[go: up one dir, main page]

CN118296381A - Solid mineral multi-scale progressive prospecting prediction method based on geological big data - Google Patents

Solid mineral multi-scale progressive prospecting prediction method based on geological big data Download PDF

Info

Publication number
CN118296381A
CN118296381A CN202410430186.8A CN202410430186A CN118296381A CN 118296381 A CN118296381 A CN 118296381A CN 202410430186 A CN202410430186 A CN 202410430186A CN 118296381 A CN118296381 A CN 118296381A
Authority
CN
China
Prior art keywords
data
geological
ore
prospecting
thousand
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
Application number
CN202410430186.8A
Other languages
Chinese (zh)
Other versions
CN118296381B (en
Inventor
徐凯
孔春芳
吴冲龙
李岩
田宜平
吴雪超
武永进
董洋
向世泽
李瑜
赵思源
周广隆
徐城阳
吕维逸
李必亿
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.)
Wuhan Dida Quanty Technology Co ltd
Original Assignee
Wuhan Dida Quanty Technology Co ltd
China University of Geosciences Wuhan
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 Wuhan Dida Quanty Technology Co ltd, China University of Geosciences Wuhan filed Critical Wuhan Dida Quanty Technology Co ltd
Priority to CN202410430186.8A priority Critical patent/CN118296381B/en
Publication of CN118296381A publication Critical patent/CN118296381A/en
Application granted granted Critical
Publication of CN118296381B publication Critical patent/CN118296381B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
    • G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; 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
    • G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
    • G06F16/367—Ontology
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N20/00—Machine learning
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; 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
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0637—Strategic management or analysis, e.g. setting a goal or target of an organisation; Planning actions based on goals; Analysis or evaluation of effectiveness of goals
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; 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)
  • Business, Economics & Management (AREA)
  • General Physics & Mathematics (AREA)
  • Physics & Mathematics (AREA)
  • Human Resources & Organizations (AREA)
  • Data Mining & Analysis (AREA)
  • Strategic Management (AREA)
  • General Engineering & Computer Science (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Economics (AREA)
  • Software Systems (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Marketing (AREA)
  • Tourism & Hospitality (AREA)
  • Evolutionary Computation (AREA)
  • General Business, Economics & Management (AREA)
  • Artificial Intelligence (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Educational Administration (AREA)
  • Animal Husbandry (AREA)
  • Computing Systems (AREA)
  • Game Theory and Decision Science (AREA)
  • Operations Research (AREA)
  • Quality & Reliability (AREA)
  • Health & Medical Sciences (AREA)
  • Primary Health Care (AREA)
  • Marine Sciences & Fisheries (AREA)
  • General Health & Medical Sciences (AREA)
  • Medical Informatics (AREA)
  • Mining & Mineral Resources (AREA)
  • Agronomy & Crop Science (AREA)
  • Development Economics (AREA)
  • Mathematical Physics (AREA)
  • Animal Behavior & Ethology (AREA)
  • Computational Linguistics (AREA)
  • Databases & Information Systems (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Evolutionary Biology (AREA)

Abstract

The invention belongs to the field of geological mineral resource prediction, and particularly relates to a solid mineral multi-scale progressive ore finding prediction method based on geological big data. The invention realizes the prospecting prediction and target area delineation by collecting the multi-scale geological, geophysical prospecting data, geochemical prospecting data, remote sensing and other data of the research area and utilizing the data mining technology and the machine learning method. The method aims at combining a three-dimensional geological model, a machine learning method and a data mining technology, processing geological big data of a predicted area, determining a target area in a multi-scale progressive manner, and providing a prospecting prediction method for mineral resource prediction; the method comprises the steps of constructing a prospecting knowledge graph based on a prospecting case complex disc, drawing a prospecting process knowledge association graph, constructing a three-dimensional geological model and an attribute data mart according to geological, geophysical prospecting, chemical prospecting and remote sensing data of which the working scale is divided into 1:50 ten thousand, 1:25 ten thousand, 1:5 ten thousand, 1:2.5 ten thousand and 1:0.5 ten thousand, analyzing rules between the prospecting conditions and the mineral control elements, and constructing a mineral formation prediction model to realize prospecting prediction.

Description

一种基于地质大数据的固体矿产多尺度递进式找矿预测方法A multi-scale progressive prospecting prediction method for solid minerals based on geological big data

技术领域Technical Field

本发明属于地质矿产资源预测领域，特别涉及一种基于地质大数据的固体矿产多尺度递进式找矿预测方法。The present invention belongs to the field of geological mineral resource prediction, and in particular relates to a multi-scale progressive prospecting prediction method for solid minerals based on geological big data.

背景技术Background technique

找矿预测是对发生在过去成矿事件的未知特征进行的估计或推断，预测的过程实质上是一种严密的科学逻辑思维过程，包括观察、分析、归纳、演绎及推理等认识环节。基于地质时空大数据进行成矿预测，涉及科学研究第四范式和地质数据科学的一系列理论、方法和关键技术。建立一个与预测工作相适应的地质大数据汇总、集成、融合、挖掘和评价的工作流程，对开展固体矿产找矿预测工作具有重要的帮助。Mineral prospecting prediction is an estimation or inference of unknown characteristics of mineralization events that occurred in the past. The prediction process is essentially a rigorous scientific logical thinking process, including observation, analysis, induction, deduction and reasoning. Mineralization prediction based on geological spatiotemporal big data involves a series of theories, methods and key technologies of the fourth paradigm of scientific research and geological data science. Establishing a workflow for the aggregation, integration, fusion, mining and evaluation of geological big data that is suitable for prediction work is of great help to the development of solid mineral prospecting prediction work.

地质大数据是一种时空大数据，主要产生于基础地质、矿产地质、水文地质、工程地质、环境地质的调查、勘查和相应的地质科学研究过程中。以找矿为目的通过露头观测记录、岩心编录、地球物理仪器记录、遥感记录、样品化学分析和物理测试获取的数据，是对现实地质世界的映射，其间包含有矿产信息，成矿预测是解决如何从采集到的多尺度异质异构数据中发现成矿信息，挖掘成矿规律，建立找矿预测模型，为找矿圈定靶区提供服务。Geological big data is a kind of spatiotemporal big data, which is mainly generated in the investigation, exploration and corresponding geological science research process of basic geology, mineral geology, hydrogeology, engineering geology and environmental geology. The data obtained for the purpose of prospecting through outcrop observation records, core compilation, geophysical instrument records, remote sensing records, sample chemical analysis and physical testing is a mapping of the real geological world, which contains mineral information. Mineralization prediction is to solve how to discover mineralization information from the collected multi-scale heterogeneous and heterogeneous data, explore mineralization laws, establish mineralization prediction models, and provide services for the delineation of target areas for prospecting.

发明内容Summary of the invention

本发明的目的旨在结合三维地质模型、机器学习方法、数据挖掘技术，处理预测区地质大数据，多尺度递进式确定靶区，为矿产资源预测提供找矿预测方法。The purpose of the present invention is to combine three-dimensional geological models, machine learning methods, and data mining technology to process geological big data in the prediction area, determine the target area in a multi-scale progressive manner, and provide a prospecting prediction method for mineral resource prediction.

