Your browser doesn't support javascript.
loading
Pollen identification through convolutional neural networks: First application on a full fossil pollen sequence.
Durand, Médéric; Paillard, Jordan; Ménard, Marie-Pier; Suranyi, Thomas; Grondin, Pierre; Blarquez, Olivier.
Afiliación
  • Durand M; Département de Géographie, Université de Montréal, Montréal, Québec, Canada.
  • Paillard J; Département de Géographie, Université de Montréal, Montréal, Québec, Canada.
  • Ménard MP; Département de Géographie, Université de Montréal, Montréal, Québec, Canada.
  • Suranyi T; Département de Géographie, Université de Montréal, Montréal, Québec, Canada.
  • Grondin P; Laboratoire Chrono-Environnement, UMR 6249 CNRS, Université de Franche-Comté, Besançon, France.
  • Blarquez O; Direction de la recherche forestière, Ministère des Ressources naturelles et des Forêts, Québec City, Québec, Canada.
PLoS One ; 19(4): e0302424, 2024.
Article en En | MEDLINE | ID: mdl-38687746
ABSTRACT
The automation of pollen identification has seen vast improvements in the past years, with Convolutional Neural Networks coming out as the preferred tool to train models. Still, only a small portion of works published on the matter address the identification of fossil pollen. Fossil pollen is commonly extracted from organic sediment cores and are used by paleoecologists to reconstruct past environments, flora, vegetation, and their evolution through time. The automation of fossil pollen identification would allow paleoecologists to save both time and money while reducing bias and uncertainty. However, Convolutional Neural Networks require a large amount of data for training and databases of fossilized pollen are rare and often incomplete. Since machine learning models are usually trained using labelled fresh pollen associated with many different species, there exists a gap between the training data and target data. We propose a method for a large-scale fossil pollen identification workflow. Our proposed method employs an accelerated fossil pollen extraction protocol and Convolutional Neural Networks trained on the labelled fresh pollen of the species most commonly found in Northeastern American organic sediments. We first test our model on fresh pollen and then on a full fossil pollen sequence totalling 196,526 images. Our model achieved an average per class accuracy of 91.2% when tested against fresh pollen. However, we find that our model does not perform as well when tested on fossil data. While our model is overconfident in its predictions, the general abundance patterns remain consistent with the traditional palynologist IDs. Although not yet capable of accurately classifying a whole fossil pollen sequence, our model serves as a proof of concept towards creating a full large-scale identification workflow.
Asunto(s)

Texto completo: 1 Colección: 01-internacional Base de datos: MEDLINE Asunto principal: Polen / Redes Neurales de la Computación / Fósiles Idioma: En Revista: PLoS One Asunto de la revista: CIENCIA / MEDICINA Año: 2024 Tipo del documento: Article País de afiliación: Canadá Pais de publicación: Estados Unidos

Texto completo: 1 Colección: 01-internacional Base de datos: MEDLINE Asunto principal: Polen / Redes Neurales de la Computación / Fósiles Idioma: En Revista: PLoS One Asunto de la revista: CIENCIA / MEDICINA Año: 2024 Tipo del documento: Article País de afiliación: Canadá Pais de publicación: Estados Unidos