Spectroscopic detection of cotton Verticillium wilt by spectral feature selection and machine learning methods

Weinan Li^1,2*Lisen Liu³Jianing Li³Weiguang Yang¹Yang Guo¹Longyu Huang²Zhaoen Yang³Jun Peng²Xiuliang Jin⁴Yubin Lan¹

• ¹College of Electronic Engineering, South China Agricultural University, Guangzhou, China
• ²Chinese Academy of Agricultural Sciences (CAAS), Beijing, Beijing Municipality, China
• ³Institute of Cotton Research, Chinese Academy of Agricultural Sciences, Anyang, Henan Province, China
• ⁴Institute of Crop Sciences, Chinese Academy of Agricultural Sciences, Beijing, China

Verticillium wilt is a severe soil-borne disease that affects cotton growth and yield. Traditional monitoring methods, which rely on manual investigation, are inefficient and impractical for large-scale applications. This study introduces a novel approach combining machine learning with feature selection to identify sensitive spectral features for accurate and efficient detection of cotton Verticillium wilt. We conducted comprehensive hyperspectral measurements using handheld devices (350–2500 nm) to analyze cotton leaves in a controlled greenhouse environment and employed Unmanned Aerial Vehicle (UAV) hyperspectral imaging (400–995 nm) to capture canopy-level data in field conditions. The hyperspectral data were pre-processed to extract wavelet coefficients and spectral indices (SI), enabling the derivation of disease-specific spectral features (DSSFs) through advanced feature selection techniques. Using these DSSFs, we developed detection models to assess both the incidence and severity of leaf damage by Verticillium wilt at the leaf scale and the incidence at the canopy scale. Initial analysis identified critical spectral reflectance bands, wavelet coefficients, and SI that exhibited dynamic responses as the disease progressed. Model validation demonstrated that the incidence detection models at the leaf scale achieved a peak classification accuracy of 85.83%, which is about 10% higher than traditional methods without feature selection. The severity detection models showed improved precision as disease severity of damage increased, with accuracy ranging from 46.82% to 93.10%. At the canopy scale, UAV-based hyperspectral data achieved a remarkable classification accuracy of 93.0% for disease incidence detection. This study highlights the significant impact of feature selection on enhancing the performance of hyperspectral-based remote sensing models for cotton wilt monitoring. It also explores the transferability of sensitive spectral features across different scales, laying the groundwork for future large-scale early warning systems and monitoring of cotton Verticillium wilt.