix factorization
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/30—Circuit design
- G06F30/36—Circuit design at the analogue level
- G06F30/367—Design verification, e.g. using simulation, simulation program with integrated circuit emphasis [SPICE], direct methods or relaxation methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/90—Dynamic range modification of images or parts thereof
- G06T5/94—Dynamic range modification of images or parts thereof based on local image properties, e.g. for local contrast enhancement
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Computer Hardware Design (AREA)
- Business, Economics & Management (AREA)
- Mathematical Physics (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Analysis (AREA)
- Tourism & Hospitality (AREA)
- Pure & Applied Mathematics (AREA)
- Mathematical Optimization (AREA)
- Computational Mathematics (AREA)
- Evolutionary Computation (AREA)
- General Business, Economics & Management (AREA)
- Computing Systems (AREA)
- Health & Medical Sciences (AREA)
- Economics (AREA)
- General Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- Development Economics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Educational Administration (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Biology (AREA)
- Algebra (AREA)
- Databases & Information Systems (AREA)
- Software Systems (AREA)
- Life Sciences & Earth Sciences (AREA)
- Microelectronics & Electronic Packaging (AREA)
- Geometry (AREA)
- Geophysics And Detection Of Objects (AREA)
Abstract
The invention discloses a site pollutant depicting method and a site pollutant depicting system based on directional smooth constraint inversion, wherein the method comprises the following steps: acquiring resistivity difference interface information on the structural boundary of the polluted site according to the drilling data and the geological measurement data of the polluted site; constructing a gray scale map according to the resistivity difference interface information; quantizing the gray-scale map into a plurality of local gray-scale maps; calculating structure tensors of the local gray-scale images, and calculating diffusion tensors and similarity according to the structure tensors; determining a final resistivity difference interface according to the similarity to the resistivity difference interface; calculating smooth weight coefficients of the final resistivity difference interface in four directions according to the diffusion tensor; constructing a four-direction weighted smoothing matrix according to the smoothing weight coefficients in the four directions and substituting the four-direction weighted smoothing matrix into an inversion algorithm to obtain an inversion resistivity prediction model; and determining the field pollutant distribution range according to the inversion resistivity prediction model. The method improves the accuracy of resistivity inversion, and ensures that the determination of the spatial distribution range of the pollutants is more accurate.
Description
Technical Field
The invention relates to the technical field of field pollutant investigation, in particular to a field pollutant characterization method and system based on directional smooth constraint inversion.
Background
With the increasingly prominent environmental problems, the site pollution condition is more serious. Because different toxic and harmful pollutants including heavy metals, pesticides, petroleum hydrocarbons, solvent organic matters and the like can be generated in the industrial production process, most sites are in a compound pollution state, and great difficulty is brought to the investigation of the polluted sites. High density resistivity is a common site contaminant investigation method, where the spatial distribution of subsurface contamination is inferred from the difference in electrical properties between the contaminant and its surrounding medium. The resistivity inversion method is that on the basis of forward modeling, iterative inversion is carried out on an initial earth-electricity model to obtain a resistivity prediction model, and the error between the forward modeling result of the finally obtained resistivity prediction model and field test data (such as a measured apparent resistivity value obtained by a high-density resistivity method) is in a specified range, so that the resistivity prediction model with certain reliability is obtained. According to the resistivity distribution condition of the underground medium, the distribution range and the depth of the underground pollutants are deduced, the defects of the traditional investigation are complemented, and the complementary effect is achieved.
The traditional resistivity inverse algorithm mostly adopts a least square method based on Gaussian Newton smooth constraint, and the calculation formula can be expressed as follows: eα(R)＝(G(R)-b)TSd(G(R)-b)+α(R-R0)TSm(R-R0) In which Eα(R) is a regularization objective function, R is a resistivity model, G (R) is forward data of the resistivity model R, b is observation data measured in the field, SdIs a weight matrix, alpha is a regularization parameter, R0Resistivity model for previous iterative inversion, SmIs a smooth matrix. Obtaining an optimal resistivity prediction model by minimizing a regularizing objective function R*＝argminEα(R)。
For two-dimensional resistivity inversion, its conventional smoothed matrix formula:
Sx、Szthe two are respectively a smoothing matrix in the horizontal direction and a smoothing matrix in the vertical direction, and the formula shows that the two are only used for smoothing the resistivity in the horizontal direction and the resistivity in the vertical direction. Therefore, when a subsurface medium has a relatively significant resistivity-difference interface (formation boundary, fault fracture, or the like), the two-direction smooth matrix may cause deviations in the profile and position of the resistivity-difference interface obtained by inversion, and an error in the resistivity inversion result around the interface may also become large. Therefore, although the above inversion method is fast and efficient in calculation, the influence of the structure boundary is ignored in the process of smooth constraint, so that when the resistivity inversion is performed in a field with an obvious structure interface, a real stratum structure cannot be accurately depicted, and the resistivity value of the underground medium obtained by inversion has a larger error than the real resistivity value, and erroneous inference is often caused when the spatial distribution of pollutants is defined, thereby causing great trouble to the survey of the polluted field.
Therefore, how to perform targeted smoothing processing in the resistivity inversion process is to better retain relatively real structure boundary information and improve the accuracy of resistivity inversion, so that the problem of relatively accurately depicting the formation structure and the spatial distribution of pollutants in a polluted site is urgently needed to be solved.
Disclosure of Invention
The invention aims to provide a site pollutant depicting method and system based on directional smooth constraint inversion, so as to improve the precision of investigating the site pollutant distribution range.
