A user-friendly method to get automated pollen analysis from environmental samples.

Autor: Gimenez B; ISEM, Univ Montpellier, CNRS, IRD, 34090, Montpellier, France., Joannin S; ISEM, Univ Montpellier, CNRS, IRD, 34090, Montpellier, France.; School of Earth, Environment & Society, McMaster University, L8S 4K1, Hamilton, ON, Canada., Pasquet J; AMIS, Univ Paul-Valérie Montpellier 3, 34090, Montpellier, France.; TETIS, INRAE, AgroParisTech, Cirad, CNRS, Univ Montpellier, 34090, Montpellier, France., Beaufort L; CEREGE, Aix Marseille Université, CNRS, IRD, Coll. France, INRAE, 13545, Aix-en-Provence, France., Gally Y; CEREGE, Aix Marseille Université, CNRS, IRD, Coll. France, INRAE, 13545, Aix-en-Provence, France., de Garidel-Thoron T; CEREGE, Aix Marseille Université, CNRS, IRD, Coll. France, INRAE, 13545, Aix-en-Provence, France., Combourieu-Nebout N; UMR 7194 CNRS, MNHN, HNHP, Institut de Paleontologie Humaine, 75013, Paris, France., Bouby L; ISEM, Univ Montpellier, CNRS, IRD, 34090, Montpellier, France., Canal S; ISEM, Univ Montpellier, CNRS, IRD, 34090, Montpellier, France., Ivorra S; ISEM, Univ Montpellier, CNRS, IRD, 34090, Montpellier, France., Limier B; ISEM, Univ Montpellier, CNRS, IRD, 34090, Montpellier, France.; INRAE, Centre Occitanie-Montpellier, 34000, Montpellier, France., Terral JF; ISEM, Univ Montpellier, CNRS, IRD, 34090, Montpellier, France., Devaux C; ISEM, Univ Montpellier, CNRS, IRD, 34090, Montpellier, France.; Institut de Recherche en Biologie Végétale, Département de Sciences Biologiques, Université de Montréal, H1X 2B2, Montreal, QC, Canada., Peyron O; ISEM, Univ Montpellier, CNRS, IRD, 34090, Montpellier, France.
Jazyk: angličtina
Zdroj: The New phytologist [New Phytol] 2024 Jul; Vol. 243 (2), pp. 797-810. Date of Electronic Publication: 2024 May 28.
DOI: 10.1111/nph.19857
Abstrakt: Automated pollen analysis is not yet efficient on environmental samples containing many pollen taxa and debris, which are typical in most pollen-based studies. Contrary to classification, detection remains overlooked although it is the first step from which errors can propagate. Here, we investigated a simple but efficient method to automate pollen detection for environmental samples, optimizing workload and performance. We applied the YOLOv5 algorithm on samples containing debris and c. 40 Mediterranean plant taxa, designed and tested several strategies for annotation, and analyzed variation in detection errors. About 5% of pollen grains were left undetected, while 5% of debris were falsely detected as pollen. Undetected pollen was mainly in poor-quality images, or of rare and irregular morphology. Pollen detection remained effective when applied to samples never seen by the algorithm, and was not improved by spending time to provide taxonomic details. Pollen detection of a single model taxon reduced annotation workload, but was only efficient for morphologically differentiated taxa. We offer guidelines to plant scientists to analyze automatically any pollen sample, providing sound criteria to apply for detection while using common and user-friendly tools. Our method contributes to enhance the efficiency and replicability of pollen-based studies.
(© 2024 The Authors. New Phytologist © 2024 New Phytologist Foundation.)
Databáze: MEDLINE
Externí odkaz: