Articles | Volume 41, issue 2
https://doi.org/10.5194/jm-41-165-2022
© Author(s) 2022. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
https://doi.org/10.5194/jm-41-165-2022
© Author(s) 2022. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
Artificial intelligence applied to the classification of eight middle Eocene species of the genus Podocyrtis (polycystine radiolaria)
Veronica Carlsson
CORRESPONDING AUTHOR
Univ. Lille, CNRS, UMR 8198 – Evo-Eco-Paleo, 59000 Lille,
France
Univ. Lille, CNRS, Centrale Lille, UMR 9189 – CRIStAL – Centre de
Recherche en Informatique Signal et Automatique de Lille, 59000 Lille,
France
Taniel Danelian
Univ. Lille, CNRS, UMR 8198 – Evo-Eco-Paleo, 59000 Lille,
France
Pierre Boulet
Univ. Lille, CNRS, Centrale Lille, UMR 9189 – CRIStAL – Centre de
Recherche en Informatique Signal et Automatique de Lille, 59000 Lille,
France
Philippe Devienne
Univ. Lille, CNRS, Centrale Lille, UMR 9189 – CRIStAL – Centre de
Recherche en Informatique Signal et Automatique de Lille, 59000 Lille,
France
Aurelien Laforge
Univ. Lille, CNRS, UMR 8198 – Evo-Eco-Paleo, 59000 Lille,
France
Univ. Lille, CNRS, Centrale Lille, UMR 9189 – CRIStAL – Centre de
Recherche en Informatique Signal et Automatique de Lille, 59000 Lille,
France
Johan Renaudie
Museum für Naturkunde, Leibniz-Institut für Evolutions- und
Biodiversitätsforschung, 10115 Berlin, Germany
Related authors
No articles found.
Cécile Figus, Steve Bohaty, Johan Renaudie, and Jakub Witkowski
Clim. Past, 21, 1431–1441, https://doi.org/10.5194/cp-21-1431-2025, https://doi.org/10.5194/cp-21-1431-2025, 2025
Short summary
Short summary
We examine trends in biosiliceous fluxes and isotopic records in the North and South Atlantic, South Pacific, and Indian oceans during two climatic and biotic events: the Latest Danian Event (LDE; ~62.2 Ma) and the Early Late Palaeocene Event (ELPE; ~59.2 Ma). Our results show a peak during the LDE and following the ELPE.
Cécile Figus, Johan Renaudie, Or M. Bialik, and Jakub Witkowski
Biogeosciences, 22, 3029–3046, https://doi.org/10.5194/bg-22-3029-2025, https://doi.org/10.5194/bg-22-3029-2025, 2025
Short summary
Short summary
The synthesis of Palaeogene deep-sea diatom-bearing sediment occurrences indicates that the deposition of diatom-bearing sediments is mainly controlled by nutrient availability and ocean circulation in the Atlantic, Pacific, and Indian oceans. Comparison with shallow marine diatomites suggests that the peak in the number of diatom-bearing sites in the Atlantic is indirectly related to tectonic reorganizations that caused the cessation of shallow marine diatomite deposition between ~46 and ~44 Ma.
Johan Renaudie and David B. Lazarus
Biogeosciences, 22, 1929–1946, https://doi.org/10.5194/bg-22-1929-2025, https://doi.org/10.5194/bg-22-1929-2025, 2025
Short summary
Short summary
We provide a new compilation of rates at which sediments deposited in the deep sea over the last 70 million years. We highlight a bias, linked to the drilling process, that makes it more likely for high rates to be recovered for younger sediments than for older ones. Correcting for this bias, the record shows, contrary to prior estimates, a more stable history, thus providing some insights on the past mismatch between physico-chemical model estimates and observations.
Volkan Özen, David Lazarus, Johan Renaudie, and Gabrielle Rodrigues de Faria
EGUsphere, https://doi.org/10.5194/egusphere-2025-555, https://doi.org/10.5194/egusphere-2025-555, 2025
Short summary
Short summary
We studied diatom fossils from the Southern Ocean to understand how ocean productivity changed ~40–30 million years ago during a major climate shift marked by the onset of permanent Antarctic glaciation and global cooling. We found striking shifts in diatom productivity, revealing critical changes in ocean circulation and nutrient supply. Our results show how these microscopic organisms may have influenced climate, acting as a geological force that shaped global climate over time.
