Decrop, W.; Lagaisse, R.; Mortelmans, J.; Muñiz, C.; Deneudt, K. (2025). Design and implementation of an automated Image classification workflow for phytoplankton monitoring, in: Praet, N. et al.Particles in Europe 2025: Conference program and proceedings, 17 - 19 September 2025, Ostend, Belgium. pp. 62-70, more
Phytoplankton are fundamental components of marine ecosystems and play a critical role in global biogeochemical cycles. Efficient monitoring of marine phytoplankton is crucial for assessing ecosystem health, forecasting harmful algal blooms and sustainable marine management. The integration of high-throughput imaging sensors like FlowCam technology with artificial intelligence (AI) for image recognition has revolutionized phytoplankton monitoring, enabling rapid and accurate class identification. This study introduces an automated image classification workflow designed to improve speed, accuracy and scalability of phytoplankton identification. By leveraging convolutional neural networks (CNNs), the system enhances performance while reducing reliance on traditional, labor-manual identification methods.
All data in the Integrated Marine Information System (IMIS) is subject to the VLIZ privacy policy
