skip to main content
DOE PAGES title logo U.S. Department of Energy
Office of Scientific and Technical Information

This content will become publicly available on June 15, 2022

Title: A best-practice guide to predicting plant traits from leaf-level hyperspectral data using partial least squares regression

Abstract

Partial least squares regression (PLSR) modelling is a statistical technique for correlating datasets, and involves the fitting of a linear regression between two matrices. One application of PLSR enables leaf traits to be estimated from hyperspectral optical reflectance data, facilitating rapid, high-throughput, non-destructive plant phenotyping. This technique is of interest and importance in a wide range of contexts including crop breeding and ecosystem monitoring. The lack of a consensus in the literature on how to perform PLSR means that interpreting model results can be challenging, applying existing models to novel datasets can be impossible, and unknown or undisclosed assumptions can lead to incorrect or spurious predictions. We address this lack of consensus by proposing best practices for using PLSR to predict plant traits from leaf-level hyperspectral data, including a discussion of when PLSR is applicable, and recommendations for data collection. Further, we provide a tutorial to demonstrate how to develop a PLSR model, in the form of an R script accompanying this manuscript. This practical guide will assist all those interpreting and using PLSR models to predict leaf traits from spectral data, and advocates for a unified approach to using PLSR for predicting traits from spectra in the plant sciences.

Authors:
ORCiD logo [1]; ORCiD logo [1]; ORCiD logo [1]; ORCiD logo [1]; ORCiD logo [1]; ORCiD logo [1]; ORCiD logo [1]; ORCiD logo [1]; ORCiD logo [1]; ORCiD logo [1]
  1. Brookhaven National Lab. (BNL), Upton, NY (United States)
Publication Date:
Research Org.:
Brookhaven National Lab. (BNL), Upton, NY (United States)
Sponsoring Org.:
USDOE Office of Science (SC), Biological and Environmental Research (BER)
OSTI Identifier:
1798476
Report Number(s):
BNL-221656-2021-JAAM
Journal ID: ISSN 0022-0957
Grant/Contract Number:  
SC0012704
Resource Type:
Accepted Manuscript
Journal Name:
Journal of Experimental Botany
Additional Journal Information:
Journal Volume: 72; Journal Issue: 18; Journal ID: ISSN 0022-0957
Publisher:
Oxford University Press
Country of Publication:
United States
Language:
English
Subject:
54 ENVIRONMENTAL SCIENCES; hyperspectral reflectance; leaf traits; LMA; modelling; plant traits; PLSR; spectra; spectroradiometer; spectroscopy

Citation Formats

Burnett, Angela C., Anderson, Jeremiah, Davidson, Kenneth J., Ely, Kim S., Lamour, Julien, Li, Qianyu, Morrison, Bailey D., Yang, Dedi, Rogers, Alistair, and Serbin, Shawn P.. A best-practice guide to predicting plant traits from leaf-level hyperspectral data using partial least squares regression. United States: N. p., 2021. Web. https://doi.org/10.1093/jxb/erab295.
Burnett, Angela C., Anderson, Jeremiah, Davidson, Kenneth J., Ely, Kim S., Lamour, Julien, Li, Qianyu, Morrison, Bailey D., Yang, Dedi, Rogers, Alistair, & Serbin, Shawn P.. A best-practice guide to predicting plant traits from leaf-level hyperspectral data using partial least squares regression. United States. https://doi.org/10.1093/jxb/erab295
Burnett, Angela C., Anderson, Jeremiah, Davidson, Kenneth J., Ely, Kim S., Lamour, Julien, Li, Qianyu, Morrison, Bailey D., Yang, Dedi, Rogers, Alistair, and Serbin, Shawn P.. Tue . "A best-practice guide to predicting plant traits from leaf-level hyperspectral data using partial least squares regression". United States. https://doi.org/10.1093/jxb/erab295.
@article{osti_1798476,
title = {A best-practice guide to predicting plant traits from leaf-level hyperspectral data using partial least squares regression},
author = {Burnett, Angela C. and Anderson, Jeremiah and Davidson, Kenneth J. and Ely, Kim S. and Lamour, Julien and Li, Qianyu and Morrison, Bailey D. and Yang, Dedi and Rogers, Alistair and Serbin, Shawn P.},
abstractNote = {Partial least squares regression (PLSR) modelling is a statistical technique for correlating datasets, and involves the fitting of a linear regression between two matrices. One application of PLSR enables leaf traits to be estimated from hyperspectral optical reflectance data, facilitating rapid, high-throughput, non-destructive plant phenotyping. This technique is of interest and importance in a wide range of contexts including crop breeding and ecosystem monitoring. The lack of a consensus in the literature on how to perform PLSR means that interpreting model results can be challenging, applying existing models to novel datasets can be impossible, and unknown or undisclosed assumptions can lead to incorrect or spurious predictions. We address this lack of consensus by proposing best practices for using PLSR to predict plant traits from leaf-level hyperspectral data, including a discussion of when PLSR is applicable, and recommendations for data collection. Further, we provide a tutorial to demonstrate how to develop a PLSR model, in the form of an R script accompanying this manuscript. This practical guide will assist all those interpreting and using PLSR models to predict leaf traits from spectral data, and advocates for a unified approach to using PLSR for predicting traits from spectra in the plant sciences.},
doi = {10.1093/jxb/erab295},
journal = {Journal of Experimental Botany},
number = 18,
volume = 72,
place = {United States},
year = {2021},
month = {6}
}

Journal Article:
Free Publicly Available Full Text
This content will become publicly available on June 15, 2022
Publisher's Version of Record

Save / Share:

Works referenced in this record:

Seasonal variability of multiple leaf traits captured by leaf spectroscopy at two temperate deciduous forests
journal, June 2016


Application of imaging spectroscopy to mapping canopy nitrogen in the forests of the central appalachian mountains using hyperion and aviris
journal, June 2003

  • Townsend, P. A.; Foster, J. R.; Chastain, R. A.
  • IEEE Transactions on Geoscience and Remote Sensing, Vol. 41, Issue 6
  • DOI: 10.1109/TGRS.2003.813205

The elephant in the room: Predictive performance of PLS models
journal, October 2016


Foliar functional traits from imaging spectroscopy across biomes in eastern North America
journal, June 2020

  • Wang, Zhihui; Chlus, Adam; Geygan, Ryan
  • New Phytologist, Vol. 228, Issue 2
  • DOI: 10.1111/nph.16711

Partial least squares regression in the social sciences
journal, June 2015

  • Sawatsky, Megan L.; Clyde, Matthew; Meek, Fiona
  • The Quantitative Methods for Psychology, Vol. 11, Issue 2
  • DOI: 10.20982/tqmp.11.2.p052

Acclimation and adaptation components of the temperature dependence of plant photosynthesis at the global scale
journal, February 2019

  • Kumarathunge, Dushan P.; Medlyn, Belinda E.; Drake, John E.
  • New Phytologist, Vol. 222, Issue 2
  • DOI: 10.1111/nph.15668

Predicting tropical plant physiology from leaf and canopy spectroscopy
journal, October 2010


Partial least-squares regression: a tutorial
journal, January 1986


New handbook for standardised measurement of plant functional traits worldwide
journal, January 2013

  • Pérez-Harguindeguy, N.; Díaz, S.; Garnier, E.
  • Australian Journal of Botany, Vol. 61, Issue 3
  • DOI: 10.1071/BT12225

Physiological breeding
journal, June 2016


Spectroscopy can predict key leaf traits associated with source–sink balance and carbon–nitrogen status
journal, February 2019

  • Ely, Kim S.; Burnett, Angela C.; Lieberman-Cribbin, Wil
  • Journal of Experimental Botany, Vol. 70, Issue 6
  • DOI: 10.1093/jxb/erz061

Partial Least Squares (PLS) methods for neuroimaging: A tutorial and review
journal, May 2011


Convergence in relationships between leaf traits, spectra and age across diverse canopy environments and two contrasting tropical forests
journal, July 2016

