基于离散小波的土壤全氮高光谱特征提取与反演  

Hyperspectral Feature Extraction and Estimation of Soil Total Nitrogen Based on Discrete Wavelet Transform

作　　者：张娟娟[1,2] 牛圳 马新明 王健[1] 徐超越 时雷 Bacao Fernando 司海平[1,2] ZHANG Juan-juan;NIU Zhen;MA Xin-ming;WANG Jian;XU Chao-yue;SHI Lei;Bacao Fernando;SI Hai-ping(Henan Agricultural University,College of Information and Management Science,Zhengzhou 450002,China;Henan Agricultural University,Collaborative Innovation Center of Henan Grain Crops,Zhengzhou 450002,China;Universidade Nova de Lisboa,NOVA Information Management School,Lisboa,1070-312,Portugal)

机构地区：[1]河南农业大学信息与管理科学学院,河南郑州450002 [2]河南粮食作物协同创新中心,河南郑州450002 [3]Universidade Nova de Lisboa,NOVA Informantion Managment School,Lisboa,1070-312,Portugal

出　　处：《光谱学与光谱分析》2023年第10期3223-3229,共7页Spectroscopy and Spectral Analysis

基　　金：国家重点研发计划项目(2021YFD1700905);河南省科技攻关项目(192102110012);河南省现代农业(小麦)产业技术体系项目(S2016-01-G04)资助。

摘　　要：土壤全氮是重要的养分指标,利用高光谱技术研究并构建砂姜黑土全氮含量高光谱估测模型,为作物施肥及发展精确农业提供参考。尝试研究离散小波估测土壤全氮含量的可行性,以河南省商水县不同小麦氮肥处理为试验区,采集100份0~20 cm的砂姜黑土,土壤样本风干并经研磨过筛等处理后,在实验室暗室内采集光谱。利用含量梯度法,将总样本(100个砂姜黑土)划分为建模集75个和验证集25个。将原始光谱进行一阶导数变换,并对一阶导数光谱分别进行相关分析和离散小波变换,同时结合支持向量机和K邻近算法构建高光谱土壤全氮估测模型。系统分析了原始光谱和一阶导数光谱的单波段与土壤全氮的相关性,结果表明,经一阶导数变换后的光谱与土壤全氮有更好的相关性,在1373 nm处相关系数达到最高为0.84。利用离散小波算法对一阶导数光谱进行最佳母小波和分解层次选择,结果显示,经sym8函数分解的小波系数能较好的重构土壤全氮光谱信息,进一步基于分解层L_(1)—L_(11)的低频系数分别建立支持向量回归和K邻近回归土壤全氮含量估测模型,比较全部估测模型,以分解层L_(5)的低频系数结合K邻近构建的模型最优,建模决定系数为0.90,均方根偏差为0.09 g·kg^(-1),相对分析误差为3.78,验证决定系数为0.97,均方根偏差为0.05 g·kg^(-1),相对分析误差为4.30。同时与全波段和经相关分析后挑选出的敏感波段作为输入构建的模型进行比较,K邻近模型精度提高了3.2%和9%,支持向量机模型精度提高了6.7%和11.6%。研究结果表明一阶导数变换与离散小波技术可有效减少噪声影响,提高土壤全氮含量的估测精度,又实现了光谱数据降维,简化了模型复杂度,为砂浆黑土全氮含量的精确估测提供参考。Soil total nitrogen is an important nutrient index.Hyperspectral technology is used to study and build a hyperspectral estimation model of total nitrogen content in Shajiang black soil,which provides a reference for crop fertilization and the development of precision agriculture.This paper attempts to study the feasibility of discrete wavelets to estimate soil total nitrogen content.Taking different wheat nitrogen fertilizer treatments in Shangshui County,Henan Province,as the experimental area,100 samples of Shajiang black soil with a depth of 0~20 cm were collected.After the soil samples were air-dried in the dark and processed by grinding and screening,the spectra were collected in the darkroom of the laboratory.The total samples(100 sand ginger black soil)were divided into 75 modeling sets and 25 validation sets.The original spectrum was transformed by the first derivative,and the first derivative spectrum was analyzed by correlation analysis and discrete wavelet transform respectively.At the same time,the hyperspectral estimation model of soil total nitrogen content was constructed by combining the support vector machine and the k-nearest neighbor algorithm.The correlation between the single band of the original spectrum and the first derivative spectrum and soil total nitrogen were systematically analyzed.The results showed that after the first derivative transformation,the spectrum had a better correlation with soil total nitrogen,and the correlation coefficient reached 0.84 at 1373 nm.The discrete wavelet algorithm selects the best mother wavelet and decomposition level of the first derivative spectrum.The results show that the wavelet coefficients decomposed by the Sym8 function can better reconstruct the spectral information of soil total nitrogen.Further,based on the low-frequency coefficients of decomposition layer L_(1)—L_(11),the support vector regression and k-nearest neighbor regression estimation models of soil total nitrogen content were established respectively,and all the estimation models w

关 键 词：砂姜黑土 全氮 高光谱 离散小波 K邻近算法 

分 类 号：S151.9[农业科学—土壤学]