File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Conference Paper: A co-training approach to the classification of local climate zones with multi-source data

TitleA co-training approach to the classification of local climate zones with multi-source data
Authors
KeywordsLocal climate zone
self-paced learning
co-training
Issue Date2017
Citation
International Geoscience and Remote Sensing Symposium (IGARSS), 2017, v. 2017-July, p. 1209-1212 How to Cite?
Abstract© 2017 IEEE. Local climate zone (LCZ) classification system provides standard urban morphological classification for urban heat island studies and weather and climate modelling. Based on the definition of the LCZ, various semi-supervised classification approaches have been proposed to generate LCZ maps for different cities using available satellite data. Given that the acquisition of training data is labor intensive, it is practical to develop new models that are suitable for LCZ classification for any cities without the need for training data/samples. In this study, a novel domain-adaptation co-training approach with self-paced learning is designed to generate LCZ maps for new cities with which valid training samples from existing cities are explored and transferred to new target cities for classification. Experimental results show that the proposed approach could derive LCZ maps for the four testing cities, with an overall accuracy of 69.8%, which is over 10% more accurate than conventional approaches. Compared with conventional approaches, the novel approach does not need prior knowledge about the target cities, and it can automatically generate worldwide LCZ maps to support urban-climate studies for cities in the world.
Persistent Identifierhttp://hdl.handle.net/10722/262781

 

DC FieldValueLanguage
dc.contributor.authorXu, Yong-
dc.contributor.authorMa, Fan-
dc.contributor.authorMeng, Deyu-
dc.contributor.authorRen, Chao-
dc.contributor.authorLeung, Yee-
dc.date.accessioned2018-10-08T02:47:01Z-
dc.date.available2018-10-08T02:47:01Z-
dc.date.issued2017-
dc.identifier.citationInternational Geoscience and Remote Sensing Symposium (IGARSS), 2017, v. 2017-July, p. 1209-1212-
dc.identifier.urihttp://hdl.handle.net/10722/262781-
dc.description.abstract© 2017 IEEE. Local climate zone (LCZ) classification system provides standard urban morphological classification for urban heat island studies and weather and climate modelling. Based on the definition of the LCZ, various semi-supervised classification approaches have been proposed to generate LCZ maps for different cities using available satellite data. Given that the acquisition of training data is labor intensive, it is practical to develop new models that are suitable for LCZ classification for any cities without the need for training data/samples. In this study, a novel domain-adaptation co-training approach with self-paced learning is designed to generate LCZ maps for new cities with which valid training samples from existing cities are explored and transferred to new target cities for classification. Experimental results show that the proposed approach could derive LCZ maps for the four testing cities, with an overall accuracy of 69.8%, which is over 10% more accurate than conventional approaches. Compared with conventional approaches, the novel approach does not need prior knowledge about the target cities, and it can automatically generate worldwide LCZ maps to support urban-climate studies for cities in the world.-
dc.languageeng-
dc.relation.ispartofInternational Geoscience and Remote Sensing Symposium (IGARSS)-
dc.subjectLocal climate zone-
dc.subjectself-paced learning-
dc.subjectco-training-
dc.titleA co-training approach to the classification of local climate zones with multi-source data-
dc.typeConference_Paper-
dc.description.natureLink_to_subscribed_fulltext-
dc.identifier.doi10.1109/IGARSS.2017.8127175-
dc.identifier.scopuseid_2-s2.0-85041860810-
dc.identifier.volume2017-July-
dc.identifier.spage1209-
dc.identifier.epage1212-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats