A user‐friendly method to get automated pollen analysis from environmental samples
Authors:
- Betty GimenezBGBetty Gimenez
- Sébastien JoanninSJSébastien Joannin
- Jérôme PasquetJPJérôme Pasquet
- Luc BeaufortLBLuc Beaufort
- Thibault de Garidel‐ThoronTGThibault de Garidel‐Thoron
- Nathalie Combourieu‐NeboutNCNathalie Combourieu‐Nebout
- Laurent BoubyLBLaurent Bouby
- Sarah IvorraSISarah Ivorra
- Jean‐Frédéric TerralJTJean‐Frédéric Terral
Open Access
- 28 May 2024
- journal article
- research article
- Published by Wiley in New Phytologist
- Vol. 243 (2) , 797-810
Abstract
Summary: 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.Keywords
This publication has 35 references indexed in Scilit:
- False positives: handling them operationally for automatic pollen monitoringAerobiologia, 2022
- Object detection using YOLO: challenges, architectural successors, datasets and applicationsMultimedia Tools and Applications, 2022
- Pattern recognition methodologies for pollen grain image classification: a surveyMachine Vision and Applications, 2022
- Combating data incompetence in pollen images detection and classification for pollinosis preventionComputers in Biology and Medicine, 2022
- Detection of mold on the food surface using YOLOv5Current Research in Food Science, 2021
- POLLEN73S: An image dataset for pollen grains classificationEcological Informatics, 2020
- Automated recognition by multiple convolutional neural networks of modern, fossil, intact and damaged pollen grainsComputers & Geosciences, 2020
- The discrimination of honey origin using melissopalynology and Raman spectroscopy techniques coupled with multivariate analysisFood Chemistry, 2015
- Annual pollen traps reveal the complexity of climatic control on pollen productivity in Europe and the CaucasusVegetation History and Archaeobotany, 2010
- The needs and prospects for automation in palynologyQuaternary Science Reviews, 1996