  • Wu, Jin; Chavana-Bryant, Cecilia; Prohaska, Neill
  • New Phytologist, Vol. 214, Issue 3
  • DOI: 10.1111/nph.14051

Spectroscopic determination of ecologically relevant plant secondary metabolites
journal, July 2016

  • Couture, John J.; Singh, Aditya; Rubert-Nason, Kennedy F.
  • Methods in Ecology and Evolution, Vol. 7, Issue 11
  • DOI: 10.1111/2041-210X.12596

Global photosynthetic capacity is optimized to the environment
journal, January 2019

  • Smith, Nicholas G.; Keenan, Trevor F.; Colin Prentice, I.
  • Ecology Letters, Vol. 22, Issue 3
  • DOI: 10.1111/ele.13210

Spectroscopic determination of leaf morphological and biochemical traits for northern temperate and boreal tree species
journal, October 2014

  • Serbin, Shawn P.; Singh, Aditya; McNeil, Brenden E.
  • Ecological Applications, Vol. 24, Issue 7
  • DOI: 10.1890/13-2110.1

The worldwide leaf economics spectrum
journal, April 2004

  • Wright, Ian J.; Reich, Peter B.; Westoby, Mark
  • Nature, Vol. 428, Issue 6985
  • DOI: 10.1038/nature02403

Global-scale environmental control of plant photosynthetic capacity
journal, December 2015

  • Ali, Ashehad A.; Xu, Chonggang; Rogers, Alistair
  • Ecological Applications, Vol. 25, Issue 8
  • DOI: 10.1890/14-2111.1

From tropics to tundra: Global convergence in plant functioning
journal, December 1997

  • Reich, P. B.; Walters, M. B.; Ellsworth, D. S.
  • Proceedings of the National Academy of Sciences, Vol. 94, Issue 25
  • DOI: 10.1073/pnas.94.25.13730

Diurnal regulation of plant growth*
journal, March 2006


Beyond greenness: Detecting temporal changes in photosynthetic capacity with hyperspectral reflectance data
journal, December 2017


High-throughput field phenotyping using hyperspectral reflectance and partial least squares regression (PLSR) reveals genetic modifications to photosynthetic capacity
journal, September 2019

  • Meacham-Hensold, Katherine; Montes, Christopher M.; Wu, Jin
  • Remote Sensing of Environment, Vol. 231
  • DOI: 10.1016/j.rse.2019.04.029

Let the concept of trait be functional!
journal, May 2007


Source:sink imbalance detected with leaf‐ and canopy‐level spectroscopy in a field‐grown crop
journal, April 2021

  • Burnett, Angela C.; Serbin, Shawn P.; Rogers, Alistair
  • Plant, Cell & Environment
  • DOI: 10.1111/pce.14056

Prediction of δ 13 C and δ 15 N in plant tissues with near-infrared reflectance spectroscopy
journal, November 2009


Modified Jack-knife estimation of parameter uncertainty in bilinear modelling by partial least squares regression (PLSR)
journal, January 2000


Plant functional trait change across a warming tundra biome
journal, September 2018


Estimation of photosynthesis traits from leaf reflectance spectra: Correlation to nitrogen content as the dominant mechanism
journal, July 2017

  • Dechant, Benjamin; Cuntz, Matthias; Vohland, Michael
  • Remote Sensing of Environment, Vol. 196
  • DOI: 10.1016/j.rse.2017.05.019

Characterizing canopy biochemistry from imaging spectroscopy and its application to ecosystem studies
journal, September 2009

  • Kokaly, Raymond F.; Asner, Gregory P.; Ollinger, Scott V.
  • Remote Sensing of Environment, Vol. 113
  • DOI: 10.1016/j.rse.2008.10.018

PLS-regression: a basic tool of chemometrics
journal, October 2001

  • Wold, Svante; Sjöström, Michael; Eriksson, Lennart
  • Chemometrics and Intelligent Laboratory Systems, Vol. 58, Issue 2
  • DOI: 10.1016/S0169-7439(01)00155-1

