{"id":14289,"date":"2023-01-10T16:54:43","date_gmt":"2023-01-10T15:54:43","guid":{"rendered":"https:\/\/www.cerege.fr\/?page_id=14289"},"modified":"2023-02-01T09:56:39","modified_gmt":"2023-02-01T08:56:39","slug":"applications-micropaleontologie-automatisee-2","status":"publish","type":"page","link":"https:\/\/www.cerege.fr\/fr\/equipements\/poles-techniques\/micropaleontologie-automatisee\/applications-micropaleontologie-automatisee-2\/","title":{"rendered":"Applications Micropal\u00e9ontologie automatis\u00e9e"},"content":{"rendered":"\t\t<div data-elementor-type=\"wp-page\" data-elementor-id=\"14289\" class=\"elementor elementor-14289\" data-elementor-post-type=\"page\">\n\t\t\t\t\t\t<section class=\"elementor-section elementor-top-section elementor-element elementor-element-581763d2 elementor-section-full_width elementor-section-height-min-height elementor-section-height-default elementor-section-items-middle\" data-id=\"581763d2\" data-element_type=\"section\" data-e-type=\"section\" data-settings=\"{&quot;background_background&quot;:&quot;classic&quot;}\">\n\t\t\t\t\t\t<div class=\"elementor-container elementor-column-gap-default\">\n\t\t\t\t\t<div class=\"elementor-column elementor-col-100 elementor-top-column elementor-element elementor-element-1b97b22b\" data-id=\"1b97b22b\" data-element_type=\"column\" data-e-type=\"column\">\n\t\t\t<div class=\"elementor-widget-wrap\">\n\t\t\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/section>\n\t\t\t\t<section class=\"elementor-section elementor-top-section elementor-element elementor-element-53a56ad9 elementor-section-boxed elementor-section-height-default elementor-section-height-default\" data-id=\"53a56ad9\" data-element_type=\"section\" data-e-type=\"section\">\n\t\t\t\t\t\t<div class=\"elementor-container elementor-column-gap-default\">\n\t\t\t\t\t<div class=\"elementor-column elementor-col-100 elementor-top-column elementor-element elementor-element-a524c3c\" data-id=\"a524c3c\" data-element_type=\"column\" data-e-type=\"column\">\n\t\t\t<div class=\"elementor-widget-wrap elementor-element-populated\">\n\t\t\t\t\t\t<div class=\"elementor-element elementor-element-7e9dd683 elementor-widget elementor-widget-shortcode\" data-id=\"7e9dd683\" data-element_type=\"widget\" data-e-type=\"widget\" data-widget_type=\"shortcode.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t<div class=\"elementor-shortcode\"><nav aria-label=\"breadcrumbs\">\n            <div class=\"breadcrumb-container theme1\">\n                <ol>\n                                    <\/ol>\n            <\/div>\n        <\/nav>    <script type=\"application\/ld+json\">\n        {\n            \"@context\": \"http:\/\/schema.org\",\n            \"@type\": \"BreadcrumbList\",\n            \"itemListElement\": [\n                            ]\n        }\n    <\/script>\n   \n    <script>\n            <\/script>\n<\/div>\n\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/section>\n\t\t\t\t<section class=\"elementor-section elementor-top-section elementor-element elementor-element-16a04d8e elementor-section-boxed elementor-section-height-default elementor-section-height-default\" data-id=\"16a04d8e\" data-element_type=\"section\" data-e-type=\"section\">\n\t\t\t\t\t\t<div class=\"elementor-container elementor-column-gap-extended\">\n\t\t\t\t\t<div class=\"elementor-column elementor-col-50 elementor-top-column elementor-element elementor-element-6113c0a6\" data-id=\"6113c0a6\" data-element_type=\"column\" data-e-type=\"column\">\n\t\t\t<div class=\"elementor-widget-wrap elementor-element-populated\">\n\t\t\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t<div class=\"elementor-column elementor-col-50 elementor-top-column elementor-element elementor-element-405301d9\" data-id=\"405301d9\" data-element_type=\"column\" data-e-type=\"column\">\n\t\t\t<div class=\"elementor-widget-wrap elementor-element-populated\">\n\t\t\t\t\t\t<div class=\"elementor-element elementor-element-303c2f2b elementor-widget elementor-widget-heading\" data-id=\"303c2f2b\" data-element_type=\"widget\" data-e-type=\"widget\" data-widget_type=\"heading.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t<h2 class=\"elementor-heading-title elementor-size-default\">SYRACO<\/h2>\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-1c48a468 elementor-widget elementor-widget-text-editor\" data-id=\"1c48a468\" data-element_type=\"widget\" data-e-type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t\t\t<p>SYRACO (SYst\u00e8me de Reconnaissance Automatique de COccolithes) est en d\u00e9veloppement depuis 1994. Les premiers r\u00e9seaux de neurones utilisant la r\u00e9tropropagation du gradient de l\u2019erreur (Backpropagation) ont \u00e9t\u00e9 \u00e9crits en C++ par Denis Dollfus (th\u00e8se CEREGE en 1997) dans une version originale (Dollfus et Beaufort, Fat neural network for recognition of position-normalised objects, <em>Neural Networks, <\/em>1998).