CN112800158A - Vectorization representation method of geological map - Google Patents
Vectorization representation method of geological map Download PDFInfo
- Publication number
- CN112800158A CN112800158A CN202110068210.4A CN202110068210A CN112800158A CN 112800158 A CN112800158 A CN 112800158A CN 202110068210 A CN202110068210 A CN 202110068210A CN 112800158 A CN112800158 A CN 112800158A
- Authority
- CN
- China
- Prior art keywords
- geological
- map
- elements
- geological map
- information
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/29—Geographical information databases
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/26—Visual data mining; Browsing structured data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/38—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/387—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using geographical or spatial information, e.g. location
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/284—Lexical analysis, e.g. tokenisation or collocates
-
- 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
- G06N3/08—Learning methods
Abstract
The invention discloses a vectorization representation method of a geological map, wherein the analysis and processing capacity of geoscience data is promoted by big data and artificial intelligence technology, a geological map is a main form of geological big data accumulated for a long time, wherein the geological map comprises abundant and important information of geological evolution, mineral deposit formation and mineral deposit distribution, and is an important information source for geological research and mineral finding prediction, the geological map information is difficult to be used for quantitative geological analysis and mineral finding prediction, good conditions are created for processing and analyzing geological big data by the big data and the artificial intelligence technology, and the key for realizing intelligent mineral finding prediction is to convert the geological map into a form which can be used for machine learning. The invention discloses a vectorization representation method of a geological map, which converts semantic information contained in the geological map into a computable form so that rich information contained in the geological map can be quantitatively analyzed and calculated.
Description
Technical Field
The invention relates to the technical field of geological survey and mineral geological survey and exploration, in particular to a vectorization representation method of a geological map.
Background
Geological mapping is a main form of geological big data accumulated for a long time, which includes abundant and important geological evolution, mineral deposit formation and deposit distribution, and is a very important information source for geological research and mineral finding prediction. Geological mapping information has long been difficult to use for quantitative geological analysis and prospecting predictions. The rise of big data and artificial intelligence technology creates good conditions for processing and analyzing geological big data, and under the background, the key for realizing intelligent prospecting prediction is to convert geological type images into a form which can be used for machine learning.
The invention discloses a vectorization representation method of a geological map. The semantic information contained in the geological map is converted into a vector form which can be calculated by a computer by adopting a natural language processing technology. In the process of converting the geological map into a gridding form, the geological semantic information of each grid unit is expressed by a vector according to a geological language model, so that rich geological information contained in the geological map can be analyzed and calculated quantitatively. The vectorized representation of the geological map may represent rich geological information contained by the geological map. The method is mainly applied to the fields of mineral geological survey and mineral exploration.
Wherein the geological map comprises: regional geological map, regional mineral geological map, remote sensing geological interpretation map, geophysical interpretation map, geological profile and other geological maps.
Word embedding, sentence embedding, text embedding and other natural language processing technologies can convert words, sentences and texts into a multidimensional vector, and the words, sentences and texts with similar semantics are relatively close to each other in a multidimensional vector space. The attributes of geological elements are commonly expressed in the form of words, sentences or texts, a geological element, such as an invaded rock mass, generally has the characteristics of spatial position, formation era, rock composition and the like, the basic characteristics of the rock mass can be expressed by early chalky second-long granite, and the early chalky second-long granite can be expressed in the form of vectors by trained language models, such as [0.27853, 0.32456, 0.54573, 0.05467,0.15673 and … ], the vectors represent the attributes of the formation era and the material composition of the rock mass, and the position of the word vector in the vector space records the context semantic relationship of the word.
By representing the attribute information of the geological elements as vectors, complex and various geological attribute representation forms can be processed, the attribute characteristics of the geological elements can be uniformly represented, and the deep learning-based mining prediction of a large area and even nationwide can be realized.
Gridding and location attributes. After determining the attribute vectors for the geological elements of the defined region, attribute vectors may be assigned to each grid cell. After the geological map is expressed in a vector form, the attribute features of geological elements are semantically and formally unified, and can be effectively fused with geophysical prospecting, chemical prospecting and remote sensing data, and tasks such as classification and prediction are performed by a machine learning or deep learning method.
Disclosure of Invention
This section is for the purpose of summarizing some aspects of embodiments of the invention and to briefly introduce some preferred embodiments. In this section, as well as in the abstract and the title of the invention of this application, simplifications or omissions may be made to avoid obscuring the purpose of the section, the abstract and the title, and such simplifications or omissions are not intended to limit the scope of the invention.
Therefore, the invention aims to provide a method for vectorizing and representing a geological map, which converts semantic information contained in the geological map into a computable form so that rich information contained in the geological map can be used for quantitative analysis and calculation.
To solve the above technical problem, according to an aspect of the present invention, the present invention provides the following technical solutions:
a method of vectorized representation of a geological map, comprising the steps of:
s1: constructing a corpus according to regional geological data, and training a deep learning language model;
s2: the method comprises the steps of obtaining vectorization representation of geological attributes of each geological element based on a trained model according to attributes of the geological elements of the geological map, such as stratum era, rock combinations and the like, generating different geological element layers aiming at different geological elements, such as stratum units, rock masses, fractures and the like, and superposing the vector representations of the different geological elements to form complete representation of geological map information.
S3: the position information of each grid unit is synthesized on a vector, so that each grid unit contains space, time and composition information of the geological elements, different from the traditional geological map gridding method, the geological elements are represented by 0 and 1, and the space, time and material composition information of the geological elements can be represented by the geological map vectorization representation method.
As a preferred embodiment of the method for vectorized representation of a geological map according to the present invention, wherein: in the step S1, on the basis of a geological corpus constructed according to a large amount of geological data, monographs, and treatises, a geological language model capable of including various geological concepts is constructed by training a language model, such as a skip-gram.
As a preferred embodiment of the method for vectorized representation of a geological map according to the present invention, wherein: in step S2, the above language model is used to convert the attribute information of the geocellular into an attribute vector according to the attribute of the geocellular.
As a preferred embodiment of the method for vectorized representation of a geological map according to the present invention, wherein: in step S2, the region of interest is divided into grids of m rows × n columns in a predetermined grid cell size, for example, 50m × 50m, 100m × 100m, and the attribute vector of each cell is assigned to the corresponding geocell.
As a preferred embodiment of the method for vectorized representation of a geological map according to the present invention, wherein: in step S2, a distance x parameter between each grid cell and the geological element is calculated, and d-e is adopted-bxCalculating a distance-dependent parameter d, wherein b isThe attenuation coefficient.
As a preferred embodiment of the method for vectorized representation of a geological map according to the present invention, wherein: the step S3 adds distance parameters to the attribute vectors so that each grid cell contains spatial, temporal and compositional information of the geological element.
Compared with the prior art: and gridding the geological map by adopting a natural language processing technology, and converting semantic information contained in the geological map into a form which can be calculated by a computer. The geological map is converted into a gridding form, so that rich information contained in the geological map can be analyzed and calculated quantitatively, the vectorization representation result of the geological map can represent the rich geological information contained in the geological map, and the vectorization representation method of the geological map converts semantic information contained in the geological map into a form which can be calculated by a computer, so that the rich information contained in the geological map can be analyzed and calculated quantitatively.
Detailed Description
The present invention will be described in detail with reference to the following embodiments in order to make the aforementioned objects, features and advantages of the invention more comprehensible.
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention, but the present invention may be practiced in other ways than those specifically described herein, and it will be apparent to those of ordinary skill in the art that the present invention may be practiced without departing from the spirit and scope of the present invention, and therefore the present invention is not limited to the specific embodiments disclosed below.
In order to make the objects, technical solutions and advantages of the present invention more apparent, embodiments of the present invention will be described in further detail below.