Diurnal Fluctuations in Cotton Leaf Carbon Export, Carbohydrate Content, and Sucrose Synthesizing Enzymes
journal, June 1986

  • Hendrix, Donald L.; Huber, Steven C.
  • Plant Physiology, Vol. 81, Issue 2
  • DOI: 10.1104/pp.81.2.584

The relationship of leaf photosynthetic traits - V cmax and J max - to leaf nitrogen, leaf phosphorus, and specific leaf area: a meta-analysis and modeling study
journal, July 2014

  • Walker, Anthony P.; Beckerman, Andrew P.; Gu, Lianhong
  • Ecology and Evolution, Vol. 4, Issue 16
  • DOI: 10.1002/ece3.1173

Leaf chlorophyll content as a proxy for leaf photosynthetic capacity
journal, January 2017

  • Croft, Holly; Chen, Jing M.; Luo, Xiangzhong
  • Global Change Biology, Vol. 23, Issue 9
  • DOI: 10.1111/gcb.13599

High Spectral Resolution Remote Sensing of Forest Canopy Lignin, Nitrogen, and Ecosystem Processes
journal, May 1997


Remote sensing of foliar chemistry
journal, December 1989


Reflectance spectroscopy of fresh whole leaves for the estimation of chemical concentration
journal, February 1992


Global plant trait relationships extend to the climatic extremes of the tundra biome
journal, March 2020


Remote sensing of the distribution and abundance of host species for spruce budworm in Northern Minnesota and Ontario
journal, October 2008


A handbook of protocols for standardised and easy measurement of plant functional traits worldwide
journal, January 2003

  • Cornelissen, J. H. C.; Lavorel, S.; Garnier, E.
  • Australian Journal of Botany, Vol. 51, Issue 4
  • DOI: 10.1071/BT02124

Functional and biological diversity of foliar spectra in tree canopies throughout the Andes to Amazon region
journal, June 2014

  • Asner, Gregory P.; Martin, Roberta E.; Carranza-Jiménez, Loreli
  • New Phytologist, Vol. 204, Issue 1
  • DOI: 10.1111/nph.12895

Effect of leaf temperature on the estimation of photosynthetic and other traits of wheat leaves from hyperspectral reflectance
journal, November 2020

  • Khan, Hammad A.; Nakamura, Yukiko; Furbank, Robert T.
  • Journal of Experimental Botany, Vol. 72, Issue 4
  • DOI: 10.1093/jxb/eraa514

Hyperspectral reflectance as a tool to measure biochemical and physiological traits in wheat
journal, December 2017

  • Silva-Perez, Viridiana; Molero, Gemma; Serbin, Shawn P.
  • Journal of Experimental Botany, Vol. 69, Issue 3
  • DOI: 10.1093/jxb/erx421

Systems Analysis of a Maize Leaf Developmental Gradient Redefines the Current C 4 Model and Provides Candidates for Regulation
journal, December 2011

  • Pick, Thea R.; Bräutigam, Andrea; Schlüter, Urte
  • The Plant Cell, Vol. 23, Issue 12
  • DOI: 10.1105/tpc.111.090324

Using imaging spectroscopy to detect variation in terrestrial ecosystem productivity across a water-stressed landscape
journal, May 2018

  • DuBois, Sean; Desai, Ankur R.; Singh, Aditya
  • Ecological Applications, Vol. 28, Issue 5
  • DOI: 10.1002/eap.1733

Investigating a Physical Basis for Spectroscopic Estimates of Leaf Nitrogen Concentration
journal, February 2001


Diurnal Carbohydrate Metabolism of Barley Primary Leaves
journal, September 1984

  • Sicher, Richard C.; Kremer, Diane F.; Harris, William G.
  • Plant Physiology, Vol. 76, Issue 1
  • DOI: 10.1104/pp.76.1.165

High-Throughput Phenotyping of Maize Leaf Physiological and Biochemical Traits Using Hyperspectral Reflectance
journal, November 2016