<\/p><p>Un prototype de microscope a \u00e9t\u00e9 automatis\u00e9 au CEREGE 1996 puis remplac\u00e9 par un microscope automatis\u00e9 par Leica en 1997.<\/p><p>SYRACO permit la premi\u00e8re publication de r\u00e9sultats scientifiques provenant de l\u2019intelligence artificielle (Beaufort et al., ENSO-like forcing on Oceanic Primary Production during the late Pleistocene,\u00a0 <em>Science<\/em> 2001).<\/p><p>SYRACO a ensuite \u00e9volu\u00e9 en suivant les avanc\u00e9es technologiques des ordinateurs (rapidit\u00e9), des r\u00e9seaux de neurones (ex.: augmentation du nombre de couches), des cam\u00e9ras, de l\u2019optique (passage successivement de la polarisation lin\u00e9aire, rotative, circulaire \u00e0 bidirectionnal circular polarization (Beaufort et al., A universal method for measuring the thickness of microscopic calcite crystals, based on bidirectional circular polarization, Biogeosc., 2021)).<\/p><p>La premi\u00e8re \u00e9tude de microcharbons d\u00e9tect\u00e9s automatiquement a \u00e9t\u00e9 publi\u00e9e en 2003 (Beaufort et al., Continental Biomass Burning and Oceanic Primary Production Estimates in the Sulu Sea Over the Last 380 kyr and the East Asian Monsoon Dynamics, <em>Mar. Geol<\/em>. 2003)<\/p><p>La d\u00e9tection de coccosph\u00e8res non fossiles dans des \u00e9chantillons d\u2019eau marine a \u00e9t\u00e9 publi\u00e9e en 2008: Beaufort et a. Calcite production by Coccolithophores in the South East Pacific Ocean, BioGeosc. 2008.<\/p><p>Gr\u00e2ce \u00e0 l\u2019ANR FIRST nous avons d\u00e9velopp\u00e9 un Syst\u00e8me d&#8217;imagerie et de tri automatique de foraminif\u00e8res (contact Thibault de Garidel-Thoron : <a href=\"mailto:garidel@cerege.fr\">garidel@cerege.fr<\/a>)avec un d\u00e9veloppement d\u2019un robot de tri (MISO) par la soci\u00e9t\u00e9 ATG. (Marchant et al., Automated analysis of foraminifera fossil records by image classification using a convolutional neural network. <em>\u00a0J. Micropalaeontol. <\/em>2020.<\/p><p>La classification automatique des radiolaires a d\u00e9but\u00e9 en 2020 (Tetard, et al., A new automated radiolarian image acquisition, stacking, processing, segmentation and identification workflow. Climate of the Past 2020) en m\u00eame temps que celle des pollens (Bourel, et al., Automated recognition by multiple convolutional neural networks of modern, fossil, intact and damaged pollen grains, Computers &amp; Geosciences 2020)<\/p><p>Un syst\u00e8me de suivi de culture automatis\u00e9e avec prise de vue diurne et \u00ab\u00a0nocturne\u00a0\u00bb acceptant jusqu\u2019\u00e0 48 cultures simultan\u00e9es de souches distinctes de coccolithophores dans une atmosph\u00e8re<\/p>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/section>\n\t\t\t\t<\/div>\n\t\t","protected":false},"excerpt":{"rendered":"<p>SYRACO SYRACO (SYst\u00e8me de Reconnaissance Automatique de COccolithes) est en d\u00e9veloppement depuis 1994. Les premiers r\u00e9seaux de neurones utilisant la r\u00e9tropropagation du gradient de l\u2019erreur (Backpropagation) ont \u00e9t\u00e9 \u00e9crits en [&hellip;]<\/p>\n","protected":false},"author":551,"featured_media":12643,"parent":9324,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"","meta":{"_acf_changed":false,"footnotes":""},"class_list":["post-14289","page","type-page","status-publish","has-post-thumbnail","hentry"],"acf":[],"publishpress_future_action":{"enabled":false,"date":"2026-04-22 06:21:30","action":"change-status","newStatus":"draft","terms":[],"taxonomy":"","extraData":[]},"publishpress_future_workflow_manual_trigger":{"enabledWorkflows":[]},"_links":{"self":[{"href":"https:\/\/www.cerege.fr\/fr\/wp-json\/wp\/v2\/pages\/14289","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.cerege.fr\/fr\/wp-json\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/www.cerege.fr\/fr\/wp-json\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/www.cerege.fr\/fr\/wp-json\/wp\/v2\/users\/551"}],"replies":[{"embeddable":true,"href":"https:\/\/www.cerege.fr\/fr\/wp-json\/wp\/v2\/comments?post=14289"}],"version-history":[{"count":5,"href":"https:\/\/www.cerege.fr\/fr\/wp-json\/wp\/v2\/pages\/14289\/revisions"}],"predecessor-version":[{"id":16415,"href":"https:\/\/www.cerege.fr\/fr\/wp-json\/wp\/v2\/pages\/14289\/revisions\/16415"}],"up":[{"embeddable":true,"href":"https:\/\/www.cerege.fr\/fr\/wp-json\/wp\/v2\/pages\/9324"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.cerege.fr\/fr\/wp-json\/wp\/v2\/media\/12643"}],"wp:attachment":[{"href":"https:\/\/www.cerege.fr\/fr\/wp-json\/wp\/v2\/media?parent=14289"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}