[go: up one dir, main page]

CN117951551B - Mineral resource prediction method based on singularity index and self-organizing neural network - Google Patents

Mineral resource prediction method based on singularity index and self-organizing neural network Download PDF

Info

Publication number
CN117951551B
CN117951551B CN202410157104.7A CN202410157104A CN117951551B CN 117951551 B CN117951551 B CN 117951551B CN 202410157104 A CN202410157104 A CN 202410157104A CN 117951551 B CN117951551 B CN 117951551B
Authority
CN
China
Prior art keywords
ore
catchment basin
geological
neural network
self
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
Application number
CN202410157104.7A
Other languages
Chinese (zh)
Other versions
CN117951551A (en
Inventor
汪海城
沈睿文
王大伟
杨娅敏
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Command Center Of Natural Resources Comprehensive Survey Of China Geological Survey
Original Assignee
Command Center Of Natural Resources Comprehensive Survey Of China Geological Survey
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Command Center Of Natural Resources Comprehensive Survey Of China Geological Survey filed Critical Command Center Of Natural Resources Comprehensive Survey Of China Geological Survey
Priority to CN202410157104.7A priority Critical patent/CN117951551B/en
Publication of CN117951551A publication Critical patent/CN117951551A/en
Application granted granted Critical
Publication of CN117951551B publication Critical patent/CN117951551B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • GPHYSICS
    • G06COMPUTING OR CALCULATING; COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00Pattern recognition
    • G06F18/20Analysing
    • G06F18/23Clustering techniques
    • GPHYSICS
    • G06COMPUTING OR CALCULATING; COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/29Geographical information databases
    • GPHYSICS
    • G06COMPUTING OR CALCULATING; COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00Pattern recognition
    • G06F18/10Pre-processing; Data cleansing
    • GPHYSICS
    • G06COMPUTING OR CALCULATING; COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00Pattern recognition
    • G06F18/20Analysing
    • G06F18/24Classification techniques
    • GPHYSICS
    • G06COMPUTING OR CALCULATING; COUNTING
    • G06NCOMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00Computing arrangements based on biological models
    • G06N3/02Neural networks
    • G06N3/08Learning methods
    • G06N3/088Non-supervised learning, e.g. competitive learning

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • Evolutionary Computation (AREA)
  • Artificial Intelligence (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Evolutionary Biology (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Databases & Information Systems (AREA)
  • Health & Medical Sciences (AREA)
  • Remote Sensing (AREA)
  • Biomedical Technology (AREA)
  • Biophysics (AREA)
  • Computational Linguistics (AREA)
  • General Health & Medical Sciences (AREA)
  • Molecular Biology (AREA)
  • Computing Systems (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Geophysics And Detection Of Objects (AREA)

Abstract

The invention discloses a mineral resource prediction method based on a singularity index and a self-organizing neural network, which belongs to the technical field of mineral exploration and comprises the following steps: s1, obtaining the spatial distribution of catchment basins of a research area; s2, counting the singularity index of each catchment basin; s3, extracting geological ore control elements of the research area; s4, obtaining the ore formation contribution of each geological ore control element to the catchment basin; s5, classifying catchment basins through the self-organizing neural network; s6, identifying an ore-forming beneficial area of the research area. The mineral resource prediction method based on the singularity index and the self-organizing neural network aims at the problem that mineralization information of key metal mineral resources is weak and difficult to identify, and based on the sampling principle of water system sediments, a sampling unit is used as a basic unit for geochemistry anomaly extraction, geological mineral control factors in a catchment basin unit are introduced as constraint conditions, so that the geochemistry anomalies are identified, and a reference is provided for the next mineral exploration.

Description

Mineral resource prediction method based on singularity index and self-organizing neural network
Technical Field
The invention relates to the technical field of mineral exploration, in particular to a mineral resource prediction method based on a singularity index and a self-organizing neural network.
Background
The water system sediment is the most commonly used sampling medium in the mineral exploration process, and the distribution of elements in the water system sediment is researched through systematic sampling analysis, so that geochemistry anomalies are found, a prospecting remote area and an ore-forming favorable section are defined, and a basis is provided for further detailed geoexploration and geological measurement. The current research is mainly based on element data of geochemical sampling points, ignores the enrichment effect of a sampling unit catchment basin of water system sediment on geochemical elements, and particularly, is difficult to obtain satisfactory results on key mineral resources with 'thin, fine and complicated geochemical behaviors', so that research and development of a new method for mining geochemical mineralization information of the water system sediment are needed, and theory and technical support are provided for the prospecting breakthrough of the key mineral resources. Based on the above, a mineral resource prediction method based on a singularity index and a self-organizing neural network is provided.
Disclosure of Invention
The invention aims to provide a mineral resource prediction method based on a singularity index and a self-organizing neural network, aiming at weak mineralization information of key metal mineral resources and difficult to identify, based on a sampling principle of water system sediment, a sampling unit of the water system sediment is used as a basic unit for geochemical anomaly extraction, geological mineral control factors in a catchment basin unit are introduced as constraint conditions, the geochemical anomalies are identified, and a reference is provided for the next mineral exploration.
In order to achieve the above object, the present invention provides a mineral resource prediction method based on a singularity index and a self-organizing neural network, comprising the steps of:
S1, extracting the spatial distribution of the catchment basin based on high-precision remote sensing digital elevation data through hydrologic analysis, and carrying out data correction by combining the existing spatial distribution of the water system to obtain the spatial distribution of the catchment basin in the research area;
s2, calculating the singularity index of each water system sediment sampling position, and counting the average value of the singularity index in each catchment basin and taking the average value as the geochemical characteristic of each catchment basin;
S3, extracting geological ore control elements of the research area based on the ore-forming geological background of the research area;
s4, calculating a weight index of the geological ore control element based on the influence degree of the geological ore control element on ore formation, and obtaining the geological ore control element ore formation favorability of each catchment basin;
s5, performing unsupervised cluster analysis through a self-organizing neural network, and classifying mineralization potential of each catchment basin;
S6, based on the result of the unsupervised self-organizing neural network analysis, hierarchical clustering is utilized to further classify the ore-forming potential of the catchment basin of the research area, and the ore-forming beneficial area of the research area is identified.
Preferably, in the step S1, hydrologic analysis is performed based on the high-precision remote sensing digital elevation data set, the spatial distribution of the catchment basin in the research area is extracted, and the spatial distribution of the extracted catchment basin is corrected by combining the existing river spatial distribution in the research area, so as to obtain the high-precision spatial distribution of the catchment basin in the research area.
Preferably, in the step S3, geological ore control elements beneficial to ore formation in the research area are extracted based on regional ore formation rule research, and geological ore control marks such as stratum, rock mass and structure beneficial to ore formation in the research area are extracted.
Preferably, in the step S4, according to the influence degree of the geological ore control element on the ore formation, the geological ore control element is respectively subjected to a distance buffer analysis, the ore formation favor is quantified according to a distance function, and the weight sum of all geological ore control elements in each catchment basin is respectively calculated to obtain the weight index of the geological ore control element.
Preferably, in the step S5, the singular index of the catchment basin in the step S2 and the geological minescence favorability parameter in the step S4 are combined to form a characteristic variable for measuring the minescence potential of the catchment basin, and the minescence potential of the catchment basin is classified by using an ad hoc neural network.
Preferably, in the step S6, the classification effect is evaluated through the result of the self-organizing neural network, and the classification result of the self-organizing neural network is reclassified according to the hierarchical clustering method, so as to achieve the mining potential analysis of all catchment basins.
Therefore, the mineral resource prediction method based on the singularity index and the self-organizing neural network combines the singularity index analysis extracted by weak anomaly with the self-organizing neural network machine learning method based on the sampling principle of water system sediment, and quantitatively evaluates the mineral potential of each catchment basin.
Compared with the prior art, the invention breaks through the traditional geochemical processing thought of exploration aiming at the characteristics of weak, thin and thin geochemical signals of key metal mineral resources, extracts geochemical anomalies and indicates the direction for mineral exploration of the next step.
The technical scheme of the invention is further described in detail through the drawings and the embodiments.
Drawings
FIG. 1 is a flow chart of an embodiment of the present invention;
FIG. 2 is a cluster diagram of an ad hoc neural network according to an embodiment of the present invention;
FIG. 3 is a spatial distribution diagram of a catchment basin according to an embodiment of the present invention.
Detailed Description
The technical scheme of the invention is further described below through the attached drawings and the embodiments.
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are some embodiments of the present invention, but not all embodiments of the present invention.
Examples
The following is a detailed description of the present invention with reference to examples.
Taking a 1:20 ten thousand water system sediment of an inner Mongolian Umbilican scout area as an example, a research area belongs to hilly land feature, and the spatial distribution of geochemical anomalies is greatly affected by catchment basin, as shown in fig. 1-3, the specific implementation steps are as follows:
(1) Based on ASTER GDEM V digital elevation dataset of high accuracy, through ArcGIS's hydrologic analysis function, draw the spatial distribution of catchment basin in research district to combine the current river spatial distribution in research district to correct the catchment basin of extraction, obtain the spatial distribution of catchment basin in research district.
(2) The singular index spatial distribution of 39 geochemical elements in the 1:20 aqueous sediment is calculated, 3×3,5×5, 7×7, 9×9, 11×11 are selected as calculation windows, and the singular index of the central position is calculated.
(3) And calculating the average value of the singularity indexes of the sampling points in each catchment basin through the spatial overlapping relation between the spatial distribution of the singularity indexes and the catchment basin, and taking the average value as the singularity index of each catchment basin to represent the concentration degree of the elements of the catchment basin.
(4) The ore formation geological background comprises regional space-time ore formation rule research, and geological ore control conditions such as stratum, rock mass, structure and the like which are favorable for ore formation in the research region are extracted. And respectively analyzing a distance buffer zone of the geological ore control element according to the influence degree of the geological ore control element on the ore formation favorability, and quantifying influence degree weight according to a space distance fuzzy function.
(5) Based on the spatial correspondence of the catchment basin and the mineralized geological elements, the sum of the weights of the geological mineral control elements in the catchment basin is counted and used as the measure of geological mineralization favorability of the catchment basin.
(6) And combining the singularity index of the catchment basin and the geologic mineralization favorability parameter to form a characteristic combination for measuring the mineralization potential of the catchment basin, and clustering the catchment basin by using the self-organizing neural network.
(7) The clustering result of the self-organizing neural network is 10 multiplied by 13 and 130 categories are total, and the categories are too many for explaining the geochemical anomaly, so that the classification result of the self-organizing neural network based on hierarchical clustering is clustered into 10 categories again, and respectively represents different mineralization potentials of each catchment basin, wherein the categories 1 to 2 comprise most of the found minerals in the research area, and the potential of the catchment basin without the minerals found in the category is relatively large.
Therefore, the mineral resource prediction method based on the singularity index and the self-organizing neural network is used for aiming at the weak and difficult identification of mineralization information of key metal mineral resources, based on the sampling principle of water system sediment, a sampling unit of the water system sediment is used as a basic unit for geochemical anomaly extraction, geological mineral control factors in a catchment basin unit are introduced as constraint conditions, the geochemical anomalies are identified, and a reference is provided for the next mineral exploration.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present invention and not for limiting it, and although the present invention has been described in detail with reference to the preferred embodiments, it will be understood by those skilled in the art that: the technical scheme of the invention can be modified or replaced by the same, and the modified technical scheme cannot deviate from the spirit and scope of the technical scheme of the invention.

