基于极限学习机的遥感地球化学反演模型

doi:10.13278/j.cnki.jjuese.20190209

吉林大学学报(地球科学版) ›› 2020, Vol. 50 ›› Issue (6): 1929-1938.doi: 10.13278/j.cnki.jjuese.20190209

• 地球探测与信息技术 • 上一篇

基于极限学习机的遥感地球化学反演模型

孙立影¹, 杨晨¹, 赵海士², 常志勇^3,4

1. 吉林大学地球科学学院, 长春 130061;
2. 吉林大学计算机科学与技术学院, 长春 130012;
3. 吉林大学生物与农业工程学院/工程仿生教育部重点实验室(吉林大学), 长春 130022;
4. 吉林大学油页岩地下原位转化与钻采技术国家地方联合工程实验室, 长春 130021

收稿日期:2019-08-02 发布日期:2020-12-11
通讯作者: 杨晨(1981-),女,副教授,博士,主要从事遥感影像处理、机器学习方面的研究,E-mail:yangc616@jlu.edu.cn E-mail:yangc616@jlu.edu.cn
作者简介:孙立影(1995-),女,硕士研究生,主要从事空间数据处理与地学计算方面的研究,E-mail:liyings17@mails.jlu.edu.cn
基金资助:
国家自然科学基金项目（61572228）；吉林省科技发展计划项目（20190303006SF，20190302107GX）；吉林省产业技术研究与开发专项（2019C053-5，2019C053-7）

Remote Sensing Geochemical Inversion Model by Using Extreme Learning Machine

Sun Liying¹, Yang Chen¹, Zhao Haishi², Chang Zhiyong^3,4

1. College of Earth Sciences, Jilin University, Changchun 130061, China;
2. College of Computer Science and Technology, Jinlin University, Changchun 130012, China;
3. College of Biological and Agricultural Engineering, Jilin University/Key Laboratory of Bionic Engineering(Jilin University), Ministry of Education, Changchun 130022, China;
4. National-Local Joint Engineering Laboratory of In-Situ Conversion, Drilling and Exploitation Technology for Oil Shale, Jilin University, Changchun 130021, China

Received:2019-08-02 Published:2020-12-11
Supported by:
Supported by National Natural Science Foundation of China (61572228), Science-Technology Development Plan Project of Jilin Province of China (20190303006SF, 20190302107GX) and Industrial Innovation Special Funds Project of Jilin Province (2019C053-5, 2019C053-7)

摘要/Abstract

摘要： 地球化学勘查研究涉及大量采样工作，但在工作环境恶劣人们难以到达的地区，大范围、大比例尺的地球化学数据极难获取。本文基于极限学习机（ELM）构建遥感地球化学反演模型，弥补因为区域数据不足导致的找矿工作困难。依据偏最小二乘回归（PLSR）方法选取与地球化学数据相关性强的遥感影像成分，并根据极限学习机建立地球化学数据与遥感影像之间的非线性对应关系来获取未知地球化学异常，以此来指导找矿工作。实验中，选取研究区铜元素1：20万土壤地球化学数据与Landsat 8 OLI遥感影像进行反演分析。实验结果表明，基于ELM的遥感地球化学反演所取得的异常分布与已知矿点具有很好的对应度，验证了本文所提出模型的有效性。

关键词: 极限学习机, 偏最小二乘回归, 遥感地球化学, 反演

Abstract: Geochemical exploration research involves a large amount of sampling work, which is extremely difficult in inaccessible terrain with harsh working environments. The authors propose a geochemical inversion model with remote sensing images by using extreme learning machine (ELM) to alleviate the difficulty of ore prospecting in the areas with insufficient regional data. The partial least squares regression (PLSR) method is used to select the remote sensing image features which are highly correlated with geochemistry data. In this model, the nonlinear relationship between the geochemical data and the remote sensing images is established using ELM for getting unknown geochemical anomalies, after which the ore prospecting work can be further promoted. In the experiment, 1:200 000 soil geochemical data of Cu element and the Landsat 8 OLI remote sensing images were used for the inversion analysis. The experimental results showed that the anomalous distribution obtained by the ELM-based inversion model had a good correspondence with known ore spots, which verified the effectiveness of the proposed model.