Cécile Figus, Or M. Bialik, Andrey Y. Gladenkov, Tatyana V. Oreshkina, Johan Renaudie, Pavel Smirnov, and Jakub Witkowski
Clim. Past, 20, 2629–2644, https://doi.org/10.5194/cp-20-2629-2024, https://doi.org/10.5194/cp-20-2629-2024, 2024
Short summary
Short summary
A global-scale compilation of Palaeogene diatomite occurrences shows how palaeogeographic and palaeoceanographic changes impacted diatom accumulation, especially in the middle Eocene. Diatomite deposition dropped in epicontinental seas between ~ 46 and ~ 44 Ma, while diatom accumulation began around 43.5 Ma in open-ocean settings. The compilation also shows an indirect correlation between Palaeogene climate fluctuations and diatomite deposition in shallow-marine and freshwater environments.
Gabrielle Rodrigues de Faria, David Lazarus, Johan Renaudie, Jessica Stammeier, Volkan Özen, and Ulrich Struck
Clim. Past, 20, 1327–1348, https://doi.org/10.5194/cp-20-1327-2024, https://doi.org/10.5194/cp-20-1327-2024, 2024
Short summary
Short summary
Export productivity is part of the global carbon cycle, influencing the climate system via biological pump. About 34 million years ago, the Earth's climate experienced a climate transition from a greenhouse state to an icehouse state with the onset of ice sheets in Antarctica. Our study shows important productivity events in the Southern Ocean preceding this climatic shift. Our findings strongly indicate that the biological pump potentially played an important role in that past climate change.
Clément Coiffard, Haytham El Atfy, Johan Renaudie, Robert Bussert, and Dieter Uhl
Biogeosciences, 20, 1145–1154, https://doi.org/10.5194/bg-20-1145-2023, https://doi.org/10.5194/bg-20-1145-2023, 2023
Short summary
Short summary
Eighty-million-year-old fossil leaf assemblages suggest a widespread distribution of tropical rainforest in northeastern Africa.
Mathias Meunier and Taniel Danelian
J. Micropalaeontol., 41, 1–27, https://doi.org/10.5194/jm-41-1-2022, https://doi.org/10.5194/jm-41-1-2022, 2022
Short summary
Short summary
This study presents the biostratigraphic analysis of radiolaria (siliceous zooplankton) from a section of middle Eocene age located in the equatorial Atlantic. Our study allows the refinement of the age of 71 radiolarian bioevents. Based on a comparison with previously reported ages in the equatorial Pacific and northwestern Atlantic, we establish the synchronicity of several bioevents between the two oceans. Some of these synchronous bioevents were used to define seven new subzones.
Cited articles
Aitchison, J. C., Suzuki, N., Caridroit, M., Danelian, T., and Noble, P.:
Paleozoic radiolarian biostratigraphy, in: Catalogue of Paleozoic Radiolarian Genera, edited by: Danelian, T., Caridroit, M., Noble,
P., and Aitchison, J. C., Geodiversitas, Vol. 39, 503–531, Scientific
Publications of the Muséum National d'Histoire Naturelle, Paris, https://doi.org/10.5252/g2017n3a5, 2017.
Beaufort, L. and Dollfus, D.: Automatic recognition of coccoliths by
dynamical neural networks, Mar. Micropaleontol., 51, 57–73, https://doi.org/10.1016/j.marmicro.2003.09.003, 2004.
Beaufort, L., de Garidel Thoron, T., Mix, A. C., and Pisias, N. G.: ENSO-like
forcing on Oceanic Primary Production during the late Pleistocene, Science,
293, 2440–2444, https://doi.org/10.1126/science.293.5539.2440, 2001.
Brocher, J.: biovoxxel/BioVoxxel-Toolbox: BioVoxxel Toolbox (v2.5.3),
Zenodo, https://doi.org/10.5281/zenodo.5986129, 2022.
Carlsson, V.: Podocyrtis Image Dataset, Recherche Data Gouv [data set], https://doi.org/10.57745/G7CHQL,
2022.
