A leaf-level spectral library to support high-throughput plant phenotyping: predictive accuracy and model transfer

Wijewardane, Nuwan K.; Zhang, Huichun; Yang, Jinliang; Schnable, James C.; Schachtman, Daniel P.; Ge, Yufeng; Lunn, ed., John

doi:10.1093/jxb/erad129

Title: A leaf-level spectral library to support high-throughput plant phenotyping: predictive accuracy and model transfer

Journal Article · 04 April 2023 · Journal of Experimental Botany

DOI: https://doi.org/10.1093/jxb/erad129 · OSTI ID:1993631

; Zhang, Huichun;

;

; Lunn, ed., John

Abstract Leaf-level hyperspectral reflectance has become an effective tool for high-throughput phenotyping of plant leaf traits due to its rapid, low-cost, multi-sensing, and non-destructive nature. However, collecting samples for model calibration can still be expensive, and models show poor transferability among different datasets. This study had three specific objectives: first, to assemble a large library of leaf hyperspectral data (n=2460) from maize and sorghum; second, to evaluate two machine-learning approaches to estimate nine leaf properties (chlorophyll, thickness, water content, nitrogen, phosphorus, potassium, calcium, magnesium, and sulfur); and third, to investigate the usefulness of this spectral library for predicting external datasets (n=445) including soybean and camelina using extra-weighted spiking. Internal cross-validation showed satisfactory performance of the spectral library to estimate all nine traits (mean R2=0.688), with partial least-squares regression outperforming deep neural network models. Models calibrated solely using the spectral library showed degraded performance on external datasets (mean R2=0.159 for camelina, 0.337 for soybean). Models improved significantly when a small portion of external samples (n=20) was added to the library via extra-weighted spiking (mean R2=0.574 for camelina, 0.536 for soybean). The leaf-level spectral library greatly benefits plant physiological and biochemical phenotyping, whilst extra-weight spiking improves model transferability and extends its utility.

View Journal Article

Cite

Export

Save

Research Organization:: Univ. of Nebraska, Lincoln, NE (United States)

Sponsoring Organization:: USDOE; USDOE Office of Science (SC)

Grant/Contract Number:: SC0020355; SC0023138

OSTI ID:: 1993631

Journal Information:: Journal of Experimental Botany, Journal Name: Journal of Experimental Botany Journal Issue: 14 Vol. 74; ISSN 0022-0957

Publisher:: Oxford University PressCopyright Statement

Country of Publication:: United Kingdom

Language:: English

References (40)

Artificial neural networks Dayhoff, Judith E.; DeLeo, James M. Cancer, Vol. 91, Issue S8 https://doi.org/10.1002/1097-0142(20010415)91:8+<1615::AID-CNCR1175>3.0.CO;2-L	journal	January 2001
The Elements of Statistical Learning Hastie, Trevor; Tibshirani, Robert; Friedman, Jerome Springer Series in Statistics https://doi.org/10.1007/978-0-387-84858-7	book	January 2009
Sulfolipid Biosynthesis and Function in Plants Benning, Christoph; Garavito, R. Michael; Shimojima, Mie Sulfur Metabolism in Phototrophic Organisms https://doi.org/10.1007/978-1-4020-6863-8_10	book	January 2008
Roles and Transport of Sodium and Potassium in Plants Nieves-Cordones, Manuel; Al Shiblawi, Fouad Razzaq; Sentenac, Hervé The Alkali Metal Ions: Their Role for Life https://doi.org/10.1007/978-3-319-21756-7_9	book	January 2016
Comparison of various modelling approaches for water deficit stress monitoring in rice crop through hyperspectral remote sensing Krishna, Gopal; Sahoo, Rabi N.; Singh, Prafull Agricultural Water Management, Vol. 213 https://doi.org/10.1016/j.agwat.2018.08.029	journal	March 2019
Temporal dynamics of maize plant growth, water use, and leaf water content using automated high throughput RGB and hyperspectral imaging Ge, Yufeng; Bai, Geng; Stoerger, Vincent Computers and Electronics in Agriculture, Vol. 127 https://doi.org/10.1016/j.compag.2016.07.028	journal	September 2016
In vivo human-like robotic phenotyping of leaf traits in maize and sorghum in greenhouse Atefi, Abbas; Ge, Yufeng; Pitla, Santosh Computers and Electronics in Agriculture, Vol. 163 https://doi.org/10.1016/j.compag.2019.104854	journal	August 2019
LeafSpec: An accurate and portable hyperspectral corn leaf imager Wang, Liangju; Jin, Jian; Song, Zhihang Computers and Electronics in Agriculture, Vol. 169 https://doi.org/10.1016/j.compag.2019.105209	journal	February 2020
Using data mining to model and interpret soil diffuse reflectance spectra Rossel, R. A. Viscarra; Behrens, T. Geoderma, Vol. 158, Issue 1-2 https://doi.org/10.1016/j.geoderma.2009.12.025	journal	August 2010
Convolutional neural network for simultaneous prediction of several soil properties using visible/near-infrared, mid-infrared, and their combined spectra Ng, Wartini; Minasny, Budiman; Montazerolghaem, Maryam Geoderma, Vol. 352 https://doi.org/10.1016/j.geoderma.2019.06.016	journal	October 2019
Improvement in spectral library-based quantification of soil properties using representative spiking and local calibration – The case of soil inorganic carbon prediction by mid-infrared spectroscopy Barthès, Bernard G.; Kouakoua, Ernest; Coll, Patrice Geoderma, Vol. 369 https://doi.org/10.1016/j.geoderma.2020.114272	journal	June 2020
Machine Learning Techniques for Predicting Crop Photosynthetic Capacity from Leaf Reflectance Spectra Heckmann, David; Schlüter, Urte; Weber, Andreas P. M. Molecular Plant, Vol. 10, Issue 6 https://doi.org/10.1016/j.molp.2017.04.009	journal	June 2017
Lights, camera, action: high-throughput plant phenotyping is ready for a close-up Fahlgren, Noah; Gehan, Malia A.; Baxter, Ivan Current Opinion in Plant Biology, Vol. 24 https://doi.org/10.1016/j.pbi.2015.02.006	journal	April 2015
High-throughput field phenotyping using hyperspectral reflectance and partial least squares regression (PLSR) reveals genetic modifications to photosynthetic capacity Meacham-Hensold, Katherine; Montes, Christopher M.; Wu, Jin Remote Sensing of Environment, Vol. 231 https://doi.org/10.1016/j.rse.2019.04.029	journal	September 2019
Phenomics – technologies to relieve the phenotyping bottleneck Furbank, Robert T.; Tester, Mark Trends in Plant Science, Vol. 16, Issue 12 https://doi.org/10.1016/j.tplants.2011.09.005	journal	December 2011
Hyperspectral reflectance-based phenotyping for quantitative genetics in crops: Progress and challenges Grzybowski, Marcin; Wijewardane, Nuwan K.; Atefi, Abbas Plant Communications, Vol. 2, Issue 4 https://doi.org/10.1016/j.xplc.2021.100209	journal	July 2021
Phosphorus acquisition and use: critical adaptations by plants for securing a nonrenewable resource Vance, Carroll P.; Uhde-Stone, Claudia; Allan, Deborah L. New Phytologist, Vol. 157, Issue 3 https://doi.org/10.1046/j.1469-8137.2003.00695.x	journal	March 2003
Comparison of different regression models and validation techniques for the assessment of wheat leaf area index from hyperspectral data Siegmann, Bastian; Jarmer, Thomas International Journal of Remote Sensing, Vol. 36, Issue 18 https://doi.org/10.1080/01431161.2015.1084438	journal	September 2015
Leaf chlorophyll content Palta, Jiwan P. Remote Sensing Reviews, Vol. 5, Issue 1 https://doi.org/10.1080/02757259009532129	journal	January 1990
Hyperspectral remote sensing of plant pigments Blackburn, G. A. Journal of Experimental Botany, Vol. 58, Issue 4 https://doi.org/10.1093/jxb/erl123	journal	November 2006
Hyperspectral reflectance as a tool to measure biochemical and physiological traits in wheat Silva-Perez, Viridiana; Molero, Gemma; Serbin, Shawn P. Journal of Experimental Botany, Vol. 69, Issue 3 https://doi.org/10.1093/jxb/erx421	journal	December 2017
Spectroscopy can predict key leaf traits associated with source–sink balance and carbon–nitrogen status Ely, Kim S.; Burnett, Angela C.; Lieberman-Cribbin, Wil Journal of Experimental Botany, Vol. 70, Issue 6 https://doi.org/10.1093/jxb/erz061	journal	February 2019
