Unsupervised Optical Classification of the Seabed Color in Shallow Oligotrophic Waters from Sentinel-2 Images: A Case Study in the Voh-Koné-Pouembout Lagoon (New Caledonia)

Remote Sensing

Farid Juillot¹  Guillaume Wattelez²  Cécile Dupouy³ 

[1] Centre IRD Noumea, Noumea 98848, New Caledonia;Interdisciplinary Laboratory for Research in Education, EA 7483, University of New Caledonia, Avenue James Cook, Noumea 98800, New Caledonia;Mediterranean Institute of Oceanography (MIO), Aix-Marseille Université, CNRS/INSU, Université de Toulon, IRD, UM 110, 13288 Marseille, France;

关键词: seabed mapping;    clustering;    machine learning;    k-means;    tropical lagoon;    Sentinel-2;   

DOI  :  10.3390/rs14040836

来源: DOAJ

【 摘 要 】

Monitoring chlorophyll-a concentration or turbidity is crucial for understanding and managing oligo- to mesotrophic coastal waters quality. However, mapping bio-optical components from space in such shallow settings remains challenging because of the strong interference of the complex bathymetry and various seabed colors. Correcting the total satellite reflectance signal from the seabed reflectance in ocean color with high resolution sensors is promising. This article shows how unsupervised clustering approaches can be applied to Sentinel-2 images to classify seabed colors in shallow waters of a tropical oligotrophic lagoon in New Caledonia. Data processing included Lyzenga correction for estimating the water column reflectance, optical spectra standardization for attenuating water absorption effects and clustering using the unsupervised k-means method. This methodological approach was applied on the 497, 560, 664 and 704 nm optical bands of the selected Sentinel-2 image. When applied on non-standardized data, our unsupervised classification retrieved three seafloor clusters, whereas five seafloor clusters could be retrieved using standardized data. For each of these two trials, the computed membership values explained more than 75% of the inertia in each Sentinel-2 wavelength band used for the clustering. However, the accuracy of the method was slightly improved when applied on standardized data. Confusion index mapping of the unsupervised clustering retrieved from these data emphasized the relevance and robustness of our methodological approach. Such an approach for seabed colors classification in optically complex shallow settings will be particularly helpful to improve remote sensing of biogeochemical indicators such as chlorophyll-a concentration and turbidity in fragile coastal environments.

【 授权许可】

Unknown