Frontiers in Plant Science (May 2022)
A Perspective on Plant Phenomics: Coupling Deep Learning and Near-Infrared Spectroscopy
- François Vasseur,
- Denis Cornet,
- Denis Cornet,
- Grégory Beurier,
- Grégory Beurier,
- Julie Messier,
- Lauriane Rouan,
- Lauriane Rouan,
- Justine Bresson,
- Martin Ecarnot,
- Mark Stahl,
- Simon Heumos,
- Simon Heumos,
- Marianne Gérard,
- Hans Reijnen,
- Pascal Tillard,
- Benoît Lacombe,
- Amélie Emanuel,
- Amélie Emanuel,
- Justine Floret,
- Justine Floret,
- Aurélien Estarague,
- Stefania Przybylska,
- Kevin Sartori,
- Lauren M. Gillespie,
- Etienne Baron,
- Elena Kazakou,
- Denis Vile,
- Cyrille Violle
Affiliations
- François Vasseur
- CEFE, Univ Montpellier, CNRS, EPHE, IRD, Montpellier, France
- Denis Cornet
- CIRAD, UMR AGAP Institut, Montpellier, France
- Denis Cornet
- UMR AGAP Institut, Univ Montpellier, CIRAD, INRAE, Institut Agro, Montpellier, France
- Grégory Beurier
- CIRAD, UMR AGAP Institut, Montpellier, France
- Grégory Beurier
- UMR AGAP Institut, Univ Montpellier, CIRAD, INRAE, Institut Agro, Montpellier, France
- Julie Messier
- Department of Biology, University of Waterloo, Waterloo, ON, Canada
- Lauriane Rouan
- CIRAD, UMR AGAP Institut, Montpellier, France
- Lauriane Rouan
- UMR AGAP Institut, Univ Montpellier, CIRAD, INRAE, Institut Agro, Montpellier, France
- Justine Bresson
- CEFE, Univ Montpellier, CNRS, EPHE, IRD, Montpellier, France
- Martin Ecarnot
- UMR AGAP Institut, Univ Montpellier, CIRAD, INRAE, Institut Agro, Montpellier, France
- Mark Stahl
- Center for Plant Molecular Biology (ZMBP), University of Tübingen, Tübingen, Germany
- Simon Heumos
- Quantitative Biology Center (QBiC), University of Tübingen, Quantitative Biology Center (QBiC), University of Tübingen, Germany
- Simon Heumos
- Biomedical Data Science, Department of Computer Science, University of Tübingen, Tübingen, Germany
- Marianne Gérard
- CEFE, Univ Montpellier, CNRS, EPHE, IRD, Montpellier, France
- Hans Reijnen
- CEFE, Univ Montpellier, CNRS, EPHE, IRD, Montpellier, France
- Pascal Tillard
- BPMP, Univ Montpellier, CNRS, INRAE, Montpellier, France
- Benoît Lacombe
- BPMP, Univ Montpellier, CNRS, INRAE, Montpellier, France
- Amélie Emanuel
- CEFE, Univ Montpellier, CNRS, EPHE, IRD, Montpellier, France
- Amélie Emanuel
- BPMP, Univ Montpellier, CNRS, INRAE, Montpellier, France
- Justine Floret
- CEFE, Univ Montpellier, CNRS, EPHE, IRD, Montpellier, France
- Justine Floret
- 0LEPSE, Univ Montpellier, INRAE, Institut Agro, Montpellier, France
- Aurélien Estarague
- CEFE, Univ Montpellier, CNRS, EPHE, IRD, Montpellier, France
- Stefania Przybylska
- CEFE, Univ Montpellier, CNRS, EPHE, IRD, Montpellier, France
- Kevin Sartori
- CEFE, Univ Montpellier, CNRS, EPHE, IRD, Montpellier, France
- Lauren M. Gillespie
- CEFE, Univ Montpellier, CNRS, EPHE, IRD, Montpellier, France
- Etienne Baron
- CEFE, Univ Montpellier, CNRS, EPHE, IRD, Montpellier, France
- Elena Kazakou
- CEFE, Univ Montpellier, CNRS, EPHE, Institut Agro, IRD, Montpellier, France
- Denis Vile
- 0LEPSE, Univ Montpellier, INRAE, Institut Agro, Montpellier, France
- Cyrille Violle
- CEFE, Univ Montpellier, CNRS, EPHE, IRD, Montpellier, France
- DOI
- https://doi.org/10.3389/fpls.2022.836488
- Journal volume & issue
-
Vol. 13
Abstract
The trait-based approach in plant ecology aims at understanding and classifying the diversity of ecological strategies by comparing plant morphology and physiology across organisms. The major drawback of the approach is that the time and financial cost of measuring the traits on many individuals and environments can be prohibitive. We show that combining near-infrared spectroscopy (NIRS) with deep learning resolves this limitation by quickly, non-destructively, and accurately measuring a suite of traits, including plant morphology, chemistry, and metabolism. Such an approach also allows to position plants within the well-known CSR triangle that depicts the diversity of plant ecological strategies. The processing of NIRS through deep learning identifies the effect of growth conditions on trait values, an issue that plagues traditional statistical approaches. Together, the coupling of NIRS and deep learning is a promising high-throughput approach to capture a range of ecological information on plant diversity and functioning and can accelerate the creation of extensive trait databases.
Keywords
- Arabidopsis thaliana
- near-infrared spectroscopy (NIRS)
- multivariate analysis
- machine learning
- functional traits
- metabolomics