High-Throughput Phenotyping of Maize Leaf Physiological and Biochemical Traits Using Hyperspectral Reflectance Yendrek, Craig R.; Tomaz, Tiago; Montes, Christopher M. Plant Physiology, Vol. 173, Issue 1 https://doi.org/10.1104/pp.16.01447	journal	November 2016
Spectral Phenotyping of Physiological and Anatomical Leaf Traits Related with Maize Water Status Cotrozzi, Lorenzo; Peron, Raquel; Tuinstra, Mitchell R. Plant Physiology, Vol. 184, Issue 3 https://doi.org/10.1104/pp.20.00577	journal	September 2020
Matplotlib: A 2D Graphics Environment Hunter, John D. Computing in Science & Engineering, Vol. 9, Issue 3 https://doi.org/10.1109/MCSE.2007.55	journal	January 2007
The NumPy Array: A Structure for Efficient Numerical Computation van der Walt, Stéfan; Colbert, S. Chris; Varoquaux, Gaël Computing in Science & Engineering, Vol. 13, Issue 2 https://doi.org/10.1109/MCSE.2011.37	journal	March 2011
Assessment of soil organic carbon at local scale with spiked NIR calibrations: effects of selection and extra-weighting on the spiking subset Guerrero, C.; Stenberg, B.; Wetterlind, J. European Journal of Soil Science, Vol. 65, Issue 2 https://doi.org/10.1111/ejss.12129	journal	February 2014
Maize association population: a high-resolution platform for quantitative trait locus dissection Flint-Garcia, Sherry A.; Thuillet, Anne-Céline; Yu, Jianming The Plant Journal, Vol. 44, Issue 6, p. 1054-1064 https://doi.org/10.1111/j.1365-313X.2005.02591.x	journal	November 2005
Calcium at the Cell Wall-Cytoplast Interface Hepler, Peter K.; Winship, Lawrence J. Journal of Integrative Plant Biology, Vol. 52, Issue 2 https://doi.org/10.1111/j.1744-7909.2010.00923.x	journal	February 2010
Predicting dark respiration rates of wheat leaves from hyperspectral reflectance Coast, Onoriode; Shah, Shahen; Ivakov, Alexander Plant, Cell & Environment, Vol. 42, Issue 7 https://doi.org/10.1111/pce.13544	journal	March 2019
High‐resolution phenotyping of sorghum genotypic and phenotypic responses to low nitrogen and synthetic microbial communities Chai, Yen Ning; Ge, Yufeng; Stoerger, Vincent Plant, Cell & Environment, Vol. 44, Issue 5 https://doi.org/10.1111/pce.14004	journal	February 2021
Assessing durum wheat ear and leaf metabolomes in the field through hyperspectral data Vergara‐Diaz, Omar; Vatter, Thomas; Kefauver, Shawn Carlisle The Plant Journal, Vol. 102, Issue 3 https://doi.org/10.1111/tpj.14636	journal	January 2020
Sorghum Association Panel whole‐genome sequencing establishes cornerstone resource for dissecting genomic diversity Boatwright, J. Lucas; Sapkota, Sirjan; Jin, Hongyu The Plant Journal, Vol. 111, Issue 3 https://doi.org/10.1111/tpj.15853	journal	July 2022
Genome-wide association analysis of stalk biomass and anatomical traits in maize Mazaheri, Mona; Heckwolf, Marlies; Vaillancourt, Brieanne BMC Plant Biology, Vol. 19, Issue 1 https://doi.org/10.1186/s12870-019-1653-x	journal	January 2019
High-throughput analysis of leaf physiological and chemical traits with VIS–NIR–SWIR spectroscopy: a case study with a maize diversity panel Ge, Yufeng; Atefi, Abbas; Zhang, Huichun Plant Methods, Vol. 15, Issue 1 https://doi.org/10.1186/s13007-019-0450-8	journal	June 2019
Prediction of Soil Carbon in the Conterminous United States: Visible and Near Infrared Reflectance Spectroscopy Analysis of the Rapid Carbon Assessment Project Wijewardane, Nuwan K.; Ge, Yufeng; Wills, Skye Soil Science Society of America Journal, Vol. 80, Issue 4 https://doi.org/10.2136/sssaj2016.02.0052	journal	January 2016
Predicting Physical and Chemical Properties of US Soils with a Mid‐Infrared Reflectance Spectral Library Wijewardane, Nuwan K.; Ge, Yufeng; Wills, Skye Soil Science Society of America Journal, Vol. 82, Issue 3 https://doi.org/10.2136/sssaj2017.10.0361	journal	April 2018
Data Structures for Statistical Computing in Python McKinney, Wes Proceedings of the Python in Science Conference https://doi.org/10.25080/Majora-92bf1922-00a	conference	January 2010
High Throughput In vivo Analysis of Plant Leaf Chemical Properties Using Hyperspectral Imaging Pandey, Piyush; Ge, Yufeng; Stoerger, Vincent Frontiers in Plant Science, Vol. 8 https://doi.org/10.3389/fpls.2017.01348	journal	August 2017
Rapid and cost-effective nutrient content analysis of cotton leaves using near-infrared spectroscopy (NIRS) Prananto, Jeremy Aditya; Minasny, Budiman; Weaver, Timothy PeerJ, Vol. 9 https://doi.org/10.7717/peerj.11042	journal	March 2021

Similar Records

High-throughput characterization, correlation, and mapping of leaf photosynthetic and functional traits in the soybean (Glycine max) nested association mapping population

Journal Article · 2022 · Genetics (Online) · OSTI ID:1869266

Montes, Christopher M.; Fox, Carolyn; Sanz-Sáez, Álvaro; +9 more

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

Journal Article · 2021 · Journal of Experimental Botany · OSTI ID:1798476

Burnett, Angela C.; Anderson, Jeremiah; Davidson, Kenneth J.; +7 more

APPL Hyperspectral_Imaging_Dataset_for_Heritability_Analysis_in_Populus_trichocarpa

Dataset · 2026 · OSTI ID:3014819

Shu, Mengjun; Lagergren, John H.; Harman-Ware, Anne E.; +5 more

Related Subjects

59 BASIC BIOLOGICAL SCIENCES
biochemical traits
camelina
extra-weighted spiking
high-throughput phenotyping
leaf hyperspectral reflectance
machine-learning
maize
partial least squares regression
sorghum
soybean
trait modeling

Title: A leaf-level spectral library to support high-throughput plant phenotyping: predictive accuracy and model transfer

Citation Formats

References (40)

Similar Records

Related Subjects