The invention provides a vectorization representation method of a geological map, which comprises the following steps:
s1: constructing a corpus according to regional geological data, and training a deep learning language model;
s2: the method comprises the steps of obtaining vectorization representation of geological attributes of each geological element based on a trained model according to attributes of the geological elements of the geological map, such as stratum era, rock combinations and the like, generating different geological element layers aiming at different geological elements, such as stratum units, rock masses, fractures and the like, and superposing the vector representations of the different geological elements to form complete representation of geological map information.
S3: the position information of each grid unit is synthesized on a vector, so that each grid unit contains space, time and composition information of the geological elements, different from the traditional geological map gridding method, the geological elements are represented by 0 and 1, and the space, time and material composition information of the geological elements can be represented by the geological map vectorization representation method.
In step S1, on the basis of a geological corpus constructed on the basis of a large amount of geological data, monographs, and treatises, a geological language model capable of including various geological concepts is constructed by training a language model, such as a skip-gram.
In step S2, the above language model is used to convert the attribute information of the geocellular into an attribute vector according to the attribute of the geocellular.
In step S2, the region of interest is divided into grids of m rows × n columns in a predetermined grid cell size, for example, 50m × 50m, 100m × 100m, and the attribute vector of each cell is assigned to the corresponding geocell.
In step S2, a distance x parameter between each grid cell and the geological element is calculated, and d-e is adopted-bxA distance-dependent parameter d is calculated, where b is the attenuation coefficient.
The step S3 adds distance parameters to the attribute vectors so that each grid cell contains spatial, temporal and compositional information of the geological element.
The technology for extracting the mineral geology big data is to grid geological elements represented by each area, arc section and line according to a mineral geology space database or a construction space database, wherein the attribute parameters of each grid unit comprise a series of parameters such as relative position, relative orientation, relative trend, relative inclination and relative inclination angle, a series of graphs can be generated through deep learning mode classification, such as a relative position mode classification graph, a relative orientation mode classification graph and the like, the graphs reflect the spatial characteristics of various geological elements, and the characteristics have important correlation with the distribution of mineral deposits. In the gridding process, the influence ranges of various geological elements are controlled by adopting a scope function, different geologic bodies and geologic boundary lines have different influence ranges on mineralization, and a possible mineralization scope can be effectively limited by selecting a proper scope model. The relative orientation mode classification map can reflect macroscopic spatial features and can reflect detailed spatial position mode features.
The relative attribute gridding method can express the correlation relationship between any one space position and any geological element in space, time and material composition. The series of attributes of each grid cell of each element layer represents information of the grid cell relative to the position, the orientation and the like of the geological element, for example, the relative position of a certain grid cell relative to the F1 fracture is 3200m and the relative orientation is NE45 degrees, and the information can be interpreted that the distance between an F1 fault and the center of the grid cell is 3200m and the grid cell is located in the NE45 degree direction of the grid cell.
In mineral geology maps, a region generally represents an invaded body, volcanic body, sedimentary body, metamorphic body, ductile shear band, altered band, and the like. Invader, ductile shear zone may be an important mineralizing geologic body, and altered zone is an important mineral finding marker. By analyzing the correlation between each grid cell and each geologic body and the relation of known ore deposits, the mineralizing geologic body can be determined, and the mineralizing rule can be found.
The arcs represent a portion of geological interfaces that may be important mineralizing geological interfaces, and through detailed gridding arc analysis, the relationship of each arc to the deposit can be revealed. The fractures are represented as lines on the mineral geology map, and the relationship between the deposit and the fractures can be found through gridding processing and pattern analysis of spatial positions of each fracture.
Various geological elements represented on the geological map are disassembled into geometric units, points, arc sections, lines and areas with different geological meanings, vectorization representation is carried out on the basis of a geological language model, and a solid foundation is laid for realizing large-data artificial intelligence analysis of the geological map.