Carlsson, V. and Laforge, A.: Codes for image preparation and MobileNet CNN,
Recherche Data Gouv [code], https://doi.org/10.57745/J4YL4I, 2022.
Carvalho, L. E., Fauth, G., Baecker Fauth, S., Krahl, G., Moreira, A. C.,
Fernandes, C. P., and von Wangenheim, A.: Automated Microfossil Identification
and Segmentation using a Deep Learning Approach, Mar. Micropaleontol.,
158, 101890, https://doi.org/10.1016/j.marmicro.2020.101890, 2020.
Chollet, F.: Keras, GitHub [code],
https://github.com/fchollet/keras (last access: 21 October 2022), 2015.
Danelian, T. and MacLeod, N.: Morphometric Analysis of Two Eocene Related
Radiolarian Species of the Podocyrtis (Lampterium) Lineage, Paleontol. Res., 23, 314–330,
2019.
Danelian, T., Le Callonec, L., Erbacher, J., Mosher, D., Malone, M.,
Berti, D., Bice, K., Bostock, H., Brumsack, H. -J., Forster, A.,
Heidersdorf, F., Henderiks, J., Janecek, T., Junium, C., Macleod, K.,
Meyers, P., Mutterlose J., Nishi, H., Norris, R., Ogg, J., O'Regan, M., Rea,
B., Sexton, P., Sturt, H., Suganuma, Y., Thurow, J., Wilson, P., Wise, S.,
and Glatz, C.: Preliminary results on Cretaceous-Tertiary tropical Atlantic
pelagic sedimentation (Demerara Rise, ODP Leg 207), C. R. Geosci., 337, 609–616, https://doi.org/10.1016/j.crte.2005.01.011, 2005.
Danelian, T., Saint Martin, S., and Blanc-Valleron, M.-M.: Middle Eocene
radiolarian and diatom accumulation in the equatorial Atlantic (Demerara
Rise, ODP Leg 207): Possible links with climatic and palaeoceanographic
changes, C. R. Palevol., 6, 103–114, https://doi.org/10.1016/j.crpv.2006.08.002, 2007.
Davies, M., Wild, A., Orchard, G., Sandamirskaya, Y., Fonseca Guerra, G. A.,
Joshi, P., Plank, P., and Risbud, S.: Advancing Neuromorphic Computing with
Loihi: A Survey of Results and Outlook, Proc. IEEE,
109, 911–934, https://doi.org/10.1109/JPROC.2021.3067593, 2021.
De Lima, R. P., Welch, K. F., Barrick, J. E., Marfurt, K. J., Burkhalter,
R., Cassel, M., and Soreghan, G. S.: Convolutional Neural Networks As An Aid
To Biostratigraphy And Micropaleontology: A Test On Late Paleozoic
Microfossils, Palaios, 35, 391–402, https://doi.org/10.2110/palo.2019.102, 2020.
Dollfus, D. and Beaufort, L.: Fat neural network for recognition of
position-normalised objects, Neural Networks, 12, 553–560, https://doi.org/10.1016/S0893-6080(99)00011-8, 1999.
Ehrenberg, C. G.: Uber eine halibiolithische, von Herrn R. Schomburgk
entdeckte, vorherrschend aus mikroskopischen Polycystinen gebildete,
Gebirgsmasse von Barbados, Bericht uber die zu Bekanntmachung geeigneten
Verhandlungen der Koniglichen Preussische Akademie der Wissenschaften zu
Berlin, Jahre 1846, 382–385, 1846.
Ehrenberg, C. G.: Über die mikroskopischen kieselschaligen Polycystinen
als mächtige Gebirgsmasse von Barbados und über das Verhältniss
deraus mehr als 300 neuen Arten bestehenden ganz eigenthümlichen
Formengruppe jener Felsmasse zu den jetzt lebenden Thieren und zur
Kreidebildung, Eine neue Anregung zur Erforschung des Erdlebens, K. Preuss.
Akad. Wiss., Berlin, Jahre 1847, 40–60, 1847.
Ehrenberg, C. G.: Mikrogeologie: das Erden und Felsen schaffende Wirken des unsichtbar kleinen selbstständigen Lebens auf der Erde, Leopold Voss, Leipzig, Germany, 374 pp.,
https://doi.org/10.5962/bhl.title.118752, 1854.
Ehrenberg, C. G.: Grössere Felsproben des Polycystinen-Mergels von
Barbados mit weiteren Erläuterungen, K. Preuss. Akad. Wiss., Berlin,
Monatsberichte, Jahre 1873, 213–263, 1874.
Gonçalves, A. B., Souza, J. S., Silva, G. G., Cereda, M. P., Pott, A.,
Naka, M. H., and Pistori, H.: Feature Extraction and Machine Learning for the
Classification of Brazilian Savannah Pollen Grains, PLoS One, 11, e0157044, https://doi.org/10.1371/journal.pone.0157044, 2016.
Haeckel, E.: Report on the Radiolaria collected by H.M.S. Challenger during
the years 1873–1876, Report on the Scientific Results of the Voyage of the
H.M.S. Challenger, Zoology, 18, https://doi.org/10.5962/bhl.title.6513, 1887.
Hijazi, S., Kumar, R., and Rowen, C.: Using Convolutional Neural Networks for
Image Recognition, Cadence, Cadence Design Systems Inc., San Jose, 1–12, 2015.
Howard, A. G., Zhu, M., Chen, B., Kalenichenko, D., Wang, W., Weyand, T.,
Andreetto, M., and Adam, H.: Mobilenets: Efficient convolutional neural
networks for mobile vision applications, arXiv preprint arXiv:1704.04861, https://doi.org/10.48550/arXiv.1704.04861,
2017.
Hsiang, A. Y., Brombacher, A., Rillo, M.C., Mleneck-Vautravers, M. J., Conn,
S.,Lordsmith, S., Jentzen, A., J. Henehan, M., Metcalfe, B., Fenton, I. S.,
Wade, B. S., Fox, L., Meilland, J., Davis, C. V., Baranowski, U.,
Groeneveld, J., Edgar, K. M., Movellan, A., Aze, T., Dowsett, H. J., Giles
Miller, C., Rios, N., and Hull, P. M.: Endless Forams: >34 000
modern planktonic foraminiferal images for taxonomic training and automated
species recognition using convolutional neural networks, Paleoceanogr.
Paleocl., 34, 1157–1177, https://doi.org/10.1029/2019PA003612, 2019.
Itaki, T., Taira, Y., Kuwamori, N., Saito, H., Ikehara, M., and Hoshino, T.:
Innovative microfossil (radiolarian) analysis using a system for automated
image collection and AI-based classification of species, Sci Rep., 10,
21136, https://doi.org/10.1038/s41598-020-77812-6, 2020.
Krizhevsky, A., Sutskever, I., and Hinton, G. E.: ImageNet Classification with
Deep Convolutional Neural Networks, Commun. ACM, 60, 84–90,
https://doi.org/10.1145/3065386, 2012.
Marchant, R., Tetard, M., Pratiwi, A., Adebayo, M., and de Garidel-Thoron,
T.: Automated analysis of foraminifera fossil records by image
classification using a convolutional neural network, J. Micropalaeontol.,
39, 183–202, https://doi.org/10.5194/jm-39-183-2020, 2020.
Meunier, M. and Danelian, T.: Astronomical calibration of late middle Eocene radiolarian bioevents from ODP Site 1260 (equatorial Atlantic, Leg 207) and refinement of the global tropical radiolarian biozonation, J. Micropalaeontol., 41, 1–27, https://doi.org/10.5194/jm-41-1-2022, 2022.
Obut, O. T. and Iwata, K.: Lower Cambrian Radiolaria from the Gorny Altai
(southern West Siberia), Novosti Paleontologii i Stratigrafii, 2/3, 33–37,
2000.
O'Dogherty, L., Caulet, J., Dumitrica, P., and Suzuki, N.: Catalogue of
Cenozoic radiolarian genera (Class Polycystinea), Geodiversitas, 43,
709–1185, https://doi.org/10.5252/geodiversitas2021v43a21, 2021.
Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel,
O., Blondel, M., Prettenhofer, P., Weiss, R., Dubourg, V., Vanderplas, J.,
Passos, A., Cournapeau, D., Brucher, M., Perrot, M., and Duchesnay, E.:
Scikit-learn: Machine Learning in Python, J. Mach. Learn.
