基于PSO算法的BP神经网络对植被叶片氮素含量的预测  

Prediction of Nitrogen Content in Vegetation Leaves by BP Neural Network Based on PSO Algorithm

作　　者：王杰 徐锡杰 解斐斐[3] WANG Jie;XU Xijie;XIE Feifei(College of Ecology and Environment,Inner Mongolia University,Hohhot Inner Mongolia 010021,China;College of Resources and Environment,University of Chinese Academy of Sciences,Beijing 100190,China;College of Geomatics,Shandong University of Science and Technology,Qingdao Shandong 266590,China)

机构地区：[1]内蒙古大学生态与环境学院,内蒙古呼和浩特010021 [2]中国科学院大学资源与环境学院,北京100190 [3]山东科技大学测绘科学与工程学院,山东青岛266590

出　　处：《北京测绘》2018年第11期1289-1292,共4页Beijing Surveying and Mapping

基　　金：国家自然科学基金(41271349);山东省自然科学基金(ZR2013DM008);山东科技大学科研创新团队支持计划(2014TDJH101);山东科技大学人才引进科研启动基金(2015RCJJ006)

摘　　要：植被叶片中的氮元素,70%存在于叶绿素中,且叶片叶绿素的测量相较于氮素测量简单,因此可以用叶绿素来估测叶片含氮量。基于lopex93数据集,利用PSO(微粒群)算法优化的BP神经网络模型把叶片叶绿素含量作为输入值、叶片含氮量作为输出值训练得到预测叶片含氮量模型训练得到预测叶片含氮量模型。同时用实验室测量的叶片数据检验,检验误差小于0.2%。说明基于PSO算法优化的BP神经网络模型利用叶绿素能很好的估计叶片含氮量。Nitrogen in the leaves of vegetation is 70% in chlorophyll, and the measurement of leaf chlorophyll is simpler than nitrogen measurement. Therefore, leaf chlorophyll can be used to estimate the nitrogen content of leaves. Based on the lopex93 dataset, the BP neural network model optimized by the PSO （particle swarm optimization） algorithm was applied to train the model of nitrogen content in the predicted leaves. The test error of the leaves measured by the laboratory is less than 0.2%. It shows that the BP neural network model based on the optimization of PSO algorithm can use chlorophyll to estimate the nitrogen content of leaves very well.

关 键 词：粒子群PSO算法 BP神经网络模型 lopex93数据集 叶绿素 叶片含氮量 

分 类 号：TP701[自动化与计算机技术—检测技术与自动化装置] TP79[自动化与计算机技术—控制科学与工程]