Cargando…
A leaf-level spectral library to support high-throughput plant phenotyping: predictive accuracy and model transfer
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...
Autores principales: | , , , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Oxford University Press
2023
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10400152/ https://www.ncbi.nlm.nih.gov/pubmed/37018460 http://dx.doi.org/10.1093/jxb/erad129 |
_version_ | 1785084402722668544 |
---|---|
author | Wijewardane, Nuwan K Zhang, Huichun Yang, Jinliang Schnable, James C Schachtman, Daniel P Ge, Yufeng |
author_facet | Wijewardane, Nuwan K Zhang, Huichun Yang, Jinliang Schnable, James C Schachtman, Daniel P Ge, Yufeng |
author_sort | Wijewardane, Nuwan K |
collection | PubMed |
description | 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 R(2)=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 R(2)=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 R(2)=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. |
format | Online Article Text |
id | pubmed-10400152 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2023 |
publisher | Oxford University Press |
record_format | MEDLINE/PubMed |
spelling | pubmed-104001522023-08-04 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 J Exp Bot Research Papers 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 R(2)=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 R(2)=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 R(2)=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. Oxford University Press 2023-04-05 /pmc/articles/PMC10400152/ /pubmed/37018460 http://dx.doi.org/10.1093/jxb/erad129 Text en © The Author(s) 2023. Published by Oxford University Press on behalf of the Society for Experimental Biology. https://creativecommons.org/licenses/by/4.0/This is an Open Access article distributed under the terms of the Creative Commons Attribution License (https://creativecommons.org/licenses/by/4.0/), which permits unrestricted reuse, distribution, and reproduction in any medium, provided the original work is properly cited. |
spellingShingle | Research Papers Wijewardane, Nuwan K Zhang, Huichun Yang, Jinliang Schnable, James C Schachtman, Daniel P Ge, Yufeng A leaf-level spectral library to support high-throughput plant phenotyping: predictive accuracy and model transfer |
title | A leaf-level spectral library to support high-throughput plant phenotyping: predictive accuracy and model transfer |
title_full | A leaf-level spectral library to support high-throughput plant phenotyping: predictive accuracy and model transfer |
title_fullStr | A leaf-level spectral library to support high-throughput plant phenotyping: predictive accuracy and model transfer |
title_full_unstemmed | A leaf-level spectral library to support high-throughput plant phenotyping: predictive accuracy and model transfer |
title_short | A leaf-level spectral library to support high-throughput plant phenotyping: predictive accuracy and model transfer |
title_sort | leaf-level spectral library to support high-throughput plant phenotyping: predictive accuracy and model transfer |
topic | Research Papers |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10400152/ https://www.ncbi.nlm.nih.gov/pubmed/37018460 http://dx.doi.org/10.1093/jxb/erad129 |
work_keys_str_mv | AT wijewardanenuwank aleaflevelspectrallibrarytosupporthighthroughputplantphenotypingpredictiveaccuracyandmodeltransfer AT zhanghuichun aleaflevelspectrallibrarytosupporthighthroughputplantphenotypingpredictiveaccuracyandmodeltransfer AT yangjinliang aleaflevelspectrallibrarytosupporthighthroughputplantphenotypingpredictiveaccuracyandmodeltransfer AT schnablejamesc aleaflevelspectrallibrarytosupporthighthroughputplantphenotypingpredictiveaccuracyandmodeltransfer AT schachtmandanielp aleaflevelspectrallibrarytosupporthighthroughputplantphenotypingpredictiveaccuracyandmodeltransfer AT geyufeng aleaflevelspectrallibrarytosupporthighthroughputplantphenotypingpredictiveaccuracyandmodeltransfer AT wijewardanenuwank leaflevelspectrallibrarytosupporthighthroughputplantphenotypingpredictiveaccuracyandmodeltransfer AT zhanghuichun leaflevelspectrallibrarytosupporthighthroughputplantphenotypingpredictiveaccuracyandmodeltransfer AT yangjinliang leaflevelspectrallibrarytosupporthighthroughputplantphenotypingpredictiveaccuracyandmodeltransfer AT schnablejamesc leaflevelspectrallibrarytosupporthighthroughputplantphenotypingpredictiveaccuracyandmodeltransfer AT schachtmandanielp leaflevelspectrallibrarytosupporthighthroughputplantphenotypingpredictiveaccuracyandmodeltransfer AT geyufeng leaflevelspectrallibrarytosupporthighthroughputplantphenotypingpredictiveaccuracyandmodeltransfer |