Early detection of soybean mosaic virus using portable Raman spectroscopy coupled with machine learning.

Abstract

Introduction Soybean mosaic virus (SMV) is one of the major pathogens affecting global soybean yield and quality, and its early and accurate detection is essential for disease warning and precision management. This study proposes a non-invasive early detection method by integrating portable Raman spectroscopy with artificial intelligence algorithms. Methods Raman spectra of leaves from both resistant and susceptible soybean cultivars were collected at different infection stages (0, 2, 4, and 6 days post-inoculation), and preprocessed using Savitzky-Golay (S-G) smoothing and adaptive iteratively reweighted penalized least squares (Air-PLS) baseline correction. Four classification models-1D-CNN, SVM, KNN, and BP-ANN-were developed to classify samples from different infection stages. Results Spectral feature analysis revealed significant changes in carotenoid levels caused by viral infection, and distinct spectral responses between resistant and susceptible cultivars during disease progression. Among the four classification models, the 1D-CNN model achieved the highest prediction accuracy of 90%. In addition, principal component analysis (PCA) indicated that the Raman spectroscopy-based method significantly advanced the early detection of SMV (SC3) to 4 days post-inoculation, compared to 7-10 days required by conventional methods. Discussion This evidences the superior capability of Raman spectroscopy for monitoring the dynamics of SMV infection and its potential to considerably reduce the duration of diagnosis. This study confirms the feasibility and efficiency of Raman spectroscopy combined with deep learning for in situ early detection of plant viral diseases and provides a promising reference for non-destructive diagnosis of early-stage foliar infections.

Plant phenotyping relevance

携帯型ラマン分光と機械学習を統合し、感染葉の病態を非破壊・早期検出する方法を開発および評価しており、植物病害状態の表現型取得が中心である。

Code and data availability

The supplied article blocks describe Raman spectral data collection (2,400 samples) and 1D-CNN/SVM/KNN/BP-ANN models, but contain no data availability statement, repository deposit, or public URL for the spectral dataset, code, or trained models. No paper-specific public asset is evidenced.

No evidence-backed public reproduction asset is currently recorded.