|Table of Contents|

Metallogenic Prediction of Continental Volcanic Copper Deposits Based on WOE-GA-BP Neural Network Model:Taking Ningwu Basin(Jiangsu Part) as an Example(PDF)

南京师范大学学报（工程技术版）[ISSN:1006-6977/CN:61-1281/TN]

Issue:
2023年03期
Page:
67-74
Research Field:
测绘科学与技术
Publishing date:

Info

Title:
Metallogenic Prediction of Continental Volcanic Copper Deposits Based on WOE-GA-BP Neural Network Model:Taking Ningwu Basin(Jiangsu Part) as an Example
Author(s):
Wang Xin1; Bai Shibiao1; 2
(1.School of Marine Science and Engineering, Nanjing Normal University, Nanjing 210023, China)
(2.Jiangsu Center for Collaborative Innovation in Geographical Information Resource Development and Application, Nanjing 210023, China)
Keywords:
Ningwu Basin;  continental volcanic rock copper deposit;  WOE;  GA-BP neural network
PACS:
P627
DOI:
10.3969/j.issn.1672-1292.2023.03.009
Abstract:
Ningwu Basin is located in the copper, gold, iron, lead, zinc, sulfur, and gypsum mineralization belt in the middle and lower reaches of the Yangtze River, with strong tectonic movement, frequent magmatic activity, and superior geological conditions for mineralization. By extracting the basic information of 9 ore-controlling factors such as strata, fault structures, aeromagnetic, and geochemical anomalies in Ningwu Basin(Jiangsu part), a coupling model of weight of evidence and BP neural network model based on genetic optimization(WOE-GA-BP)is used to conduct mineralization prediction research on continental volcanic rock copper deposit in the region, the confusion matrix and ROC curve are used to evaluate the model accuracy. After overlay analysis, there are 81.23%, 62.69%, and 100% overlap areas between the copper deposit A, B, and C prospect areas delineated based on the mineralization model and the copper deposit A, B, and C prediction areas delineated by the evaluation of important mineral potential in Jiangsu province, respectively. The results getting by this research indicate that the prediction results are relatively reliable and provide new ideas and methods for regional mineralization prediction, which has certain guiding significance for subsequent exploration work.

References:

