Estimating spatial and temporal variation in ocean surface pCO2 in the Gulf of Mexico using remote sensing and machine learning techniques

Zhiyi Fu; Linshu Hu; Zhende Chen; Feng Zhang; Zhou Shi; Bifeng Hu; Zhenhong Du; Renyi Liu

doi:10.1016/j.scitotenv.2020.140965

Estimating spatial and temporal variation in ocean surface pCO₂ in the Gulf of Mexico using remote sensing and machine learning techniques

Sci Total Environ. 2020 Nov 25:745:140965. doi: 10.1016/j.scitotenv.2020.140965. Epub 2020 Jul 19.

Authors

Zhiyi Fu¹, Linshu Hu¹, Zhende Chen¹, Feng Zhang², Zhou Shi³, Bifeng Hu⁴, Zhenhong Du⁵, Renyi Liu⁶

Affiliations

¹ School of Earth Sciences, Zhejiang University, Hangzhou 310027, China.
² School of Earth Sciences, Zhejiang University, Hangzhou 310027, China; Zhejiang Provincial Key Laboratory of Geographic Information Science, Hangzhou 310028, China. Electronic address: zfcarnation@zju.edu.cn.
³ Institute of Agricultural Remote Sensing and Information Technology Application, College of Environmental and Resource Sciences, Zhejiang University, Hangzhou 310058, China.
⁴ Unité de Recherche en Science du Sol, INRAE, Orléans 45075, France; Sciences de la Terre et de l'Univers, Orléans University, Orléans 45067, France.
⁵ School of Earth Sciences, Zhejiang University, Hangzhou 310027, China; Zhejiang Provincial Key Laboratory of Geographic Information Science, Hangzhou 310028, China.
⁶ School of Earth Sciences, Zhejiang University, Hangzhou 310027, China; Zhejiang Provincial Key Laboratory of Geographic Information Science, Hangzhou 310028, China; Ocean Academy, Zhejiang University, Zhoushan 316021, China.

PMID: 32758741
DOI: 10.1016/j.scitotenv.2020.140965

Abstract

Research on the carbon cycle of coastal marine systems has been of wide concern recently. Accurate knowledge of the temporal and spatial distributions of sea-surface partial pressure (pCO₂) can reflect the seasonal and spatial heterogeneity of CO₂ flux and is, therefore, essential for quantifying the ocean's role in carbon cycling. However, it is difficult to use one model to estimate pCO₂ and determine its controlling variables for an entire region due to the prominent spatiotemporal heterogeneity of pCO₂ in coastal areas. Cubist is a commonly-used model for zoning; thus, it can be applied to the estimation and regional analysis of pCO₂ in the Gulf of Mexico (GOM). A cubist model integrated with satellite images was used here to estimate pCO₂ in the GOM, a river-dominated coastal area, using satellite products, including chlorophyll-a concentration (Chl-a), sea-surface temperature (SST) and salinity (SSS), and the diffuse attenuation coefficient at 490 nm (Kd-490). The model was based on a semi-mechanistic model and integrated the high-accuracy advantages of machine learning methods. The overall performance showed a root mean square error (RMSE) of 8.42 μatm with a coefficient of determination (R²) of 0.87. Based on the heterogeneity of environmental factors, the GOM area was divided into 6 sub-regions, consisting estuaries, near-shores, and open seas, reflecting a gradient distribution of pCO₂. Factor importance and correlation analyses showed that salinity, chlorophyll-a, and temperature are the main controlling environmental variables of pCO₂, corresponding to both biological and physical effects. Seasonal changes in the GOM region were also analyzed and explained by changes in the environmental variables. Therefore, considering both high accuracy and interpretability, the cubist-based model was an ideal method for pCO₂ estimation and spatiotemporal heterogeneity analysis.

Keywords: Data mining; Gulf of Mexico; Remote sensing; Surface pCO(2).