Unsupervised Domain Adaptation techniques for classification of satellite image time series

Benjamin Lucas, Charlotte Pelletier, Daniel Schmidt, Geoffrey I. Webb, Francois Petitjean

Research output: Chapter in Book/Report/Conference proceedingConference PaperResearchpeer-review


Land cover maps are vitally important to many elements of environmental management. However the machine learning algorithms used to produce them require a substantive quantity of labelled training data to reach the best levels of accuracy. When researchers wish to map an area where no labelled training data are available, one potential solution is to use a classifier trained on another geographical area and adapting it to the target location-this is known as Unsupervised Domain Adaptation (DA). In this paper we undertake the first experiments using unsupervised DA methods for the classification of satellite image time series (SITS) data. Our experiments draw the interesting conclusion that existing methods provide no benefit when used on SITS data, and that this is likely due to the temporal nature of the data and the change in class distributions between the regions. This suggests that an unsupervised domain adaptation technique for SITS would be extremely beneficial for land cover mapping.

Original languageEnglish
Title of host publicationIGARSS 2020 - 2020 IEEE International Geoscience and Remote Sensing Symposium - Proceedings
EditorsJasmeet Judge, Paolo Gamba, Jiancheng Shi
Place of PublicationPiscataway NJ USA
PublisherIEEE, Institute of Electrical and Electronics Engineers
Number of pages4
ISBN (Electronic)9781728163741, 9781728163734
ISBN (Print)9781728163758
Publication statusPublished - 2020
EventIEEE International Geoscience and Remote Sensing Symposium 2020 - Virtual, Waikoloa, United States of America
Duration: 26 Sep 20202 Oct 2020
https://ieeexplore.ieee.org/xpl/conhome/9323073/proceeding (Proceedings)
https://igarss2020.org/ (Website)


ConferenceIEEE International Geoscience and Remote Sensing Symposium 2020
Abbreviated titleIGARSS 2020
CountryUnited States of America
Internet address


  • Deep Learning
  • Domain Adaptation
  • Land Cover Map
  • Satellite Image Time Series
  • Transfer Learning

Cite this