File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Article: Multisource data selection for lithologic classification with artificial neural networks

TitleMultisource data selection for lithologic classification with artificial neural networks
Authors
Issue Date1998
Citation
International Journal of Remote Sensing, 1998, v. 19, n. 18, p. 3675-3680 How to Cite?
AbstractMapping the geological lithology in remote regions is a difficult and costly endeavour. Multisource image data such as electro-optical reflectance and microwave backscatter combined with geophysical image data such as gravity, magnetic, gamma ray spectrometry, offer the potential to construct lithologic maps without extensive field surveys. Neural networks are a useful tool for classifying image data, since they bypass the statistical assumptions required by traditional multivariate discriminant functions, and they are much simpler to setup than expert systems. However, the performance of neural networks can vary significantly between individual classes. In this work we examined the effects of the different input image data on network performance. We found that the geophysical data, particularly radiation measurements, which provides subsurface information, were essential for accurate mapping of lithology. Mid-infrared reflectance was the most relevant of the remote sensing measurements. We also found that the learning styles of the various networks varied considerably. In all cases, a complete learning history for each network was required before the network can be trained for optimal performance. © 1998 Taylor and Francis Group, LLC.
Persistent Identifierhttp://hdl.handle.net/10722/296922
ISSN
2021 Impact Factor: 3.531
2020 SCImago Journal Rankings: 0.918
ISI Accession Number ID

 

DC FieldValueLanguage
dc.contributor.authorYang, G.-
dc.contributor.authorCollins, M. J.-
dc.contributor.authorGong, P.-
dc.date.accessioned2021-02-25T15:16:58Z-
dc.date.available2021-02-25T15:16:58Z-
dc.date.issued1998-
dc.identifier.citationInternational Journal of Remote Sensing, 1998, v. 19, n. 18, p. 3675-3680-
dc.identifier.issn0143-1161-
dc.identifier.urihttp://hdl.handle.net/10722/296922-
dc.description.abstractMapping the geological lithology in remote regions is a difficult and costly endeavour. Multisource image data such as electro-optical reflectance and microwave backscatter combined with geophysical image data such as gravity, magnetic, gamma ray spectrometry, offer the potential to construct lithologic maps without extensive field surveys. Neural networks are a useful tool for classifying image data, since they bypass the statistical assumptions required by traditional multivariate discriminant functions, and they are much simpler to setup than expert systems. However, the performance of neural networks can vary significantly between individual classes. In this work we examined the effects of the different input image data on network performance. We found that the geophysical data, particularly radiation measurements, which provides subsurface information, were essential for accurate mapping of lithology. Mid-infrared reflectance was the most relevant of the remote sensing measurements. We also found that the learning styles of the various networks varied considerably. In all cases, a complete learning history for each network was required before the network can be trained for optimal performance. © 1998 Taylor and Francis Group, LLC.-
dc.languageeng-
dc.relation.ispartofInternational Journal of Remote Sensing-
dc.titleMultisource data selection for lithologic classification with artificial neural networks-
dc.typeArticle-
dc.description.naturelink_to_subscribed_fulltext-
dc.identifier.doi10.1080/014311698213885-
dc.identifier.scopuseid_2-s2.0-0032458903-
dc.identifier.volume19-
dc.identifier.issue18-
dc.identifier.spage3675-
dc.identifier.epage3680-
dc.identifier.eissn1366-5901-
dc.identifier.isiWOS:000077774800012-
dc.identifier.issnl0143-1161-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats