Combining 3D-multispectral and hyperspectral imaging to identify environmental stress treatments imposed during plant growth.
9 affiliations
- 1Division of Plant Sciences, Research School of Biology, The Australian National University, Australia.
- 2Australian Plant Phenomics Network, Research School of Biology, The Australian National University, Australia.
- 3School of Computing, The Australian National University, Australia.
- 4Medicago Inc., Québec, Canada.
- 5Direction Générale de la Recherche, des Programmes et des Partenariats, Ministère de l'Agriculture, des Pêcheries et de l'Alimentation du Québec, Québec, QC, Canada.
- 6Biological Data Science Institute, The Australian National University, Australia.
- 7Department of Biology, The University of Western Ontario, Canada.
- 8Nicholas School of the Environment, Duke University, USA.
- 9Agrifood Innovation Institute, The Australian National University, Australia.
Abstract
Non-invasive, high-throughput phenotyping tools are needed that can identify environmental effects on plant structure and function to diagnose factors responsible for reduced growth in commercial and non-commercial settings. In this study, we explored whether the integration of 3D-multispectral (3D) and 2D-hyperspectral imaging (HSI), aided by machine learning (ML), could be used to identify environmental stress treatments imposed during plant growth. Controlled environment-grown Nicotiana Benthamiana plants were subjected to a range of abiotic treatments - including different growth irradiances, heat treatment and drought stress - with the treatments resulting in differences in shoot height, biomass, leaf area and spectral reflectance. ML models were trained to identify these treatments using morphological and spectral traits measured at 27, 29, 31, and 34 days after sowing (DAS). A 3D-multispectral scanner was used to obtain information on plant height, biomass, and leaf area. A visible and near-infrared (VNIR) HSI camera provided detailed spectral information for deriving spectral indices including the Normalised Difference Vegetation Index (NDVI), Photochemical Reflectance Index (PRI) and Normalised Difference Red Edge (NDRE). Manual measurements provided baseline comparative data. The 3D-multispectral scanner reliably estimated above-ground traits, with high correlations between manual and scanner-derived measurements. The ML models accurately differentiated among environmental stress treatments, with the fused 3D + HSI model achieving the best overall predictive performance across all evaluated metrics compared with models based on either imaging modality alone. Results demonstrated the effectiveness of combining 3D-multispectral and 2D-HSI data with ML analyses for non-destructive, high-throughput phenotyping. The integration of these techniques enabled non-destructive, high-throughput identification of environmental stress treatments imposed during plant growth.
Related
- Fine-grained hierarchical crop type classification from integrated hyperspectral EnMAP data and multispectral sentinel-2 time series: A large-scale dataset and dual-stream transformer method
- Combining Gene Therapy with Current Modulator Treatments for Cystic Fibrosis: A Promising Area of Research
- Integrative genotype-environment association and single-cell transcriptomic analyses identify candidate mechanisms of environmental adaptation in pigs.
- Large-scale phenotyping and multi-trait selection identify low-methane Napier grass (Cenchrus purpureus) accessions under contrasting environmental conditions
- Multispectral image analysis approach to detect adulteration of beef and pork in raw meats
BibTeX
@article{stock2026combining,
title = {{Combining 3D-multispectral and hyperspectral imaging to identify environmental stress treatments imposed during plant growth.}},
author = {Frederike Stock and Saswat Panda and Richard Poiré and Timothy Brown and Ayesha Akram and Liang Zheng and Huan Lei and Ruyi Zha and Mingrui Zhao and Sébastien Isabelle and Michèle Martel and Marc-André Comeau and Louis-Philippe Hamel and Pierre-Olivier Lavoie and Marc André D'Aoust and Hannah Reithinger and Pooja Saxena and Eric A Stone and Hongdong Li and Danielle A Way and Owen K Atkin},
journal = {Plant phenomics (Washington, D.C.)},
year = {2026},
month = oct,
doi = {10.1016/j.plaphe.2026.100291},
url = {https://europepmc.org/article/MED/42999917},
note = {CC BY-NC-ND},
}
RIS
TY - JOUR
TI - Combining 3D-multispectral and hyperspectral imaging to identify environmental stress treatments imposed during plant growth.
AU - Frederike Stock
AU - Saswat Panda
AU - Richard Poiré
AU - Timothy Brown
AU - Ayesha Akram
AU - Liang Zheng
AU - Huan Lei
AU - Ruyi Zha
AU - Mingrui Zhao
AU - Sébastien Isabelle
AU - Michèle Martel
AU - Marc-André Comeau
AU - Louis-Philippe Hamel
AU - Pierre-Olivier Lavoie
AU - Marc André D'Aoust
AU - Hannah Reithinger
AU - Pooja Saxena
AU - Eric A Stone
AU - Hongdong Li
AU - Danielle A Way
AU - Owen K Atkin
PY - 2026
DA - 2026/10/15
JO - Plant phenomics (Washington, D.C.)
DO - 10.1016/j.plaphe.2026.100291
UR - https://europepmc.org/article/MED/42999917
AB - Non-invasive, high-throughput phenotyping tools are needed that can identify environmental effects on plant structure and function to diagnose factors responsible for reduced growth in commercial and non-commercial settings. In this study, we explored whether the integration of 3D-multispectral (3D) and 2D-hyperspectral imaging (HSI), aided by machine learning (ML), could be used to identify environmental stress treatments imposed during plant growth. Controlled environment-grown Nicotiana Benthamiana plants were subjected to a range of abiotic treatments - including different growth irradiances, heat treatment and drought stress - with the treatments resulting in differences in shoot height, biomass, leaf area and spectral reflectance. ML models were trained to identify these treatments using morphological and spectral traits measured at 27, 29, 31, and 34 days after sowing (DAS). A 3D-multispectral scanner was used to obtain information on plant height, biomass, and leaf area. A visible and near-infrared (VNIR) HSI camera provided detailed spectral information for deriving spectral indices including the Normalised Difference Vegetation Index (NDVI), Photochemical Reflectance Index (PRI) and Normalised Difference Red Edge (NDRE). Manual measurements provided baseline comparative data. The 3D-multispectral scanner reliably estimated above-ground traits, with high correlations between manual and scanner-derived measurements. The ML models accurately differentiated among environmental stress treatments, with the fused 3D + HSI model achieving the best overall predictive performance across all evaluated metrics compared with models based on either imaging modality alone. Results demonstrated the effectiveness of combining 3D-multispectral and 2D-HSI data with ML analyses for non-destructive, high-throughput phenotyping. The integration of these techniques enabled non-destructive, high-throughput identification of environmental stress treatments imposed during plant growth.
SN - 2643-6515
ER -