In-Field Whole-Plant Maize Architecture Characterized by Subcanopy Rovers and Latent Space Phenotyping
Abstract
Core Ideas * Subcanopy rovers enabled 3D characterization of thousands of hybrid maize plots. * Machine learning produces heritable latent traits that describe plant architecture. * Rover-based phenotyping is far more efficient than manual phenotyping. * Latent phenotypes from rovers are ready for application to plant biology and breeding. Collecting useful, interpretable, and biologically relevant phenotypes in a resource-efficient manner is a bottleneck to plant breeding, genetic mapping, and genomic prediction. Autonomous and affordable subcanopy rovers are an efficient and scalable way to generate sensor-based datasets of in-field crop plants. Rovers equipped with lidar can produce three-dimensional reconstructions of entire hybrid maize (Zea mays L.) fields. In this study, we collected 2103 lidar scans of hybrid maize field plots and extracted phenotypic data from them by latent space phenotyping. We performed latent space phenotyping by two methods, principal component analysis and a convolutional autoencoder, to extract meaningful, quantitative latent space phenotypes (LSPs) describing whole-plant architecture and biomass distribution. The LSPs had heritabilities of up to 0.44, similar to some manually measured traits, indicating that they can be selected on or genetically mapped. Manually measured traits can be successfully predicted by using LSPs as explanatory variables in partial least squares regression,more »
- Authors:
-
- Cornell Univ., Ithaca, NY (United States). Inst. for Genomic Diversity
- Drexel Univ., Philadelphia, PA (United States). Dept. of Mechanical Engineering
- US Dept. of Agriculture (USDA), Ithaca, NY (United States). Agricultural Research Service
- Cornell Univ., Ithaca, NY (United States)
- EarthSense, Inc., Champaign, IL (United States)
- Univ. of Illinois, Champaign, IL (United States). Dept. of Agricultural and Biological Engineering
- Publication Date:
- Research Org.:
- Univ. of Illinois at Urbana-Champaign, IL (United States)
- Sponsoring Org.:
- USDOE Advanced Research Projects Agency - Energy (ARPA-E)
- OSTI Identifier:
- 1603650
- Grant/Contract Number:
- AR0000598
- Resource Type:
- Accepted Manuscript
- Journal Name:
- The Plant Phenome Journal
- Additional Journal Information:
- Journal Volume: 2; Journal Issue: 1; Journal ID: ISSN 2578-2703
- Country of Publication:
- United States
- Language:
- English
- Subject:
- 59 BASIC BIOLOGICAL SCIENCES
Citation Formats
Gage, Joseph L., Richards, Elliot, Lepak, Nicholas, Kaczmar, Nicholas, Soman, Chinmay, Chowdhary, Girish, Gore, Michael A., and Buckler, Edward S. In-Field Whole-Plant Maize Architecture Characterized by Subcanopy Rovers and Latent Space Phenotyping. United States: N. p., 2019.
Web. doi:10.2135/tppj2019.07.0011.
Gage, Joseph L., Richards, Elliot, Lepak, Nicholas, Kaczmar, Nicholas, Soman, Chinmay, Chowdhary, Girish, Gore, Michael A., & Buckler, Edward S. In-Field Whole-Plant Maize Architecture Characterized by Subcanopy Rovers and Latent Space Phenotyping. United States. https://doi.org/10.2135/tppj2019.07.0011
Gage, Joseph L., Richards, Elliot, Lepak, Nicholas, Kaczmar, Nicholas, Soman, Chinmay, Chowdhary, Girish, Gore, Michael A., and Buckler, Edward S. Fri .
"In-Field Whole-Plant Maize Architecture Characterized by Subcanopy Rovers and Latent Space Phenotyping". United States. https://doi.org/10.2135/tppj2019.07.0011. https://www.osti.gov/servlets/purl/1603650.
