Cargando…

Predicting direct and indirect non-target impacts of biocontrol agents using machine-learning approaches

Biological pest control (i.e. ‘biocontrol’) agents can have direct and indirect non-target impacts, and predicting these effects (especially indirect impacts) remains a central challenge in biocontrol risk assessment. The analysis of ecological networks offers a promising approach to understanding t...

Descripción completa

Detalles Bibliográficos
Autores principales: Kotula, Hannah J., Peralta, Guadalupe, Frost, Carol M., Todd, Jacqui H., Tylianakis, Jason M.
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Public Library of Science 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8168882/
https://www.ncbi.nlm.nih.gov/pubmed/34061885
http://dx.doi.org/10.1371/journal.pone.0252448
_version_ 1783701949350150144
author Kotula, Hannah J.
Peralta, Guadalupe
Frost, Carol M.
Todd, Jacqui H.
Tylianakis, Jason M.
author_facet Kotula, Hannah J.
Peralta, Guadalupe
Frost, Carol M.
Todd, Jacqui H.
Tylianakis, Jason M.
author_sort Kotula, Hannah J.
collection PubMed
description Biological pest control (i.e. ‘biocontrol’) agents can have direct and indirect non-target impacts, and predicting these effects (especially indirect impacts) remains a central challenge in biocontrol risk assessment. The analysis of ecological networks offers a promising approach to understanding the community-wide impacts of biocontrol agents (via direct and indirect interactions). Independently, species traits and phylogenies have been shown to successfully predict species interactions and network structure (alleviating the need to collect quantitative interaction data), but whether these approaches can be combined to predict indirect impacts of natural enemies remains untested. Whether predictions of interactions (i.e. direct effects) can be made equally well for generalists vs. specialists, abundant vs. less abundant species, and across different habitat types is also untested for consumer-prey interactions. Here, we used two machine-learning techniques (random forest and k-nearest neighbour; KNN) to test whether we could accurately predict empirically-observed quantitative host-parasitoid networks using trait and phylogenetic information. Then, we tested whether the accuracy of machine-learning-predicted interactions depended on the generality or abundance of the interacting partners, or on the source (habitat type) of the training data. Finally, we used these predicted networks to generate predictions of indirect effects via shared natural enemies (i.e. apparent competition), and tested these predictions against empirically observed indirect effects between hosts. We found that random-forest models predicted host-parasitoid pairwise interactions (which could be used to predict attack of non-target host species) more successfully than KNN. This predictive ability depended on the generality of the interacting partners for KNN models, and depended on species’ abundances for both random-forest and KNN models, but did not depend on the source (habitat type) of data used to train the models. Further, although our machine-learning informed methods could significantly predict indirect effects, the explanatory power of our machine-learning models for indirect interactions was reasonably low. Combining machine-learning and network approaches provides a starting point for reducing risk in biocontrol introductions, and could be applied more generally to predicting species interactions such as impacts of invasive species.
format Online
Article
Text
id pubmed-8168882
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher Public Library of Science
record_format MEDLINE/PubMed
spelling pubmed-81688822021-06-11 Predicting direct and indirect non-target impacts of biocontrol agents using machine-learning approaches Kotula, Hannah J. Peralta, Guadalupe Frost, Carol M. Todd, Jacqui H. Tylianakis, Jason M. PLoS One Research Article Biological pest control (i.e. ‘biocontrol’) agents can have direct and indirect non-target impacts, and predicting these effects (especially indirect impacts) remains a central challenge in biocontrol risk assessment. The analysis of ecological networks offers a promising approach to understanding the community-wide impacts of biocontrol agents (via direct and indirect interactions). Independently, species traits and phylogenies have been shown to successfully predict species interactions and network structure (alleviating the need to collect quantitative interaction data), but whether these approaches can be combined to predict indirect impacts of natural enemies remains untested. Whether predictions of interactions (i.e. direct effects) can be made equally well for generalists vs. specialists, abundant vs. less abundant species, and across different habitat types is also untested for consumer-prey interactions. Here, we used two machine-learning techniques (random forest and k-nearest neighbour; KNN) to test whether we could accurately predict empirically-observed quantitative host-parasitoid networks using trait and phylogenetic information. Then, we tested whether the accuracy of machine-learning-predicted interactions depended on the generality or abundance of the interacting partners, or on the source (habitat type) of the training data. Finally, we used these predicted networks to generate predictions of indirect effects via shared natural enemies (i.e. apparent competition), and tested these predictions against empirically observed indirect effects between hosts. We found that random-forest models predicted host-parasitoid pairwise interactions (which could be used to predict attack of non-target host species) more successfully than KNN. This predictive ability depended on the generality of the interacting partners for KNN models, and depended on species’ abundances for both random-forest and KNN models, but did not depend on the source (habitat type) of data used to train the models. Further, although our machine-learning informed methods could significantly predict indirect effects, the explanatory power of our machine-learning models for indirect interactions was reasonably low. Combining machine-learning and network approaches provides a starting point for reducing risk in biocontrol introductions, and could be applied more generally to predicting species interactions such as impacts of invasive species. Public Library of Science 2021-06-01 /pmc/articles/PMC8168882/ /pubmed/34061885 http://dx.doi.org/10.1371/journal.pone.0252448 Text en © 2021 Kotula et al https://creativecommons.org/licenses/by/4.0/This is an open access article distributed under the terms of the Creative Commons Attribution License (https://creativecommons.org/licenses/by/4.0/) , which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.
spellingShingle Research Article
Kotula, Hannah J.
Peralta, Guadalupe
Frost, Carol M.
Todd, Jacqui H.
Tylianakis, Jason M.
Predicting direct and indirect non-target impacts of biocontrol agents using machine-learning approaches
title Predicting direct and indirect non-target impacts of biocontrol agents using machine-learning approaches
title_full Predicting direct and indirect non-target impacts of biocontrol agents using machine-learning approaches
title_fullStr Predicting direct and indirect non-target impacts of biocontrol agents using machine-learning approaches
title_full_unstemmed Predicting direct and indirect non-target impacts of biocontrol agents using machine-learning approaches
title_short Predicting direct and indirect non-target impacts of biocontrol agents using machine-learning approaches
title_sort predicting direct and indirect non-target impacts of biocontrol agents using machine-learning approaches
topic Research Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8168882/
https://www.ncbi.nlm.nih.gov/pubmed/34061885
http://dx.doi.org/10.1371/journal.pone.0252448
work_keys_str_mv AT kotulahannahj predictingdirectandindirectnontargetimpactsofbiocontrolagentsusingmachinelearningapproaches
AT peraltaguadalupe predictingdirectandindirectnontargetimpactsofbiocontrolagentsusingmachinelearningapproaches
AT frostcarolm predictingdirectandindirectnontargetimpactsofbiocontrolagentsusingmachinelearningapproaches
AT toddjacquih predictingdirectandindirectnontargetimpactsofbiocontrolagentsusingmachinelearningapproaches
AT tylianakisjasonm predictingdirectandindirectnontargetimpactsofbiocontrolagentsusingmachinelearningapproaches