Abstract
Sea surface salinity (SSS) is a key physicochemical characteristic of the ocean that plays a significant role in describing the climate. Routine SSS retrieval algorithms exploiting remote sensing data have been developed and validated with high precision for typical regions of the World Ocean. Their effectiveness is worse in the Arctic though. To address this limitation, in this study, we employ machine learning (ML) techniques to enhance the quality of standard algorithms. We evaluate a few ML models, ranging from classical methods that process vector features, provided by standard Soil Moisture Active Passive (SMAP) satellite salinity algorithms, to deep artificial neural networks that combine vector features with two-dimensional fields extracted from the ERA5 reanalysis. We validate these models using in situ the data collected by the Shirshov Institute of Oceanology RAS during the expeditions to the Barents, Kara, Laptev, and East Siberian seas from 2015 to 2021. The results of the study indicate that the SMAP sea surface salinity standard product is improved in these regions. The ML models developed in this study make it possible to further study the Arctic region using enhanced sea surface salinity maps.
REFERENCES
P. J. Durack, T. Lee, N. T. Vinogradova, and D. Stammer, Nat. Clim. Change 6, 228 (2016). https://doi.org/10.1038/nclimate2946
E. C. Carmack, Deep Sea Res., Part II 54, 2578 (2007). https://doi.org/10.1016/j.dsr2.2007.08.018
E. P. Dinnat, D. M. Le Vine, J. Boutin, et al., Remote Sens. 11, 750 (2019). https://doi.org/10.3390/rs11070750
N. Reul, S. A. Grodsky, M. Arias, et al., Remote Sens. Environ. 242, 111769 (2020). https://doi.org/10.1016/j.rse.2020.111769
A. Supply, J. Boutin, J.-L. Vergely, et al., Remote Sens. Environ. 249, 112027 (2020). https://doi.org/10.1016/j.rse.2020.112027
S. Qin, H. Wang, J. Zhu, et al., Acta Oceanol. Sin. 39, 148 (2020). https://doi.org/10.1007/s13131-020-1533-0
W. Tang, S. Yueh, D. Yang, et al., Remote Sens. 10, 869 (2018). https://doi.org/10.3390/rs10060869
E. C. Carmack, M. Yamamoto-Kawai, T. W. N. Haine, et al., J. Geophys. Res. Biogeosci. 121, 675 (2016). https://doi.org/10.1002/2015JG003140
A. Matsuoka, M. Babin, and E. C. Devred, Remote Sens. Environ. 184, 124 (2016). https://doi.org/10.1016/j.rse.2016.05.006
E. Jang, Y. J. Kim, J. Im, and Y.-G. Park, GIScience Remote Sens. 58, 138 (2021). https://doi.org/10.1080/15481603.2021.1872228
D. Cho, C. Yoo, J. Im, et al., GIScience Remote Sens. 57, 633 (2020). https://doi.org/10.1080/15481603.2020.1766768
T. D. Pham, K. Yoshino, and D. T. Bui, GIScience Remote Sens. 54, 329 (2017). https://doi.org/10.1080/15481603.2016.1269869
L. Breiman, Mach. Learn. 45, 5 (2001). https://doi.org/10.1023/A:1010933404324
F. Pedregosa, G. Varoquaux, A. Gramfort, et al., J. Mach. Learn. Res. 12, 2825 (2011).
A. V. Dorogush, V. Ershov, and A. Gulin, arXiv Preprint (2018). https://doi.org/10.48550/arXiv.1810.11363
T. Akiba, S. Sano, T. Yanase, et al., in Proc. 25th ACM SIGKDD Int. Conf. on Knowledge Discovery and Data Mining, Anchorage, Alaska, 2019 (Association for Computing Machinery, New York, 2019), pp. 2623–2631. https://doi.org/10.1145/3292500.3330701
A. Paszke, S. Gross, F. Massa, et al., in 2019 Fifth Workshop on Energy Efficient Machine Learning and Cognitive Computing–NeurIPS Edition (EMC2-NIPS 2019), Ed. by H. Wallach, H. Larochelle, A. Beygelzimer, F. d’Alché-Buc, E. Fox, and R. Garnett (IEEE, Vancouver, British Columbia, Canada, 2019), p. 8024.
Funding
This research was funded by the Moscow Institute of Physics and Technology Development Program (Priority-2030) (numerical modelling) and the Russian Science Foundation, research project 23-17-00087 (processing of in situ data).
Author information
Authors and Affiliations
Corresponding authors
Ethics declarations
The authors of this work declare that they have no conflicts of interest.
Additional information
Publisher’s Note.
Allerton Press remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
About this article
Cite this article
Savin, A.S., Krinitskiy, M.A. & Osadchiev, A.A. SMAP Sea Surface Salinity Improvement in the Arctic Region Using Machine Learning Approaches. Moscow Univ. Phys. 78 (Suppl 1), S210–S216 (2023). https://doi.org/10.3103/S0027134923070299
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.3103/S0027134923070299