File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Conference Paper: Geological applications of machine learning on hyperspectral remote sensing data

TitleGeological applications of machine learning on hyperspectral remote sensing data
Authors
KeywordsCluster classification
CRISM
Hyperspectral
Unsupervised learning
Issue Date2015
PublisherSPIE - International Society for Optical Engineering. The Journal's web site is located at http://spie.org/x1848.xml
Citation
Image Processing: Machine Vision Applications VIII (Conference 9405), San Francisco, CA., 10-11 February 2015. In Proceedings of SPIE, 2015, v. 9405, article no. 940512, p. 1-6 How to Cite?
AbstractThe CRISM imaging spectrometer orbiting Mars has been producing a vast amount of data in the visible to infrared wavelengths in the form of hyperspectral data cubes. These data, compared with those obtained from previous remote sensing techniques, yield an unprecedented level of detailed spectral resolution in additional to an ever increasing level of spatial information. A major challenge brought about by the data is the burden of processing and interpreting these datasets and extract the relevant information from it. This research aims at approaching the challenge by exploring machine learning methods especially unsupervised learning to achieve cluster density estimation and classification, and ultimately devising an efficient means leading to identification of minerals. A set of software tools have been constructed by Python to access and experiment with CRISM hyperspectral cubes selected from two specific Mars locations. A machine learning pipeline is proposed and unsupervised learning methods were implemented onto pre-processed datasets. The resulting data clusters are compared with the published ASTER spectral library and browse data products from the Planetary Data System (PDS). The result demonstrated that this approach is capable of processing the huge amount of hyperspectral data and potentially providing guidance to scientists for more detailed studies.
Persistent Identifierhttp://hdl.handle.net/10722/211420
ISBN
ISSN

 

DC FieldValueLanguage
dc.contributor.authorTse, CH-
dc.contributor.authorLi, Y-
dc.contributor.authorLam, EY-
dc.date.accessioned2015-07-13T03:24:33Z-
dc.date.available2015-07-13T03:24:33Z-
dc.date.issued2015-
dc.identifier.citationImage Processing: Machine Vision Applications VIII (Conference 9405), San Francisco, CA., 10-11 February 2015. In Proceedings of SPIE, 2015, v. 9405, article no. 940512, p. 1-6-
dc.identifier.isbn978-162841495-0-
dc.identifier.issn0277-786X-
dc.identifier.urihttp://hdl.handle.net/10722/211420-
dc.description.abstractThe CRISM imaging spectrometer orbiting Mars has been producing a vast amount of data in the visible to infrared wavelengths in the form of hyperspectral data cubes. These data, compared with those obtained from previous remote sensing techniques, yield an unprecedented level of detailed spectral resolution in additional to an ever increasing level of spatial information. A major challenge brought about by the data is the burden of processing and interpreting these datasets and extract the relevant information from it. This research aims at approaching the challenge by exploring machine learning methods especially unsupervised learning to achieve cluster density estimation and classification, and ultimately devising an efficient means leading to identification of minerals. A set of software tools have been constructed by Python to access and experiment with CRISM hyperspectral cubes selected from two specific Mars locations. A machine learning pipeline is proposed and unsupervised learning methods were implemented onto pre-processed datasets. The resulting data clusters are compared with the published ASTER spectral library and browse data products from the Planetary Data System (PDS). The result demonstrated that this approach is capable of processing the huge amount of hyperspectral data and potentially providing guidance to scientists for more detailed studies.-
dc.languageeng-
dc.publisherSPIE - International Society for Optical Engineering. The Journal's web site is located at http://spie.org/x1848.xml-
dc.relation.ispartofProceedings of SPIE-
dc.rightsProceedings of SPIE. Copyright © SPIE - International Society for Optical Engineering.-
dc.rightsCopyright notice format: Copyright 2015 Society of Photo-Optical Instrumentation Engineers. One print or electronic copy may be made for personal use only. Systematic reproduction and distribution, duplication of any material in this paper for a fee or for commercial purposes, or modification of the content of the paper are prohibited.-
dc.subjectCluster classification-
dc.subjectCRISM-
dc.subjectHyperspectral-
dc.subjectUnsupervised learning-
dc.titleGeological applications of machine learning on hyperspectral remote sensing data-
dc.typeConference_Paper-
dc.identifier.emailLi, Y: yiliang@hku.hk-
dc.identifier.emailLam, EY: elam@eee.hku.hk-
dc.identifier.authorityLi, Y=rp01354-
dc.identifier.authorityLam, EY=rp00131-
dc.identifier.doi10.1117/12.2178400-
dc.identifier.scopuseid_2-s2.0-84926667819-
dc.identifier.hkuros245308-
dc.identifier.volume9405-
dc.identifier.spage1-
dc.identifier.epage6-
dc.publisher.placeUnited States-
dc.customcontrol.immutablesml 150713-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats