Classification of the global Sentinel-1 SAR vignettes for ocean surface process studies

REMOTE SENSING OF ENVIRONMENT

卷:234

Article

Wang, Chen^1,2  Tandeo, Pierre²  Mouche, Alexis¹  Stopa, Justin E.³  Gressani, Victor¹  Longepe, Nicolas⁴  Vandemark, Douglas⁵  Foster, Ralph C.⁶  Chapron, Bertrand¹ 

[1] Univ Brest, CNRS, IFREMER, IRD,LOPS, Brest, France

[2] UBL, Lab STICC, IMT Atlantique, Brest, France

[3] Univ Hawaii Manoa, Dept Ocean Resources & Engn, Honolulu, HI 96822 USA

[4] CLS, Space & Ground Segment, Plouzane, France

[5] Univ New Hampshire, Ocean Proc Anal Lab, Durham, NH 03824 USA

[6] Univ Washington, Appl Phys Lab, Seattle, WA 98105 USA

关键词: Synthetic aperture radar (SAR);    Ocean surface phenomena;    Sentinel-1 wave mode;    Deep learning;    Convolutional neural network (CNN);    Image classification;   

DOI  :  10.1016/j.rse.2019.111457

来源: Elsevier

【 摘 要 】

Spaceborne synthetic aperture radar (SAR) can provide finely-resolved (meters-scale) images of ocean surface roughness day-or-night in nearly all weather conditions. This makes it a unique asset for many geophysical applications. Initially designed for the measurement of directional ocean wave spectra, Sentinel-1 SAR wave mode (WV) vignettes are small 20 km scenes that have been collected globally since 2014. Recent WV data exploration reveals that many important oceanic and atmospheric phenomena are also well captured, but not yet employed by the scientific community. However, expanding applications of this whole massive dataset beyond ocean waves requires a strategy to automatically identify these geophysical phenomena. In this study, we propose to apply the emerging deep learning approach in ocean SAR scenes classification. The training is performed using a hand-curated dataset that describes ten commonly-occurring atmospheric or oceanic processes. Our model evaluation relies on an independent assessment dataset and shows satisfactory and robust classification results. To further illustrate the model performance, regional patterns of rain and sea ice are qualitatively analyzed and found to be very consistent with independent remote sensing datasets. In addition, these high-resolution WV SAR data can resolve fine, sub-km scale, spatial structure of rain events and sea ice that complement other satellite measurements. Overall, such automated SAR vignettes classification may open paths for broader geophysical application of maritime Sentinel-1 acquisitions.

【 授权许可】

Free