Machteld Rijkeboer
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Machteld Rijkeboer has a total of 23 co-authors. Here are the top co-authors by number of shared publications:
- Alain Lefebvre
Ifremer, COAST, Laboratoire Environnement et Ressources, F62200 Boulogne-sur-Mer, France
3 shared publications Arnold Veen
3 shared publications- Hedy M. Aardema
Climate Geochemistry Department, Max Planck Institute for Chemistry
3 shared publications - Jacco C. Kromkamp
NIOZ Royal Netherlands Institute for Sea Research, Department of Estuarine and Delta Systems, and Utrecht University, P.O. Box 140, 4400 AC Yerseke, the Netherlands
3 shared publications - Arnaud Louchart
Université du Littoral Côte d’Opale, Université de Lille, CNRS, IRD, UMR 8187 LOG, Laboratoire d’Océanologie et Géosciences, F62930 Wimereux, France
2 shared publications - Denys Pommeret
Ecole Centrale Aix-Marseille University CNRS I2M Campus de Luminy 13288 Marseille cedex 9 France
1 shared publication
Latest Publications
- 9 December 2023
- Published by Springer Nature in Marine Biology
- Vol. 171 (1) , 1-22
The importance of niches in defining phytoplankton functional beta diversity during a spring bloom
- 9 December 2023
- Published by Springer Nature in Marine Biology
- Vol. 171 (1) , 1-22
The importance of niches in defining phytoplankton functional beta diversity during a spring bloom
- Open Access
- 2 June 2022
- Published by Wiley in Limnology and Oceanography: Methods
- Vol. 20 (7) , 387-399
Automatic recognition of flow cytometric phytoplankton functional groups using convolutional neural networks
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.
- 2 June 2022
- Published by Wiley in Limnology and Oceanography: Methods
- Vol. 20 (7) , 387-399
Open AccessAutomatic recognition of flow cytometric phytoplankton functional groups using convolutional neural networks
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.
- Open Access
- 30 September 2019
- Published by Copernicus GmbH in Ocean Science
- Vol. 15 (5) , 1267-1285
High-resolution underway measurements of phytoplankton photosynthesis and abundance as an innovative addition to water quality monitoring programs
Marine waters can be highly heterogeneous both on a spatial and temporal scale, yet monitoring programs currently rely primarily on low-resolution methods. This potentially leads to undersampling. This study explores the potential of two high-resolution methods for monitoring phytoplankton dynamics: fast repetition rate fluorometry for information on phytoplankton photosynthesis and productivity and automated scanning flow cytometry for information on phytoplankton abundance and community composition. These methods were tested in combination with an underway Ferrybox system during four cruises on the Dutch North Sea in April, May, June, and August 2017. The high-resolution methods were able to visualize both the spatial and temporal variability of the phytoplankton community in the Dutch North Sea. Spectral cluster analysis was applied to objectively interpret the multitude of parameters and visualize potential spatial patterns. This resulted in the identification of biogeographic regions with distinct phytoplankton communities, which varied per cruise. Our results clearly show that the sampling based on fixed stations does not give a good representation of the spatial patterns, showing the added value of underway high-resolution measurements. To fully exploit the potential of the tested high-resolution measurement setup, methodological constraints need further research. Among these constraints are accounting for the diurnal cycle in photophysiological parameters concurrent to the spatial variation, better predictions of the electron requirement for carbon fixation to estimate gross primary productivity, and the identification of more flow cytometer clusters with informative value. Nevertheless, the richness of additional information provided by high-resolution methods can improve existing low-resolution monitoring programs towards a more precise and ecosystemic ecological assessment of the phytoplankton community and productivity.
- 30 September 2019
- Published by Copernicus GmbH in Ocean Science
- Vol. 15 (5) , 1267-1285
Open AccessHigh-resolution underway measurements of phytoplankton photosynthesis and abundance as an innovative addition to water quality monitoring programs
Marine waters can be highly heterogeneous both on a spatial and temporal scale, yet monitoring programs currently rely primarily on low-resolution methods. This potentially leads to undersampling. This study explores the potential of two high-resolution methods for monitoring phytoplankton dynamics: fast repetition rate fluorometry for information on phytoplankton photosynthesis and productivity and automated scanning flow cytometry for information on phytoplankton abundance and community composition. These methods were tested in combination with an underway Ferrybox system during four cruises on the Dutch North Sea in April, May, June, and August 2017. The high-resolution methods were able to visualize both the spatial and temporal variability of the phytoplankton community in the Dutch North Sea. Spectral cluster analysis was applied to objectively interpret the multitude of parameters and visualize potential spatial patterns. This resulted in the identification of biogeographic regions with distinct phytoplankton communities, which varied per cruise. Our results clearly show that the sampling based on fixed stations does not give a good representation of the spatial patterns, showing the added value of underway high-resolution measurements. To fully exploit the potential of the tested high-resolution measurement setup, methodological constraints need further research. Among these constraints are accounting for the diurnal cycle in photophysiological parameters concurrent to the spatial variation, better predictions of the electron requirement for carbon fixation to estimate gross primary productivity, and the identification of more flow cytometer clusters with informative value. Nevertheless, the richness of additional information provided by high-resolution methods can improve existing low-resolution monitoring programs towards a more precise and ecosystemic ecological assessment of the phytoplankton community and productivity.
