CN112906940A - Sniffing intelligent ore finding prediction method based on deep learning - Google Patents
Sniffing intelligent ore finding prediction method based on deep learning Download PDFInfo
- Publication number
- CN112906940A CN112906940A CN202110068202.XA CN202110068202A CN112906940A CN 112906940 A CN112906940 A CN 112906940A CN 202110068202 A CN202110068202 A CN 202110068202A CN 112906940 A CN112906940 A CN 112906940A
- Authority
- CN
- China
- Prior art keywords
- data
- prospecting
- geological
- prediction
- deep learning
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 53
- 238000013135 deep learning Methods 0.000 title claims abstract description 23
- 229910052500 inorganic mineral Inorganic materials 0.000 claims abstract description 21
- 239000011707 mineral Substances 0.000 claims abstract description 21
- 239000000126 substance Substances 0.000 claims abstract description 16
- 238000012549 training Methods 0.000 claims abstract description 14
- 238000013527 convolutional neural network Methods 0.000 claims abstract description 13
- 238000011160 research Methods 0.000 claims description 16
- 238000005065 mining Methods 0.000 claims description 7
- 238000005516 engineering process Methods 0.000 claims description 6
- 238000012795 verification Methods 0.000 claims description 5
- 230000002159 abnormal effect Effects 0.000 claims description 3
- 238000013136 deep learning model Methods 0.000 claims description 3
- 238000005553 drilling Methods 0.000 claims description 3
- 230000001089 mineralizing effect Effects 0.000 claims description 3
- 238000012360 testing method Methods 0.000 abstract description 3
- 230000001131 transforming effect Effects 0.000 abstract 1
- PCHJSUWPFVWCPO-UHFFFAOYSA-N gold Chemical compound [Au] PCHJSUWPFVWCPO-UHFFFAOYSA-N 0.000 description 9
- 229910052737 gold Inorganic materials 0.000 description 9
- 239000010931 gold Substances 0.000 description 9
- 238000011161 development Methods 0.000 description 4
- 238000007418 data mining Methods 0.000 description 2
- 229910052787 antimony Inorganic materials 0.000 description 1
- 229910052785 arsenic Inorganic materials 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 229910052802 copper Inorganic materials 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000004836 empirical method Methods 0.000 description 1
- 230000002349 favourable effect Effects 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 229910052748 manganese Inorganic materials 0.000 description 1
- 229910052753 mercury Inorganic materials 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000007500 overflow downdraw method Methods 0.000 description 1
- 239000011435 rock Substances 0.000 description 1
- 229910052709 silver Inorganic materials 0.000 description 1
- 229910052718 tin Inorganic materials 0.000 description 1
- 229910052721 tungsten Inorganic materials 0.000 description 1
- 229910052725 zinc Inorganic materials 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/02—Agriculture; Fishing; Forestry; Mining
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Strategic Management (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- General Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Molecular Biology (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Data Mining & Analysis (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Artificial Intelligence (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Agronomy & Crop Science (AREA)
- Primary Health Care (AREA)
- Mining & Mineral Resources (AREA)
- Marine Sciences & Fisheries (AREA)
- Animal Husbandry (AREA)
- Development Economics (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Geophysics And Detection Of Objects (AREA)
Abstract
The invention discloses an intelligent sniffing ore-finding prediction method based on deep learning, which can predict the position of an unknown ore deposit according to the position of the known ore deposit, belongs to the technical field of mineral geological survey and mineral exploration, and directly uses all kinds of acquired geological data, such as DEM (digital elevation model), geology, chemical exploration, geophysical prospecting, remote sensing and the like, without basically transforming geological concepts, so as to realize the intelligent ore-finding prediction taking multi-source data as driving force. The method is characterized in that a 'sniffing' method based on convolutional neural network learning is adopted for mine finding prediction, OreGO can 'sniff' the mineral geological information of the position given the position of the ore deposit, automatically extract features, then designate regions to search and obtain model training data and test data, and provide basis for mine finding prediction. Model training data and test data are obtained by a windowing method, and different data or different data are obtained or tested by translating, rotating, zooming and the like of a window according to the position of a known deposit.
