Foliar infrared spectra track nematode density and symptom-specific phytobiome signatures in beech leaf disease

Source
DataCite
Published
2026
License
Creative Commons Zero v1.0 Universal
Themes
Forests, Plants & Vegetation, Machine Learning & AI

Get the data from DataCite

About this dataset

Beech leaf disease (BLD), caused by the foliar nematode Litylenchus crenatae ssp. mccannii (LCM) is an emerging threat to American beech (Fagus grandifolia) across eastern North America. In this study, near-infrared (NIR) spectroscopy was integrated with microbiome sequencing and machine learning approaches to evaluate whether host spectral signatures can predict pathogen abundance and associated phytobiome composition. Spectral profiles were analyzed using multivariate statistical approaches and predictive models, including random forest, support vector machines, elastic net regression, and partial least squares regression. NIR spectra accurately predicted nematode abundance and reconstructed major gradients of bacterial community differentiation derived from 16S rRNA gene sequencing, with nonlinear models exhibiting the highest predictive performance. These results indicate that...

How the data was collected

NIR spectra accurately predicted nematode abundance and reconstructed major gradients of bacterial community differentiation derived from 16S rRNA gene sequencing, with nonlinear models exhibiting the highest predictive performance.

Browse sustainability datasets on SusanHub