粒子群优化的最小二乘支持向量机在小麦白粉病监测中的应用

发布时间：2018-03-07 21:25

本文选题：遥感监测　切入点：小麦白粉病　出处：《遥感技术与应用》2017年02期 　论文类型：期刊论文

【摘要】：小麦白粉病严重影响小麦的产量和品质,区域尺度上准确、及时地监测小麦白粉病的发生情况有利于高效地指导防治工作。利用Landsat-8遥感影像,提取出对小麦白粉病病情影响较大的长势因子和生境因子,包括归一化植被指数(NDVI)、比例植被指数(RVI)、绿度(Greenness)、湿度(Wetness)和地表温度(LST),利用最小二乘支持向量机(LSSVM)对陕西省关中平原部分地区的小麦白粉病进行监测,并用粒子群算法(PSO)优化模型参数,将监测结果分别与传统支持向量机(SVM)和最小二乘支持向量机(LSSVM)的监测结果进行对比分析。结果表明:经过粒子群优化的最小二乘支持向量机模型(PSO-LSSVM)的总体监测精度达到92.8%,优于SVM的71.4%和LSSVM的85.7%,取得了较好的监测效果。
[Abstract]:Wheat powdery mildew seriously affects the yield and quality of wheat, and monitoring the occurrence of wheat powdery mildew on the regional scale accurately and timely is helpful to guide the prevention and control of wheat powdery mildew. Landsat-8 remote sensing images are used. The growth factors and habitat factors of wheat powdery mildew were extracted. Including normalized vegetation index (NDVI), proportional vegetation index (RVI), green degree of greens, humidity and surface temperature (LST), wheat powdery mildew in parts of Guanzhong Plain in Shaanxi Province was monitored by least square support vector machine (LSSVM). Particle swarm optimization algorithm (PSO) is used to optimize the model parameters. The monitoring results are compared with those of traditional support vector machine (SVM) and least squares support vector machine (LSSVM). The results show that the PSO-LSSVM model based on particle swarm optimization is the best for overall monitoring. The degree reached 92.8, better than the 71.4% of SVM and 85.7 of LSSVM.
【作者单位】：安徽大学安徽省农业生态大数据工程实验室;中国科学院遥感与数字地球研究所数字地球重点实验室;
【基金】：国家自然科学基金项目(61672032、41271412) 安徽省自然科学基金项目(1408085MF121、1608085MF139) 中国科学院国际合作局对外合作重点项目(131211KYSB20150034) 安徽省科技重大专项(16030701091)
【分类号】：S435.121.46;TP18

【相似文献】