面向地球化学异常识别的深度学习算法对比研究

doi:10.11720/wtyht.2023.2667

Abstract
Figure/Table
References
Related Citation (6)

Download: PDF (6584 KB) HTML (1 KB)
Export: BibTeX | EndNote (RIS)

Abstract

There is a lack of selection bases in the geochemical anomaly identification and the reconstruction of the geochemical background conforming to the metallogenic distribution using deep learning algorithms with different network structures. Given this, based on the 1∶200 000 stream sediment data of the copper-zinc-silver metallogenic area in southwestern Fujian Province, this study extracted the combined structural characteristics, spatial distribution characteristics, and mixed characteristics of multiple elements in the samples using three unsupervised deep learning models, i.e., AE, MCAE, and FCAE. Then, these characteristics were used to reconstruct the geochemical background and simulate the metallogenic distribution. The results show that the anomaly areas delineated by the FCAE model were the most consistent with the known copper ore occurrences, followed by the MCAE and AE models. The FCAE, MCAE, and AE models had an area under the curve (AUC) score of 0.80, 0.78, and 0.61, respectively. Moreover, the FCAE and AE models were not sensitive to the change in the convolution window size. These results indicate that when deep learning algorithms are constructed for geochemical anomaly identification, the algorithms based on the extraction of spatial distribution characteristics or mixed characteristics perform well, and those based on the extraction of combined structural characteristics or mixed characteristics have a strong anti-interference ability for the noise caused by the change or inconsistency of the spatial observation scale. This study provides some effective selection bases for constructing geochemical anomaly identification models based on deep learning algorithms.

Key words： geochemical anomaly identification convolutional autoencoder feature combination unsupervised learning feature extraction deep learning

Received: 10 December 2021 Published: 24 February 2023

ZTFLH:	TP39
	P595

Corresponding Authors: CHEN Li-Rong E-mail: 342159595@qq.com;chenlirong@mail.cgs.gov.cn

	Service

	E-mail this article
	Add to my bookshelf
	Add to citation manager
	E-mail Alert
	RSS
	Articles by authors
	Mu-Si LI
	Li-Rong CHEN
	Fei XIE
	Lan-Ding GU
	Xiao-Dong WU
	Fen MA
	Zhao-Feng YIN

Cite this article:

Mu-Si LI,Li-Rong CHEN,Fei XIE, et al. Comparison of deep learning algorithms for geochemical anomaly identification[J]. Geophysical and Geochemical Exploration, 2023, 47(1): 179-189.

URL:

https://www.wutanyuhuatan.com/EN/10.11720/wtyht.2023.2667 OR https://www.wutanyuhuatan.com/EN/Y2023/V47/I1/179

10])
">

Geological schematic diagram of the study area(modified from Guan Q F, et al.^[10])

Autoencoder model (AE)

9]
">

Multi-Convolutional Autoencoder model (MCAE)^[9]

10]
">

Feature fusion convolutional autoencoder (FCAE)^[10]

Confusion matrix of model prediction results

Flow chart of geochemical anomaly identification

Pearson correlation coefficient of Cu with other elements and oxides^[10]