In order to achieve the above object, the present invention provides a site pollutant characterization method based on directional smooth constraint inversion, which comprises:
s1: acquiring resistivity difference interface information on the structural boundary of the polluted site according to the drilling data and the geological measurement data of the polluted site; the geological survey data comprises geological radar survey data or seismic survey data; the resistivity difference interface information comprises resistivity differences of the resistivity difference interface and the resistivity difference interface;
s2: constructing a gray scale map according to the resistivity difference interface information;
s3: quantizing the gray level map into a plurality of local gray level maps by using an image recognition technology;
s4: calculating a structure tensor of the local gray-scale images, and calculating a diffusion tensor and a similarity according to the structure tensor;
s5: screening the resistivity difference interface according to the similarity to obtain a final resistivity difference interface;
s6: calculating smooth weight coefficients of the final resistivity difference interface in four directions according to the diffusion tensor;
s7: constructing a four-direction weighted smoothing matrix according to the smoothing weight coefficients in the four directions;
s8: substituting the four-direction weighted smoothing matrix into an inversion algorithm to obtain an inversion resistivity prediction model;
s9: and determining the field pollutant distribution range according to the inversion resistivity prediction model.
Optionally, the obtaining resistivity difference interface information on the structural boundary of the contaminated site according to the drilling data and the geological measurement data of the contaminated site specifically includes:
s11: determining a structural interface of a measuring section of the underground medium of the pollutant ground according to geological measurement data of the polluted site;
s12: and adjusting and optimizing a structural interface of the underground medium measurement section of the polluted site according to the drilling data of the polluted site to obtain a resistivity difference value of the resistivity difference interface and the resistivity difference interface.
Optionally, the formula for calculating the structure tensor of the plurality of local gray-scale maps is as follows:
wherein, T [ c ]]Representing the structure tensor, txxRepresenting the dot product, t, of the gradient of the pixel in the horizontal direction and itself in the local gray-scale mapzxExpressing the dot product of the pixel gradient in the vertical direction and the pixel gradient in the horizontal direction of the local gray level map, txzExpressing the dot product, t, of the pixel gradient in the horizontal direction and the pixel gradient in the vertical direction of the local gray scale mapzzRepresenting the dot product of the pixel gradient in the vertical direction of the local gray-scale map with itself, p representing the principal eigenvector of the structure tensor, m representing the secondary eigenvector of the structure tensor, λpEigenvalues of the principal eigenvector, λ, representing the structure tensormEigenvalues of the secondary eigenvectors representing the structure tensor.
Optionally, the formula for calculating the diffusion tensor from the structure tensor is:
wherein D represents the diffusion tensor, 0 < n < 1, p1A secondary eigenvector, m, representing the diffusion tensor1The principal eigenvector representing the diffusion tensor,
eigenvalues of the secondary eigenvectors, λ, representing the diffusion tensorpEigenvalues of the principal eigenvectors, λ, representing the structure tensormEigenvalues of the secondary eigenvectors representing the structure tensor.
Optionally, the formula for calculating the similarity according to the structure tensor is as follows:
wherein S represents similarity, f represents the local gray scale map, and < f > (m)vAnd v represents m or p, wherein when v is m, the m direction is the direction of the minor eigenvector of the structure tensor of the local gray-scale map, and when v is p, the p direction is the direction of the major eigenvector of the structure tensor of the local gray-scale map.
Optionally, the smoothing weight coefficients of the final resistivity-difference interface in four directions are calculated according to the diffusion tensor, and the formula is as follows:
wherein r isx、rz、rd1And rd2Respectively representing the semi-axial lengths, w, of the diffusion tensor ellipse in the horizontal direction, the vertical direction and the direction of two diagonals of the central pixel unit of the local gray-scale imagexRepresents the smoothing weight coefficient, w, of the final resistivity-difference interface in the horizontal directionzRepresents the smoothed weight coefficient, w, of the final resistivity-difference interface in the vertical directiond1And wd2And the smoothing weight coefficients of the final resistivity difference interface in the two diagonal directions of the central pixel unit of the local gray-scale image are represented.
Optionally, a four-direction weighted smoothing matrix is constructed according to the smoothing weight coefficients of the four directions, and the formula is as follows:
wherein S isx、Sz、Sd1And Sd2Representing the smoothing matrices in the horizontal, vertical and diagonal directions of the central pixel element of the local gray scale image, SmRepresenting said four-direction weighted smoothing matrix, wxRepresents a smoothing weight coefficient, w, of the resistivity-difference interface in the horizontal directionzIndicating smoothing of resistivity-difference interface in vertical directionWeight coefficient, wd1And wd2And the smoothing weight coefficients represent the resistivity difference interface in the direction of two diagonal lines of the central pixel unit of the local gray-scale image.
The invention also provides a site pollutant characterization system based on directional smooth constraint inversion, which comprises:
the information determining module is used for obtaining resistivity difference interface information on the structural boundary of the pollution site according to drilling data and geological measurement data of the pollution site; the geological survey data comprises geological radar survey data or seismic survey data; the resistivity difference interface information comprises resistivity differences of the resistivity difference interface and the resistivity difference interface;
the construction module is used for constructing a gray scale map according to the resistivity difference interface information;
a quantization module for quantizing the gray scale map into a plurality of local gray scale maps using image recognition techniques;
the calculation module is used for calculating the structure tensors of the local gray level images and calculating the diffusion tensors and the similarity according to the structure tensors;
the screening module is used for screening the resistivity difference interface according to the similarity to obtain a final resistivity difference interface;
a smooth weight coefficient determination module, configured to calculate smooth weight coefficients of the final resistivity difference interface in four directions according to the diffusion tensor;
the smooth matrix determining module is used for constructing a four-direction weighted smooth matrix according to the smooth weight coefficients in the four directions;
the substitution module is used for substituting the four-direction weighted smooth matrix into an inversion algorithm to obtain an inversion resistivity prediction model;
and the range determining module is used for determining the field pollutant distribution range according to the inversion resistivity prediction model.
