基于影像特征CART决策树的稀土矿区信息提取与动态监测
|
摘要
为准确反映赣南稀土矿区开采状况,以江西省寻乌县为研究区,选用Landsat-8多光谱影像为数据源,通过对均值纹理、裸土指数(Bare Soil Index,BSI)、归一化植被指数(Normalized Difference Vegetation Index,NDVI)3种特征信息进行提取,采用基于CART(Classification and Regression Trees)决策树的分类方法对研究区稀土矿开采信息进行识别,分类总体精度达到89.43%,其中矿区分类精度达到88%,分类精度相对于基于光谱信息的CART决策树分类和最大似然分类有明显提高。通过对研究区2013—2016年稀土矿开采区域进行遥感动态监测,发现增加的开采区域主要分布于矿权范围内,减少的开采区域在矿权界限内外均有大量分布,减少幅度达41%,说明政府和相关矿权部门对于稀土行业健康有序发展发挥了重要作用。研究表明:基于影像特征CART决策树的分类方法在稀土矿区信息提取与动态监测方面具有一定的可行性。
In order to accurately reflect the mining status of rare earth mining area in Southern Jiangxi Province,taking Xunwu County of Jiangxi Province as the study area and selecting Landsat-8 multi-spectral image as the data source,through the extraction of the feature information of mean texture,bare soil index(BSI)and normalized difference vegetation index(NDVI),the mining information ore rare earth of the study area is identified by using the classification method based on multisource data CART decision tree.The results show that the overall accuracy of the classification is 89.43% and the classification precision of the mining area is 88%.The classification accuracy is better than the ones of CART decision tree classification method based on spectral information and maximum likelihood classification method.Based on the above discussion results,remote sensing dynamic monitoring for the rare mining area in the study area from 2013 to 2016 is carried out.It is found that the increasing mining area is mainly distributed within the scope of mining boundary,the reduced mining area is distributed within and outside the mining boundary and the degree of reduction is 41%,which further indicated that the government and related departments have played an important role in developing a healthy and orderly rare earth industry.The above study results show that the classification method based on multi-source data CART decision tree has certain feasibility in information extraction and dynamic monitoring of rare earth mining area.
In order to accurately reflect the mining status of rare earth mining area in Southern Jiangxi Province,taking Xunwu County of Jiangxi Province as the study area and selecting Landsat-8 multi-spectral image as the data source,through the extraction of the feature information of mean texture,bare soil index(BSI)and normalized difference vegetation index(NDVI),the mining information ore rare earth of the study area is identified by using the classification method based on multisource data CART decision tree.The results show that the overall accuracy of the classification is 89.43% and the classification precision of the mining area is 88%.The classification accuracy is better than the ones of CART decision tree classification method based on spectral information and maximum likelihood classification method.Based on the above discussion results,remote sensing dynamic monitoring for the rare mining area in the study area from 2013 to 2016 is carried out.It is found that the increasing mining area is mainly distributed within the scope of mining boundary,the reduced mining area is distributed within and outside the mining boundary and the degree of reduction is 41%,which further indicated that the government and related departments have played an important role in developing a healthy and orderly rare earth industry.The above study results show that the classification method based on multi-source data CART decision tree has certain feasibility in information extraction and dynamic monitoring of rare earth mining area.
引文
[1]罗仙平,翁存建,徐晶,等.离子型稀土矿开发技术研究进展及发展方向[J].金属矿山,2014(6):83-90.Luo Xianping,Weng Cunjian,Xu Jing,et al.Research progress and development direction of the development of ionic rare earths[J].Metal Mine,2014(6):83-90.
[2]熊云飞.离子型稀土开采高分遥感影像识别方法研究[D].赣州:江西理工大学,2017.Xiong Yunfei.Study on High Resolution Remote Sensing Image Recognition Method for Ion-type Rare Earth Mining[D].Ganzhou:Jiangxi University of Science and Technology,2017.
[3]高志强,周启星.稀土矿露天开采过程的污染及对资源和生态环境的影响[J].生态学杂志,2011,30(12):2915-2922.Gao Zhiqiang,Zhou Qixing.Contamination from rare earth ore strip mining and its impacts on resources and ecological environmen[tJ].Chinese Journal of Ecology,2011,30(12):2915-2922.
[4]吴亚楠.基于面向对象分类的稀土矿开采动态监测研究[D].北京:中国地质大学(北京),2017.Wu Yanan.Dynamic Monitoring of Rare Earth Mining Based on Object-oriented Classification Method[D].Beijing:China University of Geosciences(Beijing),2017.
[5]王瑜玲.江西定南北部地区稀土矿矿山开发状况与环境效应遥感研究[D].北京:中国地质大学(北京),2007.Wang Yuling.Study on the Exploitive Status of the Rare Earth Mineral and Its Environment Problems Using Remote Sensing about North of Dingnan,Jiangxi Province[D].Beijing:China University of Geosciences(Beijing),2007.
[6]王陶,刘衍宏,王平,等.多源多时相遥感分类技术在赣州稀土矿区环境变化检测中的应用[J].中国矿业,2009,18(11):88-91.Wang Tao,Liu Yanhong,Wang Ping,et al.Application of multisource and multi-temporal remote sensing imag classification method in REE mineral development and environment variation in the Ganzhou mineral district[J].China Mining Magazine,2009,18(11):88-91.
[7]齐乐,岳彩荣.基于CART决策树方法的遥感影像分类[J].林业调查规划,2011,36(2):62-66.Qi Le,Yue Cairong.Remote sensing image classification based on CART decision tree method[J].Forest Inventory and Planning,2011,36(2):62-66.
[8]Zaremotlagh S,Hezarkhani A.The use of decision tree induction and artificial neural networks for recognizing the geochemical distribution patterns of LREE in the Choghart Deposit,Central Iran[J].Journal of African Earth Sciences,2017:37-46.
[9]蒙张,胡勇.基于多源数据的CART决策树冰川提取[J].地理空间信息,2018,16(2):61-63.Meng Zhang,Hu Yong.CART decision tree glacier extraction based on multi-source data[J].Geospatial Information,2018,16(2):61-63.
[10]郝泷,陈永富,刘华,等.基于纹理信息CART决策树的林芝县森林植被面向对象分类[J].遥感技术与应用,2017,32(2):386-394.Hao Shuang,Chen Yongfu,Liu Hua,et al.Object-oriented forest classification of Linzhi County based on CART decision tree with texture information[J].Remote Sensing Technology and Application,2017,32(2):386-394.
[11]陈云,戴锦芳,李俊杰.基于影像多种特征的CART决策树分类方法及其应用[J].地理与地理信息科学,2008(2):33-36.Chen Yun,Dai Jinfang,Li Junjie.CART-based decision tree classifier using multi-feature of image and its application[J].Geography and Geo-information Science,2008(2):33-36.
[12]吕利利,颉耀文,黄晓君,等.基于CART决策树分类的沙漠化信息提取方法研究[J].遥感技术与应用,2017,32(3):499-506.Lyu Lili,Xie Yaowen,Huang Xiaojun,et al.Desertification information extraction method research based on the CART decision tree classification[J].Remote Sensing Technology and Application,2017,32(3):499-506.
[13]刘欣.利用CART算法从Landsat-8卫星影像提取居民地的研究[D].兰州:兰州大学,2015.Liu Xin.Using CART Algorithm to Extract Residential from Landsat-8 Images[D].Lanzhou:Lanzhou University,2015.
[14]彭燕,何国金,张兆明,等.赣南稀土矿开发区生态环境遥感动态监测与评估[J].生态学报,2016,36(6):1676-1685.Peng Yan,He Guojin,Zhang Zhaoming,et al.Eco-environment dynamic monitoring and assessment of rare earth mining area in Southern Ganzhou using remote sensing[J].Acta Ecologica Sinica,2016,36(6):1676-1685.
[15]李恒凯,熊云飞,吴立新.面向对象的离子吸附型稀土矿开采高分遥感影像识别方法[J].稀土,2017,38(4):38-49.Li Hengkai,Xiong Yunfei,Wu Lixin.The object-oriented recognition method for remote sensing image with high spatial resolution for iron rare earth mining[J].Chinese Rare Earths,2017,38(4):38-49.
[16]吴亚楠,代晶晶,周萍.基于高空间分辨率遥感数据的稀土矿山监测研究[J].中国稀土学报,2017,35(2):262-271.Wu Yanan,Dai Jingjing,Zhou Ping.Research of rare earth minerals monitoring based on high resolution remote sensing[J].Journal of the Chinese Society of Rare Earths,2017,35(2):262-271.