1. Relative spatial position information
The geologic body is taken as an example for explanation, the geologic body is divided into fine arc segments, then the range of the arc segments is gridded, a central point in one grid is selected, and the following five spatial position attribute information are calculated and extracted:
(1) distance: the shortest distance from the center point of the grid to the arc segment represents the spatial position relationship of a given spatial position to the geologic body or geologic interface. Generally, the closer a spatial location is to an mineralizing geological body, the greater the probability of mineralizing, such as medium and low temperature magmatic gold deposits generally developing within 3km from the rock mass.
(2) Orientation: which orientation of the arc segment is at the center point of the grid. The relative orientation information shows the relative orientation relation between the designated space position and the geological elements, and the distance and orientation information are combined to determine the relative position between the designated space position and the geological elements. The geologic space has obvious anisotropy, and spatial positions in different directions have different mineralization possibilities.
(3) The trend is as follows: the stratum trend of the central point of the grid and the trend of the geologic body at the arc section form an included angle, and the attribute characteristics reflect the relationship of the trend of the stratum (fracture and rock body boundary) where the grid unit is located. If the strata trend is oblique to the rock mass boundary, if the rock mass is an ore-forming geologic body, the formation is possibly beneficial because the strata boundary can be a migration channel of the ore-forming fluid.
(4) Tendency: the relationship between the stratigraphic (fracture, etc.) inclination of the center point of the grid and the inclination of the geologic volume at the arc segments.
(5) Inclination angle: the relationship between the dip of the formation at the center point of the grid and the dip of the geologic volume at the arc segment.
2. Temporal relationship
Representing the temporal relevance of a certain grid cell to a geological element. If the stratum age of the designated position is older than that of the mineralized rock mass, the stratum unit has the possibility of mineralization, otherwise, the stratum unit does not have the possibility of mineralization; if the dike of the designated position is close to the formation age of the ore-forming rock mass, the designated position has the ore-forming possibility and is a favorable ore finding position.
3. Composition relationship of matter
Representing the relevance of a grid cell to a geological element in terms of material composition. For example, the dike developed at a designated position has correlation with the mineralizing rock mass in material composition (main elements, trace elements, rare earth elements and isotopes), and the dike is closely related to mineralizing.
4. Energy of
Representing the relevance of a certain grid cell to a geological element in terms of energy supply. If the designated position has contact metamorphism or thermal alteration and is near the mineralizing geologic body, the designated position and the mineralizing rock body have correlation in energy.
The multiple attributes of a grid cell characterize its time-space-material-energy (TSME) attribute. The attribute features representing any grid cell relative to a certain geological element (e.g., fracture F2) can be quantified by relative attribute gridding. For example, F2 is located at NE45 ° of grid cell (row, col) at a distance of 35 m.
The relative attribute of the grid unit describes the incidence relation between any one spatial position and geological elements in the aspect of TSME, and the relation between known ore deposit (point) and the relative attribute is combined, so that the mining control factor, the ore finding mark, the mining rule and the ore deposit development position can be effectively analyzed, and the favorable mining position can be predicted.
Example (b):
1. influence of geological factors on mineralization
Various geological elements have obviously different influences on the mineralization, the rock mass is usually an mineralization geologic body of a medium-low temperature magma hydrothermal gold deposit, the distance from the rock mass is an important factor influencing the mineralization, and the mineralization strength generally shows an attenuation trend along with the increase of the distance from the rock mass; mineralization generally develops relatively within or near the fracture zone, and does not develop outside the fracture zone. The silico-calcium surface is an important mineralizing geological interface.
2. Influence of geological factors on mineralization
The influence strength of the geological elements on the mineralization and the relation between various geological elements and the mineralization can be expressed by using the function of the distance. And performing geological map gridding on the basis. The range of influence 3 of a certain geological element on mineralization is called scope (or influence domain): such as the extent to which the outer contact zone is associated with mineralization.
The influence function is a function for describing the influence (range and strength) of a certain geological element on the mineralization, different functions can be used for describing the relation between the geological element and the mineralization, such as a linear function, an exponential function, a tanh function and the like (table 1), the exponential function (formula 1-1) can describe the process of the attenuation of the influence strength along with the increase of the distance from the geological element, the influence function is a common influence function for describing the relation between the geological element and the mineralization, and different attenuation coefficients can be adopted for different geological elements:
I＝ae-bx (1-1)
where a and b are coefficients, and a represents the magnitude of the effect, and is usually 1.0; b represents a decay coefficient, the rate of decay being faster the larger the value; x represents the distance from the geological element; i denotes the influence intensity.
TABLE 1 Primary influence function
While the invention has been described above with reference to an embodiment, various modifications may be made and equivalents may be substituted for elements thereof without departing from the scope of the invention. In particular, the various features of the disclosed embodiments of the invention may be used in any combination, provided that no structural conflict exists, and the combinations are not exhaustively described in this specification merely for the sake of brevity and resource conservation. Therefore, it is intended that the invention not be limited to the particular embodiments disclosed, but that the invention will include all embodiments falling within the scope of the appended claims.
Claims (6)
1. A method for vectorized representation of a geological map, comprising the steps of:
s1: a corpus is constructed according to regional geological data, and a deep learning geological language model is trained;
s2: the method comprises the steps of obtaining vectorization representation of geological properties of each geological element based on a trained geological language model according to the properties of the geological elements of the geological map, such as stratum era, rock combinations and the like, generating different geological element layers aiming at different geological elements, such as stratum units, rock masses, fractures and the like, and superposing the vector representations of different geological elements to form complete representation of geological map information.
S3: the position information of each grid unit is synthesized on a vector, so that each grid unit contains space, time and composition information of the geological elements, different from the traditional geological map gridding method, the geological elements are represented by 0 and 1, and the space, time and material composition information of the geological elements can be represented by the geological map vectorization representation method.
2. The method of claim 1, wherein in step S1, a language model, such as skip-gram, is used to build a geologic language model capable of including various geologic concepts by training the language model based on a geologic corpus built from a large amount of geologic data, monographs, and treatises.
3. The method of claim 1, wherein in step S2, the attribute information of the geocellular is converted into the attribute vector by using the geologic language model according to the attribute of the geocellular.
4. The method of claim 1, wherein in step S2, the area under study is divided into m rows by n columns of grids according to a certain grid cell size, such as 50m x 50m or 100m x 100m, and the attribute vector of each grid cell is assigned to the grid cell according to the geological cell in which the grid cell is located.
5. According to the rightThe method of vectorizing a geological map according to claim 1, wherein in step S2, a distance x parameter between each grid cell and a geological element is calculated, and d-e is adopted-bxA distance-dependent parameter d is calculated, where b is the attenuation coefficient.