Optionally, the information determining module specifically includes:
the structure interface determining unit is used for determining a structure interface of the measuring section of the underground medium of the pollutant ground according to the geological measurement data of the polluted site;
and the adjusting unit is used for adjusting and optimizing the structural interface of the underground medium measuring section of the polluted site according to the drilling data of the polluted site to obtain the resistivity difference value of the resistivity difference interface and the resistivity difference interface.
Optionally, the formula for calculating the structure tensor of the plurality of local gray-scale maps is as follows:
wherein, T [ c ]]Representing the structure tensor, txxRepresenting the dot product, t, of the gradient of the pixel in the horizontal direction and itself in the local gray-scale mapzxExpressing the dot product of the pixel gradient in the vertical direction and the pixel gradient in the horizontal direction of the local gray level map, txzExpressing the dot product, t, of the pixel gradient in the horizontal direction and the pixel gradient in the vertical direction of the local gray scale mapzzRepresenting the dot product of the pixel gradient in the vertical direction of the local gray-scale map with itself, p representing the principal eigenvector of the structure tensor, m representing the secondary eigenvector of the structure tensor, λpEigenvalues of the principal eigenvectors, λ, representing the structure tensormEigenvalues of the secondary eigenvectors representing the structure tensor.
According to the specific embodiment provided by the invention, the invention discloses the following technical effects:
the invention discloses a site pollutant depicting method and a site pollutant depicting system based on directional smooth constraint inversion, wherein the method comprises the following steps: firstly, acquiring resistivity difference interface information on a structure boundary of a polluted site according to drilling data and geological measurement data of the polluted site; constructing a gray scale map according to the resistivity difference interface information; quantizing the gray-scale map into a plurality of local gray-scale maps; calculating structure tensors of the local gray level images, and calculating diffusion tensors and similarity according to the structure tensors; determining a final resistivity difference interface according to the similarity to the resistivity difference interface; calculating smooth weight coefficients of the final resistivity difference interface in four directions according to the diffusion tensor; constructing a four-direction weighted smoothing matrix according to the smoothing weight coefficients in the four directions and substituting the four-direction weighted smoothing matrix into an inversion algorithm to obtain an inversion resistivity prediction model; and determining the field pollutant distribution range according to the inversion resistivity prediction model. The method improves the accuracy of resistivity inversion, and ensures that the determination of the spatial distribution range of the pollutants is more accurate.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings needed in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings without creative efforts.
FIG. 1 is a flowchart of a field pollutant characterization method based on directional smooth constraint inversion according to embodiment 1 of the present invention;
FIG. 2 is a gray scale diagram of embodiment 1 of the present invention;
FIG. 3 is a partial gray scale of embodiment 1 of the present invention;
FIG. 4 is a partial gray scale diagram of a plurality of pixel units according to embodiment 1 of the present invention;
FIG. 5 is an elliptical schematic view of the diffusion tensor in the grayscale image of embodiment 1 of the present invention;
FIG. 6 is a schematic diagram of similarity in gray scale images according to embodiment 1 of the present invention;
FIG. 7 is a schematic diagram of calculating smooth weight coefficients in four directions according to embodiment 1 of the present invention;
fig. 8 is a structural diagram of a field pollutant characterization system based on directional smooth constraint inversion in embodiment 2 of the present invention.
Wherein 1, a grayscale map, 2, a resistivity contrast interface, 3, a local grayscale map, 4, a pixel value corresponding to a low resistivity layer, 5, a pixel value corresponding to a high resistivity layer, 6, a structure tensor ellipse, 7, a principal eigenvector of the structure tensor, 8, a secondary eigenvector of the structure tensor, 9, a diffusion tensor ellipse, 10, a principal eigenvector of the diffusion tensor, 11, a secondary eigenvector of the diffusion tensor, 12, a pixel unit, 13, a final resistivity contrast interface, 14, a horizontal direction, 15, a vertical direction, 16, a first diagonal direction of the local grayscale map central pixel unit, 17, a second diagonal direction of the local grayscale map central pixel unit, 18, a half axial length of the diffusion tensor ellipse in the horizontal direction, 19, a half axial length of the diffusion tensor ellipse in the vertical direction, 20, a half axial length of the diffusion tensor ellipse in the first diagonal direction of the local grayscale map central pixel unit, 21. the method comprises the steps of determining the semi-axis length of a diffusion tensor ellipse in the second diagonal direction of a central pixel unit of a local gray-scale image, 401, determining a module for information, 402, constructing a module, 403, quantizing the diffusion tensor ellipse, 404, calculating the diffusion tensor ellipse, 405, screening the diffusion tensor ellipse, 406, determining a smooth weight coefficient, 407, determining a smooth matrix, 408, substituting the diffusion tensor ellipse into the diffusion tensor ellipse, 409 and determining a range.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. 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.
The invention aims to provide a site pollutant depicting method and system based on directional smooth constraint inversion, so as to improve the precision of investigating the site pollutant distribution range.
In order to make the aforementioned objects, features and advantages of the present invention more comprehensible, the present invention is described in detail with reference to the accompanying drawings and the detailed description thereof.
Example 1
Fig. 1 is a flowchart of a site pollutant characterization method based on directional smooth constraint inversion according to an embodiment of the present invention, and as shown in fig. 1, the method includes:
s1: acquiring resistivity difference interface information on a structural boundary of the polluted site according to drilling data and geological measurement data of the polluted site; the geological survey data comprises geological radar survey data or seismic survey data; the resistivity-difference interface information includes the resistivity difference between the resistivity-difference interface 2 and the resistivity-difference interface.
S2: and constructing a gray scale map 1 according to the resistivity difference interface information. As shown in fig. 2, the resistivity-difference interface 2 is represented by a pixel-difference boundary, and the resistivity difference is represented by a pixel difference. A pixel value 4 corresponding to a low resistivity formation is determined as well as a pixel value 5 corresponding to a high resistivity geology. And adjusting the size of the gray image to be consistent with the size of the inversion model.
S3: the gray map 1 is quantized into a plurality of local gray maps 3 using image recognition techniques, as shown in fig. 3. The plurality of local gray maps are discretized into a plurality of pixel cells 12 as shown in fig. 4. And adjusting the pixel unit size to enable the center of the local gray level image to correspond to the unit center of the inversion model one by one. The unit of the inverse model is preset.
S4: and calculating a structure tensor of the plurality of local gray-scale images, and calculating a diffusion tensor and a similarity according to the structure tensor.
S5: and screening the resistivity difference interface according to the similarity to obtain a final resistivity difference interface 13. The similarity range is 0-1, and the smaller the value is, the stronger the resistivity difference interface is. As shown in fig. 6, given that the threshold value of the similarity is 0.93, when the similarity is less than 0.93, the final resistivity difference interface 13 is defined, and we calculate the smoothing weight coefficients of four directions only at this position, and the default smoothing weight coefficients are all 0.25 at other positions.
S6: and calculating smooth weight coefficients of the final resistivity difference interface in four directions according to the diffusion tensor.
S7: and constructing a four-direction weighted smoothing matrix according to the smoothing weight coefficients of the four directions.
S8: and substituting the four-direction weighted smooth matrix into an inversion algorithm to obtain an inversion resistivity prediction model.
S9: and determining the field pollutant distribution range according to the inversion resistivity prediction model.
In an embodiment of the present invention, the obtaining resistivity difference interface information on a structural boundary of a contaminated site according to drilling data and geological measurement data of the contaminated site specifically includes:
s11: and determining the structural interface of the measuring section of the underground medium of the polluted site according to the geological measurement data of the polluted site.
S12: and adjusting and optimizing a structural interface of the underground medium measurement section of the polluted site according to the drilling data of the polluted site to obtain a resistivity difference value of the resistivity difference interface and the resistivity difference interface.
In this embodiment of the present invention, the formula for calculating the structure tensor of the plurality of local gray-scale maps is as follows:
wherein, T [ c ]]Representing the structure tensor, txxRepresents the dot product of the pixel gradient and the local gray level image in the horizontal direction, tzxExpressing the dot product of the pixel gradient in the vertical direction and the pixel gradient in the horizontal direction of the local gray level map, txzExpressing the dot product, t, of the pixel gradient in the horizontal direction and the pixel gradient in the vertical direction of the local gray scale mapzzRepresenting the dot product of the pixel gradient in the vertical direction with the local gray-scale map and itself, p representing the principal eigenvector 7 of the structure tensor, m representing the secondary eigenvector 8 of the structure tensor, λpEigenvalues of the principal eigenvectors, λ, representing the structure tensormEigenvalues of the secondary eigenvectors representing the structure tensor.
In this embodiment of the present invention, the formula for calculating the diffusion tensor according to the structure tensor is:
wherein D represents the diffusion tensor, 0 < n < 1, p1The secondary eigenvectors 11, m representing the diffusion tensor1The principal eigenvector 10 representing the diffusion tensor,
order of the diffusion tensorThe eigenvalues, λ, of the eigenvectorspEigenvalues of the principal eigenvector, λ, representing the structure tensormEigenvalues of the secondary eigenvectors representing the structure tensor. As shown in FIG. 5, the diffusion tensor is the orientation of the resistivity-difference interface in the gray scale map, the main direction of which is the extension direction of the resistivity-difference interface and passes through the eigenvalue of the minor eigenvector 11
And quantifying the difference degree of the resistivity difference interface, and in order to quantify the difference degree of the resistivity difference interface, better quantifying and smoothing the boundary, wherein the value of n is 0.5.
In the embodiment of the present invention, the directions of the principal eigenvector 7 of the structure tensor and the secondary eigenvector 11 of the diffusion tensor are on a straight line, and the lengths are unit lengths. The directions of the minor eigenvector 8 of the structure tensor and the major eigenvector 10 of the diffusion tensor are on a straight line, and the lengths are both vectors of unit length.
In the embodiment of the present invention, the formula for calculating the similarity according to the structure tensor is as follows:
wherein S represents similarity, f represents the local gray scale map, < f > (R) < >vAnd v represents m or p, wherein when v is m, the m direction is the direction of the minor eigenvector of the structure tensor of the local gray-scale map, and when v is p, the p direction is the direction of the major eigenvector of the structure tensor of the local gray-scale map.
In this embodiment of the present invention, the calculating, according to the diffusion tensor, smoothing weight coefficients of the final resistivity-difference interface in four directions is performed by using the following formula:
wherein, as shown in FIG. 7, rxThe semi-axial length 18, r in the horizontal direction 14 of the ellipse 9 of the diffusion tensor is representedzThe semi-axial length 19, r of the ellipse representing the diffusion tensor in the vertical direction 15d1The semi-axial length 20, r of the diffusion tensor ellipse in the first diagonal direction 16 of the central pixel element of the local gray scale imaged2The semi-axial length 21 of the diffusion tensor ellipse in the second diagonal direction 17 of the central pixel element of the local gray scale image. w is axRepresents the smoothing weight coefficient, w, of the final resistivity-difference interface in the horizontal directionzRepresents the smoothed weight coefficient, w, of the final resistivity-difference interface in the vertical directiond1And wd2And the smoothing weight coefficients of the final resistivity difference interface in the two diagonal directions of the central pixel unit of the local gray-scale image are represented. The diffusion tensor ellipse 9 is determined from the diffusion tensor. A structure tensor ellipse 6 is determined from the structure tensor.
