Towards Phytoplankton Parasite Detection Using Autoencoders

Abstract

Phytoplankton parasites are largely understudied microbial components with a potentially significant ecological influence on phytoplankton bloom dynamics. To better understand the impact of phytoplankton parasites, improved detection methods are needed to integrate phytoplankton parasite interactions into monitoring of aquatic ecosystems. Automated imaging devices commonly produce vast amounts of phytoplankton image data, but the occurrence of anomalous phytoplankton data in such datasets is rare. Thus, we propose an unsupervised anomaly detection system based on the similarity between the original and autoencoder-reconstructed samples. With this approach, we were able to reach an overall F1 score of 0.75 in nine phytoplankton species, which could be further improved by species-specific fine-tuning. The proposed unsupervised approach was further compared with the supervised Faster R-CNN-based object detector. Using this supervised approach and the model trained on plankton species and anomalies, we were able to reach a highest F1 score of 0.86. However, the unsupervised approach is expected to be more universal as it can also detect unknown anomalies and it does not require any annotated anomalous data that may not always be available in sufficient quantities. Although other studies have dealt with plankton anomaly detection in terms of non-plankton particles or air bubble detection, our paper is, according to our best knowledge, the first that focuses on automated anomaly detection considering putative phytoplankton parasites or infections.Phytoplankton parasites are largely understudied microbial components with a potentially significant ecological influence on phytoplankton bloom dynamics. To better understand the impact of phytoplankton parasites, improved detection methods are needed to integrate phytoplankton parasite interactions into monitoring of aquatic ecosystems. Automated imaging devices commonly produce vast amounts of phytoplankton image data, but the occurrence of anomalous phytoplankton data in such datasets is rare. Thus, we propose an unsupervised anomaly detection system based on the similarity between the original and autoencoder-reconstructed samples. With this approach, we were able to reach an overall F1 score of 0.75 in nine phytoplankton species, which could be further improved by species-specific fine-tuning. The proposed unsupervised approach was further compared with the supervised Faster R-CNN-based object detector. Using this supervised approach and the model trained on plankton species and anomalies, we were able to reach a highest F1 score of 0.86. However, the unsupervised approach is expected to be more universal as it can also detect unknown anomalies and it does not require any annotated anomalous data that may not always be available in sufficient quantities. Although other studies have dealt with plankton anomaly detection in terms of non-plankton particles or air bubble detection, our paper is, according to our best knowledge, the first that focuses on automated anomaly detection considering putative phytoplankton parasites or infections.