File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Article: ROBOT: A spatiotemporal fusion model toward seamless data cube for global remote sensing applications

TitleROBOT: A spatiotemporal fusion model toward seamless data cube for global remote sensing applications
Authors
KeywordsComputing efficiency
Missing data
Seamless data cube
Spatiotemporal fusion
Time series
Issue Date20-May-2023
PublisherElsevier
Citation
Remote Sensing of Environment, 2023, v. 294 How to Cite?
Abstract

Dense time-series high-resolution satellite images are extremely valuable for long-term monitoring of land dynamics. Spatiotemporal fusion (STF) techniques have been developed to integrate multi-resolution satellite images to produce data with high spatial resolution and temporal frequency. Due to the large volume and diversity of higher resolution global Earth Observation (EO) data, large-scale data processing methods need to be computationally efficient, free of parameter fine-tuning, and adaptive to various data structures without process customization. These requirements are especially critical for the production of global Seamless Data Cube (SDC). Considering the limitations of existing STF methods, we propose a ROBust OpTimization-based (ROBOT) fusion model that exploits time-series information to obtain more accurate predictions. ROBOT maintains stable under varied data conditions by adopting a temporal-coherence regularization term. And being free of parameter tuning, ROBOT can be applied to arbitrary spatiotemporally distributed data without repetitive process customization. Its performance was compared with eight representative STF methods. Results show that ROBOT outperforms existing STF methods in most cases and is computationally efficient, about 4000-fold faster than ESTARFM and 600-fold faster than FSDAF. The proposed method has demonstrated its potential for global-scale SDC generation to support subsequent remote sensing applications.


Persistent Identifierhttp://hdl.handle.net/10722/331955
ISSN
2023 Impact Factor: 11.1
2023 SCImago Journal Rankings: 4.310
ISI Accession Number ID

 

DC FieldValueLanguage
dc.contributor.authorChen, Shuang-
dc.contributor.authorWang, Jie-
dc.contributor.authorGong, Peng-
dc.date.accessioned2023-09-28T04:59:51Z-
dc.date.available2023-09-28T04:59:51Z-
dc.date.issued2023-05-20-
dc.identifier.citationRemote Sensing of Environment, 2023, v. 294-
dc.identifier.issn0034-4257-
dc.identifier.urihttp://hdl.handle.net/10722/331955-
dc.description.abstract<p><span>Dense time-series high-resolution satellite images are extremely valuable for long-term monitoring of land dynamics. Spatiotemporal fusion (STF) techniques have been developed to integrate multi-resolution satellite images to produce data with </span><a href="https://www.sciencedirect.com/topics/earth-and-planetary-sciences/high-spatial-resolution" title="Learn more about high spatial resolution from ScienceDirect's AI-generated Topic Pages">high spatial resolution</a><span> and temporal frequency. Due to the large volume and diversity of higher resolution global Earth Observation (EO) data, large-scale data processing methods need to be computationally efficient, free of parameter fine-tuning, and adaptive to various data structures without process customization. These requirements are especially critical for the production of global Seamless Data Cube (SDC). Considering the limitations of existing STF methods, we propose a ROBust OpTimization-based (ROBOT) fusion model that exploits time-series information to obtain more accurate predictions. ROBOT maintains stable under varied data conditions by adopting a temporal-coherence regularization term. And being free of parameter tuning, ROBOT can be applied to arbitrary spatiotemporally distributed data without repetitive process customization. Its performance was compared with eight representative STF methods. Results show that ROBOT outperforms existing STF methods in most cases and is computationally efficient, about 4000-fold faster than ESTARFM and 600-fold faster than <a href="https://www.sciencedirect.com/topics/earth-and-planetary-sciences/multisensor-fusion" title="Learn more about FSDAF from ScienceDirect's AI-generated Topic Pages">FSDAF</a>. The proposed method has demonstrated its potential for global-scale SDC generation to support subsequent <a href="https://www.sciencedirect.com/topics/earth-and-planetary-sciences/remote-sensing-application" title="Learn more about remote sensing applications from ScienceDirect's AI-generated Topic Pages">remote sensing applications</a>.</span><br></p>-
dc.languageeng-
dc.publisherElsevier-
dc.relation.ispartofRemote Sensing of Environment-
dc.subjectComputing efficiency-
dc.subjectMissing data-
dc.subjectSeamless data cube-
dc.subjectSpatiotemporal fusion-
dc.subjectTime series-
dc.titleROBOT: A spatiotemporal fusion model toward seamless data cube for global remote sensing applications-
dc.typeArticle-
dc.identifier.doi10.1016/j.rse.2023.113616-
dc.identifier.scopuseid_2-s2.0-85159552844-
dc.identifier.volume294-
dc.identifier.isiWOS:001009494700001-
dc.identifier.issnl0034-4257-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats