AUTHOR=Chen Yuanhong , Liu Li , Chen Xueen , Wei Zhiqiang , Sun Xiang , Yuan Chunxin , Gao Zhen 

TITLE=Data driven three-dimensional temperature and salinity anomaly reconstruction of the northwest Pacific Ocean

JOURNAL=Frontiers in Marine Science

VOLUME=Volume 10 - 2023

YEAR=2023

URL=https://www.frontiersin.org/journals/marine-science/articles/10.3389/fmars.2023.1121334

DOI=10.3389/fmars.2023.1121334

ISSN=2296-7745

ABSTRACT=By virtue of the rapid development of ocean observation technologies, tens of petabytes of data archives have been recorded, among which, the largest portion are those derived from the orbital satellites, embodying the character of ocean surface. Nevertheless, the insufficiency of information below the subsurface restricts the utilization of these data and the understanding of ocean dynamics. To circumvent these difficulties, we present the spatially three-dimensional reconstruction of ocean hydrographic profiles at depth based on the satellites and in-situ measurement data. In this manuscript, long short-term memory network (LSTM) and Gaussian process regression (GPR) methods are invoked to predict the temperature and salinity profiles in the northwest Pacific Ocean, which show satisfactory results, with the root mean square error (RMSE) of temperature is less than 1.45, and the RMSE of salinity is less than 0.19. Nonetheless, the large volume of data results in a high cost of computation and storage, and to improve this, the proper orthogonal decomposition (POD) method is subtly incorporated into these two models. The incorporation of POD method, sufficiently accelerates efficiency, while the speed improvement is more prominent in LSTM, with an improvement of 7.5 folds in general, but without much loss of accuracy.  The sensitivity of different sea surface parameters on the reconstructed profiles reveals that sea surface height anomaly and latitude significantly influence the reconstruction of  temperature anomaly (TA) and salinity anomaly (SA) profiles. Besides, sea surface salinity and sea surface temperature anomalies can improve the model's estimation ability for the upper TAs and SAs, respectively. The contribution of monthly climatology to temperature and salinity profile estimation is also explored in this paper. It is shown that adding monthly mean climatology to the input of the model can achieve more accurate estimates.