具体采用的技术方案为：一种基于地质大数据的固体矿产多尺度递进式找矿预测方法，通过有模型数据和无模型数据耦合、多源数据融合、构建找矿知识图谱、数据挖掘和构建三维属性模型形成成矿预测模型，具体步骤如下：The specific technical solution adopted is: a multi-scale progressive prospecting prediction method for solid minerals based on geological big data, which forms a mineralization prediction model through coupling model data and model-free data, multi-source data fusion, construction of prospecting knowledge graph, data mining and construction of three-dimensional attribute model. The specific steps are as follows:

步骤1：根据找矿预测目的整理收集待研究区的数据，根据待研究区是否存在现有成矿模型，将收集到的待研究区的数据分为有模型数据和无模型数据，所述有模型数据至少包括现有成矿系统、现有成矿模式和找矿案例，所述无模型数据至少包括地质、物探、化探和遥感数据；且无模型数据根据工作比例尺分为1:50万、1:25万、1:5万、1:2.5万和1:0.5万的地质、物探、化探和遥感数据；Step 1: According to the purpose of prospecting and prediction, the data of the area to be studied are sorted and collected. According to whether there is an existing mineralization model in the area to be studied, the collected data of the area to be studied are divided into model data and non-model data. The model data at least include the existing mineralization system, the existing mineralization model and prospecting cases, and the non-model data at least include geological, geophysical, geochemical and remote sensing data; and the non-model data are divided into geological, geophysical, geochemical and remote sensing data of 1:500,000, 1:250,000, 1:50,000, 1:25,000 and 1:5,000 according to the working scale;

步骤2：通过步骤1的有模型数据的现有成矿系统和现有成矿模式分析找矿过程中重要节点，以每个重要节点之间的关系为基础绘制找矿过程知识关联图；再基于贝叶斯网络，分析重要节点之间的找矿知识，将所述找矿知识与有模型数据的找矿案例结合构建找矿知识图谱，所构建的找矿知识图谱至少包括待研究区构造、地层、岩性数据、矿产资源空间分布范围数据、矿床空间分布范围数据、矿床位置、层位和规模数据、矿体赋存位置、矿体形态、矿体厚度和矿体品位数据；Step 2: Analyze the important nodes in the prospecting process through the existing mineralization system and existing mineralization mode with model data in step 1, and draw a knowledge association diagram of the prospecting process based on the relationship between each important node; then analyze the prospecting knowledge between the important nodes based on the Bayesian network, and combine the prospecting knowledge with the prospecting cases with model data to construct a prospecting knowledge map, and the constructed prospecting knowledge map includes at least the structure, stratigraphy, lithology data, spatial distribution range data of mineral resources, spatial distribution range data of ore deposits, ore deposit location, stratigraphic and scale data, ore body occurrence location, ore body morphology, ore body thickness and ore body grade data of the area to be studied;

步骤3：提取1:50万的地质、物探、化探和遥感数据中的地质、物探和遥感异常，结合步骤1的有模型数据及步骤2的找矿知识图谱中的待研究区构造、地层、岩性数据、矿产资源空间分布范围数据，使用GIS软件从构造格架和成矿带的角度分析所述遥感、物探和化探异常与所述矿产资源空间分布范围数据之间的规律；Step 3: Extract geological, geophysical and remote sensing anomalies from the 1:500,000 geological, geophysical, geochemical and remote sensing data, combine the model data from step 1 and the structural, stratigraphic, lithological data and spatial distribution range data of the area to be studied in the prospecting knowledge map from step 2, and use GIS software to analyze the rules between the remote sensing, geophysical and geochemical anomalies and the spatial distribution range data of the mineral resources from the perspective of structural framework and mineralization belt;

步骤4：在步骤3确定的矿产资源空间分布范围中提取1:25万的地质、物探、化探和遥感数据中的地质、物探、化探和遥感异常，结合步骤1的有模型数据及步骤2的找矿知识图谱中的矿床空间分布范围数据，使用GIS软件从矿质来源、底劈通道和成矿环境的角度分析所述遥感、物探和化探异常与所述矿床空间分布范围数据之间的规律；Step 4: extract geological, geophysical, geochemical and remote sensing anomalies in the 1:250,000 geological, geophysical, geochemical and remote sensing data from the spatial distribution range of mineral resources determined in step 3, combine the model data in step 1 and the spatial distribution range data of the ore deposit in the prospecting knowledge map in step 2, and use GIS software to analyze the rules between the remote sensing, geophysical and geochemical anomalies and the spatial distribution range data of the ore deposit from the perspectives of mineral source, bottom splitting channel and mineralization environment;

步骤5：在步骤4确定的矿床空间分布范围中提取1:5万的地质、物探、化探和遥感数据中的地质、物探、化探和遥感异常，结合步骤1的有模型数据及步骤2的找矿知识图谱中的矿床位置、层位和规模数据，使用GIS软件从成矿环境、导矿构造和配矿构造的角度分析所述地质、物探和化探异常与所述矿床位置、层位和规模数据之间的规律；Step 5: Extract geological, geophysical, geochemical and remote sensing anomalies in the 1:50,000 geological, geophysical, geochemical and remote sensing data within the spatial distribution range of the ore deposit determined in step 4, combine the model data in step 1 and the ore deposit location, horizon and scale data in the ore prospecting knowledge map in step 2, and use GIS software to analyze the regularity between the geological, geophysical and geochemical anomalies and the ore deposit location, horizon and scale data from the perspective of metallogenic environment, ore guiding structure and ore matching structure;

步骤6：在步骤5确定的矿床位置、层位和规模中提取1:2.5万的地质、物探、化探和遥感数据中的大地电磁、地震、钻孔、激电、高精度磁测数据和化探异常，结合步骤1的有模型数据及步骤2的矿体赋存位置和矿体形态数据，使用GIS软件从深部通道、浅部导矿断裂、配矿断裂和容矿地质体的角度分析所述大地电磁、地震、钻孔、激电、高精度磁测数据和化探异常与所述矿体赋存位置和矿体形态数据之间的规律，并构建三维属性模型，进行三维潜在资源地段预测；Step 6: extracting magnetotelluric, seismic, drilling, induced polarization, high-precision magnetic survey data and geochemical anomalies from the 1:25,000 geological, geophysical, geochemical and remote sensing data from the ore deposit location, layer and scale determined in step 5, combining the model data of step 1 and the ore body location and ore body morphology data of step 2, using GIS software to analyze the law between the magnetotelluric, seismic, drilling, induced polarization, high-precision magnetic survey data and geochemical anomalies and the ore body location and ore body morphology data from the perspective of deep channels, shallow ore-guiding faults, ore-matching faults and ore-bearing geological bodies, and constructing a three-dimensional attribute model to predict three-dimensional potential resource areas;

步骤7：在步骤6确定的矿体赋存位置、矿体形态、矿体厚度和矿体品位数据中提取1:0.5万的地质、物探、化探和遥感数据中的大地音频电磁、钻孔和激电异常，结合步骤1的有模型数据及步骤2的矿体赋存位置、矿体形态、矿体厚度和矿体品位数据，使用GIS软件从浅部导矿断裂、配矿断裂和容矿地质体的角度分析所述大地音频电磁、钻孔和激电异常与所述矿体赋存位置、矿体形态、矿体厚度和矿体品位数据之间的规律，在构建的三维属性模型上开展成矿系统结构挖掘，进行远景矿体地段的预测。Step 7: Extract the geomagnetic, drilling and induced polarization anomalies in the 1:50000 geological, geophysical, geochemical and remote sensing data from the ore body location, ore body morphology, ore body thickness and ore body grade data determined in step 6; combine the model data in step 1 and the ore body location, ore body morphology, ore body thickness and ore body grade data in step 2; use GIS software to analyze the law between the geomagnetic, drilling and induced polarization anomalies and the ore body location, ore body morphology, ore body thickness and ore body grade data from the perspective of shallow ore-guiding faults, ore-bearing faults and ore-bearing geological bodies; carry out mineralization system structure mining on the constructed three-dimensional attribute model to predict the prospective ore body areas.

而且，使用步骤1的有模型数据和无模型数据在GIS软件中构建三维地质模型；所述GIS软件至少包括QuantyView软件。Furthermore, the three-dimensional geological model is constructed in GIS software using the modeled data and the non-modeled data in step 1; the GIS software at least includes QuantyView software.

而且，使用GIS软件分别制作步骤1中1：50万、1:25万、1：5万、1：2.5万、1：0.5万的地质、物探、化探和遥感数据；所述GIS软件至少包括QuantyView软件，所形成的地质图数据库导入至GIS数据库。Moreover, GIS software is used to produce the geological, geophysical, geochemical and remote sensing data of 1:500,000, 1:250,000, 1:50,000, 1:25,000 and 1:5,000 in step 1 respectively; the GIS software includes at least QuantyView software, and the formed geological map database is imported into the GIS database.

而且，步骤3至步骤7中所述GIS软件至少包括QuantyView软件。Moreover, the GIS software in steps 3 to 7 at least includes QuantyView software.

而且，所述1:50万的地质、物探、化探和遥感数据中，地质数据至少包括1:50万地质图，物探数据至少包括1:50万航磁，遥感数据至少包括高光谱数据、高分辨率卫星影像、雷达卫星影像数据。Moreover, among the 1:500,000 geological, geophysical, geochemical and remote sensing data, the geological data at least include 1:500,000 geological maps, the geophysical data at least include 1:500,000 aeromagnetic maps, and the remote sensing data at least include hyperspectral data, high-resolution satellite images, and radar satellite image data.

而且，所述1:25万的地质、物探、化探和遥感数据中，地质数据至少包括1:25万DEM数据、1:25万地质图，物探数据至少包括1:20万区域重力、1：20万航磁，化探数据至少包括1：20万区域地球化学扫面数据，遥感数据至少包括高光谱数据、高分辨率卫星影像、雷达卫星影像数据。Moreover, among the 1:250,000 geological, geophysical, geochemical and remote sensing data, the geological data at least include 1:250,000 DEM data and 1:250,000 geological maps, the geophysical data at least include 1:200,000 regional gravity and 1:200,000 aeromagnetic, the geochemical data at least include 1:200,000 regional geochemical scanning data, and the remote sensing data at least include hyperspectral data, high-resolution satellite images, and radar satellite image data.

而且，所述1:5万的地质、物探、化探和遥感数据中，地质数据至少包括1:5万DEM数据、1:5万地质图，物探数据至少包括1:5万重力、1:5万地面高精度磁测，化探数据至少包括1:5万水系沉积物、土壤地球化学测量和岩石测量数据，遥感数据至少包括高光谱数据、高分辨率卫星影像、雷达卫星影像数据。Moreover, among the 1:50,000 geological, geophysical, geochemical and remote sensing data, the geological data at least include 1:50,000 DEM data and 1:50,000 geological maps, the geophysical data at least include 1:50,000 gravity and 1:50,000 ground high-precision magnetic surveys, the geochemical data at least include 1:50,000 stream sediments, soil geochemical measurements and rock measurement data, and the remote sensing data at least include hyperspectral data, high-resolution satellite images and radar satellite image data.

而且，所述1:2.5万的地质、物探、化探和遥感数据中，地质数据至少包括钻孔信息、钻孔柱状图、1:1万勘探线剖面图，物探数据至少包括大地电磁测深、激电测深剖面，化探数据至少包括钻孔样品分析数据，遥感数据至少包括高光谱数据、高分辨率卫星影像、雷达卫星影像数据。Moreover, among the 1:25,000 geological, geophysical, geochemical and remote sensing data, the geological data at least include drilling information, drilling column charts, and 1:10,000 exploration line profiles; the geophysical data at least include magnetotelluric sounding and induced polarization sounding profiles; the geochemical data at least include drilling sample analysis data; and the remote sensing data at least include hyperspectral data, high-resolution satellite images, and radar satellite image data.

而且，所述1:0.5万的地质、物探、化探和遥感数据中，地质数据至少包括钻孔信息、钻孔柱状图、1:1万DEM数据、1:0.5万地质图或1:1万地质图、1:2千勘探线剖面图、中段平面地质图、矿体资源储量估算图，物探数据至少包括大地电磁测深、激电测深剖面，化探数据至少包括钻孔样品分析数据，遥感数据至少包括高光谱数据、高分辨率卫星影像、雷达卫星影像数据。Moreover, among the 1:50,000 geological, geophysical, geochemical and remote sensing data, the geological data at least include drilling information, drilling column charts, 1:10,000 DEM data, 1:50,000 geological maps or 1:10,000 geological maps, 1:2,000 exploration line profiles, mid-section plane geological maps, and ore body resource reserve estimation maps; the geophysical data at least include magnetotelluric sounding and induced polarization sounding profiles; the geochemical data at least include drilling sample analysis data; and the remote sensing data at least include hyperspectral data, high-resolution satellite images, and radar satellite image data.

与现有技术相比，本方案的有益效果在于：Compared with the prior art, the beneficial effects of this solution are:

1、将收集到的待研究区的数据分为有模型数据和无模型数据，汇聚了超高维度、超高计算复杂、超高不确定性的多尺度(1:50万，1:25万，1:5万，1:2.5万，1:0.5万)、多变量、多时态和多关联的时空结构和地质属性数据；对于现有成矿系统、现有成矿模式和找矿案例，采用“复盘”的方法，对预测区历史找矿经验、成矿模式进行深入的认识和理解，通过查阅地质报告、文献、咨询，对预测区成矿基础地质特征的有深入的认识，通过综合数据和资料的综合分析对成矿机理、成矿条件、控矿因素的深刻理解，便于构建找矿知识图谱、绘制找矿过程知识关联图。1. The collected data of the area to be studied are divided into modeled data and model-free data, which bring together multi-scale (1:500,000, 1:250,000, 1:50,000, 1:25,000, 1:5,000), multi-variable, multi-temporal and multi-correlated spatiotemporal structure and geological attribute data with ultra-high dimension, ultra-high computational complexity and ultra-high uncertainty; for the existing mineralization system, existing mineralization model and prospecting cases, the "re-examination" method is adopted to have an in-depth understanding and understanding of the historical prospecting experience and mineralization model of the prediction area, and through consulting geological reports, literature and consultation, the basic geological characteristics of mineralization in the prediction area are deeply understood. Through the comprehensive analysis of comprehensive data and information, the mineralization mechanism, mineralization conditions and ore-controlling factors are deeply understood, which is convenient for constructing a prospecting knowledge map and drawing a knowledge association map of the prospecting process.