AE and MCAE network structure

FCAE network structure

Performance comparison of three models

ROC curves and AUC distributions of three feature extraction models

Performance comparison of MCAE and FCAE with different size convolution window

-1 Geochemical anomaly distribution map based on optimal threshold of ROC curve

-2 Geochemical anomaly distribution map based on optimal threshold of ROC curve

Summary of the comparison of the three models

[1]	郭科. 复杂地质地貌区多尺度地球化学异常识别的非线性研究[D]. 成都: 成都理工大学, 2005:12.
[1]	Guo K. The study of non-linear of complex geology land form identification of the multi-dimensioned geochemistry anomaly[D]. Chengdu: Chengdu University of Technology, 2005:12.
[2]	Tobler W. On the first law of geography: A reply[J]. Annals of the Association of American Geographers, 2004, 94(2): 304-310.
[3]	Zuo R G, Xiong Y H, Wang J, et al. Deep learning and its application in geochemical mapping[J]. Earth-Science Reviews, 2019, 192: 1-14.
[4]	Zuo R G. Machine learning of mineralization-related geochemical anomalies: A review of potential methods[J]. Natural Resources Research, 2017, 26(4): 457-464.
[5]	刘艳鹏, 朱立新, 周永章. 卷积神经网络及其在矿床找矿预测中的应用——以安徽省兆吉口铅锌矿床为例[J]. 岩石学报, 2018, 34(11): 3217-3224.
[5]	Liu Y P, Zhu L X, Zhou Y Z. Application of convolutional neural network in prospecting prediction of ore deposits: Taking the Zhaojikou Pb-Zn ore deposit in Anhui Province as a case[J]. Acta Petrologica Sinica, 2018, 34(11): 3217-3224.
[6]	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.
[6]	Cai H H, Zhu W, Li Z X, et al. Prediction method of tungsten-molybdenum prospecting target area based on deep learning[J]. Journal of Geo-information Science, 2019, 21(6):928-936.
[7]	陈丽蓉. 顾及空间约束的多元地球化学异常识别自编码神经网络方法研究[D]. 武汉: 中国地质大学(武汉), 2019:79.
[7]	Chen L R. Multivariate geochemical anomaly recognition using spatial constrained autoencoders[D]. Wuhan: China University of Geosciences(Wuhan), 2019:79.
[8]	Chen L R, Guan Q F, Xiong Y H, et al. A spatially constrained multi-autoencoder approach for multivariate geochemical anomaly recognition[J]. Computers & geosciences, 2019, 125:43-54.
[9]	Chen L R, Guan Q F, Feng B, et al. A multi-convolutional autoencoder approach to multivariate geochemical anomaly recognition[J]. Minerals, 2019, 9(5):270.
[10]	Guan Q F, Ren S L, Chen L R, et al. A spatial-compositional feature fusion convolutional autoencoder for multivariate geochemical anomaly recognition[J]. Computers and Geosciences, 2021(1):104890.
[11]	高原. 闽西南铜多金属矿找矿信息挖掘与成矿预测[D]. 武汉: 中国地质大学(武汉), 2019:30.
[11]	Gao Y. Mineral prospecting information mining and mapping mineral prospectivity for copper polymetallic mineralization in southwest Fujian Province[D]. Wuhan: China University of Geosciences(Wuhan), 2019:30.
[12]	张翠光, 陈润生, 黄昌旗, 等. 武夷山成矿带成矿地质背景及成矿规律研究[M]. 北京: 地质出版社, 2014: 60.
[12]	Zhang C G, Chen R S, Huang C Q, et al. Study on the geological background of mineralization and mineralization pattern of Wuyishan mineralization zone[M]. Beijing: Geological Publishing House, 2014: 60.
[13]	刘崇民, 胡树起, 马生明, 等. 成矿元素相态对地球化学异常识别的作用[J]. 物探与化探, 2013, 37(6):1049-1055.
[13]	Liu C M, Hu S Q, Ma S M, et al. The role of the phase state of metallogenic elements in the recognition of geochemical anomalies[J]. Geophysical and Geochemical Exploration, 2013, 37(6):1049-1055.
