乔红波,焦红涛,吴 旭,司海平,时 雷,郭 伟,马新明,周益林.基于支持向量机模型的冬小麦全蚀病为害等级遥感监测[J].麦类作物学报,2014,34(12):1694 |
基于支持向量机模型的冬小麦全蚀病为害等级遥感监测 |
Hyperspectral Remote Sensing Monitoring of Wheat Take all Based on SVM |
|
DOI:10.7606/j.issn.1009-1041.2014.12.16 |
中文关键词: 冬小麦 全蚀病 高光谱 支持向量机 预测模型 |
英文关键词:Wheat Wheat take all Hyperspectral Support vector machine Forecasting model |
基金项目:国家自然科学基金项目(31301604);植物病虫害生物学国家重点实验室开放课题(SKLOF201302);河南省科技攻关项目(122102110045) |
|
摘要点击次数: 1316 |
全文下载次数: 912 |
中文摘要: |
为了解利用高光谱遥感技术对小麦全蚀病进行有效监测的可行性,对感染不同发病等级全蚀病的冬小麦冠层光谱反射率数据进行采集分析,选取监测敏感波段,在Matlab和Libsvm工具箱支持下,利用支持向量机分类方法构建小麦全蚀病病害等级预测模型。结果表明,在不同程度小麦全蚀病的为害下,小麦冠层光谱反射率存在明显变化。通过对数据分析,选择700~900 nm波段作为敏感波段进行训练建立模型的结果最好;经检验,基于此波段构建的预测模型预测值与实际值相关系数可达0.943,均方根达0.63,因此生产上可利用波段光谱特征对小麦全蚀病进行监测。 |
英文摘要: |
Wheat take all is quarantine disease and took place more and more serious in recent years, It is important to monitor it effectively. To provide technical support for the prediction and prevention of wheat take all, hyperspectral remote sensing was combined with canopy spectral reflectance data collection and investigation of the incidence of wheat take all to build the wheat prediction model for take all disease level using support vector machine(SVM) classification method.The results showed that the wheat canopy spectral reflectance changed significantly under the influence of the disease; through data analysis, the model with data at 700~900 nm wave length band as the sensitive band performed the best results; Upon examination, the forecasting model constructed based on this band was the best with the correlation coefficient up to 0.943 between the predicted value and the actual value. The results of this study suggested that it was feasible for monitoring the occurrence of take all disease in wheat using hyperspectral remote sensing. |
查看全文 查看/发表评论 下载PDF阅读器 |
关闭 |