2、构建找矿知识图谱和绘制找矿过程知识关联图可以对原始数据进行标准化和形式化处理，构建预测数据集市，以便更好地为挖掘算法和预测方法及潜在的各种数据模式。2. Constructing a prospecting knowledge graph and drawing a knowledge association graph of the prospecting process can standardize and formalize the original data and build a prediction data mart to better mine algorithms, prediction methods and potential various data patterns.

3、提取1：50万的地质、物探、化探和遥感数据中的地质、物探和遥感异常，使用GIS软件从构造格架和成矿带的角度分析所述地质、物探和遥感异常与所述矿产资源空间分布范围数据之间的规律；进一步在确定的矿产资源空间分布范围中提取1:25万的地质、物探、化探和遥感数据中的地质、物探、化探和遥感异常，使用GIS软件从矿质来源、底劈通道和成矿环境的角度分析所述地质、物探、化探和遥感异常与所述矿床空间分布范围数据之间的规律；进一步在确定的矿床空间分布范围中提取1:5万的地质、物探、化探和遥感数据中的地质、物探、化探和遥感异常，使用GIS软件从成矿环境、导矿构造和配矿构造的角度分析所述地质、物探、化探和遥感异常与所述矿床位置、层位和规模数据之间的规律；更进一步在确定的矿床位置、层位和规模中提取1:2.5万的地质、物探、化探和遥感数据中的大地电磁、地震、钻孔、激电、高精度磁测数据和化探异常，使用GIS软件从深部通道、浅部导矿断裂、配矿断裂和容矿地质体的角度分析所述大地电磁、地震、钻孔、激电、高精度磁测数据和化探异常与所述矿体赋存位置和矿体形态数据之间的规律；更进一步在矿床位置、层位和规模中提取1:0.5万的地质、物探、化探和遥感数据中的大地音频电磁、钻孔和激电异常，使用GIS软件从深部通道、浅部导矿断裂、配矿断裂和容矿地质体的角度分析所述大地音频电磁、钻孔和激电异常与所述矿体赋存位置、矿体形态、矿体厚度和矿体品位数据之间的规律。实现多尺度递进式的分析成矿条件和控矿要素之间的空间异常规则、空间关联规则、空间分布规律和空间预测规则。3. Extract geological, geophysical and remote sensing anomalies from geological, geophysical, geochemical and remote sensing data at a scale of 1:500,000, and use GIS software to analyze the regularity between the geological, geophysical and remote sensing anomalies and the spatial distribution range data of the mineral resources from the perspective of structural framework and mineralization belt; further extract geological, geophysical, geochemical and remote sensing anomalies from geological, geophysical, geochemical and remote sensing data at a scale of 1:250,000 within the determined spatial distribution range of mineral resources, and use GIS software to analyze the regularity between the geological, geophysical, geochemical and remote sensing anomalies and the spatial distribution range data of the ore deposit from the perspective of mineral source, bottom splitting channel and mineralization environment; further extract geological, geophysical, geochemical and remote sensing anomalies from geological, geophysical, geochemical and remote sensing data at a scale of 1:50,000 within the determined spatial distribution range of the ore deposit, and use GIS software to analyze the regularity between the geological, geophysical, geochemical and remote sensing anomalies and the location of the ore deposit from the perspective of mineralization environment, ore-guiding structure and ore-matching structure , stratigraphic and scale data; further extract the magnetotelluric, seismic, drilling, induced polarization, high-precision magnetic survey data and geochemical anomalies in the 1:25,000 geological, geophysical, geochemical and remote sensing data in the determined ore deposit location, stratigraphic and scale, and use GIS software to analyze the laws between the magnetotelluric, seismic, drilling, induced polarization, high-precision magnetic survey data and geochemical anomalies and the ore body occurrence location and ore body morphology data from the perspectives of deep channels, shallow ore-guiding faults, ore-bearing faults and ore-bearing geological bodies; further extract the geo-audio-frequency electromagnetic, drilling and induced polarization anomalies in the 1:5,000 geological, geophysical, geochemical and remote sensing data in the determined ore deposit location, stratigraphic and scale, and use GIS software to analyze the laws between the geo-audio-frequency electromagnetic, drilling and induced polarization anomalies and the ore body occurrence location, ore body morphology, ore body thickness and ore body grade data from the perspectives of deep channels, shallow ore-guiding faults, ore-bearing faults and ore-bearing geological bodies. Realize multi-scale progressive analysis of the spatial anomaly rules, spatial association rules, spatial distribution laws and spatial prediction rules between mineralization conditions and ore-controlling elements.

4、利用前述所归纳规律构成成矿预测模型，结合三维地质模型、机器学习方法、数据挖掘技术，处理预测区地质大数据，实现递进发现成矿可能、找矿可行、找矿有利、潜在资源、远景矿体地段，达到确定靶区的作用。4. Use the above-mentioned laws to form a mineralization prediction model, combine it with three-dimensional geological models, machine learning methods, and data mining technology to process the geological big data of the prediction area, so as to realize the progressive discovery of mineralization possibility, feasible prospecting, favorable prospecting, potential resources, and prospective ore bodies, so as to determine the target area.

附图说明BRIEF DESCRIPTION OF THE DRAWINGS

图1为本发明方法的流程图；Fig. 1 is a flow chart of the method of the present invention;

图2基于1:50万的地质、物探、化探和遥感数据中的布格重力和航磁异常数据挖掘的负向控矿构造；Figure 2 Negative ore-controlling structures based on Bouguer gravity and aeromagnetic anomaly data mining in 1:500,000 geological, geophysical, geochemical and remote sensing data;

图3为基于1:25万的地质、物探、化探和遥感数据中的物探、化探及布格重力异常数据挖掘的泥盆-石炭纪威-水北西小裂谷，并与东西向裂谷带叠加造成热液富集；Figure 3 shows the Devonian-Carboniferous Wei-Shui Northwest Small Rift Valley based on geophysical, geochemical and Bouguer gravity anomaly data mining in 1:250,000 geological, geophysical, geochemical and remote sensing data, and the superposition with the east-west rift belt caused hydrothermal enrichment;

图4为在所确定的矿床空间分布范围中，基于1:5万的地质、物探、化探和遥感数据中的地质、物探和化探异常与矿床位置、层位和规模数据之间的规律，进行的初步找矿预测；Figure 4 shows the preliminary prospecting prediction based on the regularity between geological, geophysical and geochemical anomalies and the location, stratigraphic and scale data of the ore deposits in the determined spatial distribution range of the ore deposits, based on the 1:50,000 geological, geophysical, geochemical and remote sensing data;

图5为结合1:2.5万的地质、物探、化探和遥感数据中和地质背景，构建的三维属性模型和三维潜在资源地段预测；Figure 5 shows a three-dimensional attribute model and three-dimensional potential resource location prediction constructed by combining 1:25,000 geological, geophysical, geochemical and remote sensing data and geological background;

图6为在地质剖面上开展成矿系统结构挖掘，利用勘查线设计1:2000剖面图、并处理待研究区的数据圈定的远景矿体地段。Figure 6 shows the prospective ore body area delineated by conducting structural excavation of the mineralization system on the geological profile, designing a 1:2000 profile using the exploration line, and processing the data of the area to be studied.

具体实施方式Detailed ways

下面结合附图和实施例对本发明进行详细具体说明，本发明的内容不局限于以下实施例。The present invention is described in detail below with reference to the accompanying drawings and embodiments, but the content of the present invention is not limited to the following embodiments.

使用本发明的方法在某试验区预测铅锌矿集区的实施过程如下：The implementation process of using the method of the present invention to predict the lead-zinc ore concentration area in a certain test area is as follows:

将收集到的该试验区的数据分为有模型数据和无模型数据，有模型数据至少包括现有成矿系统、现有成矿模式和找矿案例，无模型数据至少包括地质、物探、化探和遥感数据；且无模型数据根据工作比例尺分为1:50万、1:25万、1:5万、1:2.5万和1:0.5万的地质、物探、化探和遥感数据，使用QuantyView软件分别制作。The data collected in the test area are divided into modeled data and non-modeled data. The modeled data at least include the existing mineralization system, existing mineralization model and prospecting cases, and the non-modeled data at least include geological, geophysical, geochemical and remote sensing data; and the non-modeled data are divided into geological, geophysical, geochemical and remote sensing data of 1:500,000, 1:250,000, 1:50,000, 1:25,000 and 1:5,000 according to the working scale, and are produced separately using QuantyView software.

有模型数据的现有成矿系统和现有成矿模式分析找矿过程中重要节点，以每个重要节点之间的关系为基础绘制找矿过程知识关联图；再基于贝叶斯网络，分析重要节点之间的找矿知识，将所述找矿知识与有模型数据的找矿案例结合构建找矿知识图谱，所构建的找矿知识图谱至少包括待研究区构造、地层、岩性数据、矿产资源空间分布范围数据、矿床空间分布范围数据、矿床位置、层位和规模数据、矿体赋存位置、矿体形态、矿体厚度和矿体品位数据。The existing mineralization system and existing mineralization mode with model data analyze the important nodes in the prospecting process, and draw a knowledge association diagram of the prospecting process based on the relationship between each important node; then based on the Bayesian network, analyze the prospecting knowledge between the important nodes, and combine the prospecting knowledge with the prospecting cases with model data to construct a prospecting knowledge map. The constructed prospecting knowledge map includes at least the structure, stratigraphy, lithology data of the study area, spatial distribution range data of mineral resources, spatial distribution range data of ore deposits, ore deposit location, stratigraphic and scale data, ore body occurrence location, ore body morphology, ore body thickness and ore body grade data.

找出1:50万的地质、物探、化探和遥感数据中的地质、物探和遥感异常，结合有模型数据及找矿知识图谱中的待研究区构造、地层、岩性数据、矿产资源空间分布范围数据，使用GIS软件从构造格架和成矿带的角度分析出地质、物探和遥感异常与所述矿产资源空间分布范围数据之间的规律；其中该试验区1:50万的异常数据以布格重力和航磁异常数据规律性最强，从而发现了隐伏东西向震旦-寒武纪裂谷带，确定东西裂谷带为铅锌矿可能地段，如图2所示。The geological, geophysical and remote sensing anomalies in the 1:500,000 geological, geophysical, geochemical and remote sensing data were found, and the structural, stratigraphic, lithological data and spatial distribution range data of the study area in the model data and the prospecting knowledge map were combined. The regularity between the geological, geophysical and remote sensing anomalies and the spatial distribution range data of the mineral resources was analyzed from the perspective of the structural framework and the metallogenic belt using GIS software. Among them, the Bouguer gravity and aeromagnetic anomaly data of the 1:500,000 anomaly data of the test area had the strongest regularity, thus discovering the hidden east-west Sinian-Cambrian rift zone, and determining the east-west rift zone as a possible area for lead-zinc deposits, as shown in Figure 2.

在上一步骤确定的范围内，根据1:25万的地质、物探、化探和遥感数据中的地质、物探、化探和遥感异常，结合有模型数据及找矿知识图谱中的矿床空间分布范围数据，使用GIS软件从矿质来源、底劈通道和成矿环境的角度分析所述地质、物探、化探和遥感异常异常与所述矿床空间分布范围数据之间的规律；其中1:25万的异常数据以物探、化探及布格重力异常数据规律性最强，挖掘出泥盆-石炭纪威-水北西小裂，并且泥盆-石炭纪威-水北西小裂谷与上一步骤发现的东西向裂谷带叠加造成热液富集，由于两裂谷基底喷流分别提供深源铅锌和铁质，推测该交叉处(猪拱塘、菜园子、五指山工作区)能提供后期热液通道，从而确定了矿床空间分布范围，如图3所示。Within the range determined in the previous step, based on the geological, geophysical, geochemical and remote sensing anomalies in the 1:250,000 geological, geophysical, geochemical and remote sensing data, combined with the model data and the spatial distribution range data of the ore deposit in the prospecting knowledge map, GIS software is used to analyze the regularity between the geological, geophysical, geochemical and remote sensing anomalies and the spatial distribution range data of the ore deposit from the perspectives of mineral source, bottom splitting channel and mineralization environment; among them, the 1:250,000 anomaly data has the strongest regularity in the geophysical, geochemical and Bouguer gravity anomaly data, and the Devonian-Carboniferous Wei-Shuibeixi Small Rift was excavated, and the Devonian-Carboniferous Wei-Shuibeixi Small Rift and the east-west rift belt discovered in the previous step are superimposed to cause hydrothermal enrichment. Since the basement jets of the two rifts provide deep-source lead and zinc and iron respectively, it is speculated that the intersection (Zhugongtang, Caiyuanzi, Wuzhishan working area) can provide later hydrothermal channels, thereby determining the spatial distribution range of the ore deposit, as shown in Figure 3.

在所确定的矿床空间分布范围(猪拱塘、菜园子、五指山工作区)中，提取1:5万的地质、物探、化探和遥感数据中的地质、物探、化探和遥感异常异常，结合有模型数据及找矿知识图谱中的矿床位置、层位和规模数据，使用GIS软件从成矿环境、导矿构造和配矿构造的角度分析所述地质、物探、化探和遥感异常与所述矿床位置、层位和规模数据之间的规律，构建训练卷积神经网络预测模型进行初步找矿预测，预测结果如图4所示。In the determined spatial distribution range of the ore deposit (Zhugongtang, Caiyuanzi and Wuzhishan working areas), the geological, geophysical, geochemical and remote sensing anomalies in the 1:50,000 geological, geophysical, geochemical and remote sensing data are extracted, and the ore deposit location, stratigraphic and scale data in the model data and the prospecting knowledge map are combined. GIS software is used to analyze the laws between the geological, geophysical, geochemical and remote sensing anomalies and the ore deposit location, stratigraphic and scale data from the perspectives of metallogenic environment, ore-guiding structure and ore-matching structure, and a convolutional neural network prediction model is constructed and trained to carry out preliminary prospecting prediction. The prediction results are shown in Figure 4.

进一步，结合1:2.5万的地质、物探、化探和遥感数据中的大地电磁、地震、钻孔、激电、高精度磁测和化探异常和包括矿体赋存位置和矿体形态在内的地质背景，对成矿系统、成矿条件和控矿因素进行归纳基础上，构建了试验区1:2.5万三维属性模型和属性数据集市，对调查区进行了三维潜在资源地段预测，如图5所示。Furthermore, based on the summary of the mineralization system, mineralization conditions and controlling factors, a 1:25,000 three-dimensional attribute model and attribute data mart of the experimental area were constructed, and a three-dimensional potential resource area prediction was made for the survey area, as shown in Figure 5.