- Open Access
- 19 March 2018
- Published by Copernicus GmbH
Supplementary material to "High resolution in situ measurements of phytoplankton photosynthesis and abundance in the Dutch North Sea"
- 19 March 2018
- Published by Copernicus GmbH
Open AccessSupplementary material to "High resolution in situ measurements of phytoplankton photosynthesis and abundance in the Dutch North Sea"
- Open Access
- 19 March 2018
- Published by Copernicus GmbH in EGUsphere
- Vol. 2018, 1-37
High resolution in situ measurements of phytoplankton photosynthesis and abundance in the Dutch North Sea
Marine waters can be highly heterogeneous both on a spatial and temporal scale, yet monitoring is currently mainly limited to low-resolution methods. This study explores the use of two high-resolution methods to study phytoplankton dynamics; Fast Repetition Rate fluorometry (FRRf) to study phytoplankton photosynthesis and scanning flowcytometry (FCM) to study phytoplankton biomass and composition. Measurements were conducted during four cruises on the Dutch North Sea in April, May, June, and August of 2017. Both FRRf and FCM data show spatial heterogeneity with monthly variation. Automated unsupervised Hidden Markov Model (uHMM) spatial clustering resulted in the identification of regions with distinct phytoplankton communities. Manual adjustments were necessary to optimize visualization of some distinct phytoplankton communities. Stepwise multiple linear regression (n = 61) revealed that photophysiology (alpha), phytoplankton biomass (total red fluorescence) and abiotic predictors (Turbidity, DIN, time of the day and temperature) determined integrated water column gross primary productivity. Apart from spatial heterogeneity, the diurnal trend is a significant predictor exposing clear trends with other photophysiological parameters. Consequently, spatial patterns are difficult as temporal and spatial patterns occur simultaneously. Nevertheless, high-resolution monitoring is a very useful supplement in addition to regular low-resolution monitoring.
- 19 March 2018
- Published by Copernicus GmbH in EGUsphere
- Vol. 2018, 1-37
Open AccessHigh resolution in situ measurements of phytoplankton photosynthesis and abundance in the Dutch North Sea
Marine waters can be highly heterogeneous both on a spatial and temporal scale, yet monitoring is currently mainly limited to low-resolution methods. This study explores the use of two high-resolution methods to study phytoplankton dynamics; Fast Repetition Rate fluorometry (FRRf) to study phytoplankton photosynthesis and scanning flowcytometry (FCM) to study phytoplankton biomass and composition. Measurements were conducted during four cruises on the Dutch North Sea in April, May, June, and August of 2017. Both FRRf and FCM data show spatial heterogeneity with monthly variation. Automated unsupervised Hidden Markov Model (uHMM) spatial clustering resulted in the identification of regions with distinct phytoplankton communities. Manual adjustments were necessary to optimize visualization of some distinct phytoplankton communities. Stepwise multiple linear regression (n = 61) revealed that photophysiology (alpha), phytoplankton biomass (total red fluorescence) and abiotic predictors (Turbidity, DIN, time of the day and temperature) determined integrated water column gross primary productivity. Apart from spatial heterogeneity, the diurnal trend is a significant predictor exposing clear trends with other photophysiological parameters. Consequently, spatial patterns are difficult as temporal and spatial patterns occur simultaneously. Nevertheless, high-resolution monitoring is a very useful supplement in addition to regular low-resolution monitoring.
- 1 January 1990
- Published by Springer Nature
- p. 129-138
Algal growth and loss rates in Lake Loosdrecht: first evaluation of the roles of light and wind on a basis of steady state kinetics
- 1 January 1990
- Published by Springer Nature
- p. 129-138
Algal growth and loss rates in Lake Loosdrecht: first evaluation of the roles of light and wind on a basis of steady state kinetics