[17]代晶晶,王登红,陈郑辉,等.IKONOS遥感数据在离子吸附型稀土矿区环境污染调查中的应用研究--以赣南寻乌地区为例[J].地球学报,2013,34(3):354-360.Dai Jingjing,Wang Denghong,Chen Zhenghui,et al.Environment contamination investigation of ion-absorbed rare earth ore districts based on IKONOS remote sensing data:a case study of Xunwu Area in South Jiangxi[J].Acta Geoscientica Sinica,2013,34(3):354-360.
[18]雷国静.赣州市龙南地区稀土矿矿山开采现状与动态监测遥感研究[D].北京:中国地质大学(北京),2006.Lei Guojing.A Remote Sensing Study on the Exploitation Status and Dynamic Monitoring of Rare Earth Mine in Longnan,Ganzhou[D].Beijing:China University of Geosciences(Beijing),2006.
[19]李恒凯.南方稀土矿区开采与环境影响遥感监测与评估研究[D].北京:中国矿业大学(北京),2016.Li Hengkai.Study on Remote Sensing Monitoring the Rare Earth Mining and Its Environment Impacts and Evaluation in South China[D].Beijing:China University of Mining and Technology(Beijing),2016.
[20]Ii W A Y,Weckman G R,Hari V,et al.Using artificial neural networks to enhance CART[J].Neural Computing&Applications,2012,21(7):1477-1489.
[21]邹国良.离子型稀土矿不同采选工艺比较:基于成本的视角[J].有色金属科学与工程,2012,3(4):53-56.Zou Guoliang.A comparative study of the different mining and separating technologies of ion-absorbed rare earth from the perspective of production costs[J].Nonferrous Metal Science and Engineering,2012,3(4):53-56.
[22]焦蓬蓬,郭依正,刘丽娟,等.灰度共生矩阵纹理特征提取的Matlab实现[J].计算机技术与发展,2012,22(11):169-171.Jiao Pengpeng,Guo Yizheng,Liu Lijuan,et al.Implementation of gray level co-occurrence matrix texture feature extraction using Matlab[J].Computer Technology and Development,2012,22(11):169-171.
[23]杨志刚.纹理信息在遥感影像分类中的应用[D].南京:南京林业大学,2006.Yang Zhigang.Classification of Remote Sensing Imagery with Texture Information[D].Nanjing:Nanjing Forestry University,2006.
[24]Rikimaru A.Landsat TM data processing guide for forest canopy density mapping and monitoring mode[lC]//ITTO Workshop on Utilization of Remote Sensing in Site Assessment and Planning for Rehabilitation of Logged-over Forest.Bangkok,1996:1-8.
[25]左玉珊,王卫,郝彦莉,等.基于MODIS影像的土地覆被分类研究--以京津冀地区为例[J].地理科学进展,2014,33(11):1556-1565.Zuo Yushan,Wang Wei,Hao Yanli,et al.Land cover classification based on MODIS images:taking the Beijing-Tianjin-Hebei Region as an example[J].Progress in Geography,2014,33(11):1556-1565.
[26]李向军,牛铮,邓小炼,等.基于遥感分类的博鳌地区生态变化评价[J].遥感技术与应用,2006,21(3):193-199.Li Xiangjun,Niu Zheng,Deng Xiaolian,et al.The ecological assessment in Boao Region based on RS technology and landscape indices[J].Remote Sensing Technology and Application,2006,21(3):193-199.
[27]张志成.土地利用/覆被变化的遥感监测与区域对比[D].福州:福建师范大学,2005.Zhang Zhicheng.Remote Sensing Monitoring and Regional Contrast of LUCC[D].Fuzhou:Fujian Normal University,2005.
[28]吴倩雯,况润元,张刚华,等.东江源稀土矿区土地利用变化遥感监测研究[J].测绘科学,2019,44(3):51-56.Wu Qianwen,Kuang Runyuan,Zhang Ganghua,et al.Remote sensing monitoring of land-use change in rare earth mining area in the source region of Dongjiang River[J].Science of Surveying and Mapping,2019,44(3):51-56.
[2]熊云飞.离子型稀土开采高分遥感影像识别方法研究[D].赣州:江西理工大学,2017.Xiong Yunfei.Study on High Resolution Remote Sensing Image Recognition Method for Ion-type Rare Earth Mining[D].Ganzhou:Jiangxi University of Science and Technology,2017.
