Articles | Volume 20, issue 5
https://doi.org/10.5194/os-20-1149-2024
© Author(s) 2024. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
Special issue:
https://doi.org/10.5194/os-20-1149-2024
© Author(s) 2024. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
Research article
| 
19 Sep 2024
Research article |
| 19 Sep 2024
| 19 Sep 2024
Predicting particle catchment areas of deep-ocean sediment traps using machine learning
Laboratoire des Sciences de l'Environnement Marin (LEMAR), Univ Brest, CNRS, IRD, Ifremer, IUEM, Plouzané, France
Jonathan Gula
Laboratoire d’Océanographie Physique et Spatiale (LOPS), Univ Brest, CNRS, IRD, Ifremer, IUEM, Plouzané, France
Institut Universitaire de France (IUF), Paris, France
ODYSSEY, Inria, Brest, France
Ronan Fablet
IMT Atlantique, Lab-STICC, Plouzané, France
ODYSSEY, Inria, Brest, France
Jeremy Collin
Laboratoire des Sciences de l'Environnement Marin (LEMAR), Univ Brest, CNRS, IRD, Ifremer, IUEM, Plouzané, France
Laurent Mémery
Laboratoire des Sciences de l'Environnement Marin (LEMAR), Univ Brest, CNRS, IRD, Ifremer, IUEM, Plouzané, France
Related authors
Théo Picard, Chelsey A. Baker, Jonathan Gula, Ronan Fablet, Laurent Mémery, and Richard Lampitt
EGUsphere, https://doi.org/10.5194/egusphere-2024-3292, https://doi.org/10.5194/egusphere-2024-3292, 2024
Short summary
Short summary
Ocean sediment traps measure the sequestrated sinking organic carbon. While sinking, the particles are affected by local currents, which presents a challenge in linking the deep flux with the surface. We present a machine learning tool that predicts the source location of the sinking particles based on satellite data. The predictions demonstrate a stronger correlation between surface and deep carbon fluxes, allowing a more comprehensive understanding of the deep carbon sequestration drivers.
Théo Picard, Chelsey A. Baker, Jonathan Gula, Ronan Fablet, Laurent Mémery, and Richard Lampitt
EGUsphere, https://doi.org/10.5194/egusphere-2024-3292, https://doi.org/10.5194/egusphere-2024-3292, 2024
Short summary
Short summary
Ocean sediment traps measure the sequestrated sinking organic carbon. While sinking, the particles are affected by local currents, which presents a challenge in linking the deep flux with the surface. We present a machine learning tool that predicts the source location of the sinking particles based on satellite data. The predictions demonstrate a stronger correlation between surface and deep carbon fluxes, allowing a more comprehensive understanding of the deep carbon sequestration drivers.
Maxime Ballarotta, Clément Ubelmann, Valentin Bellemin-Laponnaz, Florian Le Guillou, Guillaume Meda, Cécile Anadon, Alice Laloue, Antoine Delepoulle, Yannice Faugère, Marie-Isabelle Pujol, Ronan Fablet, and Gérald Dibarboure
EGUsphere, https://doi.org/10.5194/egusphere-2024-2345, https://doi.org/10.5194/egusphere-2024-2345, 2024
Short summary
Short summary
The Surface Water and Ocean Topography (SWOT) mission provides unprecedented swath altimetry data. This study examines SWOT's impact on mapping systems, showing a moderate effect with the current nadir altimetry constellation and a stronger impact with a reduced one. Integrating SWOT with dynamic mapping techniques improves the resolution of satellite-derived products, offering promising solutions for studying and monitoring sea-level variability at finer scales.
Chloé Baumas, Robin Fuchs, Marc Garel, Jean-Christophe Poggiale, Laurent Memery, Frédéric A. C. Le Moigne, and Christian Tamburini
Biogeosciences, 20, 4165–4182, https://doi.org/10.5194/bg-20-4165-2023, https://doi.org/10.5194/bg-20-4165-2023, 2023
Short summary
Short summary
Through the sink of particles in the ocean, carbon (C) is exported and sequestered when reaching 1000 m. Attempts to quantify C exported vs. C consumed by heterotrophs have increased. Yet most of the conducted estimations have led to C demands several times higher than C export. The choice of parameters greatly impacts the results. As theses parameters are overlooked, non-accurate values are often used. In this study we show that C budgets can be well balanced when using appropriate values.
