Automatic recognition of flow cytometric phytoplankton functional groups using convolutional neural networks
Authors:
- Robin FuchsRFRobin Fuchs
- Melilotus ThyssenMTMelilotus Thyssen
- Véronique CreachVCVéronique Creach
- Mathilde DugenneMDMathilde Dugenne
- Lloyd IzardLILloyd Izard
- Arnaud LouchartALArnaud Louchart
- Pierre MarrecPMPierre Marrec
- Machteld RijkeboerMRMachteld Rijkeboer
- Gérald GrégoriGGGérald Grégori
- Denys PommeretDPDenys Pommeret
Open Access
- 2 June 2022
- journal article
- research article
- Published by Wiley in Limnology and Oceanography: Methods
- Vol. 20 (7) , 387-399
Abstract
The variability of phytoplankton distribution has been unraveled by high‐frequency measurements. Such a resolution can be approached by automated pulse‐shape recording flow cytometry (AFCM) operating at hourly sampling resolution. AFCM records morphological and physiological traits as single‐cell optical pulse shapes that can be used to classify cells into phytoplankton functional groups (PFGs). However, the associated manual post‐processing of the data coupled with the increasing size and number of datasets is time‐consuming and error‐prone. Machine learning models are increasingly used to run automatic classification. Yet, most of the existing methods either present a long training process, need to manually design features from the raw optical pulse shapes, or are dedicated to images only. In this study, we present a convolutional neural network (CNN) to classify several PFGs using AFCM pulse shapes. The uncertainties of manual classification were first estimated by comparing experts' recognition of six PFGs. Consensual particles from the manual PFG classification were used to train and validate the CNN. The CNN obtained competitive performances compared to other models used in the literature and remained robust across several sampling areas, and instrumental hardware and settings. Finally, we assessed the ability of this classifier to predict phytoplankton counts at a Mediterranean coastal station and from a cruise in the South‐West Indian Ocean, providing a comparison with the manual classification over 3‐month periods and a 2h frequency. These promising results strengthen the near real‐time observation of PFGs, especially required with the increasing use of AFCM in monitoring research programs.Keywords
Funding Information
- European Regional Development Fund (1166‐39417)
- Ministère de l'Enseignement supérieur, de la Recherche et de l'Innovation (PhD funding)
This publication has 52 references indexed in Scilit:
- Picophytoplankton biomass distribution in the global oceanEarth System Science Data, 2012
- Optimized routine flow cytometric enumeration of heterotrophic flagellates using SYBR Green ILimnology and Oceanography: Methods, 2011
- Functional analysis and classification of phytoplankton based on data from an automated flow cytometerCytometry Part A, 2011
- CONTRIBUTION OF THE CLASS CRYPTOPHYCEAE TO PHYTOPLANKTON STRUCTURE IN THE GERMAN BIGHT1Journal of Phycology, 2010
- A comparison of global estimates of marine primary production from ocean colorDeep Sea Research Part II: Topical Studies in Oceanography, 2006
- Ecosystem dynamics based on plankton functional types for global ocean biogeochemistry modelsGlobal Change Biology, 2005
- Automatic recognition of coccoliths by dynamical neural networksMarine Micropaleontology, 2004
- CytoBuoy: a step forward towards using flow cytometry in operational oceanographyScientia Marina, 2000
- Distribution patterns of autotrophic pico- and nanoplankton and their relative contribution to algal biomass during spring in the Atlantic sector of the Southern OceanDeep Sea Research Part II: Topical Studies in Oceanography, 1997
- Neural network analysis of flow cytometric data for 40 marine phytoplankton speciesCytometry, 1994