在构建的含有铅锌矿潜在资源地段的三维属性模型基础上，通过1:0.5万的地质、物探、化探和遥感数据中的大地音频电磁(AMT)、钻孔和激电异常，结合矿体赋存位置、矿体形态、矿体厚度和矿体品位数据，使用GIS软件从深部通道、浅部导矿断裂、配矿断裂和容矿地质体的角度分析所述大地电磁、地震、钻孔、激电、高精度磁测和化探异常与所述矿体赋存位置、矿体形态、矿体厚度和矿体品位数据，在地质剖面上开展成矿系统结构挖掘，再利用前述所有规律构成成矿预测模型处理待研究区的数据，图6为利用勘查线设计1:2000剖面图、并处理待研究区的数据圈定的远景矿体地段。On the basis of the constructed three-dimensional attribute model of the potential resource area containing lead and zinc ore, the geomagnetic frequency electromagnetic (AMT), drilling and induced polarization anomalies in the 1:0.5000 geological, geophysical, geochemical and remote sensing data are combined with the ore body location, ore body morphology, ore body thickness and ore body grade data. GIS software is used to analyze the geomagnetic, seismic, drilling, induced polarization, high-precision magnetic survey and geochemical anomalies and the ore body location, ore body morphology, ore body thickness and ore body grade data from the perspectives of deep channels, shallow ore-guiding faults, ore-bearing faults and ore-bearing geological bodies, and the mineralization system structure mining is carried out on the geological profile. Then, all the above laws are used to form a mineralization prediction model to process the data of the area to be studied. Figure 6 shows the prospective ore body area delineated by designing a 1:2000 profile using the exploration line and processing the data of the area to be studied.

本实施过程中所用到的详细数据列表为：The detailed data list used in this implementation process is as follows:

Claims (9)

1. A solid mineral multi-scale progressive ore finding prediction method based on geological big data is characterized by comprising the following steps of: the ore formation prediction model is formed by coupling model data and model-free data, multi-source data fusion, construction of an ore finding knowledge graph, data mining and construction of a three-dimensional attribute model, and the specific steps are as follows:
Step 1: according to the aim of ore finding prediction, sorting and collecting data of a region to be researched, and according to the fact that whether an existing ore forming model exists in the region to be researched, dividing the collected data of the region to be researched into model data and model-free data, wherein the model data at least comprise an existing ore forming system, an existing ore forming mode and an ore finding case, and the model-free data at least comprise geological, geophysical prospecting, chemical prospecting and remote sensing data; the model-free data are divided into geological, geophysical prospecting, chemical prospecting and remote sensing data of 1:50 ten thousand, 1:25 ten thousand, 1:5 ten thousand, 1:2.5 ten thousand and 1:0.5 ten thousand according to the working proportion;
Step 2: analyzing important nodes in the ore finding process through the existing ore forming system with the model data and the existing ore forming mode in the step 1, and drawing an ore finding process knowledge association diagram based on the relation between each important node; analyzing the ore finding knowledge among important nodes based on a Bayesian network, and combining the ore finding knowledge with an ore finding case with model data to construct an ore finding knowledge map, wherein the constructed ore finding knowledge map at least comprises a region structure to be researched, stratum, lithology data, mineral resource space distribution range data, mineral deposit position, horizon and scale data, a mineral body occurrence position, a mineral body form, a mineral body thickness and mineral body grade data;
Step 3: extracting geological, geophysical prospecting and remote sensing anomalies in geological, geophysical prospecting, chemical prospecting and remote sensing data of 1:50 ten thousand, and analyzing rules between the remote sensing, geophysical prospecting and chemical prospecting anomalies and the mineral resource space distribution range data from the angles of a construction grid and a mineral formation zone by using GIS software in combination with the model data in the step 1 and the to-be-researched area structure, stratum, lithology data and mineral resource space distribution range data in the prospecting knowledge graph in the step 2;
Step 4: extracting geology, geophysical prospecting, chemical prospecting and remote sensing anomalies in geological, geophysical prospecting, chemical prospecting and remote sensing data of 1:25 ten thousand in the spatial distribution range of mineral resources determined in the step 3, and analyzing rules between the remote sensing, geophysical prospecting and chemical prospecting anomalies and the spatial distribution range data of the mineral deposits by using GIS software from the angles of mineral sources, bottom splitting channels and the mineral forming environment in combination with the model data in the step 1 and the spatial distribution range data of the mineral deposits in the prospecting knowledge graph in the step 2;
Step 5: extracting geology, geophysical prospecting, chemical prospecting and remote sensing anomalies in geological, geophysical prospecting, chemical prospecting and remote sensing data of 1:5 ten thousand in the spatial distribution range of the ore deposit determined in the step 4, and analyzing rules between the geology, geophysical prospecting and chemical prospecting anomalies and the position, horizon and scale data of the ore deposit by using GIS software from the angles of an ore forming environment, an ore guiding structure and an ore matching structure in combination with the model data in the step 1 and the position, horizon and scale data of the ore deposit in the ore finding knowledge map in the step 2;
Step 6: extracting geoelectromagnetic, earthquake, drilling, excitation, high-precision magnetic measurement data and chemical detection anomalies in geological, geophysical prospecting, chemical detection and remote sensing data of 1:2.5 ten thousand from the position, horizon and scale of the ore deposit determined in the step 5, analyzing the rules among the geoelectromagnetic, earthquake, drilling, excitation, high-precision magnetic measurement data and chemical detection anomalies, the position of the ore body occurrence and the ore body form data by using GIS software from the angles of deep channels, shallow ore guiding fracture, ore distribution fracture and ore containing bodies in combination with the model data in the step 1 and the ore body occurrence position and the ore body form data in the step 2, and constructing a three-dimensional attribute model to predict three-dimensional potential resource sections;
Step 7: extracting 1:0.5 ten thousand of earth audio electromagnetic, drilling and excitation anomalies in geological, geophysical prospecting, chemical prospecting and remote sensing data from the ore body occurrence position, ore body morphology, ore body thickness and ore body grade data determined in the step 6, analyzing rules between the earth audio electromagnetic, drilling and excitation anomalies and the ore body occurrence position, ore body morphology, ore body thickness and ore body grade data by using GIS software from angles of shallow ore guiding fracture, ore matching fracture and ore body in combination with the model data in the step 1 and the ore body occurrence position, ore body morphology, ore body thickness and ore body grade data in the step 2, and developing mining of an ore forming system structure on a constructed three-dimensional attribute model to predict a distant view ore body section.
2. The geological big data-based solid mineral multi-scale progressive ore finding prediction method is characterized by comprising the following steps of: constructing a three-dimensional geological model in GIS software by using the model data and the model-free data in the step 1; the GIS software at least comprises QuantyView software.
3. The geological big data-based solid mineral multi-scale progressive ore finding prediction method is characterized by comprising the following steps of: respectively manufacturing geological, geophysical prospecting, chemical prospecting and remote sensing data in the steps 1 by using GIS software, wherein the geological, geophysical prospecting, chemical prospecting and remote sensing data are 1:50 ten thousand, 1:25 ten thousand, 1:5 ten thousand, 1:2.5 ten thousand and 1:0.5 ten thousand; the GIS software at least comprises QuantyView software, and the formed geological map database is imported into the GIS database.
4. The geological big data-based solid mineral multi-scale progressive ore finding prediction method is characterized by comprising the following steps of: the GIS software in the steps 3 to 7 at least comprises QuantyView software.
5. The geological big data-based solid mineral multi-scale progressive ore finding prediction method is characterized by comprising the following steps of: in the geological, geophysical prospecting, chemical prospecting and remote sensing data of 1:50 ten thousand, the geological data at least comprise a 1:50 ten thousand geological map, the geophysical prospecting data at least comprise a 1:50 ten thousand aeromagnetic, and the remote sensing data at least comprise hyperspectral data, high-resolution satellite images and radar satellite image data.
6. The geological big data-based solid mineral multi-scale progressive ore finding prediction method is characterized by comprising the following steps of: in the geological, geophysical prospecting, chemical prospecting and remote sensing data of 1:25 ten thousand, the geological data at least comprise 1:25 ten thousand DEM data and 1:25 ten thousand geological maps, the geophysical prospecting data at least comprise 1:20 ten thousand area gravity and 1:20 Mo Hang magnetism, the chemical prospecting data at least comprise 1:20 ten thousand area geochemical scanning data, and the remote sensing data at least comprise hyperspectral data, high-resolution satellite images and radar satellite image data.
7. The geological big data-based solid mineral multi-scale progressive ore finding prediction method is characterized by comprising the following steps of: in the geological, geophysical prospecting, chemical prospecting and remote sensing data of 1:5 ten thousand, the geological data at least comprise 1:5 ten thousand DEM data and 1:5 ten thousand geological maps, the geophysical prospecting data at least comprise 1:5 ten thousand gravity and 1:5 ten thousand ground high-precision magnetic surveying, the chemical prospecting data at least comprise 1:5 ten thousand water sediment, soil geochemical surveying and rock measuring data, and the remote sensing data at least comprise hyperspectral data, high-resolution satellite images and radar satellite image data.
8. The geological big data-based solid mineral multi-scale progressive ore finding prediction method is characterized by comprising the following steps of: in the geological, geophysical prospecting, chemical prospecting and remote sensing data of 1:2.5 ten thousand, the geological data at least comprise drilling information, a drilling histogram and a 1:1 ten thousand exploration line section, the geophysical prospecting data at least comprise geodetic electromagnetic sounding and excitation sounding sections, the chemical prospecting data at least comprise drilling sample analysis data, and the remote sensing data at least comprise hyperspectral data, high-resolution satellite images and radar satellite image data.
9. The geological big data-based solid mineral multi-scale progressive ore finding prediction method is characterized by comprising the following steps of: in the geological, geophysical prospecting, chemical prospecting and remote sensing data of 1:0.5 ten thousand, the geological data at least comprise drilling information, a drilling histogram, 1:1 ten thousand DEM data, 1:0.5 ten thousand geological maps or 1:1 ten thousand geological maps, 1:2 thousand exploration line section views, middle section plane geological maps and ore body resource reserve estimation maps, the geophysical prospecting data at least comprise magnetotelluric sounding and electric sounding sections, the chemical prospecting data at least comprise drilling sample analysis data, and the remote sensing data at least comprise hyperspectral data, high-resolution satellite images and radar satellite image data.
CN202410430186.8A 2024-04-10 2024-04-10 A multi-scale progressive prospecting prediction method for solid minerals based on geological big data Active CN118296381B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202410430186.8A CN118296381B (en) 2024-04-10 2024-04-10 A multi-scale progressive prospecting prediction method for solid minerals based on geological big data

