Header

UZH-Logo

Maintenance Infos

Dynamic species classification of microorganisms across time, abiotic and biotic environments—A sliding window approach


Pennekamp, Frank; Griffiths, Jason I; Fronhofer, Emanuel A; Garnier, Aurélie; Seymour, Mathew; Altermatt, Florian; Petchey, Owen L (2017). Dynamic species classification of microorganisms across time, abiotic and biotic environments—A sliding window approach. PLoS ONE:1-22.

Abstract

The development of video-based monitoring methods allows for rapid, dynamic and accu- rate monitoring of individuals or communities, compared to slower traditional methods, with far reaching ecological and evolutionary applications. Large amounts of data are gen- erated using video-based methods, which can be effectively processed using machine learning (ML) algorithms into meaningful ecological information. ML uses user defined classes (e.g. species), derived from a subset (i.e. training data) of video-observed quanti- tative features (e.g. phenotypic variation), to infer classes in subsequent observations. However, phenotypic variation often changes due to environmental conditions, which may lead to poor classification, if environmentally induced variation in phenotypes is not accounted for. Here we describe a framework for classifying species under changing envi- ronmental conditions based on the random forest classification. A sliding window approach was developed that restricts temporal and environmentally conditions to improve the clas- sification. We tested our approach by applying the classification framework to experimental data. The experiment used a set of six ciliate species to monitor changes in community structure and behavior over hundreds of generations, in dozens of species combinations and across a temperature gradient. Differences in biotic and abiotic conditions caused sim- plistic classification approaches to be unsuccessful. In contrast, the sliding window approach allowed classification to be highly successful, as phenotypic differences driven by environmental change, could be captured by the classifier. Importantly, classification using the random forest algorithm showed comparable success when validated against traditional, slower, manual identification. Our framework allows for reliable classification in dynamic environments, and may help to improve strategies for long-term monitoring of species in changing environments. Our classification pipeline can be applied in fields assessing species community dynamics, such as eco-toxicology, ecology and evolutionary ecology.

Abstract

The development of video-based monitoring methods allows for rapid, dynamic and accu- rate monitoring of individuals or communities, compared to slower traditional methods, with far reaching ecological and evolutionary applications. Large amounts of data are gen- erated using video-based methods, which can be effectively processed using machine learning (ML) algorithms into meaningful ecological information. ML uses user defined classes (e.g. species), derived from a subset (i.e. training data) of video-observed quanti- tative features (e.g. phenotypic variation), to infer classes in subsequent observations. However, phenotypic variation often changes due to environmental conditions, which may lead to poor classification, if environmentally induced variation in phenotypes is not accounted for. Here we describe a framework for classifying species under changing envi- ronmental conditions based on the random forest classification. A sliding window approach was developed that restricts temporal and environmentally conditions to improve the clas- sification. We tested our approach by applying the classification framework to experimental data. The experiment used a set of six ciliate species to monitor changes in community structure and behavior over hundreds of generations, in dozens of species combinations and across a temperature gradient. Differences in biotic and abiotic conditions caused sim- plistic classification approaches to be unsuccessful. In contrast, the sliding window approach allowed classification to be highly successful, as phenotypic differences driven by environmental change, could be captured by the classifier. Importantly, classification using the random forest algorithm showed comparable success when validated against traditional, slower, manual identification. Our framework allows for reliable classification in dynamic environments, and may help to improve strategies for long-term monitoring of species in changing environments. Our classification pipeline can be applied in fields assessing species community dynamics, such as eco-toxicology, ecology and evolutionary ecology.

Statistics

Altmetrics

Downloads

6 downloads since deposited on 05 Sep 2017
6 downloads since 12 months
Detailed statistics

Additional indexing

Item Type:Journal Article, refereed, original work
Communities & Collections:07 Faculty of Science > Institute of Evolutionary Biology and Environmental Studies
Dewey Decimal Classification:570 Life sciences; biology
590 Animals (Zoology)
Language:English
Date:4 May 2017
Deposited On:05 Sep 2017 12:14
Last Modified:06 Sep 2017 09:19
Publisher:Public Library of Science (PLoS)
ISSN:1932-6203
Funders:This work was supported by Swiss National Science Foundation 31003A_159498 to OLP and Swiss National Science Foundation 31003A_135622 and PP00P3_150698 to FA.
Free access at:Publisher DOI. An embargo period may apply.
Publisher DOI:https://doi.org/10.1371/journal.pone.0176682

Download

Download PDF  'Dynamic species classification of microorganisms across time, abiotic and biotic environments—A sliding window approach'.
Preview
Content: Published Version
Filetype: PDF
Size: 6MB
View at publisher
Licence: Creative Commons: Attribution 4.0 International (CC BY 4.0)