[3]高志强,周启星.稀土矿露天开采过程的污染及对资源和生态环境的影响[J].生态学杂志,2011,30(12):2915-2922.Gao Zhiqiang,Zhou Qixing.Contamination from rare earth ore strip mining and its impacts on resources and ecological environmen[tJ].Chinese Journal of Ecology,2011,30(12):2915-2922.
[4]吴亚楠.基于面向对象分类的稀土矿开采动态监测研究[D].北京:中国地质大学(北京),2017.Wu Yanan.Dynamic Monitoring of Rare Earth Mining Based on Object-oriented Classification Method[D].Beijing:China University of Geosciences(Beijing),2017.
[5]王瑜玲.江西定南北部地区稀土矿矿山开发状况与环境效应遥感研究[D].北京:中国地质大学(北京),2007.Wang Yuling.Study on the Exploitive Status of the Rare Earth Mineral and Its Environment Problems Using Remote Sensing about North of Dingnan,Jiangxi Province[D].Beijing:China University of Geosciences(Beijing),2007.
[6]王陶,刘衍宏,王平,等.多源多时相遥感分类技术在赣州稀土矿区环境变化检测中的应用[J].中国矿业,2009,18(11):88-91.Wang Tao,Liu Yanhong,Wang Ping,et al.Application of multisource and multi-temporal remote sensing imag classification method in REE mineral development and environment variation in the Ganzhou mineral district[J].China Mining Magazine,2009,18(11):88-91.
[7]齐乐,岳彩荣.基于CART决策树方法的遥感影像分类[J].林业调查规划,2011,36(2):62-66.Qi Le,Yue Cairong.Remote sensing image classification based on CART decision tree method[J].Forest Inventory and Planning,2011,36(2):62-66.
[8]Zaremotlagh S,Hezarkhani A.The use of decision tree induction and artificial neural networks for recognizing the geochemical distribution patterns of LREE in the Choghart Deposit,Central Iran[J].Journal of African Earth Sciences,2017:37-46.
[9]蒙张,胡勇.基于多源数据的CART决策树冰川提取[J].地理空间信息,2018,16(2):61-63.Meng Zhang,Hu Yong.CART decision tree glacier extraction based on multi-source data[J].Geospatial Information,2018,16(2):61-63.
[10]郝泷,陈永富,刘华,等.基于纹理信息CART决策树的林芝县森林植被面向对象分类[J].遥感技术与应用,2017,32(2):386-394.Hao Shuang,Chen Yongfu,Liu Hua,et al.Object-oriented forest classification of Linzhi County based on CART decision tree with texture information[J].Remote Sensing Technology and Application,2017,32(2):386-394.
[11]陈云,戴锦芳,李俊杰.基于影像多种特征的CART决策树分类方法及其应用[J].地理与地理信息科学,2008(2):33-36.Chen Yun,Dai Jinfang,Li Junjie.CART-based decision tree classifier using multi-feature of image and its application[J].Geography and Geo-information Science,2008(2):33-36.
[12]吕利利,颉耀文,黄晓君,等.基于CART决策树分类的沙漠化信息提取方法研究[J].遥感技术与应用,2017,32(3):499-506.Lyu Lili,Xie Yaowen,Huang Xiaojun,et al.Desertification information extraction method research based on the CART decision tree classification[J].Remote Sensing Technology and Application,2017,32(3):499-506.
[13]刘欣.利用CART算法从Landsat-8卫星影像提取居民地的研究[D].兰州:兰州大学,2015.Liu Xin.Using CART Algorithm to Extract Residential from Landsat-8 Images[D].Lanzhou:Lanzhou University,2015.
[14]彭燕,何国金,张兆明,等.赣南稀土矿开发区生态环境遥感动态监测与评估[J].生态学报,2016,36(6):1676-1685.Peng Yan,He Guojin,Zhang Zhaoming,et al.Eco-environment dynamic monitoring and assessment of rare earth mining area in Southern Ganzhou using remote sensing[J].Acta Ecologica Sinica,2016,36(6):1676-1685.
[15]李恒凯,熊云飞,吴立新.面向对象的离子吸附型稀土矿开采高分遥感影像识别方法[J].稀土,2017,38(4):38-49.Li Hengkai,Xiong Yunfei,Wu Lixin.The object-oriented recognition method for remote sensing image with high spatial resolution for iron rare earth mining[J].Chinese Rare Earths,2017,38(4):38-49.