Maxime Beauchamp, Quentin Febvre, Hugo Georgenthum, and Ronan Fablet
Geosci. Model Dev., 16, 2119–2147, https://doi.org/10.5194/gmd-16-2119-2023, https://doi.org/10.5194/gmd-16-2119-2023, 2023
Short summary
Short summary
4DVarNet is a learning-based method based on traditional data assimilation (DA). This new class of algorithms can be used to provide efficient reconstructions of a dynamical system based on single observations. We provide a 4DVarNet application to sea surface height reconstructions based on nadir and future Surface Water and Ocean and Topography data. It outperforms other methods, from optimal interpolation to sophisticated DA algorithms. This work is part of on-going AI Chair Oceanix projects.
Etienne Pauthenet, Loïc Bachelot, Kevin Balem, Guillaume Maze, Anne-Marie Tréguier, Fabien Roquet, Ronan Fablet, and Pierre Tandeo
Ocean Sci., 18, 1221–1244, https://doi.org/10.5194/os-18-1221-2022, https://doi.org/10.5194/os-18-1221-2022, 2022
Short summary
Short summary
Temperature and salinity profiles are essential for studying the ocean’s stratification, but there are not enough of these data. Satellites are able to measure daily maps of the surface ocean. We train a machine to learn the link between the satellite data and the profiles in the Gulf Stream region. We can then use this link to predict profiles at the high resolution of the satellite maps. Our prediction is fast to compute and allows us to get profiles at any locations only from surface data.
Takaya Uchida, Julien Le Sommer, Charles Stern, Ryan P. Abernathey, Chris Holdgraf, Aurélie Albert, Laurent Brodeau, Eric P. Chassignet, Xiaobiao Xu, Jonathan Gula, Guillaume Roullet, Nikolay Koldunov, Sergey Danilov, Qiang Wang, Dimitris Menemenlis, Clément Bricaud, Brian K. Arbic, Jay F. Shriver, Fangli Qiao, Bin Xiao, Arne Biastoch, René Schubert, Baylor Fox-Kemper, William K. Dewar, and Alan Wallcraft
Geosci. Model Dev., 15, 5829–5856, https://doi.org/10.5194/gmd-15-5829-2022, https://doi.org/10.5194/gmd-15-5829-2022, 2022
Short summary
Short summary
Ocean and climate scientists have used numerical simulations as a tool to examine the ocean and climate system since the 1970s. Since then, owing to the continuous increase in computational power and advances in numerical methods, we have been able to simulate increasing complex phenomena. However, the fidelity of the simulations in representing the phenomena remains a core issue in the ocean science community. Here we propose a cloud-based framework to inter-compare and assess such simulations.
R. Fablet, M. M. Amar, Q. Febvre, M. Beauchamp, and B. Chapron
ISPRS Ann. Photogramm. Remote Sens. Spatial Inf. Sci., V-3-2021, 295–302, https://doi.org/10.5194/isprs-annals-V-3-2021-295-2021, https://doi.org/10.5194/isprs-annals-V-3-2021-295-2021, 2021
Olivier Pannekoucke and Ronan Fablet
Geosci. Model Dev., 13, 3373–3382, https://doi.org/10.5194/gmd-13-3373-2020, https://doi.org/10.5194/gmd-13-3373-2020, 2020
Short summary
Short summary
Learning physics from data using a deep neural network is a challenge that requires an appropriate but unknown network architecture. The package introduced here helps to design an architecture by translating known physical equations into a network, which the experimenter completes to capture unknown physical processes. A test bed is introduced to illustrate how this learning allows us to focus on truly unknown physical processes in the hope of making better use of data and digital resources.
Mathieu Le Corre, Jonathan Gula, and Anne-Marie Tréguier
Ocean Sci., 16, 451–468, https://doi.org/10.5194/os-16-451-2020, https://doi.org/10.5194/os-16-451-2020, 2020
Short summary
Short summary
The ocean circulation is crucial for the climate, and the North Atlantic subpolar gyre is a key component of the meridional heat transport. In this study we use a high-resolution simulation with bottom-following coordinates to investigate the gyre dynamics. We show that nonlinear processes, underestimated in most climate models, control the circulation in the gyre interior. This result contrasts with the classical theory putting forward wind effects on the large-scale circulation.
Mathieu Morvan, Pierre L'Hégaret, Xavier Carton, Jonathan Gula, Clément Vic, Charly de Marez, Mikhail Sokolovskiy, and Konstantin Koshel
Ocean Sci., 15, 1531–1543, https://doi.org/10.5194/os-15-1531-2019, https://doi.org/10.5194/os-15-1531-2019, 2019
Short summary
Short summary
The Persian Gulf Water and Red Sea Water are salty and dense waters recirculating in the Gulf of Oman and the Gulf of Aden, in the form of small features. We study the life cycle of intense and small vortices and their impact on the spread of Persian Gulf Water and Red Sea Water by using idealized numerical simulations. Small vortices are generated along the continental slopes, drift away, merge and form larger vortices. They can travel across the domain and participate in the tracer diffusion.
Guillaume Le Gland, Laurent Mémery, Olivier Aumont, and Laure Resplandy
Biogeosciences, 14, 3171–3189, https://doi.org/10.5194/bg-14-3171-2017, https://doi.org/10.5194/bg-14-3171-2017, 2017
Short summary
Short summary
In this study, we computed the fluxes of radium-228 from the continental shelf to the open ocean by fitting a numerical model to observations. After determining appropriate model parameters (cost function and number of source regions), we found a lower and more precise global flux than previous estimates: 8.01–8.49×1023 atoms yr−1. This result can be used to assess nutrient and trace element fluxes to the open ocean, but we cannot identify specific pathways like submarine groundwater discharge.
M. S. Mallard, C. G. Nolte, T. L. Spero, O. R. Bullock, K. Alapaty, J. A. Herwehe, J. Gula, and J. H. Bowden
Geosci. Model Dev., 8, 1085–1096, https://doi.org/10.5194/gmd-8-1085-2015, https://doi.org/10.5194/gmd-8-1085-2015, 2015
Short summary
Short summary
Because global climate models (GCMs) are typically run at coarse spatial resolution, lakes are often poorly resolved in their global fields. When downscaling such GCMs using the Weather Research & Forecasting (WRF) model, use of WRF’s default interpolation methods can result in unrealistic lake temperatures and ice cover, which can impact simulated air temperatures and precipitation. Here, alternative methods for setting lake variables in WRF downscaling applications are presented and compared.
Cited articles
Alldredge, A. L. and Gotschalk, C.: In situ settling behavior of marine snow, Limnol. Oceanogr., 33, 339–351, https://doi.org/10.4319/lo.1988.33.3.0339, 1988. a
Alonso-González, I. J., Arístegui, J., Lee, C., and Calafat, A.: Regional and temporal variability of sinking organic matter in the subtropical northeast Atlantic Ocean: a biomarker diagnosis, Biogeosciences, 7, 2101–2115, https://doi.org/10.5194/bg-7-2101-2010, 2010. a
Armstrong, R. A., Lee, C., Hedges, J. I., Honjo, S., and Wakeham, S. G.: A new, mechanistic model for organic carbon fluxes in the ocean based on the quantitative association of POC with ballast minerals, Deep-Sea Res. Pt. II, 49, 219–236, https://doi.org/10.1016/S0967-0645(01)00101-1, 2001. a, b
Asper, V. L., Deuser, W. G., Knauer, G. A., and Lohrenz, S. E.: Rapid coupling of sinking particle fluxes between surface and deep ocean waters, Nature, 357, 670–672, https://doi.org/10.1038/357670a0, 1992. a
Aumont, O., Ethé, C., Tagliabue, A., Bopp, L., and Gehlen, M.: PISCES-v2: An ocean biogeochemical model for carbon and ecosystem studies, Geosci. Model Dev., 8, 2465–2513, https://doi.org/10.5194/gmd-8-2465-2015, 2015. a
Barth, A., Alvera-Azcárate, A., Licer, M., and Beckers, J.-M.: DINCAE 1.0: a convolutional neural network with error estimates to reconstruct sea surface temperature satellite observations, Geosci. Model Dev., 13, 1609–1622, https://doi.org/10.5194/gmd-13-1609-2020, 2020. a
Beauchamp, M., Febvre, Q., Georgenthum, H., and Fablet, R.: 4DVarNet-SSH: end-to-end learning of variational interpolation schemes for nadir and wide-swath satellite altimetry, Geosci. Model Dev., 16, 2119–2147, https://doi.org/10.5194/gmd-16-2119-2023, 2023. a, b, c
Bhattacharyya, A.: On a measure of divergence between two statistical populations defined by their probability distribution, Bull. Calcutta Math. Soc., 35, 99–110, 1943. a
Billett, D. S., Lampitt, R. S., Rice, A. L., and Mantoura, R. F.: Seasonal sedimentation of phytoplankton to the deep-sea benthos, Nature, 302, 520–522, https://doi.org/10.1038/302520a0, 1983. a
Bolton, T. and Zanna, L.: Applications of Deep Learning to Ocean Data Inference and Subgrid Parameterization, J. Adv. Model. Earth Sy., 11, 376–399, https://doi.org/10.1029/2018MS001472, 2019. a
Breiman, L.: Bagging predictors, Mach. Learn., 24, 123–140, https://doi.org/10.1007/bf00058655, 1996. a
Buckingham, C. E., Naveira Garabato, A. C., Thompson, A. F., Brannigan, L., Lazar, A., Marshall, D. P., George Nurser, A. J., Damerell, G., Heywood, K. J., and Belcher, S. E.: Seasonality of submesoscale flows in the ocean surface boundary layer, Geophys. Res. Lett., 43, 2118–2126, https://doi.org/10.1002/2016GL068009, 2016. a
Burd, A. B., Buchan, A., Church, M., Landry, M., McDonnell, A., Passow, U., Steinberg, D., and Benway, H.: Towards a transformative understanding of the biology of the ocean’s biological pump:Priorities for future research, Report of the NSF Biology of the Biological Pump Workshop, 19–20 February 2016, Hyatt Place New Orleans, New Orleans, LA, 67 pp., https://doi.org/10.1575/1912/8263, 2016. a
Burd, A. B., Hansell, D. A., Steinberg, D. K., Anderson, T. R., Arístegui, J., Baltar, F., Beaupré, S. R., Buesseler, K. O., DeHairs, F., Jackson, G. A., Kadko, D. C., Koppelmann, R., Lampitt, R. S., Nagata, T., Reinthaler, T., Robinson, C., Robison, B. H., Tamburini, C., and Tanaka, T.: Assessing the apparent imbalance between geochemical and biochemical indicators of meso- and bathypelagic biological activity: What the @$♯!is wrong with present calculations of carbon budgets?, Deep-Sea Res. Pt. II, 57, 1557–1571, https://doi.org/10.1016/j.dsr2.2010.02.022, 2010. a
Cael, B. B., Cavan, E. L., and Britten, G. L.: Reconciling the Size‐Dependence of Marine Particle Sinking Speed, Geophys. Res. Lett., 48, e2020GL091771, https://doi.org/10.1029/2020GL091771, 2021. a
Chapman, C. and Charantonis, A. A.: Reconstruction of Subsurface Velocities From Satellite Observations Using Iterative Self-Organizing Maps, IEEE Geosci. Remote Sens. Lett., 14, 617–620, https://doi.org/10.1109/LGRS.2017.2665603, 2017. a
Chelton, D. B., Deszoeke, R. A., Schlax, M. G., El Naggar, K., and Siwertz, N.: Geographical variability of the first baroclinic Rossby radius of deformation, J. Phys. Oceanogr., 28, 433–460, https://doi.org/10.1175/1520-0485(1998)028<0433:GVOTFB>2.0.CO;2, 1998. a
Deuser, W. G. and Ross, E. H.: Seasonal change in the flux of organic carbon to the deep Sargasso Sea, Nature 283, 364–365, https://doi.org/10.1038/283364a0, 1980. a
Deuser, W. G., Muller-Karger, F. E., and Hemleben, C.: Temporal variations of particle fluxes in the deep subtropical and tropical North Atlantic: Eulerian versus Lagrangian effects, J. Geophys. Res., 93, 6857–6862, https://doi.org/10.1029/JC093iC06p06857, 1988. a
Deuser, W. G., Muller-Karger, F. E., Evans, R. H., Brown, O. B., Esaias, W. E., and Feldman, G. C.: Surface-ocean color and deep-ocean carbon flux: how close a connection?, Deep-Sea Res. Pt. A, 37, 1331–1343, https://doi.org/10.1016/0198-0149(90)90046-X, 1990. a