In the embodiment of the invention, a four-direction weighted smoothing matrix is constructed according to the smoothing weight coefficients in four directions, and the formula is as follows:
wherein S isx、Sz、Sd1And Sd2Representing the smoothing matrices in the horizontal, vertical and diagonal directions of the central pixel element of the local gray scale image, SmRepresenting the four-way weighted smoothing matrix,wxrepresents a smoothing weight coefficient, w, of the resistivity-difference interface in the horizontal directionzRepresents the smooth weight coefficient, w, of the resistivity-difference interface in the vertical directiond1And wd2And the smoothing weight coefficients represent the resistivity difference interface in the direction of two diagonal lines of the central pixel unit of the local gray-scale image.
Further, the four-direction weighted smoothing matrix replaces the traditional two-direction smoothing matrix and is substituted into the formula: eα(R)＝(G(R)-b)TSd(G(R)-b)+α(R-R0)TSm(R-R0) Obtaining an optimal resistivity prediction model by minimizing a regularization objective function through inversion iterative computation, wherein R is*＝argminEα(R)。
Compared with the prior art, the invention has the beneficial effects that:
1. according to the method, based on the advantages that the structure difference interface and the real resistivity can be well reflected by the drilling data and the geological measurement data, the resistivity difference interface information on the structure boundary of the polluted site is comprehensively obtained, and therefore the prior information of the underground medium structure of the polluted site is more accurate.
2. The invention converts the resistivity difference interface information of the underground medium of the polluted site into directional and quantitative constraints by converting the resistivity difference interface information into a grey-scale map, identifying images, calculating diffusion tensor, similarity and smooth weight coefficients in four directions according to the resistivity difference interface information, determines the smooth direction by using the smooth weight coefficients in the four directions, and the difference degree of different resistivity interfaces is quantified, the traditional two-direction smooth matrix is replaced by a four-direction weighted smooth matrix, directional and quantitative constraint smoothing processing is realized in the resistivity inversion process, more real structural boundary information is better reserved, the resistivity inversion accuracy is improved, the research on the underground medium structure and the pollutant spatial distribution of the accurate depicting polluted site has pertinence and scientificity, and has great practical value for site pollutant investigation and later pollutant remediation work.
Example 2
As shown in fig. 8, the present invention further discloses a site pollutant characterization system based on directional smooth constraint inversion, which includes:
the information determining module 401 is configured to obtain resistivity difference interface information on a structural boundary of the contaminated site according to the drilling data and the geological measurement data of the contaminated site; the geological survey data comprises geological radar survey data or seismic survey data; the resistivity-difference interface information includes a resistivity difference between the resistivity-difference interface and the resistivity-difference interface.
A constructing module 402, configured to construct a grayscale map according to the resistivity difference interface information.
A quantization module 403, configured to quantize the grayscale map into a plurality of local grayscale maps by using an image recognition technique.
A calculating module 404, configured to calculate a structure tensor of the plurality of local grayscale images, and calculate a diffusion tensor and a similarity according to the structure tensor.
And a screening module 405, configured to screen the resistivity difference interface according to the similarity, so as to obtain a final resistivity difference interface.
A smooth weight coefficient determining module 406, configured to calculate smooth weight coefficients of the final resistivity-difference interface in four directions according to the diffusion tensor.
And a smoothing matrix determining module 407, configured to construct a four-direction weighted smoothing matrix according to the smoothing weight coefficients in the four directions.
And a substituting module 408, configured to substitute the four-direction weighted smoothing matrix into an inversion algorithm to obtain an inversion resistivity prediction model.
And the range determining module 409 is used for determining the field pollutant distribution range according to the inversion resistivity prediction model.
In this embodiment of the present invention, the information determining module specifically includes:
the structure interface determining unit is used for determining a structure interface of the measuring section of the underground medium of the pollutant ground according to the geological measurement data of the polluted site;
and the adjusting unit is used for adjusting and optimizing the structural interface of the underground medium measuring section of the polluted site according to the drilling data of the polluted site to obtain the resistivity difference value of the resistivity difference interface and the resistivity difference interface.
In this embodiment of the present invention, the formula for calculating the structure tensor of the plurality of local gray-scale maps is as follows:
wherein, T [ c ]]Representing the structure tensor, txxRepresenting the dot product, t, of the gradient of the pixel in the horizontal direction and itself in the local gray-scale mapzxRepresents the dot product of the pixel gradient in the vertical direction and the pixel gradient in the horizontal direction of the local gray-scale map, txzRepresents the dot product of the pixel gradient of the local gray-scale map in the horizontal direction and the pixel gradient in the vertical direction, tzzRepresenting the dot product of the pixel gradient in the vertical direction of the local gray-scale map with itself, p representing the principal eigenvector of the structure tensor, m representing the secondary eigenvector of the structure tensor, λpEigenvalues of the principal eigenvector, λ, representing the structure tensormEigenvalues of the secondary eigenvectors representing the structure tensor.
In the present specification, the embodiments are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other. For the system disclosed by the embodiment, the description is relatively simple because the system corresponds to the method disclosed by the embodiment, and the relevant points can be referred to the method part for description.