Key words: extreme learning machine (ELM), partial least squares regression, remote sensing geochemistry, inversion

中图分类号:

TP751.1

孙立影, 杨晨, 赵海士, 常志勇. 基于极限学习机的遥感地球化学反演模型[J]. 吉林大学学报(地球科学版), 2020, 50(6): 1929-1938.

Sun Liying, Yang Chen, Zhao Haishi, Chang Zhiyong. Remote Sensing Geochemical Inversion Model by Using Extreme Learning Machine[J]. Journal of Jilin University(Earth Science Edition), 2020, 50(6): 1929-1938.

参考文献

[1] 王健. 基于地质统计学模拟的地球化学异常信息提取[D]. 武汉:中国地质大学, 2018. Wang Jian. Identification of Geochemical Anomalies Based on Geostatistical Simulation[D]. Wuhan:China University of Geosciences, 2018.
[2] Pieters C M, Englert P A. Remote Geochemical Analysis:Elemental and Mineralogical Composition[M]. New York:Cambridge University Press, 1993.
[3] 吴昀昭, 田庆久, 季峻峰, 等. 遥感地球化学研究[J]. 地球科学进展, 2003,18(2):228-235. Wu Yunzhao, Tian Qingjiu, Ji Junfeng, et al. Study on the Remote-Sensing Geochemistry[J]. Advance in Earth Science, 2003, 18(2):228-235.
[4] Swayze G A. The Hydrothermal and Structural History of the Cuprite Mining District, Southwestern Nevada:An Integrated Geological and Geophysical Approach[D]. Colorado:University of Colorado, 1997.
[5] 姚佛军, 杨建民, 陈红旗, 等. 西藏多龙矿集区铜元素遥感地球化学模型[J]. 岩石矿物学杂志, 2015, 34(5):710-720. Yao Fojun, Yang Jianmin, Chen Hongqi, et al. A Remote Sensing Cu Geochemical Model for the Duolong Ore Concentration Area, Tibet[J]. Acta Petrologica et Mineralogica, 2015, 34(5):710-720.
[6] Aronoff S, Goodfellow W. 图像处理对区域地球化学数据的有效分析[C]//王润生. 综合地学信息图像处理译文集. 北京:地质矿产部地质遥感中心, 1987:16-23. Aronoff S, Goodfellow W. Effective Analysis of Regional Geochemical Data by Image Processing[C]//Wang Runsheng. Integrated Geological Information Image Processing Translation Collection. Beijing:Geological Remote Sensing Center, Ministry of Geology and Mineral Resources, 1987:16-23.
[7] Eliason P T, Donovan T J, Chavez P S. Integration of Geologic, Geochemical, and Geophysical Data of the Cement Oil Field, Oklahoma, Using Spatial Array Processing[J]. Geophysics, 1982, 1(1):474-475.
[8] 吕凤军, 李锌铭, 张应刚, 等. 冀西北银地球化学块体与遥感成矿信息集成研究[J]. 地质学刊, 2014, 38(2):259-263. Lü Fengjun, Li Xinming, Zhang Yinggang, et al.Study on Silver Geochemistry Block and Remote Sensing Metallogenic Information Integration in Northwest Hebei[J]. Journal of Geology, 2014, 38(2):259-263.
[9] 陈勇敢, 王美娟, 李鹏. 基于HJ-1A-HSI提取稀土元素地球化学异常信息研究[J]. 光谱学与光谱分析, 2015, 35(11):3172-3175. Chen Yonggan, Wang Meijuan, Li Peng. Study on the Geochemical Anomalies Identification of REE Based on HJ-1A-HSI[J]. Spectroscopy and Spectral Analysis, 2015, 35(11):3172-3175.
[10] Lucey P G, Blewett D T, Hawke B R. Mapping the FeO and TiO₂, Content of the Lunar Surface with Multispectral Imagery[J]. Journal of Geophysical Research Planets, 1998, 103(E2):3679-3699.
