Multi-source deep data fusion and super-resolution for downscaling sea surface temperature guided by Generative Adversarial Network-based spatiotemporal dependency learning
In this study, we propose a deep learning framework for multi-source deep data fusion and super-resolution for generative adversarial network-based spatiotemporal dependency learning to produce accurately downscaled sea surface temperature (SST) through simultaneously achieving error correction and...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2023-05-01
|
| Series: | International Journal of Applied Earth Observations and Geoinformation |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S1569843223001346 |
| _version_ | 1827948787921846272 |
|---|---|
| author | Jinah Kim Taekyung Kim Joon-Gyu Ryu |
| author_facet | Jinah Kim Taekyung Kim Joon-Gyu Ryu |
| author_sort | Jinah Kim |
| collection | DOAJ |
| description | In this study, we propose a deep learning framework for multi-source deep data fusion and super-resolution for generative adversarial network-based spatiotemporal dependency learning to produce accurately downscaled sea surface temperature (SST) through simultaneously achieving error correction and improvement of spatial resolution. The proposed method is applied to the global ocean and the Korean waters, which is a regional sea, and experiments are conducted to downscale the SST by 2.5 and 5 times, respectively. The multi-source SST data used are numerical reanalysis, multiple satellite composites, and in-situ measurements, and two loss functions of super-resolution and mean square error are applied for adversarial learning. For more reliable performance evaluation, spatially, the global ocean and Korean waters are divided into a number of regional seas classified by characteristics of ocean physics, and temporally, the overall test period is divided into seasons and when extreme events occur. The overall results showed good performance for most experiments when both error correction through data fusion and spatiotemporal dependency learning from consecutive multiple input sequences using low-resolution reanalysis data, high-resolution satellite composite, and in-situ measurements were performed. However, for summer, winter, or extreme event periods, high performance was shown when using low-resolution satellite composite data with the same modality as the target data was used as an input. Furthermore, as a result of a blind test on the trained model with high-resolution target data used as target for the test period as input, the model that learned spatiotemporal dependency learning with error correction through data fusion showed the best and most consistent generalized downscaling performance compared to the test performance. |
| first_indexed | 2024-04-09T13:00:21Z |
| format | Article |
| id | doaj.art-519759c804074a5eb30fa54cf336b53e |
| institution | Directory Open Access Journal |
| issn | 1569-8432 |
| language | English |
| last_indexed | 2024-04-09T13:00:21Z |
| publishDate | 2023-05-01 |
| publisher | Elsevier |
| record_format | Article |
| series | International Journal of Applied Earth Observations and Geoinformation |
| spelling | doaj.art-519759c804074a5eb30fa54cf336b53e2023-05-13T04:24:34ZengElsevierInternational Journal of Applied Earth Observations and Geoinformation1569-84322023-05-01119103312Multi-source deep data fusion and super-resolution for downscaling sea surface temperature guided by Generative Adversarial Network-based spatiotemporal dependency learningJinah Kim0Taekyung Kim1Joon-Gyu Ryu2Coastal Disaster Research Center, Korea Institute of Ocean Science and Technology, Busan, 49111, South Korea; Corresponding author.Coastal Disaster Research Center, Korea Institute of Ocean Science and Technology, Busan, 49111, South KoreaSatellite Wide area Infra Research Section, Electronics and Telecommunications Research Institute, Daejeon, 34129, South KoreaIn this study, we propose a deep learning framework for multi-source deep data fusion and super-resolution for generative adversarial network-based spatiotemporal dependency learning to produce accurately downscaled sea surface temperature (SST) through simultaneously achieving error correction and improvement of spatial resolution. The proposed method is applied to the global ocean and the Korean waters, which is a regional sea, and experiments are conducted to downscale the SST by 2.5 and 5 times, respectively. The multi-source SST data used are numerical reanalysis, multiple satellite composites, and in-situ measurements, and two loss functions of super-resolution and mean square error are applied for adversarial learning. For more reliable performance evaluation, spatially, the global ocean and Korean waters are divided into a number of regional seas classified by characteristics of ocean physics, and temporally, the overall test period is divided into seasons and when extreme events occur. The overall results showed good performance for most experiments when both error correction through data fusion and spatiotemporal dependency learning from consecutive multiple input sequences using low-resolution reanalysis data, high-resolution satellite composite, and in-situ measurements were performed. However, for summer, winter, or extreme event periods, high performance was shown when using low-resolution satellite composite data with the same modality as the target data was used as an input. Furthermore, as a result of a blind test on the trained model with high-resolution target data used as target for the test period as input, the model that learned spatiotemporal dependency learning with error correction through data fusion showed the best and most consistent generalized downscaling performance compared to the test performance.http://www.sciencedirect.com/science/article/pii/S1569843223001346Sea surface temperatureDownscalingSuper-resolutionDeep data fusionSpatiotemporal dependency learningGenerative adversarial network |
| spellingShingle | Jinah Kim Taekyung Kim Joon-Gyu Ryu Multi-source deep data fusion and super-resolution for downscaling sea surface temperature guided by Generative Adversarial Network-based spatiotemporal dependency learning International Journal of Applied Earth Observations and Geoinformation Sea surface temperature Downscaling Super-resolution Deep data fusion Spatiotemporal dependency learning Generative adversarial network |
| title | Multi-source deep data fusion and super-resolution for downscaling sea surface temperature guided by Generative Adversarial Network-based spatiotemporal dependency learning |
| title_full | Multi-source deep data fusion and super-resolution for downscaling sea surface temperature guided by Generative Adversarial Network-based spatiotemporal dependency learning |
| title_fullStr | Multi-source deep data fusion and super-resolution for downscaling sea surface temperature guided by Generative Adversarial Network-based spatiotemporal dependency learning |
| title_full_unstemmed | Multi-source deep data fusion and super-resolution for downscaling sea surface temperature guided by Generative Adversarial Network-based spatiotemporal dependency learning |
| title_short | Multi-source deep data fusion and super-resolution for downscaling sea surface temperature guided by Generative Adversarial Network-based spatiotemporal dependency learning |
| title_sort | multi source deep data fusion and super resolution for downscaling sea surface temperature guided by generative adversarial network based spatiotemporal dependency learning |
| topic | Sea surface temperature Downscaling Super-resolution Deep data fusion Spatiotemporal dependency learning Generative adversarial network |
| url | http://www.sciencedirect.com/science/article/pii/S1569843223001346 |
| work_keys_str_mv | AT jinahkim multisourcedeepdatafusionandsuperresolutionfordownscalingseasurfacetemperatureguidedbygenerativeadversarialnetworkbasedspatiotemporaldependencylearning AT taekyungkim multisourcedeepdatafusionandsuperresolutionfordownscalingseasurfacetemperatureguidedbygenerativeadversarialnetworkbasedspatiotemporaldependencylearning AT joongyuryu multisourcedeepdatafusionandsuperresolutionfordownscalingseasurfacetemperatureguidedbygenerativeadversarialnetworkbasedspatiotemporaldependencylearning |