Description
Technical Field
The invention relates to the technical field of mineral geological survey and mineral exploration, in particular to an intelligent ore finding prediction method based on deep learning.
Background
Generally, variables needing to be considered for mineral resource prediction have diversity, and relate to various subjects such as geology, geochemistry, geophysical, remote sensing and the like, and according to the traditional method, namely a mathematical statistics method, an empirical method and the like, the mineral exploration prospective prediction is carried out according to a plurality of indexes, the reliability of the prediction result in known data cannot be quantitatively predicted in a probability mode and evaluated, and all the variables cannot be reasonably verified, so that the method has great defects. At present, the development of big data and artificial intelligence technology prompts the mine-searching prediction technology to enter a new development stage, the invention mainly provides an intelligent prediction method based on deep learning, which relies on machine learning to carry out mine-forming characteristic learning on geological big data and realizes intelligent mine-searching prediction by taking multi-source data as driving force
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 an intelligent sniffing mine finding prediction method based on deep learning, which realizes intelligent mine finding prediction by taking multi-source data such as geology, geophysical prospecting, chemical prospecting, remote sensing and the like as driving force; and acquiring training data and verification data of the model by adopting a windowing mode through a data enhancement technology.
To solve the above technical problem, according to an aspect of the present invention, the present invention provides the following technical solutions:
a sniffing intelligent mine finding prediction method based on deep learning comprises the following steps:
s1: inputting multi-source geoscience data of geology, geophysical prospecting, chemical prospecting and remote sensing;
s2: gridding geological data by adopting a relative attribute gridding method, and gridding multi-source geoscience data of geophysical prospecting and chemical prospecting by adopting interpolation methods such as a Kriging method and the like;
s3: setting a proper window size according to a known deposit, and constructing a training data set and a verification data set by adopting a data enhancement method;
s4: carrying out network model training by adopting an improved convolutional neural network architecture to generate a prospecting prediction model;
s5: calculating the ore finding probability of each window area of the research area by using the trained model parameters;
s6: and further evaluating the effectiveness of the prospecting prediction area according to the mineralizing geological conditions of the research area.
As a preferable scheme of the sniffing intelligent prospecting prediction method based on deep learning of the invention, the method comprises the following steps: in the step S3, the texture structure of the "image" may also be extracted by a convolutional neural network, the gridded geological, geophysical, geochemical, and remote sensing data may be regarded as the "image", and the analysis of the geological, geochemical, geophysical, and remote sensing abnormal spatial structure types may be performed by a convolutional method, which includes the following specific steps:
(1) carrying out grid interpolation on a research area according to geological data, geophysical prospecting data, chemical prospecting data and remote sensing data according to a certain grid interval;
(2) selecting a certain window size: and acquiring a training data set by adopting data enhancement technologies such as moving and rotating window positions and the like according to the position of the known ore deposit by adopting 16 grid units multiplied by 16 grid units or 32 grid units multiplied by 32 grid units.
As a preferable scheme of the sniffing intelligent prospecting prediction method based on deep learning of the invention, the method comprises the following steps: in the step S4, based on geological, geophysical prospecting, chemical prospecting, remote sensing and drilling data, a deep learning method is adopted to extract geological big data features of mineral products, and the relation between known mineral deposits and all known geological elements is mined, so that a deep learning model for predicting a prospect and delineating a target area of the prospect is established.
As a preferable scheme of the sniffing intelligent prospecting prediction method based on deep learning of the invention, the method comprises the following steps: in the step S5, the mining area prediction and target area delineation are performed by using a mining big data mining prediction system to perform dimension reduction by using a deep learning network such as CNN and self-coding, performing pattern classification on the basis of the dimension reduction, mining the relation between geological elements and known mineral deposits, predicting the probability of the mineral deposits existing in each grid unit of the working area by using the model established in the step S4.