6. The method of claim 1, wherein the step of adding distance parameters to the attribute vectors in step S3 is performed such that each grid cell contains spatial, temporal and compositional information of the geological element.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110068210.4A CN112800158B (en) | 2021-01-19 | 2021-01-19 | Vectorization representation method of geological map |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110068210.4A CN112800158B (en) | 2021-01-19 | 2021-01-19 | Vectorization representation method of geological map |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112800158A true CN112800158A (en) | 2021-05-14 |
| CN112800158B CN112800158B (en) | 2022-09-13 |
Family
ID=75810398
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110068210.4A Active CN112800158B (en) | 2021-01-19 | 2021-01-19 | Vectorization representation method of geological map |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112800158B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113656980A (en) * | 2021-08-26 | 2021-11-16 | 中国地质科学院地质力学研究所 | Method and system for determining mining property of fracture area |
Citations (23)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6480790B1 (en) * | 1999-10-29 | 2002-11-12 | Exxonmobil Upstream Research Company | Process for constructing three-dimensional geologic models having adjustable geologic interfaces |
| US20050143921A1 (en) * | 2003-12-12 | 2005-06-30 | Exxonmobil Upstream Research Company | Method for seismic imaging in geologically complex formations |
| US20090248374A1 (en) * | 2008-03-26 | 2009-10-01 | Hao Huang | Modeling of Hydrocarbon Reservoirs Containing Subsurface Features |
| US20100191511A1 (en) * | 2007-08-24 | 2010-07-29 | Sheng-Yuan Hsu | Method For Multi-Scale Geomechanical Model Analysis By Computer Simulation |
| US20120316847A1 (en) * | 2011-06-10 | 2012-12-13 | Thomas Hantschel | Prospect assessment and play chance mapping tools |
| US20160171027A1 (en) * | 2014-03-31 | 2016-06-16 | International Business Machines Corporation | Fast and accurate geomapping |
| CN105931295A (en) * | 2016-07-13 | 2016-09-07 | 中国地质大学（北京） | Geological map thematic information extraction method |
| CN106354807A (en) * | 2016-08-29 | 2017-01-25 | 中国地质调查局发展研究中心 | Geological map compilation device and method based on data driven |
| CN106846481A (en) * | 2017-03-14 | 2017-06-13 | 中国地质科学院矿产资源研究所 | Geological profile generation method |
| CN107808413A (en) * | 2017-10-30 | 2018-03-16 | 中国煤炭地质总局水文地质局 | A kind of three-dimensional geological modeling method based on GOCAD |
| CN110163931A (en) * | 2019-04-29 | 2019-08-23 | 山东省地质矿产勘查开发局第六地质大队 | Large-scale geological mapping method for complex mining area |
| CN110244344A (en) * | 2019-06-05 | 2019-09-17 | 中南大学 | A kind of TBM method for forecasting advanced geology based on deep learning |
| CN110827405A (en) * | 2019-11-11 | 2020-02-21 | 云南农业大学 | Digital remote sensing geological mapping method and system |
| CN110888912A (en) * | 2019-10-15 | 2020-03-17 | 中国人民解放军国防科技大学 | Target behavior semantic track prediction method based on space-time big data |
| CN111080021A (en) * | 2019-12-24 | 2020-04-28 | 中国海洋石油集团有限公司 | Sand body configuration CMM neural network prediction method based on geological information base |
| US20200183047A1 (en) * | 2018-12-11 | 2020-06-11 | Exxonmobil Upstream Research Company | Automated Reservoir Modeling Using Deep Generative Networks |
| CN111273372A (en) * | 2020-02-11 | 2020-06-12 | 成都理工大学 | Mapping method for mapping potential mineralization temperature combination map based on chemical exploration abnormity |
| CN111400524A (en) * | 2020-03-03 | 2020-07-10 | 中国地质大学（北京） | AI-based variable-scale geological map text vectorization method and system |
| CN111583407A (en) * | 2020-06-05 | 2020-08-25 | 武汉正远岩土科技有限公司 | Efficient three-dimensional geological modeling intelligent processing method based on paper drilling |