Claims (2)

1. The mineral resource prediction method based on the singularity index and the self-organizing neural network is characterized by comprising the following steps of:
S1, carrying out data correction by combining the existing water system spatial distribution through hydrologic analysis to obtain the spatial distribution of the catchment basin of the research area; the method comprises the steps of carrying out hydrologic analysis based on a high-precision remote sensing digital elevation data set, extracting spatial distribution of a catchment basin in a research area, and correcting the extracted catchment basin by combining the existing river spatial distribution in the research area to obtain the high-precision catchment basin spatial distribution in the research area;
s2, calculating the singularity index of each water system sediment sampling position, and counting the average value of the singularity index in each catchment basin and taking the average value as the geochemical characteristic of each catchment basin;
S3, extracting geological ore control elements of the research area based on the ore-forming geological background of the research area;
S4, calculating a weight index of the geological ore control element based on the influence degree of the geological ore control element on ore formation, and obtaining the ore formation favorability of the geological ore control element of the catchment basin; according to the influence degree of the geological ore control elements on ore formation, respectively analyzing a distance buffer zone of the geological ore control elements, quantifying the ore formation favor according to a distance function, and respectively calculating the weight sum of all the geological ore control elements in each catchment basin to obtain the weight index of the geological ore control elements;
S5, performing unsupervised cluster analysis through a self-organizing neural network, classifying the mineral potential of each catchment basin, specifically, combining the singularity index of the catchment basin in the S2 and the geological mineral formation favorability parameter in the S4 to form a characteristic variable combination for measuring the mineral formation potential of the catchment basin, and classifying the mineral formation potential of the catchment basin by utilizing the self-organizing neural network;
S6, based on an analysis result of the unsupervised self-organizing neural network, classifying the mineralization potential of the catchment basin of the research area by using hierarchical clustering, and identifying the mineralization beneficial area of the research area: the classification effect is evaluated through the result of the self-organizing neural network, the classification result of the self-organizing neural network is classified again according to the hierarchical clustering method, and the mining potential analysis of all catchment basins is achieved.
2. The mineral resource forecasting method based on the singularity index and the self-organizing neural network according to claim 1, wherein the mineral resource forecasting method is characterized in that: in the step S3, geological ore control elements beneficial to ore formation in a research area are extracted based on regional ore formation rule research.
CN202410157104.7A 2024-02-04 2024-02-04 Mineral resource prediction method based on singularity index and self-organizing neural network Active CN117951551B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202410157104.7A CN117951551B (en) 2024-02-04 2024-02-04 Mineral resource prediction method based on singularity index and self-organizing neural network

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202410157104.7A CN117951551B (en) 2024-02-04 2024-02-04 Mineral resource prediction method based on singularity index and self-organizing neural network

Publications (2)

Publication Number Publication Date
CN117951551A CN117951551A (en) 2024-04-30
CN117951551B true CN117951551B (en) 2024-09-24

Family

ID=90802779

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202410157104.7A Active CN117951551B (en) 2024-02-04 2024-02-04 Mineral resource prediction method based on singularity index and self-organizing neural network

Country Status (1)

Country Link
CN (1) CN117951551B (en)

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
FR2930350B1 (en) * 2008-04-17 2011-07-15 Inst Francais Du Petrole PROCESS FOR SEARCHING FOR HYDROCARBONS IN A GEOLOGICALLY COMPLEX BASIN USING BASIN MODELING
CN101667206B (en) * 2009-09-27 2012-04-25 中国地质科学院矿产资源研究所 Water system sediment investigation data processing method based on open catchment basin
US20140330519A1 (en) * 2013-05-01 2014-11-06 Heiko Mueller Method to identify multivariate anomalies by computing similarity and dissimilarity between entities and considering their spatial interdependency
GB2544922B (en) * 2014-08-01 2022-01-12 Geoquest Systems Bv Methods and systems for simulating a hydrocarbon field using a multi-point well connection method

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
"甘肃省合作-美武地区综合信息找矿预测研究";张帅;《中国优秀博士论文全文数据库(工程科技I辑)》;20220415(第2022年第4期期);第7-10页,第108-111页 *
综合信息成矿系列预测的基本原理和方法;陈永清,王世称;山东地质;19950630(第01期);第58页第二节 *

Also Published As

Publication number Publication date
CN117951551A (en) 2024-04-30

Similar Documents

Publication Publication Date Title
CN110674841B (en) Logging curve identification method based on clustering algorithm
CN113779880B (en) Tunnel surrounding rock two-dimensional quality evaluation method based on advanced drilling data
Jafari et al. Spatial prediction of soil great groups by boosted regression trees using a limited point dataset in an arid region, southeastern Iran
Huang et al. Research on Piper-PCA-Bayes-LOOCV discrimination model of water inrush source in mines
CN119398493A (en) Advanced geological prediction method and system based on tunnel geological detection
CN116665067B (en) Ore finding target area optimization system and method based on graph neural network
CN101266299A (en) Method for forecasting oil gas utilizing earthquake data object constructional features
Zhao et al. Mapping landslide sensitivity based on machine learning: A case study in Ankang City, Shaanxi Province, China
CN119941434B (en) Mineral prospecting target area resource decision-making method and system based on minimizing the impact of environmentally sensitive areas
Yang et al. Mineralized-anomaly identification based on convolutional sparse autoencoder network and isolated forest
CN115019476A (en) Landslide space-time information monitoring and early warning method based on multi-source information fusion
CN117951551B (en) Mineral resource prediction method based on singularity index and self-organizing neural network
CN119004191A (en) Tunnel bad geological identification method and system based on Bayesian optimization random forest
CN114167497A (en) SSL-CNN reservoir oil and gas detection method based on similarity measure geological structure label
Sun et al. A Review of Mineral Prospectivity Mapping Using Deep Learning
CN115660512B (en) Analysis and treatment method and system for green mine construction
CN117992876A (en) Prediction method for coal seam mining plane geological structure
CN117313550A (en) Uranium resource potential prediction method based on model
Esmaeiloghli et al. Optimizing the grade classification model of mineralized zones using a learning method based on harmony search algorithm
CN113534283B (en) Quantitative evaluation method for ore-forming element characteristics of sandstone-type uranium ores
CN117951570B (en) Catchment basin mineralization potential evaluation method based on geochemical fingerprint
He et al. Uncertainty mapping method for mineral resources prospectivity integrating multi-source geology spatial data sets and evidence reasoning model
CN112579849A (en) Structure safety influence factor correlation analysis method based on full data
Rasouli et al. Optimizing Traditional Clustering Methods Using Metaheuristic Algorithms for Joint Set Identification in Copper Mines
CN112818603A (en) Method, terminal and storage medium for adaptively selecting optimal mineralization prediction elements

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