Dever, M., Nicholson, D., Omand, M. M., and Mahadevan, A.: Size‐Differentiated Export Flux in Different Dynamical Regimes in the Ocean, Global Biogeochem. Cy., 35, e2020GB006764, https://doi.org/10.1029/2020GB006764, 2021. a
Dunne, J. P., Armstrong, R. A., Gnanadesikan, A., and Sarmiento, J. L.: Empirical and mechanistic models for the particle export ratio, Global Biogeochem. Cy., 19, GB4026, https://doi.org/10.1029/2004GB002390, 2005. a
Febvre, Q., Le Sommer, J., Ubelmann, C., and Fablet, R.: Training neural mapping schemes for satellite altimetry with simulation data, J. Adv. Model. Earth Syst., 16, e2023MS003959, https://doi.org/10.1029/2023MS003959, 2024. a
Frigstad, H., Henson, S. A., Hartman, S. E., Omar, A. M., Jeansson, E., Cole, H., Pebody, C., and Lampitt, R. S.: Links between surface productivity and deep ocean particle flux at the Porcupine Abyssal Plain sustained observatory, Biogeosciences, 12, 5885–5897, https://doi.org/10.5194/bg-12-5885-2015, 2015. a, b, c
George, T. M., Manucharyan, G. E., and Thompson, A. F.: Deep learning to infer eddy heat fluxes from sea surface height patterns of mesoscale turbulence, Nat. Commun., 12, 800, https://doi.org/10.1038/s41467-020-20779-9, 2021. a
Gula, J. and Collin, J.: Pyticles: a Python/Fortran hybrid parallelized code for 3D Lagrangian particles advection using ROMS/CROCO model data, Zenodo, https://doi.org/10.5281/zenodo.4973786, 2021. a
Hartman, S. E., Bett, B. J., Durden, J. M., Henson, S. A., Iversen, M., Jeffreys, R. M., Horton, T., Lampitt, R., and Gates, A. R.: Enduring science: Three decades of observing the Northeast Atlantic from the Porcupine Abyssal Plain Sustained Observatory (PAP-SO), Prog. Oceanogr., 191, 102508, https://doi.org/10.1016/j.pocean.2020.102508, 2021. a
Haynes, K., Lagerquist, R., McGraw, M., Musgrave, K., and Ebert-Uphoff, I.: Creating and Evaluating Uncertainty Estimates with Neural Networks for Environmental-Science Applications, Artificial Intelligence for the Earth Systems, 2, 1–29, https://doi.org/10.1175/aies-d-22-0061.1, 2023. a, b
Henson, S. A., Laufkötter, C., Leung, S., Giering, S. L., Palevsky, H. I., and Cavan, E. L.: Uncertain response of ocean biological carbon export in a changing world, Nat. Geosci., 15, 248–254, https://doi.org/10.1038/s41561-022-00927-0, 2022. a
Iversen, M. H. and Lampitt, R. S.: Size does not matter after all: No evidence for a size-sinking relationship for marine snow, Prog. Oceanogr., 189, 102445, https://doi.org/10.1016/j.pocean.2020.102445, 2020. a
Jenkins, J., Paiement, A., Ourmières, Y., Sommer, J. L., Verron, J., Ubelmann, C., and Glotin, H.: A DNN Framework for Learning Lagrangian Drift With Uncertainty, Arxiv, http://arxiv.org/abs/2204.05891 (last access: 24 May 2023), 2022. a
Jokulsdottir, T. and Archer, D.: A stochastic, Lagrangian model of sinking biogenic aggregates in the ocean (SLAMS 1.0): Model formulation, validation and sensitivity, Geosci. Model Dev., 9, 1455–1476, https://doi.org/10.5194/gmd-9-1455-2016, 2016. a
Kingma, D. P. and Ba, J. L.: Adam: A method for stochastic optimization, in: 3rd International Conference on Learning Representations, ICLR 2015 – Conference Track Proceedings, San Diego, https://doi.org/10.48550/arXiv.1412.6980, 2015. a
Kostadinov, T. S., Siegel, D. A., and Maritorena, S.: Retrieval of the particle size distribution from satellite ocean color observations, J. Geophys. Res.-Ocean., 114, C09015, https://doi.org/10.1029/2009JC005303, 2009. a
Lampitt, R. S., Achterberg, E. P., Anderson, T. R., Hughes, J. A., Iglesias-Rodriguez, M. D., Kelly-Gerreyn, B. A., Lucas, M., Popova, E. E., Sanders, R., Shepherd, J. G., Smythe-Wright, D., and Yool, A.: Ocean fertilization: A potential means of geoengineering?, Philos. T. R. Soc. A, 366, 3919–3945, https://doi.org/10.1098/rsta.2008.0139, 2008. a
Lampitt, R. S., Briggs, N., Cael, B. B., Espinola, B., Hélaouët, P., Henson, S. A., Norrbin, F., Pebody, C. A., and Smeed, D.: Deep ocean particle flux in the Northeast Atlantic over the past 30 years: carbon sequestration is controlled by ecosystem structure in the upper ocean, Front. Earth Sci., 11, 1176196, https://doi.org/10.3389/feart.2023.1176196, 2023. a, b
Laurenceau‐Cornec, E. C., Le Moigne, F. A. C., Gallinari, M., Moriceau, B., Toullec, J., Iversen, M. H., Engel, A., and De La Rocha, C. L.: New guidelines for the application of Stokes' models to the sinking velocity of marine aggregates, Limnol. Oceanogr., 65, 1264–1285, https://doi.org/10.1002/lno.11388, 2020. a
Le Cann, B.: Observed mean and mesoscale upper ocean circulation in the midlatitude northeast Atlantic, J. Geophys. Res., 110, C07S05, https://doi.org/10.1029/2004JC002768, 2005. a
Le Corre, M., Gula, J., and Tréguier, A. M.: Barotropic vorticity balance of the North Atlantic subpolar gyre in an eddy-resolving model, Ocean Sci., 16, 451–468, https://doi.org/10.5194/os-16-451-2020, 2020. a
Le Moigne, F. A., Henson, S. A., Sanders, R. J., and Madsen, E.: Global database of surface ocean particulate organic carbon export fluxes diagnosed from the 234Th technique, Earth Syst. Sci. Data, 5, 295–304, https://doi.org/10.5194/essd-5-295-2013, 2013. a
Le Moigne, F. A. C.: Pathways of Organic Carbon Downward Transport by the Oceanic Biological Carbon Pump, Front. Mar. Sci., 6, 482488, https://doi.org/10.3389/fmars.2019.00634, 2019. a
Lecun, Y., Bengio, Y., and Hinton, G.: Deep learning, Nature, 521, 436–444, https://doi.org/10.1038/nature14539, 2015. a
Liu, G., Bracco, A., and Passow, U.: The influence of mesoscale and submesoscale circulation on sinking particles in the northern Gulf of Mexico, Elementa, 6, 36, https://doi.org/10.1525/elementa.292, 2018. a, b, c
Ma, W., Xiu, P., Chai, F., Ran, L., Wiesner, M. G., Xi, J., Yan, Y., and Fredj, E.: Impact of mesoscale eddies on the source funnel of sediment trap measurements in the South China Sea, Prog. Oceanogr., 194, 102566, https://doi.org/10.1016/j.pocean.2021.102566, 2021. a, b
Manucharyan, G. E., Siegelman, L., and Klein, P.: A Deep Learning Approach to Spatiotemporal Sea Surface Height Interpolation and Estimation of Deep Currents in Geostrophic Ocean Turbulence, J. Adv. Model. Earth Sy., 13, 1–17, https://doi.org/10.1029/2019MS001965, 2021. a, b
Passow, U. and Carlson, C. A.: The biological pump in a high CO2 world, Mar. Ecol. Prog. Ser., 470, 249–271, https://doi.org/10.3354/meps09985, 2012. a
Paszke, A., Gross, S., Massa, F., Lerer, A., Bradbury, J., Chanan, G., Killeen, T., Lin, Z., Gimelshein, N., Antiga, L., Desmaison, A., Kopf, A., Yang, E., DeVito, Z., Raison, M., Tejani, A., Chilamkurthy, S., Steiner, B., Fang, L., Bai, J., and Chintala, S.: PyTorch: An Imperative Style, High-Performance Deep Learning Library, Adv. Neur. In., 32, 8024–8035, 2019. a
Pauthenet, E., Bachelot, L., Balem, K., Maze, G., Tréguier, A. M., Roquet, F., Fablet, R., and Tandeo, P.: Four-dimensional temperature, salinity and mixed-layer depth in the Gulf Stream, reconstructed from remote-sensing and in situ observations with neural networks, Ocean Sci., 18, 1221–1244, https://doi.org/10.5194/os-18-1221-2022, 2022. a, b
