Articles | Volume 39, issue 2
https://doi.org/10.5194/jm-39-183-2020
© Author(s) 2020. 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-39-183-2020
© Author(s) 2020. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
Research article
| 
15 Oct 2020
Research article |
| 15 Oct 2020
| 15 Oct 2020
Automated analysis of foraminifera fossil records by image classification using a convolutional neural network
Aix-Marseille Université, CNRS, IRD, Coll. De France, INRAE, CEREGE, Technopôle de l'Arbois-Méditerranée, Aix-en-Provence, 13545, France
School of Electrical Engineering & Robotics, Queensland University of Technology, Brisbane, Australia
Martin Tetard
Aix-Marseille Université, CNRS, IRD, Coll. De France, INRAE, CEREGE, Technopôle de l'Arbois-Méditerranée, Aix-en-Provence, 13545, France
Adnya Pratiwi
Aix-Marseille Université, CNRS, IRD, Coll. De France, INRAE, CEREGE, Technopôle de l'Arbois-Méditerranée, Aix-en-Provence, 13545, France
Michael Adebayo
Aix-Marseille Université, CNRS, IRD, Coll. De France, INRAE, CEREGE, Technopôle de l'Arbois-Méditerranée, Aix-en-Provence, 13545, France
Thibault de Garidel-Thoron
Aix-Marseille Université, CNRS, IRD, Coll. De France, INRAE, CEREGE, Technopôle de l'Arbois-Méditerranée, Aix-en-Provence, 13545, France
Related authors
Martin Tetard, Ross Marchant, Giuseppe Cortese, Yves Gally, Thibault de Garidel-Thoron, and Luc Beaufort
Clim. Past, 16, 2415–2429, https://doi.org/10.5194/cp-16-2415-2020, https://doi.org/10.5194/cp-16-2415-2020, 2020
Short summary
Short summary
Radiolarians are marine micro-organisms that produce a siliceous shell that is preserved in the fossil record and can be used to reconstruct past climate variability. However, their study is only possible after a time-consuming manual selection of their shells from the sediment followed by their individual identification. Thus, we develop a new fully automated workflow consisting of microscopic radiolarian image acquisition, image processing and identification using artificial intelligence.
Babette Hoogakker, Catherine Davis, Yi Wang, Stepanie Kusch, Katrina Nilsson-Kerr, Dalton Hardisty, Allison Jacobel, Dharma Reyes Macaya, Nicolaas Glock, Sha Ni, Julio Sepúlveda, Abby Ren, Alexandra Auderset, Anya Hess, Katrina Meissner, Jorge Cardich, Robert Anderson, Christine Barras, Chandranath Basak, Harold Bradbury, Inda Brinkmann, Alexis Castillo, Madelyn Cook, Kassandra Costa, Constance Choquel, Paula Diz, Jonas Donnenfield, Felix Elling, Zeynep Erdem, Helena Filipsson, Sebastian Garrido, Julia Gottschalk, Anjaly Govindankutty Menon, Jeroen Groeneveld, Christian Hallman, Ingrid Hendy, Rick Hennekam, Wanyi Lu, Jean Lynch-Stieglitz, Lelia Matos, Alfredo Martínez-García, Giulia Molina, Práxedes Muñoz, Simone Moretti, Jennifer Morford, Sophie Nuber, Svetlana Radionovskaya, Morgan Raven, Christopher Somes, Anja Studer, Kazuyo Tachikawa, Raúl Tapia, Martin Tetard, Tyler Vollmer, Shuzhuang Wu, Yan Zhang, Xin-Yuan Zheng, and Yuxin Zhou
EGUsphere, https://doi.org/10.5194/egusphere-2023-2981, https://doi.org/10.5194/egusphere-2023-2981, 2024
Short summary
Short summary
Paleo-oxygen proxies can extend current records, bound pre-anthropogenic baselines, provide datasets necessary to test climate models under different boundary conditions, and ultimately understand how ocean oxygenation responds on longer timescales. Here we summarize current proxies used for the reconstruction of Cenozoic seawater oxygen levels. This includes an overview of the proxy's history, how it works, resources required, limitations, and future recommendations.
Martin Tetard, Laetitia Licari, Ekaterina Ovsepyan, Kazuyo Tachikawa, and Luc Beaufort
Biogeosciences, 18, 2827–2841, https://doi.org/10.5194/bg-18-2827-2021, https://doi.org/10.5194/bg-18-2827-2021, 2021
Short summary
Short summary
Oxygen minimum zones are oceanic regions almost devoid of dissolved oxygen and are currently expanding due to global warming. Investigation of their past behaviour will allow better understanding of these areas and better prediction of their future evolution. A new method to estimate past [O2] was developed based on morphometric measurements of benthic foraminifera. This method and two other approaches based on foraminifera assemblages and porosity were calibrated using 45 core tops worldwide.
Martin Tetard, Ross Marchant, Giuseppe Cortese, Yves Gally, Thibault de Garidel-Thoron, and Luc Beaufort
Clim. Past, 16, 2415–2429, https://doi.org/10.5194/cp-16-2415-2020, https://doi.org/10.5194/cp-16-2415-2020, 2020
Short summary
Short summary
Radiolarians are marine micro-organisms that produce a siliceous shell that is preserved in the fossil record and can be used to reconstruct past climate variability. However, their study is only possible after a time-consuming manual selection of their shells from the sediment followed by their individual identification. Thus, we develop a new fully automated workflow consisting of microscopic radiolarian image acquisition, image processing and identification using artificial intelligence.
Related subject area
Planktic foraminifera
Rediscovering Globigerina bollii Cita and Premoli Silva 1960
Biochronology and evolution of Pulleniatina (planktonic foraminifera)
Globigerinoides rublobatus – a new species of Pleistocene planktonic foraminifera
Analysing planktonic foraminiferal growth in three dimensions with foram3D: an R package for automated trait measurements from CT scans
Spine-like structures in Paleogene muricate planktonic foraminifera
Taxonomic review of living planktonic foraminifera
Upper Eocene planktonic foraminifera from northern Saudi Arabia: implications for stratigraphic ranges
Jurassic planktic foraminifera from the Polish Basin
Middle Jurassic (Bajocian) planktonic foraminifera from the northwest Australian margin
Ontogenetic disparity in early planktic foraminifers
Seasonal and interannual variability in population dynamics of planktic foraminifers off Puerto Rico (Caribbean Sea)
Calcification depth of deep-dwelling planktonic foraminifera from the eastern North Atlantic constrained by stable oxygen isotope ratios of shells from stratified plankton tows
Reproducibility of species recognition in modern planktonic foraminifera and its implications for analyses of community structure
Factors affecting consistency and accuracy in identifying modern macroperforate planktonic foraminifera
Alessio Fabbrini, Maria Rose Petrizzo, Isabella Premoli Silva, Luca M. Foresi, and Bridget S. Wade
J. Micropalaeontol., 43, 121–138, https://doi.org/10.5194/jm-43-121-2024, https://doi.org/10.5194/jm-43-121-2024, 2024
Short summary
Short summary
We report on the rediscovery of Globigerina bollii, a planktonic foraminifer described by Cita and Premoli Silva (1960) in the Mediterranean Basin. We redescribe G. bollii as a valid species belonging to the genus Globoturborotalita. We report and summarise all the recordings of the taxon in the scientific literature. Then we discuss how the taxon might be a palaeogeographical indicator of the intermittent gateways between the Mediterranean Sea, Paratethys, and Indian Ocean.
Paul N. Pearson, Jeremy Young, David J. King, and Bridget S. Wade
J. Micropalaeontol., 42, 211–255, https://doi.org/10.5194/jm-42-211-2023, https://doi.org/10.5194/jm-42-211-2023, 2023
Short summary
Short summary
Planktonic foraminifera are marine plankton that have a long and continuous fossil record. They are used for correlating and dating ocean sediments and studying evolution and past climates. This paper presents new information about Pulleniatina, one of the most widespread and abundant groups, from an important site in the Pacific Ocean. It also brings together a very large amount of information on the fossil record from other sites globally.
Marcin Latas, Paul N. Pearson, Christopher R. Poole, Alessio Fabbrini, and Bridget S. Wade
J. Micropalaeontol., 42, 57–81, https://doi.org/10.5194/jm-42-57-2023, https://doi.org/10.5194/jm-42-57-2023, 2023
Short summary
Short summary
Planktonic foraminifera are microscopic single-celled organisms populating world oceans. They have one of the most complete fossil records; thanks to their great abundance, they are widely used to study past marine environments. We analysed and measured series of foraminifera shells from Indo-Pacific sites, which led to the description of a new species of fossil planktonic foraminifera. Part of its population exhibits pink pigmentation, which is only the third such case among known species.
Anieke Brombacher, Alex Searle-Barnes, Wenshu Zhang, and Thomas H. G. Ezard
J. Micropalaeontol., 41, 149–164, https://doi.org/10.5194/jm-41-149-2022, https://doi.org/10.5194/jm-41-149-2022, 2022
Short summary
Short summary
Foraminifera are sand-grain-sized marine organisms that build spiral shells. When they die, the shells sink to the sea floor where they are preserved for millions of years. We wrote a software package that automatically analyses the fossil spirals to learn about evolution of new shapes in the geological past. With this software we will be able to analyse larger datasets than we currently can, which will improve our understanding of the evolution of new species.
Paul N. Pearson, Eleanor John, Bridget S. Wade, Simon D'haenens, and Caroline H. Lear
J. Micropalaeontol., 41, 107–127, https://doi.org/10.5194/jm-41-107-2022, https://doi.org/10.5194/jm-41-107-2022, 2022
Short summary
Short summary
The microscopic shells of planktonic foraminifera accumulate on the sea floor over millions of years, providing a rich archive for understanding the history of the oceans. We examined an extinct group that flourished between about 63 and 32 million years ago using scanning electron microscopy and show that they were covered with needle-like spines in life. This has implications for analytical methods that we use to determine past seawater temperature and acidity.
Geert-Jan A. Brummer and Michal Kučera
J. Micropalaeontol., 41, 29–74, https://doi.org/10.5194/jm-41-29-2022, https://doi.org/10.5194/jm-41-29-2022, 2022
Short summary
Short summary
To aid researchers working with living planktonic foraminifera, we provide a comprehensive review of names that we consider appropriate for extant species. We discuss the reasons for the decisions we made and provide a list of species and genus-level names as well as other names that have been used in the past but are considered inappropriate for living taxa, stating the reasons.
Bridget S. Wade, Mohammed H. Aljahdali, Yahya A. Mufrreh, Abdullah M. Memesh, Salih A. AlSoubhi, and Iyad S. Zalmout
J. Micropalaeontol., 40, 145–161, https://doi.org/10.5194/jm-40-145-2021, https://doi.org/10.5194/jm-40-145-2021, 2021
Short summary
Short summary
We examined the planktonic foraminifera (calcareous zooplankton) from a section in northern Saudi Arabia. We found the assemblages to be diverse, well-preserved and of late Eocene age. Our study provides new insights into the stratigraphic ranges of many species and indicates that the late Eocene had a higher tropical/subtropical diversity of planktonic foraminifera than previously reported.
Maria Gajewska, Zofia Dubicka, and Malcolm B. Hart
J. Micropalaeontol., 40, 1–13, https://doi.org/10.5194/jm-40-1-2021, https://doi.org/10.5194/jm-40-1-2021, 2021
Marjorie Apthorpe
J. Micropalaeontol., 39, 93–115, https://doi.org/10.5194/jm-39-93-2020, https://doi.org/10.5194/jm-39-93-2020, 2020
Short summary
Short summary
Three well-preserved new species of Middle Jurassic (Bajocian) planktonic foraminifera from the continental margin of northwest Australia are described. This is on the southern shelf of the Tethys Ocean, and these planktonics are the first to be reported from the Jurassic Southern Hemisphere. Described as new are Globuligerina bathoniana australiana n. ssp., G. altissapertura n. sp. and Mermaidogerina loopae n. gen. n. sp. The research is part of a study of regional Jurassic foraminifera.
Sophie Kendall, Felix Gradstein, Christopher Jones, Oliver T. Lord, and Daniela N. Schmidt
J. Micropalaeontol., 39, 27–39, https://doi.org/10.5194/jm-39-27-2020, https://doi.org/10.5194/jm-39-27-2020, 2020
Short summary
Short summary
Changes in morphology during development can have profound impacts on an organism but are hard to quantify as we lack preservation in the fossil record. As they grow by adding chambers, planktic foraminifera are an ideal group to study changes in growth in development. We analyse four different species of Jurassic foraminifers using a micro-CT scanner. The low morphological variability suggests that strong constraints, described in the modern ocean, were already acting on Jurassic specimens.
Anna Jentzen, Joachim Schönfeld, Agnes K. M. Weiner, Manuel F. G. Weinkauf, Dirk Nürnberg, and Michal Kučera
J. Micropalaeontol., 38, 231–247, https://doi.org/10.5194/jm-38-231-2019, https://doi.org/10.5194/jm-38-231-2019, 2019
Short summary
Short summary
The study assessed the population dynamics of living planktic foraminifers on a weekly, seasonal, and interannual timescale off the coast of Puerto Rico to improve our understanding of short- and long-term variations. The results indicate a seasonal change of the faunal composition, and over the last decades. Lower standing stocks and lower stable carbon isotope values of foraminifers in shallow waters can be linked to the hurricane Sandy, which passed the Greater Antilles during autumn 2012.
Andreia Rebotim, Antje Helga Luise Voelker, Lukas Jonkers, Joanna J. Waniek, Michael Schulz, and Michal Kucera
J. Micropalaeontol., 38, 113–131, https://doi.org/10.5194/jm-38-113-2019, https://doi.org/10.5194/jm-38-113-2019, 2019
Short summary
Short summary
To reconstruct subsurface water conditions using deep-dwelling planktonic foraminifera, we must fully understand how the oxygen isotope signal incorporates into their shell. We report δ18O in four species sampled in the eastern North Atlantic with plankton tows. We assess the size and crust effect on the isotopic δ18O and compared them with predictions from two equations. We reveal different patterns of calcite addition with depth, highlighting the need to perform species-specific calibrations.
Nadia Al-Sabouni, Isabel S. Fenton, Richard J. Telford, and Michal Kučera
J. Micropalaeontol., 37, 519–534, https://doi.org/10.5194/jm-37-519-2018, https://doi.org/10.5194/jm-37-519-2018, 2018
Short summary
Short summary
In this study we investigate consistency in species-level identifications and whether disagreements are predictable. Overall, 21 researchers from across the globe identified sets of 300 specimens or digital images of planktonic foraminifera. Digital identifications tended to be more disparate. Participants trained by the same person often had more similar identifications. Disagreements hardly affected transfer-function temperature estimates but produced larger differences in diversity metrics.
Isabel S. Fenton, Ulrike Baranowski, Flavia Boscolo-Galazzo, Hannah Cheales, Lyndsey Fox, David J. King, Christina Larkin, Marcin Latas, Diederik Liebrand, C. Giles Miller, Katrina Nilsson-Kerr, Emanuela Piga, Hazel Pugh, Serginio Remmelzwaal, Zoe A. Roseby, Yvonne M. Smith, Stephen Stukins, Ben Taylor, Adam Woodhouse, Savannah Worne, Paul N. Pearson, Christopher R. Poole, Bridget S. Wade, and Andy Purvis
J. Micropalaeontol., 37, 431–443, https://doi.org/10.5194/jm-37-431-2018, https://doi.org/10.5194/jm-37-431-2018, 2018
Short summary
Short summary
In this study we investigate consistency in species-level identifications and whether disagreements are predictable. Twenty-three scientists identified a set of 100 planktonic foraminifera, noting their confidence in each identification. The median accuracy of students was 57 %; 79 % for experienced researchers. Where they were confident in the identifications, the values are 75 % and 93 %, respectively. Accuracy was significantly higher if the students had been taught how to identify species.
