Anouk Ollevier
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Anouk Ollevier has a total of 29 co-authors. Here are the top co-authors by number of shared publications:
Jonas Mortelmans
Flanders Marine Institute (VLIZ) Oostende Belgium
3 shared publicationsKlaas Deneudt
Flanders Marine Institute (VLIZ) Oostende Belgium
2 shared publications- A. Frank van der Stappen
Department of Information and Computing Sciences Utrecht University Utrecht The Netherlands
1 shared publication Anaïs Aubert
Flanders Marine Institute (VLIZ), Ostend, Belgium
1 shared publicationCedric Goossens
Flanders Marine Institute (VLIZ) Oostende Belgium
1 shared publication- Dick van Oevelen
Department of Estuarine and Delta Systems, Royal Netherlands Institute for Sea Research (NIOZ), PO Box 140, 4400 AC, Yerseke, The Netherlands
1 shared publication
Latest Publications
- Open Access
Optimizing automated classification for zooplankton in coastal conditions: the impact of model selection, imaging instruments, and colour information
The advancement in deep learning techniques has made Convolutional Neural Networks (CNNs) a powerful tool for the fully automated classification of zooplankton images. In this study, we systematically investigate how network selection, colour information and differences in imaging instruments affect the classification of zooplankton images by comparing multiple state-of-the-art CNNs on images of zooplankton and marine snow from the in situ Continuous Particle Imaging and Classification Sensor (CPICS), Video Plankton Recorder (VPR), In Situ Ichtyoplankton Imaging System (ISIIS), and the on-board Plankton Imager (Pi-10). With differences between models of 7.8 to 19% in F1-score, we find that model selection strongly affects the classification performance, with EfficientNetV2S showing the most reliable overall performance. Moreover, differences between model architectures are largest for the least abundant classes ( < 100 labeled images), which implies that when these are present, careful model selection is most beneficial. The high image quality of the Pi-10 strongly increases the performance for the least abundant classes compared to the other instruments. In addition, we find a significant correlation ( r = 0.597) between ImageNet the performance and F1-score on zooplankton images, which implies that more generally, a model that performs well on ImageNet will perform well for zooplankton classification. Colour information increases the F1-score of the best performing classifier with 2.8%, but provides a stronger benefit (25% F1-score) for classes with < 100 images. The overall performance increase of colour information is less than expected and questions the advantage of recording colour information for zooplankton.
Open AccessOptimizing automated classification for zooplankton in coastal conditions: the impact of model selection, imaging instruments, and colour information
The advancement in deep learning techniques has made Convolutional Neural Networks (CNNs) a powerful tool for the fully automated classification of zooplankton images. In this study, we systematically investigate how network selection, colour information and differences in imaging instruments affect the classification of zooplankton images by comparing multiple state-of-the-art CNNs on images of zooplankton and marine snow from the in situ Continuous Particle Imaging and Classification Sensor (CPICS), Video Plankton Recorder (VPR), In Situ Ichtyoplankton Imaging System (ISIIS), and the on-board Plankton Imager (Pi-10). With differences between models of 7.8 to 19% in F1-score, we find that model selection strongly affects the classification performance, with EfficientNetV2S showing the most reliable overall performance. Moreover, differences between model architectures are largest for the least abundant classes ( < 100 labeled images), which implies that when these are present, careful model selection is most beneficial. The high image quality of the Pi-10 strongly increases the performance for the least abundant classes compared to the other instruments. In addition, we find a significant correlation ( r = 0.597) between ImageNet the performance and F1-score on zooplankton images, which implies that more generally, a model that performs well on ImageNet will perform well for zooplankton classification. Colour information increases the F1-score of the best performing classifier with 2.8%, but provides a stronger benefit (25% F1-score) for classes with < 100 images. The overall performance increase of colour information is less than expected and questions the advantage of recording colour information for zooplankton.
- 12 February 2025
- Published by Wiley in Limnology and Oceanography: Methods
Picturing plankton: Complementing net‐based plankton community assessments with optical imaging across diverse marine environments
In recent years, optical imaging has emerged as a promising tool for in situ observations of plankton. In this study, we aimed to compare the plankton community estimates obtained from a Video Plankton Recorder (VPR) imaging device with net‐based approaches. By collecting VPR and net samples in clear waters with large‐sized plankton and eutrophic waters with small‐sized plankton, spatial and temporal patterns in plankton densities and community composition were compared. Furthermore, it allowed the evaluation of the performance of imaging methods under diverse hydrographic conditions. We observed pronounced spatial differences in density estimates. In the eutrophic site, the WP2 net densities consistently surpassed those from a VPR, while in the clear water site the observed densities of the VPR and a MultiNet were more similar. Variations in water column turbidity, plankton body size, plankton nets and their mesh size, and the total sampled water volume were found to likely play a role in the observed inconsistencies between the sampling sites. The results suggested that a VPR is particularly well‐suited for use in clear waters inhabited by large‐sized plankton. The VPR demonstrated potential in enhancing density estimates of fragile (Phaeocystis) and gelatinous taxa (Cnidaria and Ctenophora) in specific environments being non‐invasive. Overall, the VPR and other optical imaging devices show valuable insights into zooplankton ecology and distribution, complementing density estimates of traditional net sampling methods, and enhancing our understanding of the role of zooplankton in marine ecosystems.
