Deep Learning-Based Spatiotemporal Fusion Architecture of Landsat 8 and Sentinel-2 Data for 10 m Series Imagery.
Saved in:
| Title: | Deep Learning-Based Spatiotemporal Fusion Architecture of Landsat 8 and Sentinel-2 Data for 10 m Series Imagery. |
|---|---|
| Authors: | Cheng, Qing1 (AUTHOR) qingcheng@whu.edu.cn, Xie, Ruixiang1 (AUTHOR) 1725303065@cug.edu.cn, Wu, Jingan2 (AUTHOR) wujg5@mail.sysu.edu.cn, Ye, Fan1 (AUTHOR) yefan@cug.edu.cn |
| Source: | Remote Sensing. Mar2024, Vol. 16 Issue 6, p1033. 21p. |
| Subjects: | Landsat satellites, Scale-free network (Statistical physics), Surface of the earth, Feature extraction, Land cover |
| Abstract: | Medium- to high-resolution imagery is indispensable for various applications. Combining images from Landsat 8 and Sentinel-2 can improve the accuracy of observing dynamic changes on the Earth's surface. Many researchers use Sentinel-2 10 m resolution data in conjunction with Landsat 8 30 m resolution data to generate 10 m resolution data series. However, current fusion techniques have some algorithmic weaknesses, such as simple processing of coarse or fine images, which fail to extract image features to the fullest extent, especially in rapidly changing land cover areas. Facing the aforementioned limitations, we proposed a multiscale and attention mechanism-based residual spatiotemporal fusion network (MARSTFN) that utilizes Sentinel-2 10 m resolution data and Landsat 8 15 m resolution data as auxiliary data to upgrade Landsat 8 30 m resolution data to 10 m resolution. In this network, we utilized multiscale and attention mechanisms to extract features from coarse and fine images separately. Subsequently, the features outputted from all input branches are combined and further feature information is extracted through residual networks and skip connections. Finally, the features obtained from the residual network are merged with the feature information of the coarsely processed images from the multiscale mechanism to generate accurate prediction images. To assess the efficacy of our model, we compared it with existing models on two datasets. Results demonstrated that our fusion model outperformed baseline methods across various evaluation indicators, highlighting its ability to integrate Sentinel-2 and Landsat 8 data to produce 10 m resolution data. [ABSTRACT FROM AUTHOR] |
| Copyright of Remote Sensing is the property of MDPI and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) | |
| Database: | Engineering Source |
|
Full text is not displayed to guests.
Login for full access.
|
|
| FullText | Links: – Type: pdflink Text: Availability: 1 |
|---|---|
| Header | DbId: egs DbLabel: Engineering Source An: 176366604 AccessLevel: 6 PubType: Academic Journal PubTypeId: academicJournal PreciseRelevancyScore: 0 |
| IllustrationInfo | |
| Items | – Name: Title Label: Title Group: Ti Data: Deep Learning-Based Spatiotemporal Fusion Architecture of Landsat 8 and Sentinel-2 Data for 10 m Series Imagery. – Name: Author Label: Authors Group: Au Data: <searchLink fieldCode="AR" term="%22Cheng%2C+Qing%22">Cheng, Qing</searchLink><relatesTo>1</relatesTo> (AUTHOR)<i> qingcheng@whu.edu.cn</i><br /><searchLink fieldCode="AR" term="%22Xie%2C+Ruixiang%22">Xie, Ruixiang</searchLink><relatesTo>1</relatesTo> (AUTHOR)<i> 1725303065@cug.edu.cn</i><br /><searchLink fieldCode="AR" term="%22Wu%2C+Jingan%22">Wu, Jingan</searchLink><relatesTo>2</relatesTo> (AUTHOR)<i> wujg5@mail.sysu.edu.cn</i><br /><searchLink fieldCode="AR" term="%22Ye%2C+Fan%22">Ye, Fan</searchLink><relatesTo>1</relatesTo> (AUTHOR)<i> yefan@cug.edu.cn</i> – Name: TitleSource Label: Source Group: Src Data: <searchLink fieldCode="JN" term="%22Remote+Sensing%22">Remote Sensing</searchLink>. Mar2024, Vol. 16 Issue 6, p1033. 