Mineral Prospectivity Prediction via Convolutional Neural Networks Based on Geological Big Data

作     者：Shi Li Jianping Chen Chang Liu Yang Wang Shi Li;Jianping Chen;Chang Liu;Yang Wang

作者机构：School of Earth Sciences and ResourcesChina University of GeosciencesBeijing 100083China Land Resources Information Development and Research Key Laboratory of BeijingBeijing 100083China Haikou Marine Geological Survey CenterChina Geological SurveyHaikou 570100China 

出 版 物：《Journal of Earth Science》 (地球科学学刊（英文版）)

年 卷 期：2021年第32卷第2期

页      面：327-347页

核心收录：

学科分类：081801[工学-矿产普查与勘探] 08[工学] 0818[工学-地质资源与地质工程] 

基　　金：financially supported by the Chinese MOST project“Methods and Models for Quantitative Prediction of Deep Metallogenic Geological Anomalies”(No.2017YFC0601502)and“Research on key technology of mineral prediction based on geological big data analysis”(No.6142A01190104) 

主　　题：big data mineral prospectivity mapping 3D geological modeling 3D CNN Huayuan Mn deposit 

摘      要：Today’s era of big data is witnessing a gradual increase in the amount of data,more correlations between data,as well as growth in their spatial *** linear statistical models applied to mineral prospectivity mapping(MPM)perform poorly because of the random and nonlinear nature of metallogenic *** overcome this performance degradation,deep learning models have been introduced in 3 D *** this study,taking the Huayuan sedimentary Mn deposit in Hunan Province as an example,we construct a 3 D digital model of this deposit based on the prospectivity model of the study *** this approach,3 D predictor layers are converted from the conceptual model and employed in a 3 D convolutional neural network(3 D CNN).The characteristics of the spatial distribution are extracted by the 3 D ***,we divide the 22 extracted ore-controlling variables into six groups for contrast experiments based on various combinations and further apply the 3 D CNN model and weight of evidence(WofE)method on each *** predictive model is trained on the basis of the coupling correlation between the spatial distributions of the variables and the underground occurrence space of the Mn orebodies,and the correlation between different ore-controlling *** analysis of 12 factors indicates that the 3 D CNN model performs well in the 3 D MPM,achieving a promising accuracy of up to 100%and a loss value below 0.001.A comparison shows that the 3 D CNN model outperforms the WofE model in terms of predictive evaluation indexes,namely the success rate and ore-controlling *** particular,the 1–12 ore-controlling factors selected in experiment 5 provide a significantly better prediction effect than the other ***,we conclude that the Mn deposit in the study area is not only related to the stratum and interlaminar anomalous bodies but also to the spatial distribution of the *** experimental results confirm that the proposed 3 D CNN is prom