Machine Learning for Plankton Species Identification and Classification: A New Era in Marine Ecology

As a key component of aquatic food webs and a major contributor to global biogeochemical cycles, plankton identification and classification are critical tasks in marine biology. While identifying and categorizing plankton species manually can be time-consuming, it requires considerable expertise. Machine learning approaches are proposed here for identifying and categorizing plankton. As well as providing insights into plankton ecology and biogeochemistry, automatic identification and classification of plankton species can inform management strategies for marine ecosystems. Training the model required a dataset of images of phytoplankton and zooplankton, which were classified into multiple categories by the model. The model was also evaluated for robustness against noise, occlusion, and illumination variations. A threshold-based segmentation method is used to detect plankton objects during the classification phase. Plankton classification using this threshold-based segmentation method requires the extraction of features from the image, such as shape, size, color, and texture. These features are used to categorize the different species of plankton. The model was then tested on field images to validate its accuracy. The results showed that the model was able to achieve high accuracy in classifying the different plankton species.