文献类型： 外文期刊

作者： Wen, Tiantian ¹ ; Liu, Juan ² ; Fu, Yuanyuan ¹ ; Yue, Jibo ¹ ; Li, Yuheng ³ ; Guo, Wei ¹ ;

作者机构： 1.Henan Agr Univ, Coll Informat & Management Sci, Zhengzhou 450046, Peoples R China

2.Henan Acad Agr Sci, Peanut Res Inst, Zhengzhou 450002, Peoples R China

3.East China Normal Univ, Sch Math Sci, Shanghai 200241, Peoples R China

关键词： Agroathelia rolfsii Sacc; canopy hyperspectral reflectance; spectral index

期刊名称：HORTICULTURAE （ 影响因子：3.1； 五年影响因子：3.4 ）

ISSN：

年卷期： 2024 年 10 卷 2 期

页码：

收录情况： SCI

摘要： Peanut southern blight is a soil-borne fungal disease caused by Agroathelia rolfsii (syn. Sclerotium rolfsii) Sacc, which seriously affects peanut yield. The disease mainly affects the stem, pod, and root of the plant, and it is difficult to detect the disease by visual interpretation. Detecting peanut southern blight using existing technology is an urgent problem that needs to be solved. To address this issue, field experiments were conducted in September 2022 to determine whether hyperspectral techniques could be used to assess the severity of peanut southern blight. In this study, we obtained 610 canopy-scale spectral data through field experiments. Firstly, 18 traditional spectral features were calculated. Then, wavelengths of 544 nm, 678 nm, and 769 nm were selected as sensitive by the Relief-F algorithm, and the NDSISB and NSISB were constructed using normalization and ratio calculation methods. Finally, Support Vector Machine (SVM), Light Gradient Boosting Machine (LightGBM), Categorical Boosting (CatBoost), and ANN were used to evaluate the diagnostic ability of all spectral features to assess disease severity levels. The results showed that the NSISB had the highest association with peanut southern blight (R2 = 0.817), exceeding the other spectral features. Compared to the other three models, CatBoost demonstrated superior accuracy, with an overall accuracy (OA) and Kappa coefficient of 84.18% and 78.31%, respectively. The findings of this study can serve as a reference for estimating the severity levels of peanut southern blight using ground-based hyperspectral data.