Cited articles
Abadi, M., Agarwal, A., Barham, P., Brevdo, E., Chen, Z., Citro, C., Corrado,
G. S., Davis, A., Dean, J., Devin, M., Ghemawat, S., Goodfellow, I., Harp,
A., Irving, G., Isard, M., Jia, Y., Jozefowicz, R., Kaiser, L., Kudlur, M.,
Levenberg, J., Mane, D., Monga, R., Moore, S., Murray, D., Olah, C.,
Schuster, M., Shlens, J., Steiner, B., Sutskever, I., Talwar, K., Tucker, P.,
Vanhoucke, V., Vasudevan, V., Viegas, F., Vinyals, O., Warden, P.,
Wattenberg, M., Wicke, M., Yu, Y., and Zheng, X.: TensorFlow: Large-Scale
Machine Learning on Heterogeneous Distributed Systems, arXiv [preprint], arXiv:1603.04467, 2016. a
Barbarin, N.: La reconnaissance automatisée des nannofossiles calcaires
du cénozoïque, PhD thesis, Aix-Marseille Université, Aix-en-Provence, France, 2014. a
Beaufort, L.: IMAGES 3-IPHIS-MD106 cruise, RV Marion Dufresne, French Oceanographic Cruises, SISMER,
https://doi.org/10.17600/97200010, 1997. a
Beaufort, L.: MD 126/MONA cruise, RV Marion Dufresne, French Oceanographic Cruises, SISMER, https://doi.org/10.17600/2200040, 2002. a
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. a, b
Beaufort, L., de Garidel‐Thoron, T., Mix, A., and Pisias, N.: 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. a
Bollmann, J., Quinn, P. S., Vela, M., Brabec, B., Brechner, S., Cortés,
M. Y., Hilbrecht, H., Schmidt, D. N., Schiebel, R., and Thierstein, H. R.:
Image Analysis, Sediments and Paleoenvironments,
Dev. Paleoenviron. Res., Kluwer Academic Publishers,
Dordrecht, 7, 229–252, https://doi.org/10.1007/1-4020-2122-4, 2005. a, b
Caromel, A. G. M., Schmidt, D. N., Fletcher, I., and Rayfield, E. J.: Morphological Change During The Ontogeny Of The Planktic Foraminifera, J. Micropalaeontol., 35, 2–19, https://doi.org/10.1144/jmpaleo2014-017, 2016. a
Cartapanis, O., Tachikawa, K., and Bard, E.: Northeastern Pacific oxygen
minimum zone variability over the past 70 kyr: Impact of biological
production and oceanic ventilation, Paleoceanography, 26, 4,
https://doi.org/10.1029/2011PA002126, 2011. a
Cartapanis, O., Tachikawa, K., Romero, O. E., and Bard, E.: Persistent millennial-scale link between Greenland climate and northern Pacific Oxygen Minimum Zone under interglacial conditions, Clim. Past, 10, 405–418, https://doi.org/10.5194/cp-10-405-2014, 2014. a
CLIMAP: Seasonal reconstruction of the earth's surface at the last glacial
maximum, Geological Society of America, Map and Chart Series, 36, 18 pp., 1981. a
Culverhouse, P., Simpson, R., Ellis, R., Lindley, J., Williams, R., Parisini,
T., Reguera, B., Bravo, I., Zoppoli, R., Earnshaw, G., McCall, H., and Smith,
G.: Automatic classification of field-collected dinoflagellates by
artificial neural network, Mar. Ecol. Prog. Ser., 139, 281–287,
https://doi.org/10.3354/meps139281, 1996. a, b, c, d
Culverhouse, P., Williams, R., Reguera, B., Herry, V., and González-Gil, S.:
Do experts make mistakes? A comparison of human and machine identification
