Publications

Chen, SL; Hu, CM; Barnes, BB; Wanninkhof, R; Cai, WJ; Barbero, L; Pierrot, D (2019). A machine learning approach to estimate surface ocean pCO(2) from satellite measurements. REMOTE SENSING OF ENVIRONMENT, 228, 203-226.

Abstract
Surface seawater partial pressure of CO2 (pCO(2)) is a critical parameter in the quantification of air-sea CO2 flux, which further plays an important role in quantifying the global carbon budget and understanding ocean acidification. Yet, the remote estimation of pCO(2) in coastal waters (under influences of multiple processes) has been difficult due to complex relationships between environmental variables and surface pCO(2). To date there is no unified model to remotely estimate surface pCO(2) in oceanic regions that are dominated by different oceanic processes. In our study area, the Gulf of Mexico (GOM), this challenge is addressed through the evaluation of different approaches, including multi-linear regression (MLR), multi-nonlinear regression (MNR), principle component regression (PCR), decision tree, supporting vector machines (SVMs), multilayer perceptron neural network (MPNN), and random forest based regression ensemble (RFRE). After modeling, validation, and extensive tests using independent cruise datasets, the RFRE model proved to be the best approach. The RFRE model was trained using data comprised of extensive pCO(2) datasets (collected over 16 years by many groups) and MODIS (Moderate Resolution Imaging Spectroradiometer) estimated sea surface temperature (SST), sea surface salinity (SSS), surface chlorophyll concentration (Chl), and diffuse attenuation of downwelling irradiance (Kd). This RFRE-basedpCO(2) model allows for the estimation of surface pCO(2) from satellites with a spatial resolution of 1 km. It showed an overall performance of a root mean square difference (RMSD) of 9.1 mu atm, with a coefficient of determination (R-2) of 0.95, a mean bias (MB) of - 0.03 mu atm, a mean ratio (MR) of 1.00, an unbiased percentage difference (UPD) of 0.07%, and a mean ratio difference (MRD) of 0.12% for pCO(2) ranging between 145 and 550 mu atm. The model, with its original parameterization, has been tested with independent datasets collected over the entire GOM, with satisfactory performance in each case (RMSD of <= similar to 10 mu atm for open GOM waters and RMSD of <= similar to 25 mu atm for coastal and river-dominated waters). The sensitivity of the RFRE-based pCO(2) model to uncertainties of each input environmental variable was also thoroughly examined. The results showed that all induced uncertainties were close to, or within, the uncertainty of the model itself with higher sensitivity to uncertainties in SST and SSS than to uncertainties in Chl and Kd. The extensive validation, evaluation, and sensitivity analysis indicate the robustness of the RFRE model in estimating surface pCO(2) for the range of 145-550 mu atm in most GOM waters. The RFRE model approach was applied to the Gulf of Maine (a contrasting oceanic region to GOM), with local model training. The results showed significant improvement over other models suggesting that the RFRE may serve as a robust approach for other regions once sufficient field measured pCO(2) data are available for model training.

DOI:
10.1016/j.rse.2019.04.019

ISSN:
0034-4257