Harshith Bachimanchi, Matthew I. M. Pinder, Chloé Robert, Pierre De Wit, Jonathan Havenhand, Alexandra Kinnby, Daniel Midtvedt, Erik Selander, Giovanni Volpe
{"title":"Deep-learning-powered data analysis in plankton ecology","authors":"Harshith Bachimanchi, Matthew I. M. Pinder, Chloé Robert, Pierre De Wit, Jonathan Havenhand, Alexandra Kinnby, Daniel Midtvedt, Erik Selander, Giovanni Volpe","doi":"10.1002/lol2.10392","DOIUrl":null,"url":null,"abstract":"<p>The implementation of deep learning algorithms has brought new perspectives to plankton ecology. Emerging as an alternative approach to established methods, deep learning offers objective schemes to investigate plankton organisms in diverse environments. We provide an overview of deep-learning-based methods including detection and classification of phytoplankton and zooplankton images, foraging and swimming behavior analysis, and finally ecological modeling. Deep learning has the potential to speed up the analysis and reduce the human experimental bias, thus enabling data acquisition at relevant temporal and spatial scales with improved reproducibility. We also discuss shortcomings and show how deep learning architectures have evolved to mitigate imprecise readouts. Finally, we suggest opportunities where deep learning is particularly likely to catalyze plankton research. The examples are accompanied by detailed tutorials and code samples that allow readers to apply the methods described in this review to their own data.</p>","PeriodicalId":18128,"journal":{"name":"Limnology and Oceanography Letters","volume":null,"pages":null},"PeriodicalIF":5.1000,"publicationDate":"2024-04-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/lol2.10392","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Limnology and Oceanography Letters","FirstCategoryId":"93","ListUrlMain":"https://onlinelibrary.wiley.com/doi/10.1002/lol2.10392","RegionNum":2,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"LIMNOLOGY","Score":null,"Total":0}
引用次数: 0
Abstract
The implementation of deep learning algorithms has brought new perspectives to plankton ecology. Emerging as an alternative approach to established methods, deep learning offers objective schemes to investigate plankton organisms in diverse environments. We provide an overview of deep-learning-based methods including detection and classification of phytoplankton and zooplankton images, foraging and swimming behavior analysis, and finally ecological modeling. Deep learning has the potential to speed up the analysis and reduce the human experimental bias, thus enabling data acquisition at relevant temporal and spatial scales with improved reproducibility. We also discuss shortcomings and show how deep learning architectures have evolved to mitigate imprecise readouts. Finally, we suggest opportunities where deep learning is particularly likely to catalyze plankton research. The examples are accompanied by detailed tutorials and code samples that allow readers to apply the methods described in this review to their own data.
期刊介绍:
Limnology and Oceanography Letters (LO-Letters) serves as a platform for communicating the latest innovative and trend-setting research in the aquatic sciences. Manuscripts submitted to LO-Letters are expected to present high-impact, cutting-edge results, discoveries, or conceptual developments across all areas of limnology and oceanography, including their integration. Selection criteria for manuscripts include their broad relevance to the field, strong empirical and conceptual foundations, succinct and elegant conclusions, and potential to advance knowledge in aquatic sciences.