Featured Discovery

Home > Featured Discovery > Latest Research on Remote Estimation of Sea Surface Nitrate Published in IEEE TGRS

Latest Research on Remote Estimation of Sea Surface Nitrate Published in IEEE TGRS

September 06, 2021      Author:

Recently, Yu Xiaolei, a 2019 postgraduate student of the School of Oceanography, SJTU, published a paper titled “Remote Estimation of Sea Surface Nitrate in The California Current System from Satellite Ocean Color Measurements” as first author in the international authoritative journal IEEE Transactions on Geoscience and Remote Sensing (impact factor 5.6).The paper was supervised by Chai Fei, professor of the School of Oceanography and Chen Shuangling, an associate researcher in the State Key Laboratory of Satellite Ocean Environment Dynamics (SOED).

Nitrate, as a major form of nitrogen in seawater, is an important nutrient on which marine phytoplankton thrive. The spatial and temporal variation of sea surface nitrate (SSN) concentration is of great significance to the study of marine primary productivity and the ocean carbon cycle.

In this study, a remote sensing inversion model of sea surface nitrate concentration was constructed using Stacking Random Forest based on the actual datasets collected over the past 40 years (1978-2018) in the central and southern sections of the California Current System. This model is the first remote sensing inversion model in the California Current system for SSN based on satellite ocean color measurements.

Average monthly distribution of SSN in the California Current System, 2002-2018


This study was supported by the National Natural Science Foundation of China (41906159, 42030708, 41730536).


Author: Yu Xiaolei

Source: The School of Oceanography

Translated by Chen Chen





Sea surface nitrate (SSN) is an important parameter to characterize physical and biogeochemical processes, particularly to quantify oceanic new primary production, yet its remote estimation from satellite has been difficult due to the complex relationships between environmental variables and SSN. In the central and southern sections of the California Current System (CSCCS), this challenge is attempted through modeling, validation, and extensive tests in different oceanic scenarios. Specifically, using extensive SSN datasets collected by many cruises spanning 40 years (1978-2018) and Moderate Resolution Imaging Spectroradiometer (MODIS) estimated sea surface temperature (SST) and chlorophyll-a (Chl), a stacking random forest (SRF) model of SSN has been developed and validated with a spatial resolution of ~4 km. The model showed an overall performance of root mean square difference (RMSD) = 0.83 μmol/kg, with coefficient of determination (R²) = 0.87, mean bias = -0.11 μmol/kg, and mean ratio = 1.15 for SSN ranging between 0.05 and 19.90 μmol/kg (N = 1034). Furthermore, tests of the model with its original parameterization for the upwelling period, oceanic period, and winter period all showed satisfactory performance with an overall RMSD of 1.95 μmol/kg. The sensitivity of the SRF model to uncertainties of MODIS SST and Chl was examined, with induced uncertainties of łe 2.22 μmol/kg. The extensive evaluation and sensitivity tests indicated the robustness of the SRF model in estimating SSN in the study area of the CSCCS, and it could serve as a robust approach for other regions once sufficient in situ SSN data are available for model calibration.