基于谐波分析和高光谱遥感的土壤含水量反演研究

发布时间：2019-05-16 04:45

【摘要】：土壤含水量的高光谱反演是当今研究的热点。以土壤多样化的陕西省横山县为研究区,通过野外采集土壤样品,室内利用ASD Field Spec FR地物光谱仪测定土壤样品光谱,采用称重法计算出土壤样品含水量,并分析了不同含水量土壤样品的光谱特性。针对土壤含水量光谱反演中光谱反演因子的构建问题,在研究一阶微分(FD)-主成分分析(PCA)、小波包变换(WPT)-FD-PCA反演输入因子生成方法及存在的不足的基础上,提出了基于谐波分析(HA)的WPT-FD-HA-PCA的反演输入因子构建方法。以上述三种反演输入因子为基础,建立了土壤含水量反演的FD-PCA-反向传播(BP)、WPT-FD-PCA-BP、WPT-FD-HA-PCA-BP三种BP反演模型。通过比较土壤含水量实测值与三种反演输入因子的反演结果,得出WPT-FD-HA-PCA-BP模型的反演精度最高,决定性系数R2达到0.9599,均方根误差为1.667%,其反演结果明显优于其他两种模型。这表明通过WPT和谐波分析能有效地抑制光谱噪声并压缩信号,在一定程度上明显提高了土壤含水量反演精度。
[Abstract]:Hyperspectral inversion of soil water content is a hot research topic. Taking Hengshan County, Shaanxi Province, as the study area, the soil samples were collected in the field, the spectra of soil samples were measured by ASD Field Spec FR ground object spectrometer, and the water content of soil samples was calculated by weighing method. The spectral characteristics of soil samples with different water content were analyzed. In order to solve the problem of constructing spectral inversion factors in spectral inversion of soil water content, the generation method and shortcomings of (WPT)-FD-PCA inversion input factors by (PCA), wavelet packet transform for first-order differential (FD)-principal component analysis are studied. An inverse input factor construction method for WPT-FD-HA-PCA based on harmonic analysis (HA) is proposed. Based on the above three inversion input factors, three BP inversion models of FD-PCA- back propagation (BP), WPT-FD-PCA-BP,WPT-FD-HA-PCA-BP for soil water content inversion are established. By comparing the measured values of soil water content with the inversion results of three inversion input factors, it is concluded that the inversion accuracy of WPT-FD-HA-PCA-BP model is the highest, the decisive coefficient R2 is 0.9599, and the root mean square error is 1.667%. The inversion results are obviously better than those of the other two models. This shows that the spectral noise can be effectively suppressed and the signal compressed by WPT and harmonic analysis, and the inversion accuracy of soil water content is obviously improved to a certain extent.
【作者单位】：同济大学测绘与地理信息学院;山东农业大学信息科学与工程学院;
【基金】：上海市科委项目(13231203602)
【分类号】：S127;S152.7

【相似文献】