论文部分内容阅读
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。
Wheat powdery mildew seriously affects the yield and quality of wheat. Accurate and timely monitoring of the occurrence of wheat powdery mildew on a regional scale is conducive to effectively guiding prevention and control work. Landsat-8 remote sensing images were used to extract the growth and habitat factors that have a great impact on wheat powdery mildew, including NDVI, RVI, Greenness and Wetness ) And surface temperature (LST) were measured. The wheat powdery mildew was monitored in least part of the Guanzhong plain by using least square support vector machine (LSSVM). Particle swarm optimization (PSO) was used to optimize the model parameters. The results were compared with the traditional support Vector Machine (SVM) and Least Squares Support Vector Machine (LSSVM) monitoring results for comparative analysis. The results show that the PSO-LSSVM achieves a total monitoring accuracy of 92.8%, which is better than 71.4% of SVM and 85.7% of LSSVM and achieves better monitoring results.