Cargando…

Unsupervised Plot-Scale LAI Phenotyping via UAV-Based Imaging, Modelling, and Machine Learning

High-throughput phenotyping has become the frontier to accelerate breeding through linking genetics to crop growth estimation, which requires accurate estimation of leaf area index (LAI). This study developed a hybrid method to train the random forest regression (RFR) models with synthetic datasets...

Descripción completa

Detalles Bibliográficos
Autores principales: Chen, Qiaomin, Zheng, Bangyou, Chenu, Karine, Hu, Pengcheng, Chapman, Scott C.
Formato: Online Artículo Texto
Lenguaje:English
Publicado: AAAS 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9317541/
https://www.ncbi.nlm.nih.gov/pubmed/35935677
http://dx.doi.org/10.34133/2022/9768253
_version_ 1784755082487660544
author Chen, Qiaomin
Zheng, Bangyou
Chenu, Karine
Hu, Pengcheng
Chapman, Scott C.
author_facet Chen, Qiaomin
Zheng, Bangyou
Chenu, Karine
Hu, Pengcheng
Chapman, Scott C.
author_sort Chen, Qiaomin
collection PubMed
description High-throughput phenotyping has become the frontier to accelerate breeding through linking genetics to crop growth estimation, which requires accurate estimation of leaf area index (LAI). This study developed a hybrid method to train the random forest regression (RFR) models with synthetic datasets generated by a radiative transfer model to estimate LAI from UAV-based multispectral images. The RFR models were evaluated on both (i) subsets from the synthetic datasets and (ii) observed data from two field experiments (i.e., Exp16, Exp19). Given the parameter ranges and soil reflectance are well calibrated in synthetic training data, RFR models can accurately predict LAI from canopy reflectance captured in field conditions, with systematic overestimation for LAI<2 due to background effect, which can be addressed by applying background correction on original reflectance map based on vegetation-background classification. Overall, RFR models achieved accurate LAI prediction from background-corrected reflectance for Exp16 (correlation coefficient (r) of 0.95, determination coefficient (R(2)) of 0.90~0.91, root mean squared error (RMSE) of 0.36~0.40 m(2) m(−2), relative root mean squared error (RRMSE) of 25~28%) and less accurate for Exp19 (r =0.80~0.83, R(2) = 0.63~0.69, RMSE of 0.84~0.86 m(2) m(−2), RRMSE of 30~31%). Additionally, RFR models correctly captured spatiotemporal variation of observed LAI as well as identified variations for different growing stages and treatments in terms of genotypes and management practices (i.e., planting density, irrigation, and fertilization) for two experiments. The developed hybrid method allows rapid, accurate, nondestructive phenotyping of the dynamics of LAI during vegetative growth to facilitate assessments of growth rate including in breeding program assessments.
format Online
Article
Text
id pubmed-9317541
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher AAAS
record_format MEDLINE/PubMed
spelling pubmed-93175412022-08-04 Unsupervised Plot-Scale LAI Phenotyping via UAV-Based Imaging, Modelling, and Machine Learning Chen, Qiaomin Zheng, Bangyou Chenu, Karine Hu, Pengcheng Chapman, Scott C. Plant Phenomics Research Article High-throughput phenotyping has become the frontier to accelerate breeding through linking genetics to crop growth estimation, which requires accurate estimation of leaf area index (LAI). This study developed a hybrid method to train the random forest regression (RFR) models with synthetic datasets generated by a radiative transfer model to estimate LAI from UAV-based multispectral images. The RFR models were evaluated on both (i) subsets from the synthetic datasets and (ii) observed data from two field experiments (i.e., Exp16, Exp19). Given the parameter ranges and soil reflectance are well calibrated in synthetic training data, RFR models can accurately predict LAI from canopy reflectance captured in field conditions, with systematic overestimation for LAI<2 due to background effect, which can be addressed by applying background correction on original reflectance map based on vegetation-background classification. Overall, RFR models achieved accurate LAI prediction from background-corrected reflectance for Exp16 (correlation coefficient (r) of 0.95, determination coefficient (R(2)) of 0.90~0.91, root mean squared error (RMSE) of 0.36~0.40 m(2) m(−2), relative root mean squared error (RRMSE) of 25~28%) and less accurate for Exp19 (r =0.80~0.83, R(2) = 0.63~0.69, RMSE of 0.84~0.86 m(2) m(−2), RRMSE of 30~31%). Additionally, RFR models correctly captured spatiotemporal variation of observed LAI as well as identified variations for different growing stages and treatments in terms of genotypes and management practices (i.e., planting density, irrigation, and fertilization) for two experiments. The developed hybrid method allows rapid, accurate, nondestructive phenotyping of the dynamics of LAI during vegetative growth to facilitate assessments of growth rate including in breeding program assessments. AAAS 2022-07-02 /pmc/articles/PMC9317541/ /pubmed/35935677 http://dx.doi.org/10.34133/2022/9768253 Text en Copyright © 2022 Qiaomin Chen et al. https://creativecommons.org/licenses/by/4.0/Exclusive Licensee Nanjing Agricultural University. Distributed under a Creative Commons Attribution License (CC BY 4.0).
spellingShingle Research Article
Chen, Qiaomin
Zheng, Bangyou
Chenu, Karine
Hu, Pengcheng
Chapman, Scott C.
Unsupervised Plot-Scale LAI Phenotyping via UAV-Based Imaging, Modelling, and Machine Learning
title Unsupervised Plot-Scale LAI Phenotyping via UAV-Based Imaging, Modelling, and Machine Learning
title_full Unsupervised Plot-Scale LAI Phenotyping via UAV-Based Imaging, Modelling, and Machine Learning
title_fullStr Unsupervised Plot-Scale LAI Phenotyping via UAV-Based Imaging, Modelling, and Machine Learning
title_full_unstemmed Unsupervised Plot-Scale LAI Phenotyping via UAV-Based Imaging, Modelling, and Machine Learning
title_short Unsupervised Plot-Scale LAI Phenotyping via UAV-Based Imaging, Modelling, and Machine Learning
title_sort unsupervised plot-scale lai phenotyping via uav-based imaging, modelling, and machine learning
topic Research Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9317541/
https://www.ncbi.nlm.nih.gov/pubmed/35935677
http://dx.doi.org/10.34133/2022/9768253
work_keys_str_mv AT chenqiaomin unsupervisedplotscalelaiphenotypingviauavbasedimagingmodellingandmachinelearning
AT zhengbangyou unsupervisedplotscalelaiphenotypingviauavbasedimagingmodellingandmachinelearning
AT chenukarine unsupervisedplotscalelaiphenotypingviauavbasedimagingmodellingandmachinelearning
AT hupengcheng unsupervisedplotscalelaiphenotypingviauavbasedimagingmodellingandmachinelearning
AT chapmanscottc unsupervisedplotscalelaiphenotypingviauavbasedimagingmodellingandmachinelearning