[11] 周贤锋, 赵书河, 吴昀昭, 等. 基于光学遥感数据虹湾地区铁钛含量反演研究[J]. 中国科学:物理学力学天文学, 2013, 43(8):987-1003. Zhou Xianfeng, Zhao Shuhe, Wu Yunzhao, et al. Research on Extraction of FeO and TiO₂ Contents of the Sinus Iridum Region Based on Optical Remote Sensing Data[J]. Scientia Sinica:Physica, Mechanica & Astronomica, 2013, 43(8):987-1003.
[12] 凌宗成, 张江, 刘建忠, 等. 嫦娥一号干涉成像光谱仪数据再校正与全月铁钛元素反演[J]. 岩石学报, 2016, 32(1):87-98. Ling Zongcheng, Zhang Jiang, Liu Jianzhong,et al. Lunar Global FeO and TiO₂ Mapping Based on the Recalibrated Chang'e-1 IIM Dataset[J]. Acta Petrologica Sinica, 2016, 32(1):87-98.
[13] 李晓芃, 陈建平, 王翔. 基于嫦娥一号反射率数据月表正面FeO、Al₂O₃反演[J]. 中国矿业, 2018, 27(7):150-156. Li Xiaopeng, Chen Jianping, Wang Xiang.Inversion of Lunar Nearside FeO and Al₂O₃ Based on Chang'e-1 Reflectance Data[J]. China Mining Magazine, 2018, 27(7):150-156.
[14] Li S, Li L, Milliken R, et al. Hybridization of Partial Least Squares and Neural Network Models for Quantifying Lunar Surface Minerals[J]. Icarus, 2012, 221(1):208-225.
[15] 赵海士. 基于ETM+的遥感地球化学非线性反演模型研究[D]. 长春:吉林大学, 2017. Zhao Haishi. Research on a Remote-Sensing Geochemistry Nonlinear Inversion Model Based on ETM+ Data[D]. Changchun:Jilin University, 2017.
[16] Huang G B, Zhu Q Y, Siew C K. Extreme Learning Machine:Theory and Applications[J]. Neurocomputing, 2006, 70(1):489-501.
[17] Huang G B, Wang D H, Lan Y. Extreme Learning Machines:A Survey[J]. International Journal of Machine Learning and Cybernetics, 2011, 2(2):107-122.
[18] Huang G B, Zhou H, Ding X, et al. Extreme Learning Machine for Regression and Multiclass Classification[J], IEEE Transactions on Systems Man & Cybernetics Part B, 2012, 42(2):513.
[19] 王明常, 张馨月, 张旭晴, 等. 基于极限学习机的GF-2影像分类[J]. 吉林大学学报(地球科学版), 2018, 48(2):373-378. Wang Mingchang, Zhang Xinyue, Zhang Xuqing, et al. GF-2 Image Classification Based on Extreme Learning Machine[J]. Journal of Jilin University (Earth Science Edition), 2018, 48(2):373-378.
[20] 张守林. 基于ETM数据矿化蚀变信息定量提取方法研究[D]. 北京:中国地质大学(北京), 2006. Zhang Shoulin. A Study on Methods Used to Quantitatively Extract Mineralized Alteration Information from ETM Data[D]. Beijing:China University of Geosciences (Beijing), 2006.
[21] 吴应瑞, 吴道夫, 张兰喜, 等. 三道桥幅K-48-291:20万区域地质调查报告[R]. 北京:全国地质资料馆, 1982. Wu Yingrui, Wu Daofu, Zhang Lanxi, et al. Three-Way Bridge K-48-291:200000 Regional Geological Survey Report[R]. Beijing:National Geological Data Center, 1982.
[22] 刘永顺, 周世军, 杨俊泉,等. 内蒙古1:5万那仁宝力格幅、瑙云乌苏幅、希宁乌苏庙幅、玻璃庙幅区域地质调查报告[R]. 北京:全国地质资料馆, 2011. Liu Yongshun, Zhou Shijun, Yang Junquan, et al. Inner Mongolia 1:50000 Renbao Lige, Nayun Wusu, Xining Wusu Temple, Glass Temple Regional Geological Survey Report[R]. Beijing:National Geological Data Center, 2011.
[23] 冯翼鹏, 张维杰, 王根厚, 等. 阿拉善银根-额济纳盆地苏红图火山机构特征及火山喷发作用演化[J]. 矿物岩石地球化学通报, 2019,38(24):1-10. Feng Yipeng, Zhang Weijie, Wang Genhou, et al.Evolution of the Suhongtu Volcanic Edifice and Volcanic Effusive Activity in the Inngen-Ejin Qi Basin, Alxa[J]. Bulletin of Mineralogy, Petrology and Geochemistry, 2019, 38(24):1-10.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed

基于极限学习机的遥感地球化学反演模型

Remote Sensing Geochemical Inversion Model by Using Extreme Learning Machine

PDF (PC)

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

Metrics

本文评价

推荐阅读 0

[1]	王铁兴, 王德利, 孙婧, 胡斌, 刘思秀. 基于三维稀疏反演的混合震源数据分离与一次波估计[J]. 吉林大学学报(地球科学版), 2020, 50(3): 895-904.
[2]	陈守田, 吴玉金, 付喜春, 张文龙, 安朝晖, 丛培泓. 肇源地区薄砂体精细刻画及水平井轨迹设计[J]. 吉林大学学报(地球科学版), 2020, 50(2): 598-607.
[3]	闫英伟, 王者江, 韩飞, 刘聪, 曾凡杰. 多模式面波非线性反演[J]. 吉林大学学报(地球科学版), 2019, 49(6): 1768-1779.
[4]	罗腾, 冯晅, 郭智奇, 刘财, 刘喜武. 基于模拟退火粒子群优化算法的裂缝型储层各向异性参数地震反演[J]. 吉林大学学报(地球科学版), 2019, 49(5): 1466-1476.
[5]	杨悦, 翁爱华, 张艳辉, 李世文, 李建平, 唐裕. 基于可控源电磁法阻抗信息的有限内存拟牛顿法三维反演[J]. 吉林大学学报(地球科学版), 2019, 49(2): 591-602.
[6]	梁生贤. 互相关系数自约束的重力三维反演与高效求解[J]. 吉林大学学报(地球科学版), 2018, 48(5): 1473-1482.
[7]	郑国磊, 徐新学, 李世斌, 袁航, 马为, 叶青. 天津市重力数据反演解释[J]. 吉林大学学报(地球科学版), 2018, 48(4): 1221-1230.
[8]	王泰涵, 黄大年, 马国庆, 李野, 林松. 基于并行预处理算法的三维重力快速反演[J]. 吉林大学学报(地球科学版), 2018, 48(2): 384-393.
[9]	王明常, 张馨月, 张旭晴, 王凤艳, 牛雪峰, 王红. 基于极限学习机的GF-2影像分类[J]. 吉林大学学报(地球科学版), 2018, 48(2): 373-378.
[10]	刘新彤, 刘四新, 孟旭, 傅磊. 低频缺失下跨孔雷达包络波形反演[J]. 吉林大学学报(地球科学版), 2018, 48(2): 474-482.
[11]	翁爱华, 李斯睿, 杨悦, 李大俊, 李建平, 李世文. 磁电法基本原理、发展现状及前景展望[J]. 吉林大学学报(地球科学版), 2017, 47(6): 1838-1854.
[12]	王通, 王德利, 冯飞, 程浩, 魏敬轩, 田密. 三维稀疏反演多次波预测及曲波域匹配相减技术[J]. 吉林大学学报(地球科学版), 2017, 47(6): 1865-1874.
[13]	陈帅, 李桐林, 张镕哲. 考虑激发极化效应的瞬变电磁一维Occam反演[J]. 吉林大学学报(地球科学版), 2017, 47(4): 1278-1285.
[14]	张代磊, 黄大年, 张冲. 基于遗传算法优化的BP神经网络在密度界面反演中的应用[J]. 吉林大学学报(地球科学版), 2017, 47(2): 580-588.
[15]	高秀鹤, 黄大年, 孙思源, 于平. 重力梯度数据协克里金三维反演确定岩脉倾向[J]. 吉林大学学报(地球科学版), 2017, 47(2): 589-596.