No cloud on the horizon: probabilistic gap filling in satellite image series

Raphael Fischer, Nico Piatkowski, Charlotte Pelletier, Geoffrey I. Webb, Francois Petitjean, Katharina Morik

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

5 Citations (Scopus)


Spatiooral data sets such as satellite image series are of utmost importance for understanding global developments like climate change or urbanization. However, incompleteness of data can greatly impact usability and knowledge discovery. In fact, there are many cases where not a single data point in the set is fully observed. For filling gaps, we introduce a novel approach that utilizes Markov random fields (MRFs). We extend the probabilistic framework to also consider empirical prior information, which allows to train even on highly incomplete data. Moreover, we devise a way to make discrete MRFs predict continuous values via state superposition. Experiments on real-world remote sensing imagery suffering from cloud cover show that the proposed approach outperforms state-of-the-art gap filling techniques.

Original languageEnglish
Title of host publicationProceedings - 2020 IEEE 7th International Conference on Data Science and Advanced Analytics, DSAA 2020
EditorsGeoff Webb, Zhongfei Zhang, Vincent S. Tseng, Graham Williams, Michalis Vlachos, Longbing Cao
Place of PublicationPiscataway NJ USA
PublisherIEEE, Institute of Electrical and Electronics Engineers
Number of pages10
ISBN (Electronic)9781728182063
ISBN (Print)9781728182070
Publication statusPublished - 2020
EventIEEE International Conference on Data Science and Advanced Analytics 2020 - Sydney, Australia
Duration: 6 Oct 20209 Oct 2020
Conference number: 7th (Publication) (Website)


ConferenceIEEE International Conference on Data Science and Advanced Analytics 2020
Abbreviated titleDSAA 2020
Internet address


  • Gap filling
  • Graphical models
  • Probabilistic machine learning
  • Remote sensing
  • Spatiooral

Cite this