- 12 February 2025
- Published by Wiley in Limnology and Oceanography: Methods
Picturing plankton: Complementing net‐based plankton community assessments with optical imaging across diverse marine environments
In recent years, optical imaging has emerged as a promising tool for in situ observations of plankton. In this study, we aimed to compare the plankton community estimates obtained from a Video Plankton Recorder (VPR) imaging device with net‐based approaches. By collecting VPR and net samples in clear waters with large‐sized plankton and eutrophic waters with small‐sized plankton, spatial and temporal patterns in plankton densities and community composition were compared. Furthermore, it allowed the evaluation of the performance of imaging methods under diverse hydrographic conditions. We observed pronounced spatial differences in density estimates. In the eutrophic site, the WP2 net densities consistently surpassed those from a VPR, while in the clear water site the observed densities of the VPR and a MultiNet were more similar. Variations in water column turbidity, plankton body size, plankton nets and their mesh size, and the total sampled water volume were found to likely play a role in the observed inconsistencies between the sampling sites. The results suggested that a VPR is particularly well‐suited for use in clear waters inhabited by large‐sized plankton. The VPR demonstrated potential in enhancing density estimates of fragile (Phaeocystis) and gelatinous taxa (Cnidaria and Ctenophora) in specific environments being non‐invasive. Overall, the VPR and other optical imaging devices show valuable insights into zooplankton ecology and distribution, complementing density estimates of traditional net sampling methods, and enhancing our understanding of the role of zooplankton in marine ecosystems.
- Open Access
- 2 March 2024
- Published by Elsevier in Estuarine, Coastal and Shelf Science
- Vol. 300
Diel vertical migration and tidal influences on plankton densities in dynamic coastal systems
- 2 March 2024
- Published by Elsevier in Estuarine, Coastal and Shelf Science
- Vol. 300
Open AccessDiel vertical migration and tidal influences on plankton densities in dynamic coastal systems
- Open Access
- 11 October 2023
- Published by MDPI AG in Remote Sensing
- Vol. 15 (20) , 4918
The Potential of Multibeam Sonars as 3D Turbidity and SPM Monitoring Tool in the North Sea
Monitoring turbidity is essential for sustainable coastal management because an increase in turbidity leading to diminishing water clarity has a detrimental ecological impact. Turbidity in coastal waters is strongly dependent on the concentration and physical properties of particles in the water column. In the Belgian part of the North Sea, turbidity and suspended particulate matter (SPM) concentrations have been monitored for decades by satellite remote sensing, but this technique only focuses on the surface layer of the water column. Within the water column, turbidity and SPM concentrations are measured in stations or transects with a suite of optical and acoustic sensors. However, the dynamic nature of SPM variability in coastal areas and the recent construction of offshore windmill parks and dredging and dumping activities justifies the need to monitor natural and human-induced SPM variability in 3D instead. A possible solution lies in modern multibeam echosounders (MBES), which, in addition to seafloor bathymetry data, are also able to deliver acoustic backscatter data from the water column. This study investigates the potential of MBES as a 3D turbidity and SPM monitoring tool. For this purpose, a novel empirical approach is developed, in which 3D MBES water column and in-situ optical sensor datasets were collected during ship transects to yield an empirical relation using linear regression modeling. This relationship was then used to predict SPM volume concentrations from the 3D acoustic measurements, which were further converted to SPM mass concentrations using calculated densities. Our results show that these converted mean mass concentrations at the Kwinte and Westdiep swale areas are within the limits of the reported yearly averages. Moreover, they are in the same order of magnitude as the measured mass concentrations from Niskin water samples during each campaign. While there is still need for further improvement of acquisition and processing workflows, this study presents a promising approach for converting MBES water column data to turbidity and SPM measurements. This opens possibilities for improving future monitoring tools, both in scientific and industrial sectors.