[16]吴亚楠,代晶晶,周萍.基于高空间分辨率遥感数据的稀土矿山监测研究[J].中国稀土学报,2017,35(2):262-271.Wu Yanan,Dai Jingjing,Zhou Ping.Research of rare earth minerals monitoring based on high resolution remote sensing[J].Journal of the Chinese Society of Rare Earths,2017,35(2):262-271.
[17]代晶晶,王登红,陈郑辉,等.IKONOS遥感数据在离子吸附型稀土矿区环境污染调查中的应用研究--以赣南寻乌地区为例[J].地球学报,2013,34(3):354-360.Dai Jingjing,Wang Denghong,Chen Zhenghui,et al.Environment contamination investigation of ion-absorbed rare earth ore districts based on IKONOS remote sensing data:a case study of Xunwu Area in South Jiangxi[J].Acta Geoscientica Sinica,2013,34(3):354-360.
[18]雷国静.赣州市龙南地区稀土矿矿山开采现状与动态监测遥感研究[D].北京:中国地质大学(北京),2006.Lei Guojing.A Remote Sensing Study on the Exploitation Status and Dynamic Monitoring of Rare Earth Mine in Longnan,Ganzhou[D].Beijing:China University of Geosciences(Beijing),2006.
[19]李恒凯.南方稀土矿区开采与环境影响遥感监测与评估研究[D].北京:中国矿业大学(北京),2016.Li Hengkai.Study on Remote Sensing Monitoring the Rare Earth Mining and Its Environment Impacts and Evaluation in South China[D].Beijing:China University of Mining and Technology(Beijing),2016.
[20]Ii W A Y,Weckman G R,Hari V,et al.Using artificial neural networks to enhance CART[J].Neural Computing&Applications,2012,21(7):1477-1489.
[21]邹国良.离子型稀土矿不同采选工艺比较:基于成本的视角[J].有色金属科学与工程,2012,3(4):53-56.Zou Guoliang.A comparative study of the different mining and separating technologies of ion-absorbed rare earth from the perspective of production costs[J].Nonferrous Metal Science and Engineering,2012,3(4):53-56.
[22]焦蓬蓬,郭依正,刘丽娟,等.灰度共生矩阵纹理特征提取的Matlab实现[J].计算机技术与发展,2012,22(11):169-171.Jiao Pengpeng,Guo Yizheng,Liu Lijuan,et al.Implementation of gray level co-occurrence matrix texture feature extraction using Matlab[J].Computer Technology and Development,2012,22(11):169-171.
[23]杨志刚.纹理信息在遥感影像分类中的应用[D].南京:南京林业大学,2006.Yang Zhigang.Classification of Remote Sensing Imagery with Texture Information[D].Nanjing:Nanjing Forestry University,2006.
[24]Rikimaru A.Landsat TM data processing guide for forest canopy density mapping and monitoring mode[lC]//ITTO Workshop on Utilization of Remote Sensing in Site Assessment and Planning for Rehabilitation of Logged-over Forest.Bangkok,1996:1-8.
[25]左玉珊,王卫,郝彦莉,等.基于MODIS影像的土地覆被分类研究--以京津冀地区为例[J].地理科学进展,2014,33(11):1556-1565.Zuo Yushan,Wang Wei,Hao Yanli,et al.Land cover classification based on MODIS images:taking the Beijing-Tianjin-Hebei Region as an example[J].Progress in Geography,2014,33(11):1556-1565.
[26]李向军,牛铮,邓小炼,等.基于遥感分类的博鳌地区生态变化评价[J].遥感技术与应用,2006,21(3):193-199.Li Xiangjun,Niu Zheng,Deng Xiaolian,et al.The ecological assessment in Boao Region based on RS technology and landscape indices[J].Remote Sensing Technology and Application,2006,21(3):193-199.
[27]张志成.土地利用/覆被变化的遥感监测与区域对比[D].福州:福建师范大学,2005.Zhang Zhicheng.Remote Sensing Monitoring and Regional Contrast of LUCC[D].Fuzhou:Fujian Normal University,2005.
[28]吴倩雯,况润元,张刚华,等.东江源稀土矿区土地利用变化遥感监测研究[J].测绘科学,2019,44(3):51-56.Wu Qianwen,Kuang Runyuan,Zhang Ganghua,et al.Remote sensing monitoring of land-use change in rare earth mining area in the source region of Dongjiang River[J].Science of Surveying and Mapping,2019,44(3):51-56.