Feature-Oriented Principal Component Selection (FPCS) for Delineation of the Geological Units Using the Integration of SWIR and TIR ASTER Data

Ronak Jain
{"title":"Feature-Oriented Principal Component Selection (FPCS) for Delineation of the Geological Units Using the Integration of SWIR and TIR ASTER Data","authors":"Ronak Jain","doi":"10.5772/intechopen.99046","DOIUrl":null,"url":null,"abstract":"Geological studies have been performed using the Band Ratios (BR), Relative Band Depth (RBD), Mineral Indices (MI), Principal Component Analysis (PCA), Independent Component Analysis (ICA), lithological and mineral classification techniques from Short-Wave Infrared (SWIR) and Thermal Infrared (TIR) data. The chapter aims to delineate various geological units present in the area using the combination of SWIR and TIR ASTER bands through the Feature-Oriented Principal Component Selection (FPCS) technique. Different BRs and RBDs were applied to map the minerals having Al-OH and Mg-OH compounds with the chemical composition of clay (kaolinite, smectite), mica (sericite, muscovite, illite), ultramafic (lizardite, antigorite, chrysotile), talc, and carbonate (dolomite) from SWIR bands. The MI was used to map quartz-rich, mafic/ultramafic, and carbonate rocks using TIR bands. The BRs, RBDs, and MIs mapped the geological units but every single greyscale image showed a variety of features. To compile these features False Color Composite (FCC) was prepared by the combination of RBDs and MIs in the R:G:B channels which demarked various geological units to a larger extent present in the region. To overcome the limitation, the FPCS technique was applied with the integration of all BRs, RBDs, and MIs. The FPCS technique extracts valuable information from different input bands and shifts the information in the first few bands. The generated eigenvalues and eigenvectors represented the retrieved information in the specific band. The loadings of the eigenvector were used for the selection of the different brands to create the FCC for the delineation of geological strata. The best discrimination was made by the selection of FPCS1, FPCS3, and FPCS6 which differentiated all the geological units like ultramafics, dolomites, thin bands of talc, and muscovite and illite (as phyllite and mica-schist), silica-rich rocks (as quartzite), and granite outcrops.","PeriodicalId":430576,"journal":{"name":"Remote Sensing [Working Title]","volume":"38 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2021-10-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"4","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Remote Sensing [Working Title]","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.5772/intechopen.99046","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 4

Abstract

Geological studies have been performed using the Band Ratios (BR), Relative Band Depth (RBD), Mineral Indices (MI), Principal Component Analysis (PCA), Independent Component Analysis (ICA), lithological and mineral classification techniques from Short-Wave Infrared (SWIR) and Thermal Infrared (TIR) data. The chapter aims to delineate various geological units present in the area using the combination of SWIR and TIR ASTER bands through the Feature-Oriented Principal Component Selection (FPCS) technique. Different BRs and RBDs were applied to map the minerals having Al-OH and Mg-OH compounds with the chemical composition of clay (kaolinite, smectite), mica (sericite, muscovite, illite), ultramafic (lizardite, antigorite, chrysotile), talc, and carbonate (dolomite) from SWIR bands. The MI was used to map quartz-rich, mafic/ultramafic, and carbonate rocks using TIR bands. The BRs, RBDs, and MIs mapped the geological units but every single greyscale image showed a variety of features. To compile these features False Color Composite (FCC) was prepared by the combination of RBDs and MIs in the R:G:B channels which demarked various geological units to a larger extent present in the region. To overcome the limitation, the FPCS technique was applied with the integration of all BRs, RBDs, and MIs. The FPCS technique extracts valuable information from different input bands and shifts the information in the first few bands. The generated eigenvalues and eigenvectors represented the retrieved information in the specific band. The loadings of the eigenvector were used for the selection of the different brands to create the FCC for the delineation of geological strata. The best discrimination was made by the selection of FPCS1, FPCS3, and FPCS6 which differentiated all the geological units like ultramafics, dolomites, thin bands of talc, and muscovite and illite (as phyllite and mica-schist), silica-rich rocks (as quartzite), and granite outcrops.
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
基于特征的主成分选择(FPCS)——基于SWIR和TIR ASTER数据的地质单元圈定
利用波段比(BR)、相对波段深度(RBD)、矿物指数(MI)、主成分分析(PCA)、独立成分分析(ICA)以及短波红外(SWIR)和热红外(TIR)数据的岩性和矿物分类技术进行了地质研究。本章旨在通过面向特征的主成分选择(FPCS)技术,利用SWIR和TIR ASTER波段的组合来描绘该地区存在的各种地质单元。利用不同的BRs和RBDs在SWIR波段对含有Al-OH和Mg-OH化合物的矿物进行了谱图,这些矿物的化学成分包括粘土(高岭石、蒙脱石)、云母(绢云母、白云母、伊云母)、超镁铁质(丽沙长石、反长云母、温石棉)、滑石和碳酸盐(白云石)。MI用于利用TIR波段绘制富石英、基性/超基性和碳酸盐岩。BRs、rbd和mi绘制了地质单元,但每一张灰度图像都显示出各种各样的特征。为了编制这些特征,将R:G:B通道的rbd和mi组合在一起制备了假色合成(FCC),该通道在很大程度上划分了该区域存在的各种地质单元。为了克服这一限制,FPCS技术被应用于所有BRs、rbd和MIs的整合。FPCS技术从不同的输入波段中提取有价值的信息,并对前几个波段的信息进行移位。生成的特征值和特征向量表示检索到的特定波段的信息。特征向量的载荷用于选择不同的品牌,以创建用于地质地层圈定的FCC。选择FPCS1、FPCS3和FPCS6对超镁铁岩、白云岩、滑石细带、白云母和伊立岩(如千叶岩和云母片岩)、富硅岩(如石英岩)和花岗岩露头等地质单元进行区分效果最好。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 去求助
来源期刊
自引率
0.00%
发文量
0
期刊最新文献
Application of UAV Remote Sensing in Monitoring Banana Fusarium Wilt Feature-Oriented Principal Component Selection (FPCS) for Delineation of the Geological Units Using the Integration of SWIR and TIR ASTER Data Image Enhancement Methods for Remote Sensing: A Survey Utilization of Remote Sensing Technology for Carbon Offset Identification in Malaysian Forests Optical Remote Sensing of Planetary Space Environment
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1