...
  • 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Multimedia Tools and Applications >A hyperspectral GA-PLSR model for prediction of pine wilt disease
【24h】

A hyperspectral GA-PLSR model for prediction of pine wilt disease

机译：一种高光谱GA-PLSR模型，用于预测松树枯萎病

获取原文
获取原文并翻译 | 示例
           
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

Pine wilt disease caused by a forest-invasive alien species, the pine wood nematode (Bursaphelenchus xylophilus) is considered as one of the most destructive pest problems. In recent years, spectroscopic technologies have shown great potentials for the assessment of forest damage due to their nondestructive, noninvasive, cost-effective, and rapidly responsive nature. This paper first identified the hyperspectral characteristics of pine wilt disease by measuring and analyzing the changes in spectral reflectance of healthy and infected Pinus massoniana trees. Then 16 spectral features were extracted from the spectral bands covering the green region (510～580 nm), the red region (620～680 nm), the red edge (680～760 nm), the near-infrared region (780～1100 nm), and coded as genes composing the chromosome of a genetic algorithm (GA). Based on the optimal spectral features with suitable fitness from the GA, a partial least squares regression (PLSR) prediction model was built with highest determination coefficient R~2_c = 0.91, R~2_v =0.82, relative prediction deviation RPD = 3.3 and lowest root mean square error RMSE_c = 0.23, RMSE_v = 0.33 on the calibration and validation datasets. Compared with other PLSR models, our proposed GA-based approach significantly improves the prediction accuracy with few input spectral features.
机译：松树枯萎病引起的森林侵袭性外来物种，松木线虫（Bursaphelenchus Xylophilus）被认为是最具破坏性的害虫问题之一。近年来，光谱技术由于其无损，非侵入性，成本效益和快速响应性的性质而显着评估森林损伤的巨大潜力。本文首先通过测量和分析了健康和感染的Pinus Massoniana树的光谱反射变化来确定松树枯萎病的高光谱特征。然后从覆盖绿色区域（510〜580nm）的光谱带中提取16个光谱特征，红色区域（620〜680nm），红色边缘（680〜760nm），近红外区域（780〜1100 NM），并作为组合遗传算法（GA）染色体的基因编码。基于具有来自Ga合适的最佳光谱特征，基于最高确定系数R〜2_C = 0.91，R〜2_V = 0.82，相对预测偏差RPD = 3.3和最低根，构建了偏最小二乘回归（PLSR）预测模型（PLSR）预测模型。校准和验证数据集上的均方误差rmse_c = 0.23，rmse_v = 0.33。与其他PLSR模型相比，我们所提出的基于GA的方法显着提高了少量输入光谱特征的预测精度。

著录项

  • 来源
    《Multimedia Tools and Applications》 |2020年第24期|16645-16661|共17页
  • 作者

    Sulan Zhang; Jinlong Huang; Jim Hanan; Lin Qin;

  • 作者单位

    College of Big Data and Intelligent Engineering Yangtze Normal University Chongqing 408100 China Queensland Alliance for Agriculture & Food Innovation Centre for Horticultural Science The University of Queensland Brisbane 4072 Australia Hyperspectral Remote Sensing Monitoring Center for Ecological Environment of the Three Gorges Reservoir Area Yangtze Normal University Chongqing 408100 China;

    College of Big Data and Intelligent Engineering Yangtze Normal University Chongqing 408100 China;

    Queensland Alliance for Agriculture & Food Innovation Centre for Horticultural Science The University of Queensland Brisbane 4072 Australia;

    Hyperspectral Remote Sensing Monitoring Center for Ecological Environment of the Three Gorges Reservoir Area Yangtze Normal University Chongqing 408100 China College of Electronic Information Engineering Yangtze Normal University Chongqing 408100 China;

  • 收录信息
  • 原文格式 PDF
  • 正文语种 eng
  • 中图分类
  • 关键词

    Pine wilt disease; Pinus massoniana; Spectral features; Partial least squares regression (PLSR); Prediction model;

    机译：松枯萎病;Pinus Massoniana;光谱特征;部分最小二乘回归（PLSR）;预测模型;

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号