首页 | 本学科首页   官方微博 | 高级检索  
     

宁夏盐碱地土壤盐分高光谱反演
引用本文:彭金英,蒋金豹,崔希民,张建,王思佳,王明国,聂铖. 宁夏盐碱地土壤盐分高光谱反演[J]. 矿山测量, 2021, 49(1): 69-73. DOI: 10.3969/j.issn.1001-358X.2021.01.016
作者姓名:彭金英  蒋金豹  崔希民  张建  王思佳  王明国  聂铖
作者单位:中国矿业大学(北京)地球与测绘工程学院,北京 100083;中国矿业大学(北京)地球与测绘工程学院,北京 100083;中国矿业大学(北京)地球与测绘工程学院,北京 100083;中国矿业大学(北京)地球与测绘工程学院,北京 100083;北京师范大学 地理科学学部,北京 100875;宁夏农业技术推广总站,宁夏 银川 750001;中国矿业大学(北京)地球与测绘工程学院,北京 100083
基金项目:宁夏农牧厅东西部合作项目"银北地区盐碱地农艺改良遥感监测研究";国家自然科学基金项目;大学生创新训练项目
摘    要:土地盐碱化给农业生产带来了巨大的影响,需要研究快速、高效、大面积诊断盐碱地及评估其严重度的技术方法.文中选取宁夏平罗县典型盐碱地为研究对象,采集土样并测定其室内高光谱数据和化学参数,通过分析离子含量确定主要研究离子为Na+、Cl-、Mg2+和SO2-4,将光谱进行一阶微分与连续统处理,通过相关性分析选出特征波段,分别构...

关 键 词:宁夏盐碱地  高光谱  反演  PLSR  PSO-RBF

Hyperspectral inversion of the soil salt content in saline-alkali land of Ningxia
Peng Jinying,Jiang Jinbao,Cui Ximin,Zhang Jian,Wang Sijia,Wang Mingguo,Nie Cheng. Hyperspectral inversion of the soil salt content in saline-alkali land of Ningxia[J]. Mine Surveying, 2021, 49(1): 69-73. DOI: 10.3969/j.issn.1001-358X.2021.01.016
Authors:Peng Jinying  Jiang Jinbao  Cui Ximin  Zhang Jian  Wang Sijia  Wang Mingguo  Nie Cheng
Affiliation:(College of Geosciences and Surveying Engineering,China University of Mining and Technology(Beijing),Beijing 100083,China;Faculty of Geographical Science,Beijing Normal University,Beijing 100875,China;Ningxia Agriculture Technology Extension Service Centre,Yinchuan 750001,China)
Abstract:Land salinization had a great impact on agricultural production,and it was necessary to study technical methods of rapid,efficient and large-scale diagnosis of saline-alkali land and evaluating the severity.In this paper,saline-alkali land was selected as the research object in Pingluo County in Ningxia Province,the soil samples were collected and the laboratory hyperspectral data and the chemical parameters were measured.By analyzing the ion contents,sodium ions,chloride ions,magnesium ions and sulfate ions were determined the main research ions.Spectrum was carried out the first order differential and continuum removal processing,and the characteristic bands were selected by correlation analysis,and Partial Least Squares Regression(PLSR)model and Particle Swarm Optimization Radial Basis(PSO-RBF)neural network model were established respectively.Results showed that PSO-RBF neural network model was superior to PLSR model,and PSO-RBF neural network model based on continuum removal was better than the model based on the first order differential.
Keywords:saline-alkali land of Ningxia  hyperspectral  inversion  PLSR  PSO-RBF
本文献已被 CNKI 维普 万方数据 等数据库收录!
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号