@article{osti_1603650,
title = {In-Field Whole-Plant Maize Architecture Characterized by Subcanopy Rovers and Latent Space Phenotyping},
author = {Gage, Joseph L. and Richards, Elliot and Lepak, Nicholas and Kaczmar, Nicholas and Soman, Chinmay and Chowdhary, Girish and Gore, Michael A. and Buckler, Edward S.},
abstractNote = {Core Ideas * Subcanopy rovers enabled 3D characterization of thousands of hybrid maize plots. * Machine learning produces heritable latent traits that describe plant architecture. * Rover-based phenotyping is far more efficient than manual phenotyping. * Latent phenotypes from rovers are ready for application to plant biology and breeding. Collecting useful, interpretable, and biologically relevant phenotypes in a resource-efficient manner is a bottleneck to plant breeding, genetic mapping, and genomic prediction. Autonomous and affordable subcanopy rovers are an efficient and scalable way to generate sensor-based datasets of in-field crop plants. Rovers equipped with lidar can produce three-dimensional reconstructions of entire hybrid maize (Zea mays L.) fields. In this study, we collected 2103 lidar scans of hybrid maize field plots and extracted phenotypic data from them by latent space phenotyping. We performed latent space phenotyping by two methods, principal component analysis and a convolutional autoencoder, to extract meaningful, quantitative latent space phenotypes (LSPs) describing whole-plant architecture and biomass distribution. The LSPs had heritabilities of up to 0.44, similar to some manually measured traits, indicating that they can be selected on or genetically mapped. Manually measured traits can be successfully predicted by using LSPs as explanatory variables in partial least squares regression, indicating that the LSPs contain biologically relevant information about plant architecture. These techniques can be used to assess crop architecture at a reduced cost and in an automated fashion for breeding, research, or extension purposes, as well as to create or inform crop growth models.},
doi = {10.2135/tppj2019.07.0011},
journal = {The Plant Phenome Journal},
number = 1,
volume = 2,
place = {United States},
year = {2019},
month = {11}
}
Free Publicly Available Full Text
Publisher's Version of Record
Other availability
Search WorldCat to find libraries that may hold this journal
Save to My Library
You must Sign In or Create an Account in order to save documents to your library.
Works referenced in this record:
Unmanned Aerial Vehicle Remote Sensing for Field-Based Crop Phenotyping: Current Status and Perspectives
journal, June 2017
- Yang, Guijun; Liu, Jiangang; Zhao, Chunjiang
- Frontiers in Plant Science, Vol. 8
In-field High Throughput Phenotyping and Cotton Plant Growth Analysis Using LiDAR
journal, January 2018
- Sun, Shangpeng; Li, Changying; Paterson, Andrew H.
- Frontiers in Plant Science, Vol. 9
Evaluating maize phenotype dynamics under drought stress using terrestrial lidar
journal, February 2019
- Su, Yanjun; Wu, Fangfang; Ao, Zurui
- Plant Methods, Vol. 15, Issue 1
Multivariate Density Estimation: Theory, Practice, and Visualization
book, March 2015
- Scott, David W.
- Wiley Series in Probability and Statistics
BreedVision — A Multi-Sensor Platform for Non-Destructive Field-Based Phenotyping in Plant Breeding
journal, February 2013
- Busemeyer, Lucas; Mentrup, Daniel; Möller, Kim
- Sensors, Vol. 13, Issue 3
Field Scanalyzer: An automated robotic field phenotyping platform for detailed crop monitoring
journal, January 2017
- Virlet, Nicolas; Sabermanesh, Kasra; Sadeghi-Tehran, Pouria
- Functional Plant Biology, Vol. 44, Issue 1
NU-Spidercam: A large-scale, cable-driven, integrated sensing and robotic system for advanced phenotyping, remote sensing, and agronomic research
journal, May 2019
- Bai, Geng; Ge, Yufeng; Scoby, David
- Computers and Electronics in Agriculture, Vol. 160
Under canopy light detection and ranging‐based autonomous navigation
journal, December 2018
- Higuti, Vitor A. H.; Velasquez, Andres E. B.; Magalhaes, Daniel Varela
- Journal of Field Robotics, Vol. 36, Issue 3
Field-Based High-Throughput Phenotyping for Maize Plant Using 3D LiDAR Point Cloud Generated With a “Phenomobile”
journal, May 2019
- Qiu, Quan; Sun, Na; Bai, He
- Frontiers in Plant Science, Vol. 10
A High-Throughput, Field-Based Phenotyping Technology for Tall Biomass Crops
journal, June 2017
- Salas Fernandez, Maria G.; Bao, Yin; Tang, Lie
- Plant Physiology, Vol. 174, Issue 4
Image Analysis: The New Bottleneck in Plant Phenotyping [Applications Corner]
journal, July 2015
- Minervini, Massimo; Scharr, Hanno; Tsaftaris, Sotirios A.
