Spectroscopic detection of cotton Verticillium wilt by spectral feature selection and machine learning methods
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 cotton Verticillium wilt.
Authors
- Zhaoen Yang (ORCID: https://orcid.org/0000-0003-2323-4654)
- Longyu Huang
- Xiuliang Jin (ORCID: https://orcid.org/0000-0002-6769-214X)
- Lisen Liu (ORCID: https://orcid.org/0009-0004-9715-1522)
- Weiguang Yang (ORCID: https://orcid.org/0000-0002-9862-5839)
- Jianing Li (ORCID: https://orcid.org/0009-0006-2298-8074)
- Yubin Lan (ORCID: https://orcid.org/0000-0001-6664-5571)
- Jun Peng (ORCID: https://orcid.org/0000-0003-1802-7300)
- Weinan Li (ORCID: https://orcid.org/0009-0005-6923-5312)
- Yang Guo (ORCID: https://orcid.org/0009-0005-6622-8483)
Institutions
- South China Agricultural University (CN)
- Cotton Research Institute (CN)
- Hainan Provincial Academy of Agricultural Sciences (CN)
- Chinese Academy of Agricultural Sciences (CN)
- Sanya University (CN)
- Institute of Crop Sciences (CN)
Publication Details
- Journal
- Frontiers in Plant Science
- Published
- 2025-05-15
- DOI
- https://doi.org/10.3389/fpls.2025.1519001
- Citations
- 3
- Primary Topic
- Spectroscopy and Chemometric Analyses
- Type
- article
- Field-Weighted Citation Impact
- 2.26