High-Resolution Sea Surface Temperature and Salinity in Coastal Areas Worldwide from Raw Satellite Data

Abstract

The aim of this work is to obtain high-resolution values of sea surface salinity (SSS) and temperature (SST) in the global ocean by using raw satellite data (i.e., without any band data pre-processing or atmospheric correction). Sentinel-2 Level 1-C Top of Atmosphere (TOA) reflectance data is used to obtain accurate SSS and SST information. A deep neural network is built to link the band information with in situ data from different buoys, vessels, drifters, and other platforms around the world. The neural network used in this paper includes shortcuts, providing an improved performance compared with the equivalent feed-forward architecture. The in situ information used as input for the network has been obtained from the Copernicus Marine In situ Service. Sentinel-2 platform-centred band data has been processed using Google Earth Engine in areas of 100 m × 100 m. Accurate salinity values are estimated for the first time independently of temperature. Salinity results rely only on direct satellite observations, although it presented a clear dependency on temperature ranges. Results show the neural network has good interpolation and extrapolation capabilities. Test results present correlation coefficients of 82 % and 84 % for salinity and temperature, respectively. The most common error for both SST and SSS is 0.4 ∘ C and 0 . 4 PSU. The sensitivity analysis shows that outliers are present in areas where the number of observations is very low. The network is finally applied over a complete Sentinel-2 tile, presenting sensible patterns for river-sea interaction, as well as seasonal variations. The methodology presented here is relevant for detailed coastal and oceanographic applications, reducing the time for data pre-processing, and it is applicable to a wide range of satellites, as the information is directly obtained from TOA data.

Google Earth Engine Cloud Computing Platform for Remote Sensing Big Data Applications: A Comprehensive Review

“…Publicly available datasets within GEE along with its high computing performance allow for accurate monitoring of water resources with adequate temporal and spatial resolutions. Consequently, GEE was efficiently employed for surface water dynamics monitoring [93], [94], bathymetry [20], [95], shoreline and coastal studies [96], [97], lake and reservoir mapping and monitoring [98], [99], glacier studies [90], [100], snow ablation and snow mapping [92], [101], suspended sediments and river studies [102], [103], and water health assessment [104], [105]. For instance, [93] introduced a fully automatic method for water extraction in New Zealand.…”

Machine Learning and the End of Atmospheric Corrections: A Comparison between High-Resolution Sea Surface Salinity in Coastal Areas from Top and Bottom of Atmosphere Sentinel-2 Imagery

“…A total of approximately 2700 points (of an initial batch of about 25,000, pre-filtering) with global coverage were finally used for the May 2017-2020 period. This amount of information is less than that used in previous work (see, e.g., in [22]), however the optimal tuning of the neural network presented in this paper provides better results, even with the reduced a dataset.…”

“…The methodology follows that introduced in [22]. In situ data have been downloaded from the Copernicus Marine Environmental Monitoring Service (CMEMS) [25].…”

“…This paper explores the differences in data-driven methods using L1C and L2A Sentinel-2 imagery to estimate sea surface salinity (SSS) in coastal areas. SSS estimation from Sentinel-2 L1C TOA data in [22] followed research from in [23] to estimate SSS from multispectral sources, including high-resolution results, worldwide coverage for coastal areas and independence from sea temperature in the SSS estimation. Results in [22] showed a good agreement between multispectral properties and salinity content, with a coefficient of determination above 80% and most common errors around 0.4 PSU.…”

“…SSS estimation from Sentinel-2 L1C TOA data in [22] followed research from in [23] to estimate SSS from multispectral sources, including high-resolution results, worldwide coverage for coastal areas and independence from sea temperature in the SSS estimation. Results in [22] showed a good agreement between multispectral properties and salinity content, with a coefficient of determination above 80% and most common errors around 0.4 PSU. The present paper takes the next step by providing a comparison between SSS derived by atmospherically corrected and TOA imagery, aiming at starting a discussion about the need for atmospheric corrections when machine learning is used to link satellite and in situ data.…”