- IEEE Signal Processing Magazine, Vol. 32, Issue 4
Idea Factory: the Maize Genomes to Fields Initiative
journal, July 2019
- Lawrence‐Dill, Carolyn J.; Schnable, Patrick S.; Springer, Nathan M.
- Crop Science, Vol. 59, Issue 4
3D lidar imaging for detecting and understanding plant responses and canopy structure
journal, November 2006
- Omasa, K.; Hosoi, F.; Konishi, A.
- Journal of Experimental Botany, Vol. 58, Issue 4
The effect of artificial selection on phenotypic plasticity in maize
journal, November 2017
- Gage, Joseph L.; Jarquin, Diego; Romay, Cinta
- Nature Communications, Vol. 8, Issue 1
Development and evaluation of a field-based high-throughput phenotyping platform
journal, January 2014
- Andrade-Sanchez, Pedro; Gore, Michael A.; Heun, John T.
- Functional Plant Biology, Vol. 41, Issue 1
Maize Genomes to Fields: 2014 and 2015 field season genotype, phenotype, environment, and inbred ear image datasets
journal, July 2018
- AlKhalifah, Naser; Campbell, Darwin A.; Falcon, Celeste M.
- BMC Research Notes, Vol. 11, Issue 1
The pls Package: Principal Component and Partial Least Squares Regression in R
journal, January 2007
- Mevik, Bjørn-Helge; Wehrens, Ron
- Journal of Statistical Software, Vol. 18, Issue 2
Selection Signatures Underlying Dramatic Male Inflorescence Transformation During Modern Hybrid Maize Breeding
journal, September 2018
- Gage, Joseph L.; White, Michael R.; Edwards, Jode W.
- Genetics, Vol. 210, Issue 3
Phenomics: the next challenge
journal, November 2010
- Houle, David; Govindaraju, Diddahally R.; Omholt, Stig
- Nature Reviews Genetics, Vol. 11, Issue 12
Translating High-Throughput Phenotyping into Genetic Gain
journal, May 2018
- Araus, José Luis; Kefauver, Shawn C.; Zaman-Allah, Mainassara
- Trends in Plant Science, Vol. 23, Issue 5
EBImage--an R package for image processing with applications to cellular phenotypes
journal, March 2010
- Pau, G.; Fuchs, F.; Sklyar, O.
- Bioinformatics, Vol. 26, Issue 7
Breaking the curse of dimensionality to identify causal variants in Breeding 4
journal, December 2018
- Ramstein, Guillaume P.; Jensen, Sarah E.; Buckler, Edward S.
- Theoretical and Applied Genetics, Vol. 132, Issue 3
A Threshold Selection Method from Gray-Level Histograms
journal, January 1979
- Otsu, Nobuyuki
- IEEE Transactions on Systems, Man, and Cybernetics, Vol. 9, Issue 1
Next-generation phenotyping: requirements and strategies for enhancing our understanding of genotype–phenotype relationships and its relevance to crop improvement
journal, March 2013
- Cobb, Joshua N.; DeClerck, Genevieve; Greenberg, Anthony
- Theoretical and Applied Genetics, Vol. 126, Issue 4
Works referencing / citing this record:
Multi-dimensional machine learning approaches for fruit shape phenotyping in strawberry
journal, April 2020
- Feldmann, Mitchell J.; Hardigan, Michael A.; Famula, Randi A.
- GigaScience, Vol. 9, Issue 5