Affordable Access

Access to the full text

A combined approach for early in-field detection of beech leaf disease using near-infrared spectroscopy and machine learning

Authors
  • Fearer, Carrie J.1
  • Conrad, Anna O.2
  • Marra, Robert E.3
  • Georskey, Caroline4
  • Villari, Caterina5
  • Slot, Jason1
  • Bonello, Pierluigi1
  • 1 Department of Plant Pathology, The Ohio State University, Columbus, OH , (United States)
  • 2 USDA Forest Service, Northern Research Station, Hardwood Tree Improvement and Regeneration Center, West Lafayette, IN , (United States)
  • 3 Department of Plant Pathology and Ecology, The Connecticut Agricultural Experiment Station, New Haven, CT , (United States)
  • 4 Arabidopsis Biological Resource Center, The Ohio State University, Columbus, OH , (United States)
  • 5 D.B. Warnell School of Forestry & Natural Resources, University of Georgia, Athens, GA , (United States)
Type
Published Article
Journal
Frontiers in Forests and Global Change
Publisher
Frontiers Media S.A.
Publication Date
Jul 22, 2022
Volume
5
Identifiers
DOI: 10.3389/ffgc.2022.934545
Source
Frontiers
Keywords
Disciplines
  • Forests and Global Change
  • Original Research
License
Green

Abstract

The ability to detect diseased trees before symptoms emerge is key in forest health management because it allows for more timely and targeted intervention. The objective of this study was to develop an in-field approach for early and rapid detection of beech leaf disease (BLD), an emerging disease of American beech trees, based on supervised classification models of leaf near-infrared (NIR) spectral profiles. To validate the effectiveness of the method we also utilized a qPCR-based protocol for the quantification of the newly identified foliar nematode identified as the putative causal agent of BLD, Litylenchus crenatae ssp. mccannii (LCM). NIR spectra were collected in May, July, and September of 2021 and analyzed using support vector machine and random forest algorithms. For the May and July datasets, the models accurately predicted pre-symptomatic leaves (highest testing accuracy = 100%), but also accurately discriminated the spectra based on geographic location (highest testing accuracy = 90%). Therefore, we could not conclude that spectral differences were due to pathogen presence alone. However, the September dataset removed location as a factor and the models accurately discriminated pre-symptomatic from naïve samples (highest testing accuracy = 95.9%). Five spectral bands (2,220, 2,400, 2,346, 1,750, and 1,424 nm), selected using variable selection models, were shared across all models, indicating consistency with respect to phytochemical induction by LCM infection of pre-symptomatic leaves. Our results demonstrate that this technique holds high promise as an in-field diagnostic tool for BLD.

Report this publication

Statistics

Seen <100 times