Estimating the variability of deep-ocean particle flux collected by sediment traps using satellite data and machine learning

Picard, Théo; Baker, Chelsey A.; Gula, Jonathan; Fablet, Ronan; Mémery, Laurent; Lampitt, Richard

Estimating the variability of deep-ocean particle flux collected by sediment traps using satellite data and machine learning

Picard, Théo ORCID: https://orcid.org/0000-0002-3205-2388; Baker, Chelsey A. ORCID: https://orcid.org/0000-0002-0840-2333; Gula, Jonathan ORCID: https://orcid.org/0000-0002-0876-9557; Fablet, Ronan ORCID: https://orcid.org/0000-0002-6462-423X; Mémery, Laurent ORCID: https://orcid.org/0000-0001-6593-7222; Lampitt, Richard. 2025 Estimating the variability of deep-ocean particle flux collected by sediment traps using satellite data and machine learning. Biogeosciences, 22 (17). 4309-4331. 10.5194/bg-22-4309-2025

Before downloading, please read NORA policies.

Preview

Text
© Author(s) 2025. This work is distributed under the Creative Commons Attribution 4.0 License.
bg-22-4309-2025.pdf - Published Version
Available under License Creative Commons Attribution 4.0.
Download (9MB) | Preview

Official URL: https://doi.org/10.5194/bg-22-4309-2025

Abstract/Summary

The gravitational pump plays a key role in the ocean carbon cycle by exporting sinking organic carbon from the surface to the deep ocean. Deep sediment trap time series provide unique measurements of this sequestered carbon flux. Sinking particles are influenced by physical short-term spatio-temporal variability, which inhibits the establishment of a direct link to their surface origin. In this study, we present a novel machine learning tool, designated as U-NetSST−SSH, which is capable of predicting the catchment area of particles captured by sediment traps moored at a depth of 3000 m above the Porcupine Abyssal Plain (PAP) based solely on surface data. The machine learning tool was trained and evaluated using Lagrangian experiments in a realistic CROCO numerical simulation. The conventional approach of assuming a static 100–200 km box over the sediment trap location only yields an average prediction for ∼25 % of the source region, whilst U-NetSST−SSH predicts ∼50 %. U-NetSST−SSH was then applied to satellite observations to create a 20-year catchment area dataset, which demonstrates a stronger correlation between the PAP site deep particle fluxes and surface chlorophyll-a concentration compared with the conventional approach. However, predictions remain highly sensitive to the local deep dynamics which are not observed in surface ocean dynamics. The improved identification of the particle source region for deep-ocean sediment traps can facilitate a more comprehensive understanding of the mechanisms driving the export of particles from the surface to the deep ocean, a key component of the biological carbon pump.

Item Type:

Publication - Article

Digital Object Identifier (DOI):

10.5194/bg-22-4309-2025

ISSN:

1726-4189

NORA Subject Terms:

Marine Sciences

Date made live:

29 Oct 2025 17:13 +0 (UTC)

URI:

https://nora.nerc.ac.uk/id/eprint/540465