The principle and the embodiment of the present invention are explained by applying specific examples, and the above description of the embodiments is only used to help understanding the method and the core idea of the present invention; meanwhile, for a person skilled in the art, according to the idea of the present invention, the specific embodiments and the application range may be changed. In view of the foregoing, the description is not to be taken in a limiting sense.
Claims (4)
1. A site pollutant characterization method based on directional smooth constraint inversion is characterized by comprising the following steps:
s1: acquiring resistivity difference interface information on the structural boundary of the polluted site according to the drilling data and the geological measurement data of the polluted site; the geological survey data comprises geological radar survey data or seismic survey data; the resistivity difference interface information comprises resistivity differences of the resistivity difference interface and the resistivity difference interface;
s2: constructing a gray scale map according to the resistivity difference interface information;
s3: quantizing the gray level map into a plurality of local gray level maps by using an image recognition technology;
s4: calculating a structure tensor of the local gray-scale images, and calculating a diffusion tensor and a similarity according to the structure tensor;
s5: screening the resistivity difference interface according to the similarity to obtain a final resistivity difference interface;
s6: calculating smooth weight coefficients of the final resistivity difference interface in four directions according to the diffusion tensor;
s7: constructing a four-direction weighted smoothing matrix according to the smoothing weight coefficients in the four directions;
s8: substituting the four-direction weighted smoothing matrix into an inversion algorithm to obtain an inversion resistivity prediction model;
s9: determining a field pollutant distribution range according to the inversion resistivity prediction model;
the formula for calculating the structure tensors of the plurality of local gray-scale maps is as follows:
wherein, T [ c ]]Representing the structure tensor, txxRepresenting the dot product, t, of the gradient of the pixel in the horizontal direction and itself in the local gray-scale mapzxExpressing the dot product of the pixel gradient in the vertical direction and the pixel gradient in the horizontal direction of the local gray level map, txzIndicating local grey scale in levelDot product of directional pixel gradient and vertical pixel gradient, tzzRepresenting the dot product of the pixel gradient in the vertical direction of the local gray-scale map with itself, p representing the principal eigenvector of the structure tensor, m representing the secondary eigenvector of the structure tensor, λpEigenvalues of the principal eigenvectors, λ, representing the structure tensormEigenvalues of secondary eigenvectors representing the structure tensor;
the formula for calculating the diffusion tensor according to the structure tensor is as follows:
wherein D represents the diffusion tensor, 0 < n < 1, plA secondary eigenvector, m, representing the diffusion tensorlThe principal eigenvector representing the diffusion tensor,
eigenvalues of the secondary eigenvectors, λ, representing the diffusion tensorpEigenvalues of the principal eigenvector, λ, representing the structure tensormEigenvalues of secondary eigenvectors representing the structure tensor;
the diffusion tensor is used for positioning the direction of the resistivity difference interface in the gray-scale map, the main direction of the diffusion tensor is the extension direction of the resistivity difference interface, and the diffusion tensor passes through the eigenvalue of the secondary eigenvector
Quantifying the difference degree of the resistivity difference interface, and in order to quantify the difference degree of the resistivity difference interface, better performing quantitative smoothing processing on the boundary, wherein the value of n is 0.5;
the directions of the main eigenvector of the structure tensor and the secondary eigenvector of the diffusion tensor are on the same straight line, and the lengths are unit lengths; the directions of the secondary eigenvector of the structure tensor and the main eigenvector of the diffusion tensor are on the same straight line, and the lengths of the secondary eigenvector and the main eigenvector are unit length vectors;
the formula for calculating the similarity according to the structure tensor is as follows:
wherein S represents similarity, f represents the local gray scale map, and < f > (m)vA smoothing process representing the local gray-scale map in a v direction, v representing m or p, the m direction being a direction of a minor eigenvector of a structure tensor of the local gray-scale map when v is m, and the p direction being a direction of a major eigenvector of the structure tensor of the local gray-scale map when v is p;
calculating smooth weight coefficients of the final resistivity difference interface in four directions according to the diffusion tensor, wherein the formula is as follows:
wherein r isxThe length of the half axis in the horizontal direction of the ellipse representing the diffusion tensor, rzLength of half axis in vertical direction of ellipse representing diffusion tensor, rd1A semi-axial length, r, of the diffusion tensor ellipse in a first diagonal direction of a central pixel unit of the local gray-scale imaged2A semi-axial length of the diffusion tensor ellipse in a second diagonal direction of a central pixel unit of the local gray-scale image is represented; w is axTo representSmoothing weight coefficient, w, of the final resistivity-difference interface in the horizontal directionzRepresents the smoothed weight coefficient, w, of the final resistivity-difference interface in the vertical directiond1And wd2The smoothing weight coefficients of the final resistivity difference interface in the directions of two diagonal lines of the central pixel unit of the local gray-scale image are represented; determining a diffusion tensor ellipse according to the diffusion tensor; determining a structure tensor ellipse according to the structure tensor;
the four-direction weighted smoothing matrix is constructed according to the smoothing weight coefficients in the four directions, and the formula is as follows:
wherein S isx、Sz、Sd1And Sd2Representing the smoothing matrices in the horizontal, vertical and diagonal directions of the central pixel element of the local gray scale image, SmRepresenting said four-direction weighted smoothing matrix, wxRepresents a smoothing weight coefficient, w, of the resistivity-difference interface in the horizontal directionzRepresents a smooth weight coefficient, w, of the resistivity-difference interface in the vertical directiond1And wd2And the smoothing weight coefficients represent the resistivity difference interface in the direction of two diagonal lines of the central pixel unit of the local gray-scale image.
