Feature Selection and Spectral Indices for Identifying Maize Stress Types
Applied Spectroscopy · 2025-02 · 79 (2) · 306-319
DOI: 10.1177/00037028241279328 ↗Kurz gefasst
Fachartikel in der Zeitschrift Applied Spectroscopy, online erschienen am 23.09.2024. Verfasst von Yanru Li und 2 weiteren Autor:innen. Beteiligte Einrichtung: College of Geoscience and Surveying Engineering, China University of Mining and Technology, Beijing, China. Hauptthemen laut MEDLINE: Zea mays, Stress, Physiological, Plant Leaves, Spectrum Analysis. Die Arbeit wurde bisher 8-mal zitiert (Crossref) und nennt 45 Literaturangaben. Gefördert von: Basic Scientific Research Funds of China University of Mining and Technology (Beijing) - Top Innovative Talents Cultivation Fund for Doctoral Postgraduates, Science & Technology Fundamental Resources Investigation Program, Research Project of Huaibei Mining Co., Ltd..
Abstract (Originalsprache)
This study aims to identify different types of stress on maize leaves using feature selection and spectral index methods. Spectral data were collected from leaves under heavy metal, water, fertilizer stress, as well as under normal healthy conditions. Preprocessing steps such as continuum removal (CR), standard normal variable (SNV) transformation, multiple scattering correction (MSC), detrend correction (DT), and first-order derivative (FOD) were applied to the raw spectra. Various feature selection methods including ReliefF, chi-square test, recursive feature elimination (FRE), mutual information (MI), random forest (RF), and gradient boosting tree (GBT) were employed to determine the importance scores of different spectral bands, thus identifying sensitive spectral features capable of distinguishing various stress types. Spectral indices for stress type differentiation were constructed using label correlation method. Classification models were built using support vector machine (SVM), K-nearest neighbors (KNN), Gaussian naive Bayes (GNB), extreme gradient boosting (XGBoost), RF, and adaptive boosting (AdaBoost) algorithms. Results indicate that the characteristic spectral bands for differentiating stress types are primarily distributed around the red edge (near 700–800 nm) and water absorption valley (near 1900 nm). Spectral indices constructed using combinations of spectral bands around the near-infrared plateau absorption valley (near 1185 nm) and water absorption valley (near 1460 nm) effectively differentiate maize stress types. Among the modeling classification algorithms, RF and AdaBoost algorithms exhibited optimal performance, demonstrating high classification accuracy on both training and validation sets. These findings hold promise for providing new technical support for maize stress monitoring and diagnosis in agricultural production.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- College of Geoscience and Surveying Engineering, China University of Mining and Technology, Beijing, China.
ORCID-Profile: Yanru Li
Förderung
- Basic Scientific Research Funds of China University of Mining and Technology (Beijing) - Top Innovative Talents Cultivation Fund for Doctoral Postgraduates
- Science & Technology Fundamental Resources Investigation Program
- Research Project of Huaibei Mining Co., Ltd.
Zitieren
APA
Li, Y., Yang, K., & Wu, B. (2025). Feature Selection and Spectral Indices for Identifying Maize Stress Types. Applied Spectroscopy, 79(2), 306-319. https://doi.org/10.1177/00037028241279328
Vancouver
Li Y, Yang K, Wu B. Feature Selection and Spectral Indices for Identifying Maize Stress Types. Applied Spectroscopy. 2025;79(2):306-319. doi:10.1177/00037028241279328
BibTeX
@article{Li2025,
author = {Li, Yanru and Yang, Keming and Wu, Bing},
title = {Feature Selection and Spectral Indices for Identifying Maize Stress Types},
journal = {Applied Spectroscopy},
year = {2025},
volume = {79},
number = {2},
pages = {306--319},
doi = {10.1177/00037028241279328}
}
EUVIMED