[14]	郑泽宇, 赵庆英, 李湜先, 等. 地球化学异常识别的两种机器学习算法之比较[J]. 世界地质, 2018, 37(4): 1288-1294.
[14]	Zheng Z Y, Zhao Q Y, Li S X, et al. Comparison of two machine learning algorithms for geochemical anomaly detection[J]. Global Geology, 2018, 37(4): 1288-1294.
[15]	Rumelhart D E, Hinton G E, Williams R J. Learning representations by back propagating errors[J]. Nature, 1986, 323(6088): 533-536.
[16]	邓俊锋, 张晓龙. 基于自动编码器组合的深度学习优化方法[J]. 计算机应用, 2016, 36(3): 697-702.
[16]	Deng J F, Zhang X L. Deep learning algorithm optimization based on combination of auto-encoders[J]. Journal of Computer Applications, 2016, 36(3): 697-702.
[17]	费艳, 缪骞云, 刘学军. 一种基于卷积自动编码器的推荐系统攻击检测方法[J]. 小型微型计算机系统, 2021, 42(5): 1088-1092.
[17]	Fei Y, Miao Q Y, Liu X J. Recommendation system attack detection method based on convolutional autoencoder[J]. Journal of Chinese Computer Systems, 2021, 42(5): 1088-1092.
[18]	宋晓霞. 基于栈式自动编码器的高分辨率遥感影像分类[J]. 测绘与空间地理信息, 2021, 44(5):128-131.
[18]	Song X X. High resolution remote sensing image classification based on stacked autoencoder[J]. Geomatics & Spatial Information Technology, 2021, 44(5):128-131.
[19]	张扬. 基于卷积自编码器的异常事件检测研究[D]. 杭州: 浙江大学, 2018:10.
[19]	Zhang Y. Anomaly detection based on convolutional autoencoder[D]. Hangzhou: Zhejiang University, 2018:10.
[20]	Chen K, Seuret M, Liwicki M, et al. Page segmentation of historical document images with convolutional autoencoders[C]// 2015 13^th International Conference on Document Analysis and Recognition (ICDAR), IEEE, 2015: 1011-1015.
[21]	宋辉, 高洋, 陈伟, 等. 基于卷积降噪自编码器的地震数据去噪[J]. 石油地球物理勘探, 2020, 55(6): 1210-1219.
[21]	Song H, Gao Y, Chen W, et al. Seismic noise suppression based on convolutional denoising autoencoders[J]. Oil Geophysical Prospecting, 2020, 55(6): 1210-1219.
[22]	江金生, 任浩然, 李瀚野. 基于卷积自编码器的地震数据处理[J]. 浙江大学学报:工学版, 2020, 54(5): 978-984.
[22]	Jiang J S, Ren H R, Li H Y. Seismic data processing based on convolutional autoencoder[J]. Journal of Zhejiang University:Engineering Science, 2020, 54(5): 978-984.
[23]	An J, Cho S. Variational autoencoder based anomaly detection using reconstruction probability[J]. Special Lecture on IE, 2015, 2(1): 1-18.
[24]	Xiong Y H, Zuo R G. Recognition of geochemical anomalies using a deep autoencoder network[J]. Computers and Geosciences, 2016, 86: 75-82.
[25]	Valentine A P, Trampert J. Data space reduction, quality assessment and searching of seismograms: Autoencoder networks for waveform data[J]. Geophysical Journal International, 2012, 189(2): 1183-1202.
[26]	Fawcett T. An introduction to ROC analysis[J]. Pattern recognition letters, 2006, 27(8): 861-874.
[27]	Benesty J, Chen J, Huang Y, et al. Pearson correlation coefficient [G]// Noise reduction in speech processing. Berlin, Heidelberg: Springer, 2009: 1-4.
[28]	Chen Y L, Lu L J, Li X B. Application of continuous restricted Boltzmann machine to identify multivariate geochemical anomaly[J]. Journal of Geochemical Exploration, 2014, 140: 56-63.
[29]	Zhou J, Cui G Q, Hu S D, et al. Graph neural networks: A review of methods and applications[J]. AI Open, 2020, 1∶ 57-81.
[30]	陈志军, 成秋明, 陈建国. 利用样本排序方法比较化探异常识别模型的效果[J]. 地球科学:中国地质大学学报, 2009, 34(2):353-364.
[30]	Chen Z J, Cheng Q M, Chen J G. Comparison of different models for anomaly recognition of geochemical data by using sample ranking method[J]. Earth Science:Journal of China University of Geosciences, 2009, 34(2):353-364.