Applying machine learning to investigate long-term insect-plant interactions preserved on digitized herbarium specimens.

dc.contributor.author

Meineke, Emily K

dc.contributor.author

Tomasi, Carlo

dc.contributor.author

Yuan, Song

dc.contributor.author

Pryer, Kathleen M

dc.date.accessioned

2020-11-25T23:54:19Z

dc.date.available

2020-11-25T23:54:19Z

dc.date.issued

2020-06

dc.date.updated

2020-11-25T23:54:17Z

dc.description.abstract

Premise:Despite the economic significance of insect damage to plants (i.e., herbivory), long-term data documenting changes in herbivory are limited. Millions of pressed plant specimens are now available online and can be used to collect big data on plant-insect interactions during the Anthropocene. Methods:We initiated development of machine learning methods to automate extraction of herbivory data from herbarium specimens by training an insect damage detector and a damage type classifier on two distantly related plant species (Quercus bicolor and Onoclea sensibilis). We experimented with (1) classifying six types of herbivory and two control categories of undamaged leaf, and (2) detecting two of the damage categories for which several hundred annotations were available. Results:Damage detection results were mixed, with a mean average precision of 45% in the simultaneous detection and classification of two types of damage. However, damage classification on hand-drawn boxes identified the correct type of herbivory 81.5% of the time in eight categories. The damage classifier was accurate for categories with 100 or more test samples. Discussion:These tools are a promising first step for the automation of herbivory data collection. We describe ongoing efforts to increase the accuracy of these models, allowing researchers to extract similar data and apply them to biological hypotheses.

dc.identifier

APS311369

dc.identifier.issn

2168-0450

dc.identifier.issn

2168-0450

dc.identifier.uri

https://hdl.handle.net/10161/21731

dc.language

eng

dc.publisher

Wiley

dc.relation.ispartof

Applications in plant sciences

dc.relation.isversionof

10.1002/aps3.11369

dc.subject

Anthropocene

dc.subject

climate change

dc.subject

herbarium

dc.subject

insects

dc.subject

machine learning

dc.subject

species interactions

dc.title

Applying machine learning to investigate long-term insect-plant interactions preserved on digitized herbarium specimens.

dc.type

Journal article

duke.contributor.orcid

Pryer, Kathleen M|0000-0002-9776-6736

pubs.begin-page

e11369

pubs.issue

6

pubs.organisational-group

Trinity College of Arts & Sciences

pubs.organisational-group

Biology

pubs.organisational-group

Duke Science & Society

pubs.organisational-group

Duke

pubs.organisational-group

Initiatives

pubs.organisational-group

Institutes and Provost's Academic Units

pubs.organisational-group

Computer Science

pubs.organisational-group

Duke Institute for Brain Sciences

pubs.organisational-group

University Institutes and Centers

pubs.publication-status

Published

pubs.volume

8

Files

Original bundle

Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
Applying machine learning to investigate long-term insect-plant interactions preserved on digitized herbarium specimens.pdf
Size:
972.37 KB
Format:
Adobe Portable Document Format
Description:
Published version