2. The field pollutant characterization method based on directional smooth constraint inversion according to claim 1, wherein the obtaining resistivity difference interface information on the structure boundary of the polluted field according to the drilling data and the geological measurement data of the polluted field specifically comprises:
s11: determining a structural interface of a measuring section of the underground medium of the pollutant ground according to geological measurement data of the polluted site;
s12: and adjusting and optimizing a structural interface of the underground medium measurement section of the polluted site according to the drilling data of the polluted site to obtain a resistivity difference value of the resistivity difference interface and the resistivity difference interface.
3. A site contaminant characterization system based on directional smooth constrained inversion, the system comprising:
the information determination module is used for obtaining resistivity difference interface information on the structural boundary of the polluted site according to the drilling data and the geological measurement data of the polluted site; the geological survey data comprises geological radar survey data or seismic survey data; the resistivity difference interface information comprises resistivity differences of the resistivity difference interface and the resistivity difference interface;
the construction module is used for constructing a gray scale map according to the resistivity difference interface information;
a quantization module for quantizing the gray scale map into a plurality of local gray scale maps using image recognition techniques;
the calculation module is used for calculating the structure tensors of the local gray level images and calculating the diffusion tensors and the similarity according to the structure tensors;
the screening module is used for screening the resistivity difference interface according to the similarity to obtain a final resistivity difference interface;
a smooth weight coefficient determination module, configured to calculate smooth weight coefficients of the final resistivity difference interface in four directions according to the diffusion tensor;
the smooth matrix determining module is used for constructing a four-direction weighted smooth matrix according to the smooth weight coefficients in four directions;
the substitution module is used for substituting the four-direction weighted smooth matrix into an inversion algorithm to obtain an inversion resistivity prediction model;
the range determining module is used for determining a field pollutant distribution range according to the inversion resistivity prediction model;
the formula for calculating the structure tensors of the plurality of local gray-scale maps is as follows:
wherein the content of the first and second substances,T[c]representing the structure tensor, txxRepresenting the dot product, t, of the gradient of the pixel in the horizontal direction and itself in the local gray-scale mapzxExpressing the dot product of the pixel gradient in the vertical direction and the pixel gradient in the horizontal direction of the local gray level map, txzExpressing the dot product, t, of the pixel gradient in the horizontal direction and the pixel gradient in the vertical direction of the local gray scale mapzzRepresenting the dot product of the pixel gradient in the vertical direction of the local gray-scale map with itself, p representing the principal eigenvector of the structure tensor, m representing the secondary eigenvector of the structure tensor, λpEigenvalues of the principal eigenvectors, λ, representing the structure tensormEigenvalues of secondary eigenvectors representing the structure tensor;
the formula for calculating the diffusion tensor according to the structure tensor is as follows:
wherein D represents the diffusion tensor, 0 < n < 1, plA secondary eigenvector, m, representing the diffusion tensorlThe principal eigenvector representing the diffusion tensor,
eigenvalues of the secondary eigenvectors, λ, representing the diffusion tensorpEigenvalues of the principal eigenvectors, λ, representing the structure tensormEigenvalues of secondary eigenvectors representing the structure tensor;
the diffusion tensor is used for positioning the direction of the resistivity difference interface in the gray-scale map, the main direction of the diffusion tensor is the extension direction of the resistivity difference interface, and the diffusion tensor passes through the eigenvalue of the secondary eigenvector
Quantifying the difference degree of the resistivity difference interface, and in order to quantify the difference degree of the resistivity difference interface, better performing quantitative smoothing processing on the boundary, wherein the value of n is 0.5;
the directions of the main eigenvector of the structure tensor and the secondary eigenvector of the diffusion tensor are on the same straight line, and the lengths are unit lengths; the directions of the secondary eigenvector of the structure tensor and the main eigenvector of the diffusion tensor are on the same straight line, and the lengths of the secondary eigenvector and the main eigenvector are unit length vectors;
the formula for calculating the similarity according to the structure tensor is as follows:
wherein S represents similarity, f represents the local gray scale map, and < f > (m)vA smoothing process representing the local gray-scale map in a v direction, v representing m or p, the m direction being a direction of a minor eigenvector of a structure tensor of the local gray-scale map when v is m, and the p direction being a direction of a major eigenvector of the structure tensor of the local gray-scale map when v is p;
and calculating smooth weight coefficients of the final resistivity difference interface in four directions according to the diffusion tensor, wherein the formula is as follows:
wherein r isxThe length of the half axis in the horizontal direction of the ellipse representing the diffusion tensor, rzRepresenting the semi-axial length of the diffusion tensor ellipse in the vertical direction,rd1a semi-axial length, r, of the diffusion tensor ellipse in a first diagonal direction of a central pixel unit of the local gray-scale imaged2A semi-axial length of the diffusion tensor ellipse in a second diagonal direction of a central pixel unit of the local gray-scale image is represented; w is axRepresents the smoothing weight coefficient, w, of the final resistivity-difference interface in the horizontal directionzRepresents the smoothed weight coefficient, w, of the final resistivity-difference interface in the vertical directiond1And wd2Representing the smooth weight coefficient of the final resistivity difference interface in the directions of two diagonal lines of the central pixel unit of the local gray-scale image; determining a diffusion tensor ellipse according to the diffusion tensor; determining a structure tensor ellipse according to the structure tensor;
the four-direction weighted smoothing matrix is constructed according to the smoothing weight coefficients in the four directions, and the formula is as follows:
wherein S isx、Sz、Sd1And Sd2Representing the smoothing matrices in the horizontal, vertical and diagonal directions of the central pixel element of the local gray scale image, SmRepresenting said four-direction weighted smoothing matrix, wxRepresents a smoothing weight coefficient, w, of the resistivity-difference interface in the horizontal directionzRepresents the smooth weight coefficient, w, of the resistivity-difference interface in the vertical directiond1And wd2And the smoothing weight coefficients represent the resistivity difference interface in the direction of two diagonal lines of the central pixel unit of the local gray-scale image.