  • Yendrek, Craig R.; Tomaz, Tiago; Montes, Christopher M.
  • Plant Physiology, Vol. 173, Issue 1
  • DOI: 10.1104/pp.16.01447

Plant traits inform predictions of tundra responses to global change
journal, November 2018

  • Myers‐Smith, Isla H.; Thomas, Haydn J. D.; Bjorkman, Anne D.
  • New Phytologist, Vol. 221, Issue 4
  • DOI: 10.1111/nph.15592

From the Arctic to the tropics: multibiome prediction of leaf mass per area using leaf reflectance
journal, September 2019

  • Serbin, Shawn P.; Wu, Jin; Ely, Kim S.
  • New Phytologist, Vol. 224, Issue 4
  • DOI: 10.1111/nph.16123

Estimating Canopy Water Content of Chaparral Shrubs Using Optical Methods
journal, September 1998


Using leaf optical properties to detect ozone effects on foliar biochemistry
journal, May 2013

  • Ainsworth, Elizabeth A.; Serbin, Shawn P.; Skoneczka, Jeffrey A.
  • Photosynthesis Research, Vol. 119, Issue 1-2
  • DOI: 10.1007/s11120-013-9837-y

Imaging spectroscopy algorithms for mapping canopy foliar chemical and morphological traits and their uncertainties
journal, December 2015

  • Singh, Aditya; Serbin, Shawn P.; McNeil, Brenden E.
  • Ecological Applications, Vol. 25, Issue 8
  • DOI: 10.1890/14-2098.1

Leaf traits and canopy structure together explain canopy functional diversity: an airborne remote sensing approach
journal, November 2020

  • Kamoske, Aaron G.; Dahlin, Kyla M.; Serbin, Shawn P.
  • Ecological Applications, Vol. 31, Issue 2
  • DOI: 10.1002/eap.2230

Functional Approaches to Predicting the Ecological Effects of Global Change
journal, January 1991

  • Woodward, F. I.; Diament, A. D.
  • Functional Ecology, Vol. 5, Issue 2
  • DOI: 10.2307/2389258

Foliar Spectra and Traits of Bog Plants across Nitrogen Deposition Gradients
journal, July 2020

  • Girard, Alizée; Schweiger, Anna K.; Carteron, Alexis
  • Remote Sensing, Vol. 12, Issue 15
  • DOI: 10.3390/rs12152448

Spectrally derived values of community leaf dry matter content link shifts in grassland composition with change in biomass production
journal, January 2020

  • Wayne Polley, H.; Yang, Chenghai; Wilsey, Brian J.
  • Remote Sensing in Ecology and Conservation, Vol. 6, Issue 3
  • DOI: 10.1002/rse2.145

Plant spectral diversity integrates functional and phylogenetic components of biodiversity and predicts ecosystem function
journal, May 2018

  • Schweiger, Anna K.; Cavender-Bares, Jeannine; Townsend, Philip A.
  • Nature Ecology & Evolution, Vol. 2, Issue 6
  • DOI: 10.1038/s41559-018-0551-1

Leaf optical properties reflect variation in photosynthetic metabolism and its sensitivity to temperature
journal, October 2011

  • Serbin, Shawn P.; Dillaway, Dylan N.; Kruger, Eric L.
  • Journal of Experimental Botany, Vol. 63, Issue 1
  • DOI: 10.1093/jxb/err294

Improved temperature response functions for models of Rubisco-limited photosynthesis
journal, February 2001


Foliar spectral properties following leaf clipping and implications for handling techniques
journal, August 2006


Predicting nitrogen and chlorophyll content and concentrations from reflectance spectra (400–2500 nm) at leaf and canopy scales
journal, September 1995


TRY plant trait database – enhanced coverage and open access
journal, December 2019

  • Kattge, Jens; Bönisch, Gerhard; Díaz, Sandra
  • Global Change Biology, Vol. 26, Issue 1
  • DOI: 10.1111/gcb.14904

Quantifying photosynthetic capacity and its relationship to leaf nitrogen content for global-scale terrestrial biosphere models
journal, April 2009