Compared with the prior art:
(1) all kinds of acquired geological data such as DEM, geology, chemical exploration, geophysical exploration, remote sensing and the like are directly used, basically, conversion of geological concepts is not conducted, and intelligent ore finding prediction with multi-source data as driving force is achieved.
(2) The method comprises the steps of performing ore finding prediction by using a convolutional neural network learning-based sniffing method (OreGO), for example, giving a known ore deposit position, allowing OreGO to 'sniff' the mineral geological information of the position, automatically extracting features, then specifying an area to search and obtain model training data and test data, predicting the possibility of the ore deposit existing in the given position, and providing a basis for ore finding prediction.
(3) The method comprises the steps of adopting a convolutional neural network deep learning-based sniffing method (OreGO) to carry out ore finding prediction, giving an ore deposit position, adopting the method to sniff mineral geological information at the position, automatically extracting features, searching and judging whether an area similar to the known ore deposit features exists in a specified area, and providing a basis for ore finding prediction.
(4) The intelligent sniffing mine finding prediction method based on deep learning realizes intelligent mine finding prediction by using multi-source data as driving force.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the present invention will be described in detail with reference to the accompanying drawings and detailed embodiments, 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 inventive exercise. Wherein:
FIG. 1 is a flow chart of the present invention.
Detailed Description
In order to make the aforementioned objects, features and advantages of the present invention comprehensible, embodiments accompanied with figures are described in detail below.
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.
Next, the present invention will be described in detail with reference to the drawings, and in the detailed description of the embodiments of the present invention, the cross-sectional views illustrating the structure of the device are not enlarged partially according to the general scale for convenience of illustration, and the drawings are only examples, which should not limit the scope of the present invention.
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 detail with reference to the accompanying drawings.
The invention provides an intelligent sniffing mine finding prediction method based on deep learning, which realizes intelligent mine finding prediction by taking multi-source data such as geology, geophysical prospecting, chemical prospecting, remote sensing and the like as driving force, and adopts a windowing method to obtain training data and verification data of a model, please refer to fig. 1;
referring again to fig. 1, the method includes the following steps:
s1: inputting multi-source geoscience data of geology, geophysical prospecting, chemical prospecting and remote sensing;
s2: gridding geological data by adopting a relative attribute gridding method, and gridding multi-source geoscience data of geophysical prospecting and chemical prospecting by adopting interpolation methods such as a Kriging method and the like;
s3: setting a proper window size according to a known deposit, and constructing a training data set and a verification data set by adopting a data enhancement method;
s4: carrying out network model training by adopting an improved convolutional neural network architecture to generate a prospecting prediction model;
s5: calculating the ore finding probability of each window area of the research area by using the trained model parameters;
s6: and further evaluating the effectiveness of the prospecting prediction area according to the mineralizing geological conditions of the research area.
Referring to fig. 1 again, in step S3, the texture structure of the "image" may also be extracted by a convolutional neural network, the gridded geological, geophysical, geochemical, and remote sensing data may be regarded as the "image", and the analysis of the geological, geochemical, geophysical, and remote sensing abnormal spatial structure types may be performed by using a convolution method, which includes the following specific steps:
(1) carrying out grid interpolation on a research area according to geological data, geophysical prospecting data, chemical prospecting data and remote sensing data according to a certain grid interval;
(2) selecting a certain window size: and acquiring a training data set by adopting data enhancement technologies such as moving and rotating window positions and the like according to the position of the known ore deposit by adopting 16 grid units multiplied by 16 grid units or 32 grid units multiplied by 32 grid units.
Referring to fig. 1 again, in step S4, based on geological, geophysical prospecting, chemical prospecting, remote sensing and drilling data, a deep learning method is used to extract the geological big data features of the mineral products, and the relationship between the known mineral deposit and all known geological elements is mined, so as to establish a deep learning model for prospecting long-range view prediction and prospecting target area delineation.
