Advancing deep learning for earth sciences: from hybrid modelling to interpretability

Gustau Camps-Valls, Markus Reichstein, Xiaoxiang Zhu, Devis Tuia

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

Abstract

Machine learning and deep learning in particular have made a huge impact in many fields of science and engineering. In the last decade, advanced deep learning methods have been developed and applied to remote sensing and geoscientific data problems extensively. Applications on classification and parameter retrieval are making a difference: methods are very accurate, can handle large amounts of data, and can deal with spatial and temporal data structures efficiently. Nevertheless, several important challenges need still to be addressed. First, current standard deep architectures cannot deal with long-range dependencies so distant driving processes (in space or time) are not captured, and they cannot cope with non-Euclidean spaces efficiently. Second, as other data-driven techniques, deep learning models do not necessarily respect physical or causal relations. Finally, deep learning models are still obscure and resistant to interpretability. Advances are needed to cope with arbitrary signal structures and data relations, physical plausibility and interpretability. This paper discusses about ways forward to develop new DL methods for the Earth sciences in all three directions.
Original languageEnglish
Title of host publicationIGARSS 2020 - 2020 IEEE International Geoscience and Remote Sensing Symposium
Subtitle of host publicationProceedings
PublisherIEEE
Pages3979-3982
Number of pages4
ISBN (Electronic)9781728163741
ISBN (Print)9781728163758
DOIs
Publication statusPublished - 2 Oct 2020
EventIGARSS 2020 - 2020 IEEE International Geoscience and Remote Sensing Symposium - Waikoloa, HI, USA
Duration: 26 Sep 20202 Oct 2020

Conference

ConferenceIGARSS 2020 - 2020 IEEE International Geoscience and Remote Sensing Symposium
Period26/09/202/10/20

Keywords

  • Earth
  • Deep learning
  • Remote sensing
  • Computational modeling
  • Machine learning
  • Predictive models
  • Data models

Fingerprint

Dive into the research topics of 'Advancing deep learning for earth sciences: from hybrid modelling to interpretability'. Together they form a unique fingerprint.

Cite this