10 Jul 2023
 | 10 Jul 2023
Status: this preprint is currently under review for the journal ESSD.

A global daily gap-filled chlorophyll-a dataset in open oceans during 2001–2021 from multisource information using convolutional neural networks

Zhongkun Hong, Di Long, Xingdong Li, Yiming Wang, Jianmin Zhang, Hamouda Abdelmoghny Mohamed, and Mohamed Mostafa Ahmed Mohamed

Abstract. Ocean color data are essential for developing our understanding of biological and ecological phenomena and processes, and also important sources of input for physical and biogeochemical ocean models. Chlorophyll-a (Chl-a) is a critical variable of ocean color in the marine environment. Quantitative retrieval from satellite remote sensing is a main way to obtain large-scale oceanic Chl-a. However, data missing is a major limitation in satellite remote sensing-based Chl-a products, due mostly to the influence of cloud, sun glint contamination, and high satellite viewing angles. The common methods to reconstruct (gap filling) missing data often consider spatiotemporal information of initial images alone, such as data interpolation empirical orthogonal function, optimal interpolation, Kriging interpolation, and extended Kalman filter. However, these methods do not perform well in the presence of large-scale missing values in the image and ignore the potential of other information on missing pixels in the data reconstruction. Here we developed a convolutional neural network (CNN) named OCNET for Chl-a concentration data reconstruction in open ocean areas, considering environmental variables that are associated with ocean phytoplankton growth and distribution. Sea surface temperature (SST), salinity (SAL), photosynthetically active radiation (PAR), and sea surface pressure (SSP) from reanalysis data and satellite observations were selected as the input of OCNET to correlate with the environment and phytoplankton mass. The developed OCNET model achieves good performance in the reconstruction of global ocean Chl-a concentration data, and captures temporal variations of these features. This study also shows the potential of machine learning in large-scale ocean color data reconstruction and offers the possibility to predict Chl-a concentration trends under a changing environment.

Zhongkun Hong et al.

Status: final response (author comments only)

Comment types: AC – author | RC – referee | CC – community | EC – editor | CEC – chief editor | : Report abuse
  • RC1: 'Comment on essd-2023-257', Anonymous Referee #1, 05 Aug 2023
    • CC2: 'Reply on RC1', Zhongkun Hong, 18 Aug 2023
  • CC1: 'Comment on essd-2023-257', Andrew C. Ross, 17 Aug 2023
    • CC3: 'Reply on CC1', Zhongkun Hong, 18 Aug 2023
  • RC2: 'Comment on essd-2023-257', Anonymous Referee #2, 26 Sep 2023

Zhongkun Hong et al.

Data sets

OCNET global daily Chlorophyll-a products Zhongkun Hong, Di Long, Xingdong Li, Yiming Wang, Jianmin Zhang, Mohamed A. Hamouda, and Mohamed M. Mohamed

Zhongkun Hong et al.


Total article views: 465 (including HTML, PDF, and XML)
HTML PDF XML Total BibTeX EndNote
335 107 23 465 7 13
  • HTML: 335
  • PDF: 107
  • XML: 23
  • Total: 465
  • BibTeX: 7
  • EndNote: 13
Views and downloads (calculated since 10 Jul 2023)
Cumulative views and downloads (calculated since 10 Jul 2023)

Viewed (geographical distribution)

Total article views: 439 (including HTML, PDF, and XML) Thereof 439 with geography defined and 0 with unknown origin.
Country # Views %
  • 1
Latest update: 02 Oct 2023
Short summary
Changes in ocean chlorophyll-a (Chl-a) concentration are related to ecosystem balance. Here, we present high-quality gap-filled Chl-a data in open oceans, reflecting the distribution and changes in global Chl-a concentration. Our findings highlight the efficacy of reconstructing missing satellite observations using convolutional neural networks. This dataset and model are valuable for research in ocean color remote sensing, offering data support and methodological references for related studies.