摘要
小麦条锈病是影响小麦产量的主要病害之一,提高小麦条锈病的遥感监测精度对病害的防控具有重要意义。本文在利用F-SFM算法反演全波段SIF光谱的基础上提取了形状特征,分析了条锈病胁迫下全波段SIF光谱及其形状特征的响应特性。基于随机森林算法构建了小麦条锈病的遥感监测模型,并将其与单波段SIF模型进行对比分析。结果表明:条锈病胁迫下,小麦叶片和冠层尺度SIF光谱曲线及其形状特征均有不同的响应特性。叶片尺度下,随着小麦条锈病严重度的增加,远红光波段SIF峰值(C_(FR))、偏度(SFR)以及发射峰面积(AFR)减小,红光和远红光波段SIF峰值波长(λ_(R)、λ_(FR))以及远红光波段峰度(K_(FR))增大。冠层尺度下,C_(FR)、λ_(R)、λ_(FR)、AFR随小麦条锈病严重度的增加而减小。此外,以AFR、λ_(FR)、全波段SIF峰度(K)、红光波段SIF偏度(S_(R))、λ_(R)形状特征为自变量的小麦条锈病遥感监测模型精度较以红光波段SIF峰值(CR)和C_(FR)为自变量的模型在训练集中精度(R^(2))提高27.59%,RMSE降低19.83%,测试集中R^(2)提高96.43%,RMSE降低17.01%。利用全波段SIF提取的形状特征能够更全面、更精准地反映病害胁迫信息。
Wheat stripe rust is one of the major diseases affecting wheat yield,and improving the remote sensing monitoring accuracy of wheat stripe rust is of great significance for disease prevention and control.Based on the inversion of full-band SIF spectra by using the F-SFM algorithm,shape characteristics were extracted,and the response characteristics of full-band SIF spectra and their shape characteristics under stripe rust stress were analyzed.A remote sensing monitoring model for wheat stripe rust was constructed by using the random forest algorithm,and compared with a single-band SIF model.The results showed that under stripe rust stress,both leaf and canopy-scale SIF spectral curves and their shape characteristics exhibited different response characteristics.At the leaf level,as the severity of wheat stripe rust increased,the peak value of far-red SIF(C_(FR)),skewness of far-red SIF(SFR),and area of emission peak of far-red SIF(AFR)was decreased,while the peak wavelengths of red(λ_(R))and far-red(λ_(FR))SIF,the kurtosis of far-red SIF(K_(FR))was increased.At the canopy level,C_(FR),λ_(R),λ_(FR),and AFR were decreased with the severity of wheat stripe rust.Additionally,the remote sensing monitoring model for wheat stripe rust constructed with shape features such as AFR,λ_(FR),full-band SIF kurtosis(K),skewness of redband SIF spectra(S_(R)),andλ_(R)as independent variables showed higher accuracy compared with the model with red-band SIF peak value(CR)and C_(FR)as independent variables,with an increase of 27.59%in R^(2)and a decrease of 19.83%in RMSE in the training set,and an increase of 96.43%in R^(2)and a decrease of 17.01%in RMSE in the testing set.The shape characteristics extracted using full-band SIF can more comprehensively and accurately reflect disease stress information.
作者
竞霞
叶启星
李冰玉
张震华
赵天昊
JING Xia;YE Qixing;LI Bingyu;ZHANG Zhenhua;ZHAO Tianhao(College of Geomatics Science and Technology,Xi'an University of Science and Technology,Xi'an 710054,China)
出处
《农业机械学报》
北大核心
2025年第6期468-476,共9页
Transactions of the Chinese Society for Agricultural Machinery
基金
国家自然科学基金项目(42171394)。
作者简介
竞霞(1978-),女,教授,主要从事农业定量遥感研究,E-mail:jingxia@xust.edu.cn。