4. The field pollutant characterization system based on directional smooth constrained inversion of claim 3, wherein the information determination module specifically comprises:
the structure interface determining unit is used for determining a structure interface of a pollutant underground medium measuring section according to geological measurement data of a pollution site;
and the adjusting unit is used for adjusting and optimizing the structural interface of the underground medium measuring section of the polluted site according to the drilling data of the polluted site to obtain the resistivity difference value of the resistivity difference interface and the resistivity difference interface.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110299494.8A CN113034638B (en) | 2021-03-22 | 2021-03-22 | Site pollutant depicting method and system based on directional smooth constraint inversion |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110299494.8A CN113034638B (en) | 2021-03-22 | 2021-03-22 | Site pollutant depicting method and system based on directional smooth constraint inversion |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113034638A CN113034638A (en) | 2021-06-25 |
| CN113034638B true CN113034638B (en) | 2022-06-17 |
Family
ID=76472330
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110299494.8A Active CN113034638B (en) | 2021-03-22 | 2021-03-22 | Site pollutant depicting method and system based on directional smooth constraint inversion |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113034638B (en) |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109655891A (en) * | 2017-10-11 | 2019-04-19 | 中国石油化工股份有限公司 | Overcome the method and system of full waveform inversion cycle skipping |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103489163B (en) * | 2013-09-13 | 2016-01-20 | 电子科技大学 | Based on the seismic image structure directing noise-reduction method of regularization mixing norm filtering |
| CN107290730B (en) * | 2017-05-10 | 2020-08-07 | 长江大学 | Bistatic MIMO radar angle estimation method under cross-coupling condition |
| CN108022221A (en) * | 2017-12-06 | 2018-05-11 | 河北工业大学 | A kind of three-dimensional dispersion point cloud smoothing denoising method of Anisotropic diffusion filtering |
| CN111221048B (en) * | 2020-01-21 | 2021-04-06 | 山东大学 | Boulder boundary identification and imaging method based on cross-hole resistivity CT multi-scale inversion |
-
2021
- 2021-03-22 CN CN202110299494.8A patent/CN113034638B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109655891A (en) * | 2017-10-11 | 2019-04-19 | 中国石油化工股份有限公司 | Overcome the method and system of full waveform inversion cycle skipping |
Non-Patent Citations (1)
| Title |
|---|
| 基于结构张量的视频超分辨率算法;严宏海等;《计算机应用》;20160710(第07期);第1095-1098页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113034638A (en) | 2021-06-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Promma et al. | Application of the virtual fields method to mechanical characterization of elastomeric materials | |
| Bisdom et al. | Calibrating discrete fracture-network models with a carbonate three-dimensional outcrop fracture network: Implications for naturally fractured reservoir modeling | |
| US6662109B2 (en) | Method of constraining by dynamic production data a fine model representative of the distribution in the reservoir of a physical quantity characteristic of the subsoil structure | |
| Lin et al. | Multiscale digital porous rock reconstruction using template matching | |
| US11112516B2 (en) | Data fusion technique to compute reservoir quality and completion quality by combining various log measurements | |
| Jing et al. | Topological characterization of fractured coal | |
| EP3077618B1 (en) | Tuning digital core analysis to laboratory results | |
| Jouini et al. | Numerical estimation of rock properties and textural facies classification of core samples using X-Ray Computed Tomography images | |
| EP4024260A1 (en) | Computer simulation of multi-phase and multi-component fluid flows including physics of under-resolved porous structures | |
| Jouini et al. | Multifractal analysis of reservoir rock samples using 3D X-ray micro computed tomography images | |
| Cui et al. | VP and VS prediction from digital rock images using a combination of U-Net and convolutional neural networks | |
| Abadpour et al. | Integrated geo-modeling and ensemble history matching of complex fractured carbonate and deep offshore turbidite fields, generation of several geologically coherent solutions using ensemble methods | |
| Hajizadeh et al. | An algorithm for 3D pore space reconstruction from a 2D image using sequential simulation and gradual deformation with the probability perturbation sampler | |
| Feng et al. | A Bayesian approach for uncertainty quantification in overcoring stress estimation | |
| Karim et al. | Electrical resistivity as a binary classifier for bridge scour evaluation | |
| CN113034638B (en) | Site pollutant depicting method and system based on directional smooth constraint inversion | |
| CN112329287B (en) | P-y curve Bayes learning method based on test pile monitoring data | |
| Li et al. | Bridging Computational Stratigraphy and Reservoir Simulation for Geologically Realistic High-Resolution Reservoir Modeling | |
| Friedman et al. | A worked-out example of surrogate-based bayesian parameter and field identification methods | |
| Zhou et al. | Knowledge-based multiple point statistics for soil stratigraphy simulation | |
| CN112819813B (en) | Intelligent underground pipeline identification method and device and storage medium | |
| CN115577881A (en) | Prediction method for deep coal gas content based on support vector machine regression model | |
| Korneev et al. | Downscaling‐based segmentation for unresolved images of highly heterogeneous granular porous samples | |
| Msaddek et al. | A fuzzy mathematical model for evaluation of rock-fracture and structural complexity: application for Southern Atlas in Tunisia | |
| Azizzadeh Mehmandoust Olya et al. | Hydrocarbon reservoir potential mapping through Permeability estimation by a CUDNNLSTM Deep Learning Algorithm |
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 |