| 摘要: |
| 【目的】提出植被指数非相似性的计算方法以及利用植被指数非相似性监测水稻病虫害的方法研究【方法】首先将具有空间特性的植被指数影像假设成了具有概率统计特性的信息量,并基于信息理论和SID模型推导出两个不同区域相同大小影像的植被指数非相似性(VID)计算方法；然后根据VID计算方法,计算出无水稻病虫害的参考区域与有水稻病虫害的试验区域的10种植被指数的VID；之后利用计算出的10种植被指数的VID与实测水稻病虫害等级数据进行回归分析,判断VID与水稻病虫害等级数据的相关性；最后选择相关程度较高的几种植被指数VID进行K-fold交叉验证,判断植被指数非相似性监测水稻病虫害的精度。【结果】10种植被指数的VID与地面实测水稻病虫害等级数据进行回归分析后,R2的范围在0.63~0.95之间。三种相关程度较高的植被指数的VID与地面实测水稻病虫害等级数据进行交叉验证后, R2的范围在0.91~0.97之间,RMSE在0.16~0.24之间,广义监测精度在97.62%~100%之间。【结论】植被指数非相似性与水稻病虫害等级数据具有较强的相关性,利用三种相关程度较高的植被指数VID监测水稻病虫害等级具有很高的精度。 |
| 关键词: 遥感 Planet卫星数据 植被指数非相似性 水稻病虫害 回归分析 K-fold交叉验证 |
| DOI： |
| 分类号: |
| 基金项目:中国农业科学院基本科研专项——天空地大数据驱动的水稻病虫害智能诊断预警系统(Y2019XK24-02) |
|
| Detection and Discrimination of Pests and Diseases in Rice Using Vegetation Index Divergence |
|
Lifugen
|
|
The Institute of Agricultural Resources and Regional Planning (IARRP) of Chinese Academy of Agricultural Sciences (CAAS)
|
| Abstract: |
| [Purpose] Proposed the method of the calculation of vegetation index divergence; and study on detection and discrimination of pests and diseases in rice using vegetation index divergence [Method] Firstly, the vegetation index calculated by satellite image with spatial characteristics is supposed to be the information with probability statistical characteristics, and based on the information-theory and Spectral Information Divergence model, the method of calculation of vegetation index divergence (VID) between the same size images in two different regions is proposed; and then, according to the method of VID calculation, the VID of 10 vegetation indexes between the reference area without rice diseases and test area with pests and diseases in rice are calculated; next, the VID of 10 vegetation indexes against the measured data of pests and diseases in rice are used for regression analysis to research the correlation between the VID and measured data; finally, the VID of several vegetation indexes in high correlation with measured data were selected for K-fold cross validation to research the accuracy of detection and discrimination of pests and diseases in rice using vegetation index divergence. [Result] The result sof regression analysis between the VID of 10 vegetation indexes and the measured data of pests and diseases in rice produced the R2 ranging from 0.63 to 0.95; and results of K-fold cross validation between the VID of three vegetation indexes with goodness correlation and measured data produced the R2 ranging from 0.91 to 0.97, RMSE ranging from 0.16 to 0.24, and the general detection accuracy ranging from 97.62% to 100%. [Conclusion] There is a strong correlation between the vegetation index divergence and the measured data of pests and diseases in rice. Using the VID of three vegetation indexes with goodness correlation to detection and discrimination of pests and diseases in rice will be in high accuracy. |
| Key words: remote sensing PlanetScope vegetation index divergence pests and diseases in rice regression analysis K-fold cross validation |