摘要
为寻找一种土壤有机质快速检测技术,探究了土壤有机质含量对光谱反射率曲线的影响,分析了土壤有机质与光谱曲线间的相关性关系,采用多元逐步回归和支持向量机建立土壤有机质含量高光谱预测模型。研究结果表明:研究区土壤有机质含量对光谱曲线影响较小;光谱平滑和变换技术可以有效提高光谱特征波段与土壤有机质的相关性关系,二阶微分变换的效果最好,相关系数为-0.83;通过决定系数和均方根误差对不同模型的预测效果进行评价,其中基于二阶微分的支持向量机模型的反演效果最优R 2=0.89,RMSE为1.73。研究结果揭示了研究区土壤有机质与光谱反射率间的相关性关系,可以为实现土壤有机质快速检测和实时动态监测提供技术支持和参考。
In order to find a rapid detection technology of soil organic matter,the effect of soil organic matter concentration on spectral reflectance curve was studied.The original spectral curve was processed by three spectral transformation methods:first-order differential,second-order differential and reciprocal logarithm.The correlation between soil organic matter and spectral curve was analyzed.The hyperspectral prediction model of soil organic matter content was established by multiple stepwise regression and support vector machine.The results show that the content of soil organic matter in the study area has little influence on the spectral curve;spectral smoothing and transformation techniques can effectively improve the correlation between spectral characteristic bands and soil organic matter,of which the second-order differential transformation has the best effect,with the correlation coefficient being-0.83;The prediction effect of the model is evaluated,through the determination coefficient and root mean square error;and the optimal inversion effect of the support vector machine model based on second-order differential is R 2=0.89 and RMSE 1.73.The results reveal the correlation between soil organic matter and spectral reflectance in the study area,which can provide reference for rapid detection and real-time dynamic monitoring of soil organic matter.
作者
沈强
张世文
夏沙沙
尹炳
陈飞
邹宏光
SHEN Qiang;ZHANG Shiwen;XIA Shasha;YIN Bing;CHEN Fei;ZOU Hongguang(School of Surveying and Mapping,Anhui University of Science and Technology,Huainan Anhui 232001,China;School of Earth and Environmental Science,Anhui University of Science and Technology,Huainan Anhui 232001,China)
出处
《安徽理工大学学报（自然科学版）》
CAS
2019年第4期39-45,共7页
Journal of Anhui University of Science and Technology:Natural Science
基金
国家自然科学基金资助项目(41471186)
国家重点研发计划基金资助项目(2016YFD0300801)
陕西省土地整治中心重点实验室开放基金资助项目(2018-ZD07)
关键词
土壤有机质
高光谱
多元逐步回归
支持向量机
soil organic matter
hyperspectral
stepwise multiple linear regression
support vector machines