| CN111862778A (en) * | 2020-06-04 | 2020-10-30 | 中国地质科学院 | Shallow lithology geological map generation method and device, storage medium and equipment |
| CN111898836A (en) * | 2020-08-18 | 2020-11-06 | 石拓 | Crime space-time prediction method and system |
| GB202018798D0 (en) * | 2020-01-14 | 2021-01-13 | Landmark Graphics Corp | Techniques for extraction of vectorized content of an oil and gas play with an unstructed file |
| US20210011193A1 (en) * | 2018-06-22 | 2021-01-14 | Exxonmobil Upstream Research Company | Methods and Systems for Generating Simulation Grids via Zone by Zone Mapping from Design Space |
-
2021
- 2021-01-19 CN CN202110068210.4A patent/CN112800158B/en active Active
Patent Citations (23)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6480790B1 (en) * | 1999-10-29 | 2002-11-12 | Exxonmobil Upstream Research Company | Process for constructing three-dimensional geologic models having adjustable geologic interfaces |
| US20050143921A1 (en) * | 2003-12-12 | 2005-06-30 | Exxonmobil Upstream Research Company | Method for seismic imaging in geologically complex formations |
| US20100191511A1 (en) * | 2007-08-24 | 2010-07-29 | Sheng-Yuan Hsu | Method For Multi-Scale Geomechanical Model Analysis By Computer Simulation |
| US20090248374A1 (en) * | 2008-03-26 | 2009-10-01 | Hao Huang | Modeling of Hydrocarbon Reservoirs Containing Subsurface Features |
| US20120316847A1 (en) * | 2011-06-10 | 2012-12-13 | Thomas Hantschel | Prospect assessment and play chance mapping tools |
| US20160171027A1 (en) * | 2014-03-31 | 2016-06-16 | International Business Machines Corporation | Fast and accurate geomapping |
| CN105931295A (en) * | 2016-07-13 | 2016-09-07 | 中国地质大学（北京） | Geological map thematic information extraction method |
| CN106354807A (en) * | 2016-08-29 | 2017-01-25 | 中国地质调查局发展研究中心 | Geological map compilation device and method based on data driven |
| CN106846481A (en) * | 2017-03-14 | 2017-06-13 | 中国地质科学院矿产资源研究所 | Geological profile generation method |
| CN107808413A (en) * | 2017-10-30 | 2018-03-16 | 中国煤炭地质总局水文地质局 | A kind of three-dimensional geological modeling method based on GOCAD |
| US20210011193A1 (en) * | 2018-06-22 | 2021-01-14 | Exxonmobil Upstream Research Company | Methods and Systems for Generating Simulation Grids via Zone by Zone Mapping from Design Space |
| US20200183047A1 (en) * | 2018-12-11 | 2020-06-11 | Exxonmobil Upstream Research Company | Automated Reservoir Modeling Using Deep Generative Networks |
| CN110163931A (en) * | 2019-04-29 | 2019-08-23 | 山东省地质矿产勘查开发局第六地质大队 | Large-scale geological mapping method for complex mining area |
| CN110244344A (en) * | 2019-06-05 | 2019-09-17 | 中南大学 | A kind of TBM method for forecasting advanced geology based on deep learning |
| CN110888912A (en) * | 2019-10-15 | 2020-03-17 | 中国人民解放军国防科技大学 | Target behavior semantic track prediction method based on space-time big data |
| CN110827405A (en) * | 2019-11-11 | 2020-02-21 | 云南农业大学 | Digital remote sensing geological mapping method and system |
| CN111080021A (en) * | 2019-12-24 | 2020-04-28 | 中国海洋石油集团有限公司 | Sand body configuration CMM neural network prediction method based on geological information base |
| GB202018798D0 (en) * | 2020-01-14 | 2021-01-13 | Landmark Graphics Corp | Techniques for extraction of vectorized content of an oil and gas play with an unstructed file |
| CN111273372A (en) * | 2020-02-11 | 2020-06-12 | 成都理工大学 | Mapping method for mapping potential mineralization temperature combination map based on chemical exploration abnormity |
| CN111400524A (en) * | 2020-03-03 | 2020-07-10 | 中国地质大学（北京） | AI-based variable-scale geological map text vectorization method and system |
| CN111862778A (en) * | 2020-06-04 | 2020-10-30 | 中国地质科学院 | Shallow lithology geological map generation method and device, storage medium and equipment |
| CN111583407A (en) * | 2020-06-05 | 2020-08-25 | 武汉正远岩土科技有限公司 | Efficient three-dimensional geological modeling intelligent processing method based on paper drilling |