Referring to fig. 1 again, in the step S5, the mining area prediction and target area delineation are performed by using a mining geological data mining prediction system to perform dimension reduction by using deep learning networks such as CNN and self-coding, and performing pattern classification on the basis of the dimension reduction, mining the relationship between geological elements and known mineral deposits, predicting the probability of the mineral deposits existing in each grid unit of the working area by using the model established in the step S4.
Examples
1. Based on 14 kinds of elemental exploration data, aeromagnetic data and geological data such As Ag, As, Au, Ba, Bi, Cd, Cu, Hg, Mn, Mo, Pb, Sb, Sn, W, Zn and the like, a deep learning prediction method based on a convolutional neural network is adopted to carry out ore finding prediction application on the Gansu cliff-bridge area, a learning data set is constructed according to 9 gold deposits (points), and 6 main ore finding distant scenic areas are defined.
2, carrying out prospecting prediction analysis in the cliff-bridge region based on a multi-element fusion method, and carrying out spatial classification by adopting geological boundary (sorting) + fracture (sorting) + geological data fusion, wherein a result graph shows that a research area has complex spatial structure change characteristics. The bridge area develops an annular structure in the north-south direction, and the bridge gold ores are positioned at the edge of the annular structure area. The beneficial prospecting prediction area is determined according to the classification area where the known deposit (point) is located, the main prediction area is an NE-direction strip located in the middle of the research area, and most of the known gold deposits (points) including bridge gold are mainly located on the strip. A prediction area exists in the area of the house-securing dam, and the gold deposit of the house-securing dam is located in the prediction area. In addition, a favorable prospecting prediction area exists in the west of the research area.
3, the method of the invention more accurately determines the prospecting target area of the cliff-bridge key working area. The main prospecting predicting area of the research area is positioned on a northeast strip in the middle of the research area, the contact zone of the three-fold development system and the early-aged stratum is fractured and developed along the northeast direction of the contact zone, and the three-fold development system is the most important prospecting predicting area of the silicified cobble type gold ores in the research area. The method also has good gold ore prospecting potential in a prediction region in the southeast of a research region, and mainly develops and fractures altered rock type gold ores and silicified breccia type gold ores.
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 (4)
1. An intelligent prospecting prediction method based on deep learning is characterized by comprising the following steps:
s1: inputting multi-source geoscience data of geology, geophysical prospecting, chemical prospecting and remote sensing;
s2: gridding geological data by adopting a relative attribute gridding method, and gridding multi-source geoscience data of geophysical prospecting and chemical prospecting by adopting interpolation methods such as a Kriging method and the like;
s3: setting a proper window size according to a known deposit, and constructing a training data set and a verification data set by adopting a data enhancement method;
s4: carrying out network model training by adopting an improved convolutional neural network architecture to generate a prospecting prediction model;
s5: calculating the ore finding probability of each window area of the research area by using the trained model parameters;
s6: and further evaluating the effectiveness of the prospecting prediction area according to the mineralizing geological conditions of the research area.
2. The method for predicting the exploration intelligent prospecting mine based on the deep learning of claim 1, wherein the texture structure of the image can be extracted through a convolutional neural network in the step S3, the gridded geological, geophysical, geochemical and remote sensing data can be regarded as the image, and the analysis of the geological, geochemical, geophysical and remote sensing abnormal spatial structure types can be performed by adopting a convolutional method, which comprises the following specific steps:
(1) carrying out grid interpolation on a research area according to geological data, geophysical prospecting data, chemical prospecting data and remote sensing data according to a certain grid interval;
(2) selecting a certain window size: and acquiring a training data set by adopting data enhancement technologies such as moving and rotating window positions and the like according to the position of the known ore deposit by adopting 16 grid units multiplied by 16 grid units or 32 grid units multiplied by 32 grid units.
3. The method according to claim 1, wherein in step S4, based on geological, geophysical, chemical prospecting, remote sensing and drilling data, a deep learning method is used to extract geological big data features of mineral products, and the relationship between known mineral deposits and all known geological elements is mined, so as to establish a deep learning model for prospecting prospect prediction and target prospecting delineation.
