Hyperspectral Imaging for Early Detection and Severity Grading of Potato Bacterial Wilt.

Abstract

Potato ( Solanum tuberosum ) is a vital global non-cereal food crop severely threatened by bacterial wilt, caused by Ralstonia solanacearum ( R . solanacearum ). Conventional diagnostics like PCR and ELISA, though effective, are destructive and time-consuming, limiting large-scale field applications. This study investigates hyperspectral imaging (HSI) as a non-invasive, rapid, and accurate alternative for early detection and severity grading of potato bacterial wilt. Using a portable HSI system (400-1000 nm), spectral data were collected from inoculated potato plants ('Longshu No. 7') at 0, 24, 48, and 72 h post-inoculation, alongside disease severity assessment (grades 0-4). After comprehensive spectral preprocessing and feature band extraction via Competitivse Adaptive Reweighted Sampling (CARS), we developed two distinct sets of models: one for early detection (temporal classification) using Partial Least Squares-Discriminant Analysis (PLS-DA) and Principal Component Analysis-Linear Discriminant Analysis (PCA-LDA), and another for severity grading. The SNV + SG + MC + PLS-DA model achieved exceptional accuracy, exceeding 97% for early detection, while the MSC + SG + MC + CARS + PLS-DA model yielded >97% accuracy for severity grading. These results were supported by low misclassification rates in confusion matrices. This work establishes a robust HSI-based framework for high-throughput screening of resistant potato germplasm and advances precision agriculture strategies for bacterial wilt management.

Code and data availability

The paper's hyperspectral phenotyping data and analysis code are not publicly available; the Data Availability Statement states data are available only on request from the corresponding author. No public repository, code, or dataset URLs are provided.

No evidence-backed public reproduction asset is currently recorded.