| CN111898836A (en) * | 2020-08-18 | 2020-11-06 | 石拓 | Crime space-time prediction method and system |
Non-Patent Citations (5)
| Title |
|---|
| BLAGOJ DELIPETREV 等: "GIS MODEL OF THE BASIC GEOLOGICAL MAP AS A BASIS FOR GEODATABASE OF THE REPUBLIC OF MACADONIA", 《HTTP://EPRINTS.UGD.EDU.MK/4114/》 * |
| 宋越等: "煤系地层三维地质模型精细化表达研究", 《中国矿业》 * |
| 张雪英等: "基于深度信念网络的地质实体识别方法", 《岩石学报》 * |
| 王杨刚等: "基于空间数据和专家知识驱动的地质编图技术研究与应用", 《地质通报》 * |
| 马凯: "地质大数据表示与关联关键技术研究", 《中国博士学位论文全文数据库》 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113656980A (en) * | 2021-08-26 | 2021-11-16 | 中国地质科学院地质力学研究所 | Method and system for determining mining property of fracture area |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112800158B (en) | 2022-09-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Tadeusiewicz | Neural networks in mining sciences–general overview and some representative examples | |
| Rashid et al. | Reservoir quality prediction of gas-bearing carbonate sediments in the Qadirpur field: Insights from advanced machine learning approaches of SOM and cluster analysis | |
| Zhang et al. | Identification of sedimentary facies with well logs: an indirect approach with multinomial logistic regression and artificial neural network | |
| Parapuram et al. | An artificially intelligent technique to generate synthetic geomechanical well logs for the bakken formation | |
| Xu et al. | Evaluation of active learning algorithms for formation lithology identification | |
| CN114138923A (en) | Method for constructing geological map knowledge graph | |
| Xiao et al. | 3D mineral prospectivity mapping based on deep metallogenic prediction theory: A case study of the Lala Copper Mine, Sichuan, China | |
| Wang et al. | Recognition of significant surface soil geochemical anomalies via weighted 3D shortest-distance field of subsurface orebodies: a case study in the Hongtoushan copper mine, NE China | |
| Wang et al. | Deep learning reservoir porosity prediction using integrated neural network | |
| CN112800158B (en) | Vectorization representation method of geological map | |
| Mustafa et al. | Shale brittleness prediction using machine learning—A Middle East basin case study | |
| Sfidari et al. | Prediction of pore facies using GMDH-type neural networks: a case study from the South Pars gas field, Persian Gulf basin | |
| Qiu et al. | Geological profile-text information association model of mineral exploration reports for fast analysis of geological content | |
| Ferrer et al. | Modeling the uncertainty in the layout of geological units by implicit boundary simulation accounting for a preexisting interpretive geological model | |
| Mohammadinia et al. | Application of machine learning algorithms in classification the flow units of the Kazhdumi reservoir in one of the oil fields in southwest of Iran | |
| Sun et al. | Real-time updating method of local geological model based on logging while drilling process | |
| Wenhua et al. | Lithology classification of volcanic rocks based on conventional logging data of machine learning: A case study of the eastern depression of Liaohe oil field | |
| Gu et al. | A smart predictor used for lithologies of tight sandstone reservoirs: a case study of member of Chang 4+ 5, Jiyuan Oilfield, Ordos Basin | |
| Choubineh et al. | Machine learning to improve natural gas reservoir simulations | |
| Carranza | Mineral Prospectivity Analysis | |
| Mosegaard | Monte Carlo method | |
| Kadkhodaie et al. | Prediction of pore facies using GMDH-type neural networks: a case study from the South Pars gas field, Persian Gulf basin | |
| Hamzeh et al. | An ABC-optimized fuzzy ELECTRE approach for assessing petroleum potential at the petroleum system level | |
| Pisel et al. | Classifying basin‐scale stratigraphic geometries from subsurface formation tops with machine learning | |
| Tamoto et al. | Synthetic Slowness Shear Well-Log Prediction Using Supervised Machine Learning Models |
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 |