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202410430186.8A CN118296381B (en) 2024-04-10 2024-04-10 A multi-scale progressive prospecting prediction method for solid minerals based on geological big data

Publications (2)

Publication Number Publication Date
CN118296381A true CN118296381A (en) 2024-07-05
CN118296381B CN118296381B (en) 2024-12-27

Family

ID=91674085

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202410430186.8A Active CN118296381B (en) 2024-04-10 2024-04-10 A multi-scale progressive prospecting prediction method for solid minerals based on geological big data

Country Status (1)

Country Link
CN (1) CN118296381B (en)

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN118759600A (en) * 2024-08-02 2024-10-11 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) A prospecting prediction method suitable for tectonic altered rock type gold deposits
CN119474753A (en) * 2024-11-12 2025-02-18 四川省地质大数据中心 A multi-heterogeneous geological data fusion prospecting analysis method and system based on AI
CN119558414A (en) * 2025-02-06 2025-03-04 中国地质大学（北京） Intelligent prospecting method based on multi-source information fusion and physical-data dual drive
CN119783732A (en) * 2025-03-10 2025-04-08 云南大学 A prospecting method, device, equipment and medium based on multi-source remote sensing technology
CN120045628A (en) * 2024-12-27 2025-05-27 河北九华勘查测绘有限责任公司 Data processing method, platform and medium based on three-dimensional hierarchical data model
CN120197969A (en) * 2025-03-03 2025-06-24 中国地质调查局自然资源综合调查指挥中心 A mineral prospecting prediction system based on multi-scale big data fusion

Citations (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
AU2005234089A1 (en) * 2004-04-19 2005-10-27 Siemens Industry, Inc. System and method to query for machine conditions
CN107038505A (en) * 2017-04-25 2017-08-11 中国地质大学（北京） Ore-search models Forecasting Methodology based on machine learning
CN107346038A (en) * 2017-06-08 2017-11-14 昆明理工大学 The method of " four step formulas " large scale coordinate detection deep hydrothermal deposit or ore body
CN108960429A (en) * 2018-05-18 2018-12-07 成都理工大学 The mineral resources area of coverage, deep-seated deposit reconnoitre prediction technique and system
WO2019160003A1 (en) * 2018-02-16 2019-08-22 日本電信電話株式会社 Model learning device, model learning method, and program
US20190266501A1 (en) * 2018-02-27 2019-08-29 Cgg Services Sas System and method for predicting mineralogical, textural, petrophysical and elastic properties at locations without rock samples
CN110991075A (en) * 2019-12-16 2020-04-10 中国地质调查局西安地质调查中心 Rapid exploration and evaluation method for metal mineral products
WO2022115938A1 (en) * 2020-12-03 2022-06-09 Riskthinking.Ai Inc. Systems and methods with classification standard for computer models to measure and manage radical risk using machine learning and scenario generation
WO2023061039A1 (en) * 2021-10-13 2023-04-20 中通服和信科技有限公司 Tailing pond risk monitoring and early-warning system based on internet of things
CN116307123A (en) * 2023-02-23 2023-06-23 中国地质大学（武汉） A knowledge map-driven mineral resource prediction method and storage medium
CN117216576A (en) * 2023-10-26 2023-12-12 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) Graphite gold ore prospecting method based on Gaussian mixture clustering analysis
CN117651942A (en) * 2021-06-15 2024-03-05 西门子股份公司 Method and apparatus for missing link prediction of knowledge graph

Patent Citations (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
AU2005234089A1 (en) * 2004-04-19 2005-10-27 Siemens Industry, Inc. System and method to query for machine conditions
CN107038505A (en) * 2017-04-25 2017-08-11 中国地质大学（北京） Ore-search models Forecasting Methodology based on machine learning
CN107346038A (en) * 2017-06-08 2017-11-14 昆明理工大学 The method of " four step formulas " large scale coordinate detection deep hydrothermal deposit or ore body
WO2019160003A1 (en) * 2018-02-16 2019-08-22 日本電信電話株式会社 Model learning device, model learning method, and program
US20190266501A1 (en) * 2018-02-27 2019-08-29 Cgg Services Sas System and method for predicting mineralogical, textural, petrophysical and elastic properties at locations without rock samples
CN108960429A (en) * 2018-05-18 2018-12-07 成都理工大学 The mineral resources area of coverage, deep-seated deposit reconnoitre prediction technique and system
CN110991075A (en) * 2019-12-16 2020-04-10 中国地质调查局西安地质调查中心 Rapid exploration and evaluation method for metal mineral products
WO2022115938A1 (en) * 2020-12-03 2022-06-09 Riskthinking.Ai Inc. Systems and methods with classification standard for computer models to measure and manage radical risk using machine learning and scenario generation
CN117651942A (en) * 2021-06-15 2024-03-05 西门子股份公司 Method and apparatus for missing link prediction of knowledge graph
WO2023061039A1 (en) * 2021-10-13 2023-04-20 中通服和信科技有限公司 Tailing pond risk monitoring and early-warning system based on internet of things
CN116307123A (en) * 2023-02-23 2023-06-23 中国地质大学（武汉） A knowledge map-driven mineral resource prediction method and storage medium
CN117216576A (en) * 2023-10-26 2023-12-12 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) Graphite gold ore prospecting method based on Gaussian mixture clustering analysis

Non-Patent Citations (3)

* Cited by examiner, † Cited by third party
Title
ZHENG, Y等: "A Knowledge Graph-based Clustering Approach for Drug Side Effects Prediction", 2023 IEEE INTERNATIONAL CONFERENCE ON BIOINFORMATICS AND BIOMEDICINE (BIBM), 13 June 2023 (2023-06-13), pages 1764 - 9 *
吴冲龙等: "用于大数据预测的大塘坡式锰矿找矿过程复盘研究", 《贵州地质》, vol. 39, no. 03, 15 September 2022 (2022-09-15), pages 189 - 204 *
高莹;侯凌燕;刘秀磊;: "煤矿典型动力灾害知识库建设现状及发展方向", 煤炭科学技术, no. 1, 15 June 2018 (2018-06-15), pages 212 - 219 *

Cited By (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN118759600A (en) * 2024-08-02 2024-10-11 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) A prospecting prediction method suitable for tectonic altered rock type gold deposits
CN119474753A (en) * 2024-11-12 2025-02-18 四川省地质大数据中心 A multi-heterogeneous geological data fusion prospecting analysis method and system based on AI
CN120045628A (en) * 2024-12-27 2025-05-27 河北九华勘查测绘有限责任公司 Data processing method, platform and medium based on three-dimensional hierarchical data model
CN120045628B (en) * 2024-12-27 2025-09-12 河北九华勘查测绘有限责任公司 Data processing method, platform and medium based on three-dimensional hierarchical data model
CN119558414A (en) * 2025-02-06 2025-03-04 中国地质大学（北京） Intelligent prospecting method based on multi-source information fusion and physical-data dual drive
CN120197969A (en) * 2025-03-03 2025-06-24 中国地质调查局自然资源综合调查指挥中心 A mineral prospecting prediction system based on multi-scale big data fusion
CN120197969B (en) * 2025-03-03 2025-08-22 中国地质调查局自然资源综合调查指挥中心 A mineral prospecting prediction system based on multi-scale big data fusion
CN119783732A (en) * 2025-03-10 2025-04-08 云南大学 A prospecting method, device, equipment and medium based on multi-source remote sensing technology

Also Published As

Publication number Publication date
CN118296381B (en) 2024-12-27

Similar Documents

Publication Publication Date Title
Xiang et al. 3D mineral prospectivity mapping with random forests: A case study of Tongling, Anhui, China
CN118296381B (en) A multi-scale progressive prospecting prediction method for solid minerals based on geological big data
CN115879648B (en) A method and system for ternary deep mineralization prediction based on machine learning
Zuo et al. Explainable artificial intelligence models for mineral prospectivity mapping
Wang et al. Mineral potential targeting and resource assessment based on 3D geological modeling in Luanchuan region, China
Jin et al. 3D geological modelling and uncertainty analysis for 3D targeting in Shanggong gold deposit (China)
CN107748399B (en) Method for identifying deep tectonic layer of mountain front zone by utilizing gravity interface inversion
CN101706589B (en) Geographic tuple based quantitative prediction method of ore concentration areas
Li et al. Part II: A demonstration of integrating multiple-scale 3D modelling into GIS-based prospectivity analysis: A case study of the Huayuan-Malichang district, China
Wang et al. Quantitative assessment of mineral resources by combining geostatistics and fractal methods in the Tongshan porphyry Cu deposit (China)
Niiranen et al. Scalability of the mineral prospectivity modelling–an orogenic gold case study from northern Finland
Zuo et al. A novel data-knowledge dual-driven model coupling artificial intelligence with a mineral systems approach for mineral prospectivity mapping
CN118822771A (en) Mineral prospecting method and system based on multivariate three-dimensional information fusion and intelligent mineralization prediction technology
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
Shamseddin Meigooni et al. Application of multivariate geostatistical simulation and fractal analysis for detection of rare-earth element geochemical anomalies in the Esfordi phosphate mine, Central Iran
Zhang et al. Three-dimensional pseudo-lithologic modeling via adaptive feature weighted k-means algorithm from multi-source geophysical datasets, Qingchengzi Pb–Zn–Ag–Au District, China
CN119625167A (en) A method for constructing a three-dimensional geological model based on multi-source data fusion
CN118330771A (en) Mining system source area detection method, system and medium based on big data mining
Chen et al. Geophysical exploration of the giant Bayan Obo REE–Nb–Fe deposit in Inner Mongolia, China: Progress and challenges
CN114814982B (en) Method for predicting favorable ore-forming part of granite uranium ore
Mostafaei et al. Mineral resource estimation using a combination of drilling and IP-Rs data using statistical and cokriging methods
Shakhatova et al. Applied machine learning in geophysics taxonomy review bibliometrics and trends in generative AI
CN120471577A (en) A rapid collaborative exploration method for gold mines using air, ground and wells
Abedi et al. Collocated cokriging of iron deposit based on a model of magnetic susceptibility: a case study in Morvarid mine, Iran
Chen et al. Application of the geo-anomaly unit concept in quantitative delineation and assessment of gold ore targets in Western Shandong Uplift Terrain, Eastern China

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
TA01 Transfer of patent application right

Effective date of registration: 20241205

Address after: Building 2, 3rd Floor, China University of Geosciences Science and Technology Park, No. 19 Fozuling 1st Road, Donghu New Technology Development Zone, Wuhan City, Hubei Province, China 430205

Applicant after: WUHAN DIDA QUANTY TECHNOLOGY CO.,LTD.

Country or region after: China

Address before: 430074 No. 388 Lu Lu, Hongshan District, Hubei, Wuhan

Applicant before: CHINA University OF GEOSCIENCES (WUHAN CITY)

Country or region before: China

Applicant before: WUHAN DIDA QUANTY TECHNOLOGY CO.,LTD.

TA01 Transfer of patent application right
GR01 Patent grant
GR01 Patent grant