Res., 12, 2825–2830, 2011.
Pouille, L., Obut, O., Danelian, T., and Sennikov, N.: Lower Cambrian
(Botomian) policystine Radiolaria from the Altai Mountains (southern
Siberia, Russia), C. R. Palevol, 10, 627–633, 2011.
Renaudie, J., Danelian, T., Saint-Martin, S., Le Callonec, L., and
Tribovillard, N.: Siliceous phytoplankton response to a Middle Eocene
warming event recorded in the tropical Atlantic (Demerara Rise, ODP Site
1260A), Palaeogeogr. Palaeocl., 286, 121–134, https://doi.org/10.1016/j.palaeo.2009.12.004, 2010.
Renaudie, J., Gray, R., and Lazarus, D.: Accuracy of a neural net
classification of closely-related species of microfossils from a sparse
dataset of unedited images, PeerJ Preprints, 6, e27328v1, https://doi.org/10.7287/peerj.preprints.27328v1, 2018.
Riedel, W. R. and Sanfilippo, A.: Radiolaria, Leg 4, Deep Sea Drilling Project, in: Initial Reports of the
Deep Sea Drilling Project, edited by: Bader,
R. G., Gerard, R. D., Hay, W. W., Benson, W. E., Bolli, H. M., Rothwell Jr,
W. T., Ruef, M. H., Riedel, W. R., and Sayles, F. L., Volume IV, Washington, D.C., U.S. Govt. Printing
Office, 503–575, https://doi.org/10.2973/dsdp.proc.4.124.1970, 1970.
Rueckauer, B., Bybee, C., Goettsche, R., Singh, Y., Mishra, J., and Wild, A.:
NxTF: An API and Compiler for Deep Spiking Neural Networks on Intel Loihi, arXiv [preprint], arXiv:2101.04261,
https://doi.org/10.48550/arXiv.2101.04261, 2021.
Sanfilippo, A. and Riedel, W. R.: Moprhometric Analysis of Evolving Eocene Podocyrtis (Radiolaria) Morphotypes Using Shape Coordinates, in: Proceedings of the Michigan Morphometrics Workshop, edited by: Rolph, F. J and Bookstein, F. L., 345–362, University of Michigan Museum of Zoology, Special Publication 2, Ann Arbor, Michigan, 1990.
Sanfilippo, A. and Riedel, W. R.: Cenozoic Radiolaria (exclusive of theoperids, artostrobiids and amphipyndacids) from the Gulf of Mexico, DSDP Leg 10, in: Initial Reports of the Deep Sea Drilling Project, 10, edited by: Worzel, J. L., Bryant, W., Beall Jr., A. O., Capo, R., Dickinson, K., Foreman, H. P., Laury, R., McNeely, B. W., and Smith, L. A., U.S. Govt. Print. Office, Washington, DC, USA, 475–611,
https://doi.org/10.2973/dsdp.proc.10.119.1973, 1973.
Sanfilippo, A. and Riedel, W. R.: The origin and evolution of
Pterocorythidae (Radiolaria): A Cenozoic phylogenetic study,
Micropaleontology, 38, 1–36, 1992.
Sanfilippo, A., Westberg-Smith, M. J., and Riedel, W. R.: Cenozoic
Radiolaria, in:
Plankton Stratigraphy, edited by: Bolli, H. M., Saunders, J. B., and Perch-Nielsen, K., Cambridge University Press, Cambridge, 631–712, ISBN: 9780521367196,
1985.
Shipboard Scientific Party: Site 612, in: Initial reports of the
Deep Sea Drilling Project covering Leg 95 of the cruises of
the drilling vessel Glomar Challenger, 95, 313–337, edited by: Poag, C. W., Watts, A. B., Cousin,
M., Goldberg, D., Hart, M. B., Miller, K. G., Mountain, G. S., Nakamura, Y.,
Palmer, A. A., Schiffelbein, P. A., Schreiber, B. C., Tarafa, M. E., Thein,
J. E., Valentine, P. C., Wilkens, R. H., and Turner, K. L., St. John's, Newfoundland, to Ft.
Lauderdale, Florida, August–September 1983, Texas A & M University, Ocean
Drilling Program, College Station, TX, United States, https://doi.org/10.2973/dsdp.proc.95.103.1987, 1987.
