A Perspective on plant phenomics: Coupling deep learning and near-infrared spectroscopy

Vasseur François, Cornet Denis, Beurier Grégory, Messier Julie, Rouan Lauriane, Bresson Justine, Ecarnot Martin, Stahl Mark, Heumos Simon, Gérard Marianne, Reijnen Hans, Tillard Pascal, Lacombe Benoit, Emanuel Amélie, Floret Justine, Estarague Aurélien, Przybylska Stefania, Sartori Kevin, Gillespie Lauren M., Baron Etienne, Kazakou Elena, Vile Denis, Violle Cyrille. 2022. A Perspective on plant phenomics: Coupling deep learning and near-infrared spectroscopy. Frontiers in Plant Science, 13:13:836488, 12 p.

https://doi.org/10.3389/fpls.2022.836488

Article de revue ; Autre type d'article ; Article de revue à facteur d'impact Revue en libre accès total

Prévisualisation

Version publiée - Anglais
Sous licence

.
Vasseur et al 2022 - A Perspective on Plant Phenomics_Coupling Deep Learning and Near-Infrared Spectroscopy.pdf
Télécharger (1MB) | Prévisualisation

Résumé : 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.

Mots-clés Agrovoc : spectroscopie infrarouge, physiologie végétale, phytoécologie, morphologie végétale, adaptation physiologique, Arabidopsis thaliana, écologie, composé phénolique, spectroscopie, banque de données, mesure (activité), apprentissage, phénotype

Mots-clés libres : Arabidopsis thaliana, Near-infrared spectroscopy (NIRS), Multivariate analysis, Machine learning, Functional traits, Metabolomics, Trait-based ecology

Agences de financement européennes : European Research Council

Agences de financement hors UE : Institut National de la Recherche Agronomique, Agence Nationale de la Recherche, Région Occitanie Pyrénées-Méditerranée

Projets sur financement : (FRA) Exploration des réponses évolutives des plantes à des changements environnementaux à la lumière des théories écologiques : un test expérimental chez l'espèce modèle Arabidopsis thaliana, (EU) Ecophysiological and biophysical constraints on domestication in crop plants

Auteurs et affiliations