期刊文献+

一种新的光谱参量预测黑土养分含量模型 被引量:10

A New Model for Predicting Black Soil Nutrient Content by Spectral Parameters
下载PDF
导出
摘要 我国东北黑土富含养分,随着土壤数字制图、精确农业和土壤资源调查等研究的深入,引入航空高光谱数据并提供科学的预测结果成为研究热点。数据源为CASI-1500航空高光谱成像系统,光谱范围380~1 050nm,空间分辨率1.5m。在黑龙江建三江地区采集59个土壤样本,化验获得有机质、全氮、全磷和全钾含量数据,选择eps-regression支持向量机模型,BP神经网络和PLS1最小二乘回归模型,建立光谱与含量的机器学习模型。通过评价3种模型的预测精度,选用支持向量机方法,对航空高光谱数据进行全氮、全磷和全钾的信息提取,采用神经网络方法,反演了有机质信息。研究表明:以光谱统计量、光谱特征值和光谱信息量为大类指标,所选取的18个子指标,能够反映土壤光谱的综合情况,是一种新的土壤光谱数据处理方法。有机质和全钾信息提取精度最高的算法是神经网络法,误差分别为1.21%和0.81%,而支持向量机算法在提取全氮和全磷信息时,验证样本的实测均值和预测均值完全吻合,精度最高。评价航空高光谱提取土壤养分的综合精度,有机质、全氮、全磷和全钾提取误差分别为5.25%,6.05%,2.74%和8.90%,在全磷反演中精度最高。 In the field of soil digital mapping,precision agriculture and soil resourceinvestigation,the study of aerial hyperspectral data to provide scientific prediction results by aerial hyperspectral have become the focus of research,especially in the case of black soil rich in nutrients in Northeast China.The data source is CASI-1500 aerial hyperspectral imaging system with a spectral rangeof 380~1 050 nm,and spatial resolution of 1.5 m.59 soil samples were collected from the Jiansanjiang area in Heilongjiang,and the contents of organic matter,total nitrogen,total phosphorus and total potassium were obtained.In addition,the eps-regression support vector machine model,BP neural network and PLS1 least square regression model are selected to establish the machine learning model of spectrum and content.A support vector machine(SVM)method is used to extract the total nitrogen,total phosphorus and total potassium in aerial hyperspectral data by evaluating the prediction accuracy of the 3 models.The information of organic matter is retrieved by neural network.The results revealed that the datecomputed by the spectral statistic,spectral characteristics and spectral values is a kind of effective spectrum of training data,which can reflect the soilcomprehensive reflectance situation.The neural network method is the most accurate method for the extraction of organic matter and total potassium.The errors are1.21%and 0.81%respectively.The accuracy is the highest in the extraction of total nitrogen and total phosphorus information by support vector machines(SVM).The comprehensive accuracy of aerial hyperspectral extraction of soil nutrients was evaluated.The extraction errors of organic matter,total nitrogen,total phosphorus and total potassium were 5.25%,6.05%,2.74%and 8.90%,respectively,and the total phosphorus retrieval accuracy was the highest.
作者 张东辉 赵英俊 秦凯 ZHANG Dong-hui;ZHAO Ying-jun;QIN Kai(National Key Laboratory of Remote Sensing Information and Imagery Analyzing Technology,Beijing Research Institute of Uranium Geology,Beijing 100029,China)
出处 《光谱学与光谱分析》 SCIE EI CAS CSCD 北大核心 2018年第9期2932-2936,共5页 Spectroscopy and Spectral Analysis
基金 国家自然科学基金项目(41602333) "十三五"装备预先研究专项技术项目(32101080302) 中国地质调查局黑土地航空高光谱遥感调查项目(SYZXW2017101)资助
关键词 机器学习 航空高光谱 支持向量机 神经网络 黑土养分 Machine learning Aerial hyperspectral Support vector machines Neural networks Black soil nutrients
  • 相关文献

参考文献1

二级参考文献16

  • 1张友静,高云霄,黄浩,任立良.基于SVM决策支持树的城市植被类型遥感分类研究[J].遥感学报,2006,10(2):191-196. 被引量:42
  • 2黄昕,张良培,李平湘.基于多尺度特征融合和支持向量机的高分辨率遥感影像分类[J].遥感学报,2007,11(1):48-54. 被引量:48
  • 3BLASCHKE T. Object based image analysis for remote Sensing[J]. ISPRS Journal of Photogrammetry and Re- moteSensing, 2010,65 ( 1 ) : 2 -16.
  • 4BLASCHKE T, HAY G J, WENG Q. Collective sens ing: integrating geospatial technologies to understand urban systems : an overview[J].Remote Sensing, 2011, 3(8) :1743-1776.
  • 5BLASCHKE T, HAY G J, KELLY M, et al. Geo- graphic object-based image analysis:a new paradigm in remote sensing and geographic information science[J]. ISPRS International Journal of Photogrammetry and Remote Sensing,2014,87(1) :180-191.
  • 6BARALDI A, BOSCHETTI L. Operational automatic remote sensing image understanding systems: beyond geographic obiect based and object-oriented image a- nalysis (GEOBIA/GEOOIA). part 1 :introduction[J]. Remote Sensing, 2012,4 ( 9 ) : 2694-2735.
  • 7BARALDI A, BOSCHETTI L. Operational automatic remote sensing image understanding systems: beyond geographic object-based and object-oriented image a- nalysis (GEOBIA/GEOOIA). part 2:novel system ar- chitecture, information/knowledge representation, al- gorithm design and implementation[J]. Remote Sens ing,2012,4(9) :2768-2817.
  • 8JONATHAN C W C, DESIRE P. Evaluation of random forest and adaboost tree-based ensemble classification and spectral band selection for ecotope mapping air borne hyperspectral imagery[J]. Remote Sensing of Environment, 2008,112 ( 6 ) : 2999-3011.
  • 9NOVACK T, ESCH T, KUX H, et al. Machine learn- ing comparison between WorldView-2 and QuickBird- 2-simulated imagery regarding object-based urban land cover classification[J ]. Remote Sensing, 2011,3 ( 10 ) : 2263 -2282.
  • 10DURO D C,FRANKLIN S E,DUBE M G. A compari- son of pixel-based and object-based image analysis with selected machine learning algorithms for the classifica- tion of agricultural landscapes using SPOT-5 HRG im- agery[J]. Remote Sensing of Environment, 2012, 118 (6) :259-272.

共引文献19

同被引文献145

引证文献10

二级引证文献58

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部