[1]叶天竺,吕志成,庞振山,等. 勘查区找矿预测理论与方法(总论)[M]. 北京:地质出版社,2014.
[2]周永章,黎培兴,王树功,等. 矿床大数据及智能矿床模型研究背景与进展[J]. 矿物岩石地球化学通报,2017,36(2):327-331.
[3]YOUSEFI M,KREUZER O P,NYKÄNEN V,et al. Exploration information systems:a proposal for the future use of GIS in mineral exploration targeting[J]. Ore Geology Reviews,2019,111:103005.
[4]AGTERBERG F P. Computer programs for mineral exploration[J]. Science,1989,245(4913):76-81.
[5]AGTERBERG F P,BONHAM-CARTER G F,WRIGHT D F. Statistical pattern integration for mineral exploration[M]//GAÁL G,MERRIAM D F. Computer applications in resource estimation. Oxford,England:Pergamon Press,1990:1-21.
[6]黄海峰,姚书振,丁振举. 基于GIS的证据权重法在成矿预测中的应用——以甘肃省岷县—礼县地区的金矿预测为例[J]. 地质科技情报,2003,22(3):77-82.
[7]赵增玉,陈火根,潘懋,等. 基于证据权模型的宁芜盆地中段玢岩铁矿资源预测[J]. 北京大学学报(自然科学版),2015,51(5):863-870.
[8]CARRANZA E J M,LABORTE A G. Random forest predictive modeling of mineral prospectivity with small number of prospects and data with missing values in Abra(Philippines)[J]. Computers and Geosciences,2015,74:60-70.
[9]XU Y Y,LI Z X,XIE Z,et al. Mineral prospectivity mapping by deep learning method in Yawan-Daqiao area,Gansu[J]. Ore Geology Reviews,2021,138:104316.
[10]秦耀祖,吴伟成,谢丽凤,等. 基于机器学习的找矿预测模型在湖南岳溪锑矿田的应用[J]. 东华理工大学学报(自然科学版),2021,44(1):28-40.
[11]张振杰,成秋明,杨玠,等. 机器学习与成矿预测:以闽西南铁多金属矿预测为例[J]. 地学前缘,2021,28(3):221-235.
[12]马瑶,赵江南. 机器学习方法在矿产资源定量预测应用研究进展[J]. 地质科技通报,2021,40(1):132-141.
[13]吴冲龙,刘刚,张夏林,等. 地质科学大数据及其利用的若干问题探讨[J]. 科学通报,2016,61(16):1797-1807.
[14]李德仁,王树良,李德毅. 空间数据挖掘理论与应用[M]. 2版. 北京:科学出版社,2013.
[15]蔡惠慧,徐永洋,李孜轩,等. 基于卷积神经网络模型划分成矿远景区——以甘肃大桥地区金多金属矿田为例[J]. 地质通报,2019,38(12):1999-2009.
[16]蔡惠慧,朱伟,李孜轩,等. 基于深度学习的钨钼找矿靶区预测方法研究[J]. 地球信息科学学报,2019,21(6):928-936.
[17]杨用彪,黄顺生,黄建平. 长江中下游成矿带(江苏段)铜矿资源地球化学定量预测[J]. 地质学刊,2016,40(3):455-462.
[18]余旭辉. 宁镇中段矽卡岩型铁铜多金属矿床多元信息成矿预测研究[D]. 长沙:中南大学,2011.
[19]赵增玉,陈火根,潘懋,等. 加权Logistic回归模型在火山岩型铜矿预测中的应用:以宁芜盆地中段为例[J]. 高校地质学报,2016,22(1):105-112.
[20]姜波,徐嘉炜. 一个中生代的拉分盆地——宁芜盆地的形成及演化[J]. 地质科学,1989(4):314-322.
[21]梁锋,吕庆田,严加永,等. 长江中下游宁芜火山岩盆地深部结构特征——来自反射地震的认识[J]. 岩石学报,2014,30(4):941-956.
[22]周涛发,王世伟,袁峰,等. 长江中下游成矿带陆内斑岩型矿床的成岩成矿作用[J]. 岩石学报,2016,32(2):271-288.
[23]BONHAM-CARTER G F. Geographic information systems for geoscientists:modelling with GIS[M]. Oxford,England:Pergamon,1994.
[24]李裕伟,赵精满,李晨阳. 基于GMS、DSS和GIS的潜在矿产资源评价方法(上册)[M]. 北京:地震出版社,2007.
[25]RUMELHART D E,HINTON G E,WILLIAMS R J. Learning representations by back-propagating errors[M]//ANDERSON J A,ROSENFELD E. Neurocomputing:foundations of research. Cambridge,USA:MIT,1988.
[26]赵奕昕,李薇,朱家明. 基于 GA-BP神经网络的极端降水定量分析与预测[J]. 内蒙古师范大学学报(自然科学汉文版),2022,51(6):576-581.
[27]NYKÄNEN V,LAHTI I,NIIRANEN T,et al. Receiver operating characteristics(ROC)as validation tool for prospectivity models:a magmatic Ni-Cu case study from the Central Lapland Greenstone Belt,Northern Finland[J]. Ore Geology Reviews,2015,71:853-860.
[28]YOUSEFI M,CARRANZA E J M. Prediction-area(P-A)plot and C-A fractal analysis to classify and evaluate evidential maps for mineral prospectivity modeling[J]. Computers & Geosciences,2015,79:69-81.
[29]LOOMIS J M. Analysis of tactile and visual confusion matrices[J]. Perception & Psychophysics,1982,31(1):41-52.
[30]HENGL T. Finding the right pixel size[J]. Computers & Geosciences,2006,32(9):1283-1298.
[31]黄建平,黄震,贾根,等. 江苏省重要矿产资源潜力评价[M]. 武汉:中国地质大学出版社,2017.

Memo

Memo:
-
Last Update: 2023-09-15