Shipboard Scientific Party: Site 711, in: Proceedings of the Ocean Drilling
Program, Initial Reports, Vol. 115, edited by: Backman, J., Duncan, R. A., Peterson, R. C., Baker, A. B., Baxter, A. L., Boersma, A., Cullen, A., Droxler, A. W., Fisk., M. R., Greenough, J.D., Hargraves, R. B., Hempel., P., Hobart, M. A., Hurley, M. T., Johnson., D. A., Macdonald, A. H., Mikkelsen, N., Okada, H., Rio, D., Robinson, S. G., Schneider, D., Swart, P. K., Tatsumi, Y., Vandamme, D., Vilks, G., Vincent, E (Participating Scientists), Peterson, L. C. (Shipboard Staff Scientist), and Barbu, E. M., Ocean Drilling Program, https://doi.org/10.2973/odp.proc.ir.115.110.1988,
1988.
Shipboard Scientific Party: Site 1051, in: Proceedings of the
Ocean Drilling Program, Initial Reports, 171B, 171–239, edited by: Norris, R. D., Kroon, D., Klaus,
A., Alexander, I. T., Bardot, L. P., Barker, C. E., Bellier, J-P., Blome, C.
D., Clarke, L. J., Erbacher, J., Faul, K. L., Holmes, M. A., Huber, B. T.,
Katz, M. E., MacLeod, K. G., Marca, S., Martinez-Ruiz, F. C., Mita, I.,
Nakai, M., Ogg, J. G., Pak, D. K., Pletsch, T. K., Self-Trail, J. M.,
Shackleton, N. J., Smit, J., Ussler, W., III, Watkins, D. K., Widmark, J.,
Wilson, P. A., Baez, L. A., and Kapitan-White, E., College Station, TX,
https://doi.org/10.2973/odp.proc.ir.171b.105.1998, 1998.
Shipboard Scientific Party: Site 1260, in: Proceedings of the Ocean Drilling
Program, Initial Reports, 207, edited by: Erbacher, J., Mosher, D. C.,
Malone, M. J., Berti, D., Bice, K. L., Bostock, H., Brumsack, H.-J.,
Danelian, T., Forster, A., Glatz, C., Heidersdorf, F., Henderiks, T.,
Janecek, T. R., Junium, C., Le Callonnec, L., MacLeod, K., Meyers, P. A.,
Mutterlose, H. J., Nishi, H., Norris, R. D., Ogg, J. G., O'Regan, A. M.,
Rea, B., Sexton, P., Sturt, H., Suganuma, Y., Thurow, J. W., Wilson, P. A.,
and Wise Jr., S. W., Ocean Drill. Program, College Station, TX, USA, 1–113,
https://doi.org/10.2973/odp.proc.ir.207.107.2004, 2004.
Tetard, M., Marchant, R., Cortese, G., Gally, Y., de Garidel-Thoron, T., and Beaufort, L.: Technical note: A new automated radiolarian image acquisition, stacking, processing, segmentation and identification workflow, Clim. Past, 16, 2415–2429, https://doi.org/10.5194/cp-16-2415-2020, 2020.
Van der Walt, S., Schönberger, J. L., Nunez-Iglesias, J., Boulogne, F.,
Warner, J. D., Yager, N., Gouillart, E., Yu, T., and the scikit-image
contributors: scikit-image: Image processing in Python, PeerJ, 2, 453, https://doi.org/10.7717/peerj.453, 2014.
Van Rossum, G. and Drake, F. L.: Python 3 Reference Manual, Scotts Valley,
CA, CreateSpace, ISBN: 978-1-4414-1269-0, 2009.
Short summary
This study evaluates the use of automatic classification using AI on eight closely related radiolarian species of the genus Podocyrtis based on MobileNet CNN. Species belonging to Podocyrtis are useful for middle Eocene biostratigraphy. Numerous images of Podocyrtis species from the tropical Atlantic Ocean were used to train and validate the CNN. An overall accuracy of about 91 % was obtained. Additional Podocyrtis specimens from other ocean realms were used to test the predictive model.
This study evaluates the use of automatic classification using AI on eight closely related...