TY - JOUR

T1 - Towards automated detection of hyperhydricity in plant in vitro culture

AU - Bethge, Hans

AU - Mohammadi Nakhjiri, Zahra

AU - Rath, Thomas

AU - Winkelmann, Traud

N1 - Funding Information: We thank the technical assistants Ewa Schneider and Bärbel Ernst of the department of Woody Plant and Propagation Physiology, Institute of Horticultural Production Systems, Leibniz Universität Hannover for their excellent support in the lab. Furthermore, we thank Matthias Igelbrink and Prof. Dr. Arno Ruckelshausen at University of Applied Science Osnabrück in their support in recording the SWIR-HSI data. In addition, we are grateful for the scholarship for the completion of a dissertation of the University of Applied Science Osnabrück. Open Access funding enabled and organized by Projekt DEAL. This project took place within the research project “Experimentierfeld Agro-Nordwest”, which is funded by the Federal Ministry of Food and Agriculture (BMEL, Grant No.: 28DE103F18) via the Federal Agency for Agriculture and Food (BLE).

PY - 2023/9

Y1 - 2023/9

N2 - Hyperhydricity (HH) is one of the most important physiological disorders that negatively affects various plant tissue culture techniques. The objective of this study was to characterize optical features to allow an automated detection of HH. For this purpose, HH was induced in two plant species, apple and Arabidopsis thaliana, and the severity was quantified based on visual scoring and determination of apoplastic liquid volume. The comparison between the HH score and the apoplastic liquid volume revealed a significant correlation, but different response dynamics. Corresponding leaf reflectance spectra were collected and different approaches of spectral analyses were evaluated for their ability to identify HH-specific wavelengths. Statistical analysis of raw spectra showed significantly lower reflection of hyperhydric leaves in the VIS, NIR and SWIR region. Application of the continuum removal hull method to raw spectra identified HH-specific absorption features over time and major absorption peaks at 980 nm, 1150 nm, 1400 nm, 1520 nm, 1780 nm and 1930 nm for the various conducted experiments. Machine learning (ML) model spot checking specified the support vector machine to be most suited for classification of hyperhydric explants, with a test accuracy of 85% outperforming traditional classification via vegetation index with 63% test accuracy and the other ML models tested. Investigations on the predictor importance revealed 1950 nm, 1445 nm in SWIR region and 415 nm in the VIS region to be most important for classification. The validity of the developed spectral classifier was tested on an available hyperspectral image acquisition in the SWIR-region.

AB - Hyperhydricity (HH) is one of the most important physiological disorders that negatively affects various plant tissue culture techniques. The objective of this study was to characterize optical features to allow an automated detection of HH. For this purpose, HH was induced in two plant species, apple and Arabidopsis thaliana, and the severity was quantified based on visual scoring and determination of apoplastic liquid volume. The comparison between the HH score and the apoplastic liquid volume revealed a significant correlation, but different response dynamics. Corresponding leaf reflectance spectra were collected and different approaches of spectral analyses were evaluated for their ability to identify HH-specific wavelengths. Statistical analysis of raw spectra showed significantly lower reflection of hyperhydric leaves in the VIS, NIR and SWIR region. Application of the continuum removal hull method to raw spectra identified HH-specific absorption features over time and major absorption peaks at 980 nm, 1150 nm, 1400 nm, 1520 nm, 1780 nm and 1930 nm for the various conducted experiments. Machine learning (ML) model spot checking specified the support vector machine to be most suited for classification of hyperhydric explants, with a test accuracy of 85% outperforming traditional classification via vegetation index with 63% test accuracy and the other ML models tested. Investigations on the predictor importance revealed 1950 nm, 1445 nm in SWIR region and 415 nm in the VIS region to be most important for classification. The validity of the developed spectral classifier was tested on an available hyperspectral image acquisition in the SWIR-region.

KW - Automated object detection

KW - Hyperhydricity

KW - Machine learning

KW - Phenotyping

KW - Spectral analysis

UR - http://www.scopus.com/inward/record.url?scp=85161359903&partnerID=8YFLogxK

U2 - 10.1007/s11240-023-02528-0

DO - 10.1007/s11240-023-02528-0

M3 - Article

AN - SCOPUS:85161359903

VL - 154

SP - 551

EP - 573

JO - Plant Cell, Tissue and Organ Culture

JF - Plant Cell, Tissue and Organ Culture

SN - 0167-6857

IS - 3

ER -