Author:
Kyathanahally Sreenath P.,Hardeman Thomas,Merz Ewa,Bulas Thea,Reyes Marta,Isles Peter,Pomati Francesco,Baity-Jesi Marco
Abstract
Plankton are effective indicators of environmental change and ecosystem health in freshwater habitats, but collection of plankton data using manual microscopic methods is extremely labor-intensive and expensive. Automated plankton imaging offers a promising way forward to monitor plankton communities with high frequency and accuracy in real-time. Yet, manual annotation of millions of images proposes a serious challenge to taxonomists. Deep learning classifiers have been successfully applied in various fields and provided encouraging results when used to categorize marine plankton images. Here, we present a set of deep learning models developed for the identification of lake plankton, and study several strategies to obtain optimal performances, which lead to operational prescriptions for users. To this aim, we annotated into 35 classes over 17900 images of zooplankton and large phytoplankton colonies, detected in Lake Greifensee (Switzerland) with the Dual Scripps Plankton Camera. Our best models were based on transfer learning and ensembling, which classified plankton images with 98% accuracy and 93% F1 score. When tested on freely available plankton datasets produced by other automated imaging tools (ZooScan, Imaging FlowCytobot, and ISIIS), our models performed better than previously used models. Our annotated data, code and classification models are freely available online.
Funder
Bundesamt für Umwelt
Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung
Eidgenössische Anstalt für Wasserversorgung Abwasserreinigung und Gewässerschutz
Subject
Microbiology (medical),Microbiology
Reference68 articles.
1. Tensorflow: large-scale machine learning on heterogeneous distributed systems;Abadi;arXiv preprint arXiv:1603.04467,2016
2. Zooplankton: pivotal role in the control of ocean production: I. Biomass and production;Banse;ICES J. Mar. Sci,1995
3. Biospheric primary production during an enso transition;Behrenfeld;Science,2001
4. Deep active learning for in situ plankton classification;Bochinski,2019
5. CowenR. K.
SponaugleS.
RobinsonK.
LuoJ.
Planktonset 1.0: Plankton Imagery Data Collected From F.G. Walton Smith in Straits of Florida From 2014-06-03 to 2014-06-06 and Used in the 2015 National Data Science Bowl (NCEI Accession 0127422)2015
Cited by
12 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献