基于赤池信息量准则的冬小麦叶面积指数高光谱估测

发布时间：2019-01-20 17:37

【摘要】：冬小麦叶面积指数(leaf area index,LAI)是描述冠层结构的重要参数之一,对评价其长势和预测产量具有重要意义。该文利用灰色关联分析(grey relational analysis,GRA)对植被指数进行排序,用偏最小二乘法(partial least squares regression,PLS)选择不同的植被指数个数作为自变量进行回归建模,通过赤池信息量准则(Akaike’s information criterion,AIC)选择AIC值最小的模型作为冬小麦LAI最优估算模型,即GRA、PLS和AIC 3种方法整合建立冬小麦LAI最优估算模型。使用2008-2009年在中国北京通州区和顺义区获取的整个生育期冬小麦LAI和配套的光谱数据进行建模,利用2009-2010相关数据进行验证。研究表明:采用GRA评价标准与冬小麦LAI关联度最大的植被指数是VOG1,关联度最小的植被指数是SR;通过AIC建立的以8个植被指数作为自变量的冬小麦LAI模型效果最优,建模集的决定系数R2和标准误SE分别为0.76和0.009,验证集的R2和相对均方根误差RRMSE分别为0.63和0.004,预测模型和验证模型均具有较高的精度和可靠性。结果表明采用GRA-PLS-AIC方法进行冬小麦LAI反演是可行的,为提高冬小麦LAI遥感预测精度提供了一种有效的方法。
[Abstract]:The leaf area index (leaf area index,LAI) of winter wheat is one of the important parameters to describe the canopy structure. In this paper, (grey relational analysis,GRA (grey relational analysis) is used to sort vegetation index, and (partial least squares regression,PLS (partial least square method) is used to select different numbers of vegetation indices as independent variables for regression modeling. The model of minimum AIC value was selected as the best LAI estimation model of winter wheat by (Akaike's information criterion,AIC (Red Pool Information quantity Criterion), that is, GRA,PLS and AIC combined three methods to establish the LAI optimal estimation model of winter wheat. The LAI of winter wheat and its corresponding spectral data obtained in Tongzhou District and Shunyi District of Beijing from 2008 to 2009 were used to model the model. The data from 2009-2010 were used to verify the model. The results show that the largest vegetation index with LAI correlation degree of winter wheat using GRA evaluation criterion is SR; with the lowest VOG1, correlation degree. The LAI model of winter wheat with eight vegetation indices as independent variables was established by AIC. The determination coefficient R2 and the standard error SE of the model set were 0.76 and 0.009, respectively. The R2 and RMS errors of the verification set are 0.63 and 0.004, respectively. The prediction model and the verification model have high accuracy and reliability. The results show that the LAI inversion of winter wheat using GRA-PLS-AIC method is feasible and provides an effective method for improving the precision of LAI remote sensing prediction of winter wheat.
【作者单位】：中国矿业大学(北京)地球科学与测绘工程学院;国家农业信息化工程技术研究中心;农业部农业信息技术重点实验室;北京市农业物联网工程技术研究中心;河南工程学院土木工程学院;
【基金】：国家自然科学基金(41471285) 北京市自然科学基金项目(4141001) 北京市农林科学院科技创新能力建设项目(KJCX20140417) 地理空间信息工程国家测绘地理信息局重点实验室经费资助项目(201417)
【分类号】：S512.11;TP79

【参考文献】