Picard, T.: SPARO: v1.0.0, Zenodo [code], https://doi.org/10.5281/zenodo.10203352, 2023. a
Picard, T., Gula, J., Fablet, R., Memery, L., and Collin, J.: Data for learning-based prediction of the particles catchment area of deep ocean sediment traps, SEANOE [data set], https://doi.org/10.17882/97556, 2023. a
Rembauville, M., Blain, S., Manno, C., Tarling, G., Thompson, A., Wolff, G., and Salter, I.: The role of diatom resting spores in pelagic–benthic coupling in the Southern Ocean, Biogeosciences, 15, 3071–3084, https://doi.org/10.5194/bg-15-3071-2018, 2018. a
Shchepetkin, A. F. and McWilliams, J. C.: The regional oceanic modeling system (ROMS): A split-explicit, free-surface, topography-following-coordinate oceanic model, Ocean Model., 9, 347–404, https://doi.org/10.1016/j.ocemod.2004.08.002, 2005. a
Siegel, D. A., Granata, T. C., Michaels, A. F., and Dickey, T. D.: Mesoscale eddy diffusion, particle sinking, and the interpretation of sediment trap data, J. Geophys. Res., 95, 5305–5311, https://doi.org/10.1029/JC095iC04p05305, 1990. a
Siegel, D. A., Fields, E., and Buesseler, K. O.: A bottom-up view of the biological pump: Modeling source funnels above ocean sediment traps, Deep-Sea Res. Pt. I, 55, 108–127, https://doi.org/10.1016/j.dsr.2007.10.006, 2008. a
Siegel, D. A., Buesseler, K. O., Doney, S. C., Sailley, S. F., Behrenfeld, M. J., and Boyd, P. W.: Global assessment of ocean carbon export by combining satellite observations and food-web models, Global Biogeochem. Cy., 28, 181–196, https://doi.org/10.1002/2013GB004743, 2014. a
Soufflet, Y., Marchesiello, P., Lemarié, F., Jouanno, J., Capet, X., Debreu, L., and Benshila, R.: On effective resolution in ocean models, Ocean Model., 98, 36–50, https://doi.org/10.1016/j.ocemod.2015.12.004, 2016. a
Turner, J. T.: Zooplankton fecal pellets, marine snow, phytodetritus and the ocean's biological pump, Prog. Oceanogr., 130, 205–248, https://doi.org/10.1016/j.pocean.2014.08.005, 2015. a
Villa-Alfageme, M., de Soto, F., Le Moigne, F. A. C., Giering, S. L. C., Sanders, R., and García-Tenorio, R.: Observations and modeling of slow-sinking particles in the twilight zone, Global Biogeochem. Cy., 28, 1327–1342, https://doi.org/10.1002/2014GB004981, 2014. a
Villa-Alfageme, M., de Soto, F. C., Ceballos, E., Giering, S. L. C., Le Moigne, F. A. C., Henson, S., Mas, J. L., and Sanders, R. J.: Geographical, seasonal, and depth variation in sinking particle speeds in the North Atlantic, Geophys. Res. Lett., 43, 8609–8616, https://doi.org/10.1002/2016GL069233, 2016. a, b
Wekerle, C., Krumpen, T., Dinter, T., von Appen, W. J., Iversen, M. H., and Salter, I.: Properties of sediment trap catchment areas in fram strait: Results from Lagrangian modeling and remote sensing, Front. Mar. Sci., 9, 407, https://doi.org/10.3389/fmars.2018.00407, 2018. a, b, c
Williams, R. G. and Follows, M. J.: Ocean Dynamics and the Carbon Cycle: Principles and Mechanisms, Cambridge University Press, https://doi.org/10.1017/CBO9780511977817, 2011. a
Short summary
The biological carbon pump plays a key role in the climate system. Plankton absorb and transform CO2 into organic carbon, forming particles that sink to the ocean floor. Sediment traps catch these particles and measure the carbon stored in the abyss. However, the particles' surface origin is unknown as ocean currents alter their paths. Here, we train an AI model to predict the origin of these particles. This new tool enables a better link between deep-ocean observations and satellite images.
The biological carbon pump plays a key role in the climate system. Plankton absorb and transform...