of dinoflagellates, Mar. Ecol. Prog. Ser., 247, 17–25,
https://doi.org/10.3354/meps247017, 2003. a
de Garidel‐Thoron, T., Rosenthal, Y., Beaufort, L., Bard, E., Sonzogni, C.,
and Mix, A.: A multiproxy assessment of the western equatorial Pacific
hydrography during the last 30 kyr, Paleoceanography, 22, 1–18,
https://doi.org/10.1029/2006PA001269, 2007. a, b, c
Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., and Fei-Fei, L.:
ImageNet: A large-scale hierarchical image database, in: 2009 IEEE
Conference on Computer Vision and Pattern Recognition, 20-25 June 2009, Miami, FL, USA, 9, 248–255,
IEEE, https://doi.org/10.1109/CVPR.2009.5206848, 2009. a
Dieleman, S., De Fauw, J., and Kavukcuoglu, K.: Exploiting Cyclic Symmetry
in Convolutional Neural Networks, arXiv [preprint], arXiv:1602.02660, 2016. a, b
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. a
Fenton, I. S., Baranowski, U., Boscolo-Galazzo, F., Cheales, H., Fox, L., King, D. J., Larkin, C., Latas, M., Liebrand, D., Miller, C. G., Nilsson-Kerr, K., Piga, E., Pugh, H., Remmelzwaal, S., Roseby, Z. A., Smith, Y. M., Stukins, S., Taylor, B., Woodhouse, A., Worne, S., Pearson, P. N., Poole, C. R., Wade, B. S., and Purvis, A.: Factors affecting consistency and accuracy in identifying modern macroperforate planktonic foraminifera, J. Micropalaeontol., 37, 431–443, https://doi.org/10.5194/jm-37-431-2018, 2018. a
Ge, Q., Zhong, B., Kanakiya, B., Mitra, R., Marchitto, T., and Lobaton, E.:
Coarse-to-fine foraminifera image segmentation through 3D and deep
features, in: 2017 IEEE Symposium Series on Computational Intelligence, SSCI
2017 – Proceedings, January 2018, Honolulu, HI, USA, 1–8, https://doi.org/10.1109/SSCI.2017.8280982, 2018. a
Gradstein, F. M., Ogg, J. G., Schmitz, M. B., and Ogg, G. M.: The Geologic Time
Scale 2012, Vol. 2, 1144 pp., Elsevier, Amsterdam, Boston, 2012. a
He, K., Zhang, X., Ren, S., and Sun, J.: Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification, 2015 IEEE International Conference on Computer Vision (ICCV), Santiago, 2015, 1026–1034, https://doi.org/10.1109/ICCV.2015.123, 2015. a
He, K., Zhang, X., Ren, S., and Sun, J.: Deep Residual Learning for Image Recognition, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, 770–778, https://doi.org/10.1109/CVPR.2016.90, 2016a. a, b, c, d
He, K., Zhang, X., Ren, S., and Sun, J.: Identity Mappings in Deep Residual Networks, in: Computer Vision – ECCV 2016, edited by: Leibe, B., Matas, J., Sebe, N., and Welling, M., ECCV 2016. Lecture Notes in Computer Science, vol 9908. Springer, Cham., https://doi.org/10.1007/978-3-319-46493-0_38, 2016b. a, b, c
Hibbett, D.: Automated Taxon Identification in Systematics: Theory,
Approaches and Applications, The Systematics Association Special Volumes
Series, Volume 74, Edited by Norman MacLeod, CRC Press, Group, Boca Raton (Florida): Taylor & Francis, $99.95. xvii +339 p., 2007, Q. Rev.
