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

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.

Physiological impacts of beech leaf disease across a gradient of symptom severity among understory American beech

“…The degree of separation in the SLA data is such that there is no overlap between the three symptom categories, while the variation within categories can likely be attributed to the degree of internal damage induced by parasitic nematode feeding. A study which evaluated the spectral properties of American beech leaves identified near-infrared bands that can be used to discriminate BLD symptom types and that symptom severity was associated with Lcm populations verified through both molecular techniques (qPCR) and counting ex situ nematodes (Fearer et al, 2022a). Measurements of SLA coupled with a direct estimate of Lcm populations within a leaf could be investigated to further explore this relationship.…”

“…Crinkled leaves are diminutive with a darkened green color throughout and often exhibit areas if chlorotic and/or necrotic tissue. While BLD symptoms do occur on a natural continuous gradient, the banded and crinkled distinction is readily identifiable in the field and can be an indicator of disease severity that corresponds to nematode populations within the leaf (Fearer et al, 2022a).…”

Field Resistance of American Sycamore ‘Davis’ to Canker Pathogens

“…absorbance/reflectance signals via statistical or machine learning-based classification (Conrad et al 2014;Villari et al 2018;Mukrimin et al 2019;Conrad et al 2020;Fearer et al 2022). Such markers could be exploited to fast-forward breeding programs aiming at incorporating canker and dieback disease resistance into sycamore trees.…”

First report of Paraphaeosphaeria angularis as endophyte in sugarcane (Saccharum officinarum) from India

“…Further, the genus Paraphaeosphaeria includes plant pathogens, biocontrol agents and endophytic fungi (Baroncelli et al 2020). Along with some bacterial species, fungal species in the genus Paraphaeosphaeria is known to be either involved in or associated with beech leaf disease (Ewing et al 2021, Fearer et al 2022. Also, endophytic Paraphaesphaeria sporulosa isolated from Paepalanthus planifolius produced novel isoquinoline alkaloid (de Amorim et al 2022).…”