Machine learning for prediction of daily sea surface dimethylsulfide concentration and emission flux over the North Atlantic Ocean (1998-2021)

Karam Mansour; Stefano Decesari; Darius Ceburnis; Jurgita Ovadnevaite; Matteo Rinaldi

doi:10.1016/j.scitotenv.2023.162123

Machine learning for prediction of daily sea surface dimethylsulfide concentration and emission flux over the North Atlantic Ocean (1998-2021)

Sci Total Environ. 2023 May 1:871:162123. doi: 10.1016/j.scitotenv.2023.162123. Epub 2023 Feb 10.

Authors

Karam Mansour¹, Stefano Decesari², Darius Ceburnis³, Jurgita Ovadnevaite³, Matteo Rinaldi²

Affiliations

¹ Italian National Research Council, Institute of Atmospheric Sciences and Climate (CNR-ISAC), Bologna 40129, Italy; Oceanography Department, Faculty of Science, Alexandria University, Alexandria 21500, Egypt. Electronic address: k.mansour@isac.cnr.it.
² Italian National Research Council, Institute of Atmospheric Sciences and Climate (CNR-ISAC), Bologna 40129, Italy.
³ School of Physics, Ryan Institute's Centre for Climate and Air Pollution Studies, National University of Ireland Galway, Galway, Ireland.

PMID: 36775176
DOI: 10.1016/j.scitotenv.2023.162123

Abstract

As the most ubiquitous natural source of sulfur in the atmosphere, dimethylsulfide (DMS) promotes aerosol formation in marine environments, impacting cloud radiative forcing and precipitation, eventually influencing regional and global climate. In this study, we propose a machine learning predictive algorithm based on Gaussian process regression (GPR) to model the distribution of daily DMS concentrations in the North Atlantic waters over 24 years (1998-2021) at 0.25° × 0.25° spatial resolution. The model was built using DMS observations from cruises, combined with satellite-derived oceanographic data and Copernicus-modelled data. Further comparison was made with the previously employed machine learning methods (i.e., artificial neural network and random forest regression) and the existing empirical DMS algorithms. The proposed GPR outperforms the other methods for predicting DMS, displaying the highest coefficient of determination (R²) value of 0.71 and the least root mean square error (RMSE) of 0.21. Notably, DMS regional patterns are associated with the spatial distribution of phytoplankton biomass and the thickness of the ocean mixed layer, displaying high DMS concentrations above 50°N from June to August. The amplitude, onset, and duration of the DMS annual cycle vary significantly across different regions, as revealed by the k-means++ clustering. Based on the GPR model output, the sea-to-air flux in the North Atlantic from March to September is estimated to be 3.04 Tg S, roughly 44 % lower than the estimates based on extrapolations of in-situ data. The present study demonstrates the effectiveness of a novel method for estimating seawater DMS surface concentration at unprecedented space and time resolutions. As a result, we are able to capture high-frequency spatial and temporal patterns in DMS variability. Better predictions of DMS concentration and derived sea-to-air flux will improve the modeling of biogenic sulfur aerosol concentrations in the atmosphere and reduce aerosol-cloud interaction uncertainties in climate models.

Keywords: Biogenic sulfur emissions; DMS; Gaussian process regression; K-means++; Sea-to-air flux.