- 11 October 2023
- Published by MDPI AG in Remote Sensing
- Vol. 15 (20) , 4918
Open AccessThe Potential of Multibeam Sonars as 3D Turbidity and SPM Monitoring Tool in the North Sea
Monitoring turbidity is essential for sustainable coastal management because an increase in turbidity leading to diminishing water clarity has a detrimental ecological impact. Turbidity in coastal waters is strongly dependent on the concentration and physical properties of particles in the water column. In the Belgian part of the North Sea, turbidity and suspended particulate matter (SPM) concentrations have been monitored for decades by satellite remote sensing, but this technique only focuses on the surface layer of the water column. Within the water column, turbidity and SPM concentrations are measured in stations or transects with a suite of optical and acoustic sensors. However, the dynamic nature of SPM variability in coastal areas and the recent construction of offshore windmill parks and dredging and dumping activities justifies the need to monitor natural and human-induced SPM variability in 3D instead. A possible solution lies in modern multibeam echosounders (MBES), which, in addition to seafloor bathymetry data, are also able to deliver acoustic backscatter data from the water column. This study investigates the potential of MBES as a 3D turbidity and SPM monitoring tool. For this purpose, a novel empirical approach is developed, in which 3D MBES water column and in-situ optical sensor datasets were collected during ship transects to yield an empirical relation using linear regression modeling. This relationship was then used to predict SPM volume concentrations from the 3D acoustic measurements, which were further converted to SPM mass concentrations using calculated densities. Our results show that these converted mean mass concentrations at the Kwinte and Westdiep swale areas are within the limits of the reported yearly averages. Moreover, they are in the same order of magnitude as the measured mass concentrations from Niskin water samples during each campaign. While there is still need for further improvement of acquisition and processing workflows, this study presents a promising approach for converting MBES water column data to turbidity and SPM measurements. This opens possibilities for improving future monitoring tools, both in scientific and industrial sectors.
- Open Access
- 10 December 2021
- Published by Frontiers Media SA in Frontiers in Marine Science
- Vol. 8
Noctiluca scintillans: Dynamics, Size Measurements and Relationships With Small Soft-Bodied Plankton in the Belgian Part of the North Sea
Climate driven changes and anthropogenic pressures on the marine environment have been shown to favor the increase in certain potentially harmful species. Among them, Noctiluca scintillans, a common dinoflagellate, often blooms during warm summers and is known to affect plankton communities. In this study, we assessed the dynamics in abundance and cell size of N. scintillans as well as the relationship between N. scintillans and small soft-bodied zooplankton in the Belgian part of the North Sea (BPNS), since negative correlations between these plankton groups have been previously reported for nearby regions. This study is the first to present consistently counted N. scintillans cell numbers and measured cell lengths, through the analysis of ZooScan images from samples taken monthly at stations throughout the coastal zone of the BPNS. The results show that N. scintillans demonstrated clear seasonal dynamics with both high densities and large cell sizes in spring/summer (May-July). The occurrence of N. scintillans in the analyzed plankton samples and the abundance of N. scintillans at the observed peak intensities nearly tripled over a period of 5 years. A zero-inflated model showed a correlation of N. scintillans abundance with temperature as well as with phosphate concentrations, suggesting that anthropogenic influences such as climate change and riverine nutrient inputs could affect the temporal dynamics of the species. The results, on the other hand, did not show any negative impact of N. scintillans on the soft-bodied plankton community.
- 10 December 2021
- Published by Frontiers Media SA in Frontiers in Marine Science
- Vol. 8
Open AccessNoctiluca scintillans: Dynamics, Size Measurements and Relationships With Small Soft-Bodied Plankton in the Belgian Part of the North Sea
Climate driven changes and anthropogenic pressures on the marine environment have been shown to favor the increase in certain potentially harmful species. Among them, Noctiluca scintillans, a common dinoflagellate, often blooms during warm summers and is known to affect plankton communities. In this study, we assessed the dynamics in abundance and cell size of N. scintillans as well as the relationship between N. scintillans and small soft-bodied zooplankton in the Belgian part of the North Sea (BPNS), since negative correlations between these plankton groups have been previously reported for nearby regions. This study is the first to present consistently counted N. scintillans cell numbers and measured cell lengths, through the analysis of ZooScan images from samples taken monthly at stations throughout the coastal zone of the BPNS. The results show that N. scintillans demonstrated clear seasonal dynamics with both high densities and large cell sizes in spring/summer (May-July). The occurrence of N. scintillans in the analyzed plankton samples and the abundance of N. scintillans at the observed peak intensities nearly tripled over a period of 5 years. A zero-inflated model showed a correlation of N. scintillans abundance with temperature as well as with phosphate concentrations, suggesting that anthropogenic influences such as climate change and riverine nutrient inputs could affect the temporal dynamics of the species. The results, on the other hand, did not show any negative impact of N. scintillans on the soft-bodied plankton community.