Improving satellite retrieval of oceanic particulate organic carbon concentrations using machine learning methods

Huizeng Liu, Qingquan Li, Yan Bai, Chao Yang, Junjie Wang, Qiming ZHOU, Shuibo Hu, Tiezhu Shi, Xiaomei Liao, Guofeng Wu*

*Corresponding author for this work

Research output: Contribution to journalJournal articlepeer-review

49 Citations (Scopus)


Particulate organic carbon (POC) plays vital roles in marine carbon cycle, serving as a part of “biological pump” moving carbon to the deep ocean. The blue-to-green band ratio algorithm is applied operationally to derive POC concentrations in global oceans; it, however, tends to underestimate high values in optically complex waters. With an attempt to develop accurate and robust oceanic POC models, this study aimed to explore machine learning methods in satellite retrieval of POC concentrations. Three machine learning methods, i.e. extreme gradient boosting (XGBoost), support vector machine (SVM) and artificial neural network (ANN), were tested, and the recursive feature elimination (RFE) method was employed to identify sensitive features. Matchups of global in situ POC measurements and Ocean Colour Climate Change Initiative (OC-CCI) products were used to train and evaluate POC models. Results showed that machine learning methods produced obvious better performance than the blue-to-green band ratio algorithm, and XGBoost was the most robust among the tested three machine learning methods. However, the blue-to-green band ratio algorithm still worked well for clear open ocean waters with low POC, and ANN was more effective for optically complex waters with extremely high POC. This study provided globally applicable methods for satellite retrieval of POC concentrations, which should be helpful for studying POC dynamics in global oceans as well as in productive marginal seas.

Original languageEnglish
Article number112316
JournalRemote Sensing of Environment
Early online date2 Feb 2021
Publication statusPublished - Apr 2021

Scopus Subject Areas

  • Soil Science
  • Geology
  • Computers in Earth Sciences

User-Defined Keywords

  • Climate change
  • Machine learning
  • Marine carbon
  • Ocean colour remote sensing


Dive into the research topics of 'Improving satellite retrieval of oceanic particulate organic carbon concentrations using machine learning methods'. Together they form a unique fingerprint.

Cite this