Investigation of Using Hyperspectral Vegetation Indices to Assess Brassica Downy Mildew.

Abstract

Downy mildew caused by Hyaloperonospora brassicae is a severe disease in Brassica oleracea that significantly reduces crop yield and marketability. This study aims to evaluate different vegetation indices to assess different downy mildew infection levels in the Brassica variety Mildis using hyperspectral data. Artificial inoculation using H. brassicae sporangia suspension was conducted to induce different levels of downy mildew disease. Spectral measurements, spanning 350 nm to 1050 nm, were conducted on the leaves using an environmentally controlled setup, and the reflectance data were acquired and processed. The Successive Projections Algorithm (SPA) and signal sensitivity calculation were used to extract the most informative wavelengths that could be used to develop downy mildew indices (DMI). A total of 37 existing vegetation indices and three proposed DMIs were evaluated to indicate downy mildew (DM) infection levels. The results showed that the classification using a support vector machine achieved accuracies of 71.3%, 80.7%, and 85.3% for distinguishing healthy leaves from DM1 (early infection), DM2 (progressed infection), and DM3 (severe infection) leaves using the proposed downy mildew index. The proposed new downy mildew index potentially enables the development of an automated DM monitoring system and resistance profiling in Brassica breeding lines.

Plant phenotyping relevance

ハイパースペクトル反射データからアブラナ科植物のべと病感染レベルを推定する指標を開発・評価しており、病害表現型の取得・抽出手法が研究の中心である。

Code and data availability

The paper's hyperspectral reflectance dataset (400 spectra from healthy and downy mildew-infected Brassica leaves) and MATLAB analysis are paper-specific phenotyping assets, but the authors state the raw data will only be made available upon request, with no public URL or deposit provided.

No evidence-backed public reproduction asset is currently recorded.