Next Article in Journal
Computation of Optimized Electrode Arrays for 3-D Electrical Resistivity Tomography Surveys
Next Article in Special Issue
Comparative FT-IR Prospecting for Cellulose in Stems of Some Fiber Plants: Flax, Velvet Leaf, Hemp and Jute
Previous Article in Journal
Detecting Deception from Gaze and Speech Using a Multimodal Attention LSTM-Based Framework
Previous Article in Special Issue
NIRS Estimation of Drought Stress on Chemical Quality Constituents of Taro (Colocasia esculenta L.) and Sweet Potato (Ipomoea batatas L.) Flours
 
 
Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
Journals
Applied Sciences
Volume 11
Issue 14
10.3390/app11146392
applsci-logo
Submit to this Journal Review for this Journal Propose a Special Issue
► Article Menu

Article Menu

share Share announcement Help format_quote Cite question_answer Discuss in SciProfiles
first_page
settings
Order Article Reprints
Font Type:
Arial Georgia Verdana
Font Size:
Aa Aa Aa
Line Spacing:
Column Width:
Background:
Article

Comparing Machine Learning Methods for Classifying Plant Drought Stress from Leaf Reflectance Spectra in Arabidopsis thaliana

by
Ana Barradas
1,
Pedro M.P. Correia
1,2,
Sara Silva
3,
Pedro Mariano
4,
Margarida Calejo Pires
1,
Ana Rita Matos
1,2,
Anabela Bernardes da Silva
1,2 and
Jorge Marques da Silva
1,2,*
1
BioISI—Biosystems and Integrative Sciences Institute, Faculdade de Ciências, Universidade de Lisboa, 1749-016 Lisboa, Portugal
2
Departamento de Biologia Vegetal, Faculdade de Ciências, Universidade de Lisboa, 1749-016 Lisboa, Portugal
3
LASIGE, Faculdade de Ciências, Universidade de Lisboa, 1749-016 Lisboa, Portugal
4
Centro de Ciências e Tecnologias Nucleares, Instituto Superior Técnico, 2695-066 Bobadela, Portugal
*
Author to whom correspondence should be addressed.
Appl. Sci. 2021, 11(14), 6392; https://doi.org/10.3390/app11146392
Submission received: 8 May 2021 / Revised: 29 June 2021 / Accepted: 4 July 2021 / Published: 11 July 2021
(This article belongs to the Special Issue Applications of Optical Spectroscopy in Plant Sciences)
Browse Figures
Versions Notes

Abstract

Plant breeders and plant physiologists are deeply committed to high throughput plant phenotyping for drought tolerance. A combination of artificial intelligence with reflectance spectroscopy was tested, as a non-invasive method, for the automatic classification of plant drought stress. Arabidopsis thaliana plants (ecotype Col-0) were subjected to different levels of slowly imposed dehydration (S0, control; S1, moderate stress; S2, severe stress). The reflectance spectra of fully expanded leaves were recorded with an Ocean Optics USB4000 spectrometer and the soil water content (SWC, %) of each pot was determined. The entire data set of the reflectance spectra (intensity vs. wavelength) was given to different machine learning (ML) algorithms, namely decision trees, random forests and extreme gradient boosting. The performance of different methods in classifying the plants in one of the three drought stress classes (S0, S1 and S2) was measured and compared. All algorithms produced very high evaluation scores (F1 > 90%) and agree on the features with the highest discriminative power (reflectance at ~670 nm). Random forests was the best performing method and the most robust to random sampling of training data, with an average F1-score of 0.96 ± 0.05. This classification method is a promising tool to detect plant physiological responses to drought using high-throughput pipelines.
Keywords: Arabidopsis thaliana; water stress; soil water content; reflectance spectra; plant phenotyping; artificial intelligence; machine learning; decision trees; random forests; extreme gradient boosting Arabidopsis thaliana; water stress; soil water content; reflectance spectra; plant phenotyping; artificial intelligence; machine learning; decision trees; random forests; extreme gradient boosting

Share and Cite

MDPI and ACS Style

Barradas, A.; Correia, P.M.P.; Silva, S.; Mariano, P.; Pires, M.C.; Matos, A.R.; da Silva, A.B.; Marques da Silva, J. Comparing Machine Learning Methods for Classifying Plant Drought Stress from Leaf Reflectance Spectra in Arabidopsis thaliana. Appl. Sci. 2021, 11, 6392. https://doi.org/10.3390/app11146392

AMA Style

Barradas A, Correia PMP, Silva S, Mariano P, Pires MC, Matos AR, da Silva AB, Marques da Silva J. Comparing Machine Learning Methods for Classifying Plant Drought Stress from Leaf Reflectance Spectra in Arabidopsis thaliana. Applied Sciences. 2021; 11(14):6392. https://doi.org/10.3390/app11146392

Chicago/Turabian Style

Barradas, Ana, Pedro M.P. Correia, Sara Silva, Pedro Mariano, Margarida Calejo Pires, Ana Rita Matos, Anabela Bernardes da Silva, and Jorge Marques da Silva. 2021. "Comparing Machine Learning Methods for Classifying Plant Drought Stress from Leaf Reflectance Spectra in Arabidopsis thaliana" Applied Sciences 11, no. 14: 6392. https://doi.org/10.3390/app11146392

APA Style

Barradas, A., Correia, P. M. P., Silva, S., Mariano, P., Pires, M. C., Matos, A. R., da Silva, A. B., & Marques da Silva, J. (2021). Comparing Machine Learning Methods for Classifying Plant Drought Stress from Leaf Reflectance Spectra in Arabidopsis thaliana. Applied Sciences, 11(14), 6392. https://doi.org/10.3390/app11146392

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Metrics

Back to TopTop