Biol., 84, 295–296, https://doi.org/10.1086/644681, 2009. a
Hinton, G. E., Srivastava, N., Krizhevsky, A., Sutskever, I., and
Salakhutdinov, R. R.: Improving neural networks by preventing co-adaptation
of feature detectors, arXiv [preprint], arXiv:1207.0580, 2012. a, b, c
Hsiang, A. Y., Brombacher, A., Rillo, M. C., Mleneck‐Vautravers, M. J., Conn,
S., Lordsmith, S., Jentzen, A., Henehan, M. J., 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., Miller, C. G., Rios,
N., and Hull, P. M.: Endless Forams: >34000 Modern Planktonic
Foraminiferal Images for Taxonomic Training and Automated Species Recognition
Using Convolutional Neural Networks, Paleoceanography and Paleoclimatology,
34, 1157–1177, https://doi.org/10.1029/2019pa003612, 2019. a, b, c, d, e, f
Huang, G., Liu, Z., and Weinberger, K. Q.: Densely Connected Convolutional
Networks, in 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, 21–26 July 2017, 2261–2269, https://doi.org/10.1109/CVPR.2017.243, 2017. a
King, D. E.: Dlibml: A Machine Learning Toolkit, J. Mach. Learn. Res., 10, 1755–1758, 2009. a
Kingma, D. P. and Ba, J.: Adam: A Method for Stochastic Optimization, arXiv [preprint], arXiv:1412.6980, 2014. a
Krizhevsky, A., Sutskever, I., and Hinton, G. E.: ImageNet Classification with
Deep Convolutional Neural Networks, Adv. Neur. In., 7, 84–90,
https://doi.org/10.1145/3065386, 2012. a
Kucera, M.: Chapter Six Planktonic Foraminifera as Tracers of Past Oceanic
Environments, in: Developments in Marine Geology, edited by: Hillaire-Marcel Anne de Vernal, C., 213–262,
https://doi.org/10.1016/S1572-5480(07)01011-1, Elsevier, Amsterdam, 2007. a
Liu, S., Thonnat, M., and Berthod, M.: Automatic classification of planktonic
foraminifera by a knowledge-based system, in: Proceedings of the Tenth Conference on Artificial Intelligence for Applications, San Antonia, TX, USA, 1994, 358–364, https://doi.org/10.1109/CAIA.1994.323653, 1994. a
Marchant, R.: ParticleTrieur and MISO help and tutorials, available at: http://particle-classification.readthedocs.io, last access: 2 October 2020a. a
Marchant, R.: Particle Classification Library, Zenodo, https://doi.org/10.5281/zenodo.3996358, 2020b. a
Marchant, R., Tetard, M., Pratiwi, A., Adebayo, M., and de Garidel-Thoron, T.:
Endless Foram, MD022508 and MD9712138 training datasets, Zenodo,
https://doi.org/10.5281/zenodo.3996436, 2020. a
Mitra, R., Marchitto, T. M., Ge, Q., Zhong, B., Kanakiya, B., Cook, M. S.,
Fehrenbacher, J. S., Ortiz, J. D., Tripati, A., and Lobaton, E.: Automated
species-level identification of planktic foraminifera using convolutional
neural networks, with comparison to human performance, Mar. Micropaleontol., 147, 16–24, https://doi.org/10.1016/j.marmicro.2019.01.005, 2019. a, b, c
Nair, V. and Hinton, G.: Rectified Linear Units Improve Restricted Boltzmann
Machines, in: ICML'10: Proceedings of the 27th International Conference on
International Conference on Machine Learning, June 2010, Haifa, Israel, 807–814,
https://dl.acm.org/doi/10.5555/3104322.3104425, 2010. a
Pedraza, A., Bueno, G., Deniz, O., Cristóbal, G., Blanco, S., and
Borrego-Ramos, M.: Automated diatom classification (Part B): A deep learning
approach, Appl. Sci., 7, 1–25, https://doi.org/10.3390/app7050460, 2017. a
Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., Huang, Z.,
Karpathy, A., Khosla, A., Bernstein, M., Berg, A. C., and Fei-Fei, L.:
ImageNet Large Scale Visual Recognition Challenge, Int. J. Comput. Vision, 115, 211–252, https://doi.org/10.1007/s11263-015-0816-y,
2015. a
Schmidhuber, J.: Deep Learning in Neural Networks: An Overview, Neural Networks, 61, 85–117, https://doi.org/10.1016/j.neunet.2014.09.003,
