Machine learning approach to reconstructing high-resolution ocean subsurface salinity datasets

Earth System Science Data (2022). DOI: 10.5194/essd-14-5037-2022″ width=”800″ height=”398″/>

The estimated Var (a quantification of subgrid salinity variability) of in situ observations in this study. The original (a, c) and objectively analyzed fields (b, d) are presented for the depths of 20 m (a, b) and 300 m (c, d), respectively, as two examples. Credit: Earth System Science Data (2022). DOI: 10.5194/essd-14-5037-2022

As a key parameter of ocean water, salinity plays a crucial role in regulating ocean density, stratification, and circulation. It also indicates the link between ocean, atmosphere and land through the water cycle. Gridded ocean datasets with complete global ocean coverage are important for ocean and climate research.

Currently, most are due to the sparsity of in situ observations salinity in the sea gridded products are at 1° × 1° horizontal resolution, which is insufficient to meet the requirements of small ocean information research.

Recently, researchers from the Institute of Atmospheric Physics (IAP) of the Chinese Academy of Sciences reported a high-resolution (0.25° × 0.25°) ocean surface (1–2000 m) salinity dataset for the period 1993-2018 using a machine learning method called a feed-forward neural network.

The study was published in Earth System Science Data on Nov. 18.

The study combines in-situ salinity profile observations with high-resolution (0.25° × 0.25°) satellite remote sensing altimetry absolute dynamic topography, sea ​​surface temperaturesea ​​surface wind field data and a coarse resolution (1° × 1°) gridded salinity product.

“The IAP1° gridded salinity dataset was formally released in 2020. Two years later, we developed the new 0.25° × 0.25° reconstruction dataset, or what we call IAP0.25°,” said Prof. Cheng Lijing, corresponding author of the study.

Compared to the available IAP 1° × 1° resolution product, the new data set shows more realistic spatial signals in regions with strong mesoscale variations, e.g. Gulf Stream, Kuroshio and Antarctic Circumpolar Current regions. “This indicates the effectiveness of the machine learning approach to bring satellite observations along with in-situ observations,” Prof. Cheng said.

According to the study, the large-scale salinity patterns from IAP0.25° are consistent with the IAP1° gridded salinity field, suggesting that the large-scale signals persist in the high-resolution reconstruction. The SHAP method is also used to evaluate the effects of different inputs on the reconstruction of IAP0.25°.

More information:
The new IAP0.25° dataset is available at:…466faec736da916b5106

Tian Tian et al., Reconstructing ocean subsurface salinity at high resolution using a machine learning approach, Earth System Science Data (2022). DOI: 10.5194/essd-14-5037-2022

Citation: Machine learning approach to reconstructing high-resolution subsurface ocean salinity data sets (2022, December 5) retrieved December 5, 2022 from -ocean. html

This document is subject to copyright. Except for any fair dealing for the purpose of private study or research, no part may be reproduced without written permission. The content is provided for informational purposes only.

Related Articles

Leave a Reply

Your email address will not be published. Required fields are marked *

Back to top button