4. The method for intelligent sniffing mine finding prediction based on deep learning as claimed in claim 1, wherein in step S5, deep learning networks such as CNN and self-coding are used for dimension reduction through a mining geology big data mine finding prediction system, and based on the dimension reduction, pattern classification is performed, the relationship between geological elements and known mineral deposits is mined, the model established in step S4 is used for predicting the probability of mineral deposits existing in each grid unit of the working area, and mine finding area prediction and target area delineation are performed.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110068202.XA CN112906940A (en) | 2021-01-19 | 2021-01-19 | Sniffing intelligent ore finding prediction method based on deep learning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110068202.XA CN112906940A (en) | 2021-01-19 | 2021-01-19 | Sniffing intelligent ore finding prediction method based on deep learning |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112906940A true CN112906940A (en) | 2021-06-04 |
Family
ID=76115436
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110068202.XA Pending CN112906940A (en) | 2021-01-19 | 2021-01-19 | Sniffing intelligent ore finding prediction method based on deep learning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112906940A (en) |
Cited By (6)
| 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 |
| CN114898109A (en) * | 2022-04-14 | 2022-08-12 | 中国自然资源航空物探遥感中心 | Porphyry shallow-formation low-temperature hydrothermal type mineral prediction method and system based on deep learning |
| CN115879648A (en) * | 2023-02-21 | 2023-03-31 | 中国地质科学院 | Machine learning-based ternary deep mineralization prediction method and system |
| CN115907151A (en) * | 2022-11-21 | 2023-04-04 | 自然资源陕西省卫星应用技术中心 | Intelligent mineralization prediction method based on geological big data |
| CN116665067A (en) * | 2023-08-01 | 2023-08-29 | 吉林大学 | Ore finding target area optimization system and method based on graph neural network |
| CN117471546A (en) * | 2023-10-31 | 2024-01-30 | 山东省地质矿产勘查开发局第六地质大队(山东省第六地质矿产勘查院) | Black rock-based gold ore prospecting method |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR100988609B1 (en) * | 2010-03-03 | 2010-10-19 | 한국지질자원연구원 | Mineral deposit prediction system and predicting method using the same |
| KR20180055518A (en) * | 2016-11-17 | 2018-05-25 | 한국지질자원연구원 | System and method of 3d mineral prospectivity |
| CN108629072A (en) * | 2018-03-12 | 2018-10-09 | 山东科技大学 | Convolutional neural networks study towards the distribution of earthquake oil and gas reservoir and prediction technique |
| CN111611403A (en) * | 2020-05-20 | 2020-09-01 | 中国地质调查局发展研究中心 | Geological text data based ore finding method |
-
2021
- 2021-01-19 CN CN202110068202.XA patent/CN112906940A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR100988609B1 (en) * | 2010-03-03 | 2010-10-19 | 한국지질자원연구원 | Mineral deposit prediction system and predicting method using the same |
| KR20180055518A (en) * | 2016-11-17 | 2018-05-25 | 한국지질자원연구원 | System and method of 3d mineral prospectivity |
| CN108629072A (en) * | 2018-03-12 | 2018-10-09 | 山东科技大学 | Convolutional neural networks study towards the distribution of earthquake oil and gas reservoir and prediction technique |
| CN111611403A (en) * | 2020-05-20 | 2020-09-01 | 中国地质调查局发展研究中心 | Geological text data based ore finding method |
Non-Patent Citations (1)
| Title |
|---|
| 刘艳鹏等: "大数据挖掘与智能预测找矿靶区实验研究――卷积神经网络模型的应用", 《大地构造与成矿学》, vol. 44, no. 02, 30 April 2020 (2020-04-30), pages 192 - 202 * |
Cited By (9)
| 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 |
| CN114898109A (en) * | 2022-04-14 | 2022-08-12 | 中国自然资源航空物探遥感中心 | Porphyry shallow-formation low-temperature hydrothermal type mineral prediction method and system based on deep learning |
| CN114898109B (en) * | 2022-04-14 | 2023-05-02 | 中国自然资源航空物探遥感中心 | Zeolite type mineral product prediction method and system based on deep learning |
| CN115907151A (en) * | 2022-11-21 | 2023-04-04 | 自然资源陕西省卫星应用技术中心 | Intelligent mineralization prediction method based on geological big data |
| CN115879648A (en) * | 2023-02-21 | 2023-03-31 | 中国地质科学院 | Machine learning-based ternary deep mineralization prediction method and system |
| CN116665067A (en) * | 2023-08-01 | 2023-08-29 | 吉林大学 | Ore finding target area optimization system and method based on graph neural network |
| CN116665067B (en) * | 2023-08-01 | 2023-10-03 | 吉林大学 | Ore finding target area optimization system and method based on graph neural network |
| CN117471546A (en) * | 2023-10-31 | 2024-01-30 | 山东省地质矿产勘查开发局第六地质大队(山东省第六地质矿产勘查院) | Black rock-based gold ore prospecting method |
| CN117471546B (en) * | 2023-10-31 | 2024-04-02 | 山东省地质矿产勘查开发局第六地质大队(山东省第六地质矿产勘查院) | Black rock-based gold ore prospecting method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112906940A (en) | Sniffing intelligent ore finding prediction method based on deep learning | |
| Huang et al. | Micro-seismic event detection and location in underground mines by using Convolutional Neural Networks (CNN) and deep learning | |
| CN113946950B (en) | Method for rapidly delineating target area of gold prospecting | |
| US7519476B1 (en) | Method of seismic interpretation | |
| CN110991075B (en) | Rapid investigation and evaluation method for metal mineral products | |
| CN111639067B (en) | Multi-feature fusion convolution self-coding multi-element geochemical anomaly identification method | |
| CN113703045B (en) | Seismic facies identification method based on lightweight network | |
| CN116665067B (en) | Ore finding target area optimization system and method based on graph neural network | |
| US20230161061A1 (en) | Structured representations of subsurface features for hydrocarbon system and geological reasoning | |
| CN111080021A (en) | Sand body configuration CMM neural network prediction method based on geological information base | |
| CN110596778B (en) | Hydrothermal uranium ore exploration method | |
| CN114997501A (en) | Deep learning mineral resource classification prediction method and system based on sample unbalance | |
| CN114548299A (en) | Earthquake phase identification method and device, computer equipment and storage medium | |
| Hasan et al. | Spectral Angle Mapper and aeromagnetic data integration for gold-associated alteration zone mapping: a case study for the Central Eastern Desert Egypt | |
| Martins et al. | Cu–Au exploration target generation in the eastern Carajás Mineral Province using random forest and multi-class index overlay mapping | |
| Ren et al. | Research on identification of natural and unnatural earthquake events based on AlexNet convolutional neural network | |
| CN116611697A (en) | Method for delineating mining target area by multi-source heterogeneous information based on machine learning | |
| CN115964667A (en) | River-lake lithofacies well logging identification method based on deep learning and resampling | |
| Pilger et al. | Additional samples: where they should be located | |
| CN115081685A (en) | Three-dimensional visual positioning prediction method for metal deposit deep resource | |
| Ribeiro et al. | Geochemical multifractal modeling of soil and stream sediment data applied to gold prospectivity mapping of the Pitangui Greenstone Belt, northwest of Quadrilátero Ferrífero, Brazil | |
| Zhu et al. | Deep learning approach of drilling decision for subhorizontal drain geosteering based on APC-LSTM model | |
| Zeng et al. | Local coupled Markov chain model for simulating varied stratigraphy | |
| CN111045105A (en) | Method for predicting geochemical connate zonation model for deep exploration of volcanic rock type uranium ores | |
| CN117471546B (en) | Black rock-based gold ore prospecting method |
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 |