2015. a
Schulze, K., Tillich, U. M., Dandekar, T., and Frohme, M.: PlanktoVision –
an automated analysis system for the identification of phytoplankton, BMC
Bioinformatics, 14, 115, https://doi.org/10.1186/1471-2105-14-115,
2013. a
Simard, P., Steinkraus, D., and Platt, J.: Best practices for convolutional
neural networks applied to visual document analysis, in: Proceedings of the Seventh International Conference on Document Analysis and Recognition (ICDAR 2003), 6 August 2003, Edinburgh, UK, 958–963, https://doi.org/10.1109/ICDAR.2003.1227801,
2003. a
Simonyan, K. and Zisserman, A.: Very Deep Convolutional Networks for
Large-Scale Image Recognition, arXiv [preprint], arXiv:1409.1556, 2015. a
Simpson, R., Williams, R., Ellis, R., and Culverhouse, P.: Biological pattern
recognition by neural networks, Mar. Ecol. Prog. Ser., 79,
303–308, 1992. a
Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., and Rabinovich, A.: Going deeper with convolutions, in: 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 7–12 June 2015, Boston, MA, USA, 1–9, https://doi.org/10.1109/CVPR.2015.7298594, 2015. a
Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., and Wojna, Z.: Rethinking
the Inception Architecture for Computer Vision, in: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 27–30 June 2016, Las Vegas, NV, 2818–2826 https://doi.org/10.1109/CVPR.2016.308, 2016. a
Thompson, P. R., Bé, A. W., Duplessy, J.-C., and Shackleton, N. J.:
Disappearance of pink-pigmented Globigerinoides ruber at 120 000 yr BP in the
Indian and Pacific Oceans, Nature, 280, 554–558, https://doi.org/10.1038/280554a0, 1979. a
Wilson, A. C., Roelofs, R., Stern, M., Srebro, N., and Recht, B.: The Marginal Value of Adaptive Gradient Methods in Machine Learning, in: Proceedings of the 31st International Conference on Neural Information Processing Systems, 4151–4161, Curran Associates Inc., Red Hook, NY, USA, 2017. a
Xie, S., Girshick, R., Dollár, P., Tu, Z., and He, K.: Aggregated Residual Transformations for Deep Neural Networks, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, 2017, 5987–5995, https://doi.org/10.1109/CVPR.2017.634, 2017. a
Yu, S., Saint-Marc, P., Thonnat, M., and Berthod, M.: Feasibility study of
automatic identification of planktic foraminifera by computer vision,
J. Foramin. Res., 26, 113–123,
https://doi.org/10.2113/gsjfr.26.2.113,
1996. a
Zagoruyko, S. and Komodakis, N.: Wide Residual Networks, in: Proceedings of the British Machine Vision Conference (BMVC), edited by: Wilson, R. C., Hancock, E. R., and Smith, W. A. P., 87.1–87.12, BMVA Press, https://doi.org/10.5244/C.30.87, 2016. a, b
Zhong, B., Ge, Q., Kanakiya, B., Mitra, R., Marchitto, R. M. T., and Lobaton,
E.: A comparative study of image classification algorithms for Foraminifera
identification, in: 2017 IEEE Symposium Series on Computational Intelligence,
SSCI 2017 – Proceedings, 27 November–1 December 2017, 1–8, https://doi.org/10.1109/SSCI.2017.8285164,
2018. a, b, c
Short summary
Foraminifera are marine microorganisms with a calcium carbonate shell. Their fossil remains build up on the seafloor, forming kilometres of sediment over time. From analysis of the foraminiferal record we can estimate past climate conditions and the geological history of the Earth. We have developed an artificial intelligence system for automatically identifying foraminifera species, replacing the time-consuming manual approach and thus helping to make these analyses more efficient and accurate.
Foraminifera are marine microorganisms with a calcium carbonate shell. Their fossil remains...
