| 基于光谱FOD与优化指数的银川平原土壤有机质含量反演 |
| |
| 引用本文： | 张俊华,尚天浩,陈睿华,王怡婧,丁启东,李小林.基于光谱FOD与优化指数的银川平原土壤有机质含量反演[J].农业机械学报,2022,53(11):379-387. |
| |
| 作者姓名： | 张俊华 尚天浩 陈睿华 王怡婧 丁启东 李小林 |
| |
| 作者单位： | 宁夏大学;西安煤航遥感信息有限公司 |
| |
| 基金项目： | 国家重点研发计划项目（2021YFD1900602）、国家自然科学基金项目（42067003）和清华大学-宁夏银川水联网数字治水联合研究院联合开放基金项目（SKLHSE-2022-LOW11） |
| |
| 摘 要： | 土壤有机质（SOM）是土壤肥力的重要组成部分，是作物生长的主要养分来源。为探究分数阶微分（FOD）联合优化光谱指数对低肥力地区SOM的反演效果，以银川平原为研究对象，对野外土壤高光谱反射率原始数据进行0~2阶FOD处理（间隔0.2阶），构建优化光谱指数DI/RDI、DI/NDI、NDI/RDI、RDI/NDI、DI/GDI和RI/GDI，分析各指数与土壤有机质含量间的二维相关性，筛选出最佳优化光谱指数，并建立基于支持向量机（SVM）的SOM含量反演模型。结果表明：银川平原SOM含量整体偏低，其中93.05%处于四级到六级水平。土壤野外原始光谱反射率吸收特征差异明显，在1400、1900nm处有明显吸收峰。随着分数阶的不断增加，光谱反射率不断趋近于0。土壤DI/NDI、DI/GDI、RI/GDI、NDI/RDI和RDI/NDI在0~2阶最大相关系数绝对值（MACC）均小于0.80，DI/RDI在0.2~2.0阶范围内的MACC为0.9965~0.9986，其敏感波段主要集中在1450~1750nm和2100~2400nm之间。基于0.2阶微分处理的DI/RDI-SVM模型对SOM的反演精度最佳，建模决定系数R2c和验证决定系数R2p分别为0.98和0.99，相对分析误差（RPD）为4.31。研究结果可为低肥力地区的SOM含量快速、准确反演及制图提供科学依据。
|
| 关 键 词： | 低含量有机质 光谱特征 分数阶微分 支持向量机 反演 克里格插值 |
| 收稿时间： | 2022/7/15 0:00:00 |
Inversion of Soil Organic Matter Content in Yinchuan Plain Using Field Spectral Fractional-order Derivatives Combined with Spectral Optimization Index |
| |
| ZHANG Junhu,SHANG Tianhao,CHEN Ruihu,WANG Yijing,DING Qidong,LI Xiaolin.Inversion of Soil Organic Matter Content in Yinchuan Plain Using Field Spectral Fractional-order Derivatives Combined with Spectral Optimization Index[J].Transactions of the Chinese Society of Agricultural Machinery,2022,53(11):379-387. |
| |
| Authors: | ZHANG Junhu SHANG Tianhao CHEN Ruihu WANG Yijing DING Qidong LI Xiaolin |
| |
| Abstract: | Soil organic matter (SOM) is an important part of soil fertility and the main nutrient source for crop growth. In order to explore the inversion effect of fractional-order derivatives (FOD) combined with spectral optimization index on SOM in low fertility areas, taking Yinchuan Plain as the study object, the original data of hyperspectral reflectance of field were processed by 0~2 order FOD (with an interval of 0.2 order) after log reciprocal transformation, the spectral optimization indices DI/RDI, DI/NDI, NDI/RDI, RDI/NDI, DI/GDI and RI/GDI were constructed, the two-dimensional correlation between each index and SOM content was analyzed, the optimal spectral optimization index was selected, and a support vector machine (SVM) model was established to inverse the SOM content. The results showed that the content of SOM in Yinchuan Plain was generally low, of which 93.05% was at the level of 4~6 class. There were obvious differences in the absorption characteristics of the original spectral reflectance of soil in the field, with obvious absorption peaks at 1400nm and 1900nm. With the increasing fractional order, the spectral reflectance was approaching 0. The maximum absolute correlation coefficient (MACC) values of soil DI/NDI, DI/GDI, RI/GDI, NDI/RDI and RDI/NDI were all less than 0.80 in order 0~2. The MACC values of DI/RDI in order 0.2~2.0 were ranged from 0.9965 to 0.9986, and their sensitive bands were mainly concentrated in 1450~1750nm and 2100~2400nm. The model inversion accuracy based on DI/RDI-SVM model was the best at order 0.2, modeling determination coefficient (R2c) and verification determination coefficient (R2p) were 0.98 and 0.99, and residual predictive derivation (RPD) got 4.31. The results can provide scientific basis for rapid and accurate estimation and mapping of SOM in areas with low organic matter content. |
| |
| Keywords: | low content of soil organic matter spectral characteristics fractional-order derivative support vector machine inversion Kriging interpolation method |
|
| 点击此处可从《农业机械学报》浏览原始摘要信息 |
| 点击此处可从《农业机械学报》下载免费的PDF全文 |
|