21p. – Name: Subject Label: Subjects Group: Su Data: <searchLink fieldCode="DE" term="%22Landsat+satellites%22">Landsat satellites</searchLink><br /><searchLink fieldCode="DE" term="%22Scale-free+network+%28Statistical+physics%29%22">Scale-free network (Statistical physics)</searchLink><br /><searchLink fieldCode="DE" term="%22Surface+of+the+earth%22">Surface of the earth</searchLink><br /><searchLink fieldCode="DE" term="%22Feature+extraction%22">Feature extraction</searchLink><br /><searchLink fieldCode="DE" term="%22Land+cover%22">Land cover</searchLink> – Name: Abstract Label: Abstract Group: Ab Data: Medium- to high-resolution imagery is indispensable for various applications. Combining images from Landsat 8 and Sentinel-2 can improve the accuracy of observing dynamic changes on the Earth's surface. Many researchers use Sentinel-2 10 m resolution data in conjunction with Landsat 8 30 m resolution data to generate 10 m resolution data series. However, current fusion techniques have some algorithmic weaknesses, such as simple processing of coarse or fine images, which fail to extract image features to the fullest extent, especially in rapidly changing land cover areas. Facing the aforementioned limitations, we proposed a multiscale and attention mechanism-based residual spatiotemporal fusion network (MARSTFN) that utilizes Sentinel-2 10 m resolution data and Landsat 8 15 m resolution data as auxiliary data to upgrade Landsat 8 30 m resolution data to 10 m resolution. In this network, we utilized multiscale and attention mechanisms to extract features from coarse and fine images separately. Subsequently, the features outputted from all input branches are combined and further feature information is extracted through residual networks and skip connections. Finally, the features obtained from the residual network are merged with the feature information of the coarsely processed images from the multiscale mechanism to generate accurate prediction images. To assess the efficacy of our model, we compared it with existing models on two datasets. Results demonstrated that our fusion model outperformed baseline methods across various evaluation indicators, highlighting its ability to integrate Sentinel-2 and Landsat 8 data to produce 10 m resolution data. [ABSTRACT FROM AUTHOR] – Name: AbstractSuppliedCopyright Label: Group: Ab Data: <i>Copyright of Remote Sensing is the property of MDPI and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract.</i> (Copyright applies to all Abstracts.) |
| PLink | https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=egs&AN=176366604 |
| RecordInfo | BibRecord: BibEntity: Identifiers: – Type: doi Value: 10.3390/rs16061033 Languages: – Code: eng Text: English PhysicalDescription: Pagination: PageCount: 21 StartPage: 1033 Subjects: – SubjectFull: Landsat satellites Type: general – SubjectFull: Scale-free network (Statistical physics) Type: general – SubjectFull: Surface of the earth Type: general – SubjectFull: Feature extraction Type: general – SubjectFull: Land cover Type: general Titles: – TitleFull: Deep Learning-Based Spatiotemporal Fusion Architecture of Landsat 8 and Sentinel-2 Data for 10 m Series Imagery. Type: main BibRelationships: HasContributorRelationships: – PersonEntity: Name: NameFull: Cheng, Qing – PersonEntity: Name: NameFull: Xie, Ruixiang – PersonEntity: Name: NameFull: Wu, Jingan – PersonEntity: Name: NameFull: Ye, Fan IsPartOfRelationships: – BibEntity: Dates: – D: 15 M: 03 Text: Mar2024 Type: published Y: 2024 Identifiers: – Type: issn-print Value: 20724292 Numbering: – Type: volume Value: 16 – Type: issue Value: 6 Titles: – TitleFull: Remote Sensing Type: main |
| ResultId | 1 |
