Rapid reconstruction of temperature and salinity fields based on machine learning and the assimilation application

Abstract

Satellite observations play important roles in ocean operational forecasting systems, however, the direct assimilation of satellite observations cannot provide sufficient constraints on the model underwater structure. This study adopted the indirect assimilation method. First, we created a 3D temperature and salinity reconstruction model that took into account the advantage of the nonlinear regression of the generalized regression neural network with the fruit fly optimization (abbreviated as FOAGRNN). Compared with the reanalysis product and the WOA13 climatology data, the synthetic T/S (temperature and salinity) profiles had sufficient accuracy and could better describe the characteristics of mesoscale eddies. Then, the synthetic T/S profiles were assimilated into the Regional Ocean Model System (ROMS) using the Incremental Strong constraint 4D Variational (I4D-Var) data assimilation algorithm. The quantitative and qualitative analysis results indicated that compared with the direct assimilation of satellite observations, the root mean square errors (RMSEs) of temperature and salinity were reduced by 26.0% and 23.1% respectively by assimilating the synthetic T/S profiles. Furthermore, this method significantly improved the simulation effect of the model underwater structure, especially in the 300 m to 500 m water layer. Compared with the National Marine Data Center’s real-time analysis data, the machine learning-based assimilation system demonstrated a significant advantage in the simulation of underwater salinity structure, while showing a similar performance in the simulation of underwater temperature structure.

A Global Daily High Spatial-temporal Coverage Merged Tropospheric NO2 dataset (HSTCM-NO2) from 2007 to 2022 based on OMI and GOME-2

“…As there is strong correlation in terms of both geospatial relationships as well as retrieval approaches used to determine the VCDs between tropospheric NO2 obtained by different sensors (Wang et al, 2016;Park et al, 2020), 90 issues of spatial-temporal correlation need to be carefully taken into consideration, something that these previous approaches may not have fully considered. In this work, the machine-learning and Data Interpolating Empirical Orthogonal Functions (DINEOF) methods are selected to carry out the reconstruction, which take the advantages of both machine learning and pattern recognition in tandem, as demonstrated by previous studies reconstructing satellite chlorophyll-a data (Park et al, 2020b;Chang et al, 2017;Hilborn and Costa, 2018;Wang and Liu, 2013), filling in missing part of both sea and land surface 95 temperature data (Alvera-Azcárate et al, 2009;Zhou et al, 2017), analyzing sea surface salinity data (Alvera-Azcárate et al, 2016;Chen et al, 2022), and Jiang et al (2022) used DINEOF to reconstruct the XCO2 data of OCO-2 and OCO-3 by fusing the two effectively improving the spatiotemporal coverage of XCO2 products. This research aims to accurately and precisely reconstruct the tropospheric NO2 VCD at daily time resolution and grid-by-grid spatial resolution using OMI 2007-2022.…”