欢迎访问《中国农学通报》,

中国农学通报 ›› 2020, Vol. 36 ›› Issue (17): 134-143.doi: 10.11924/j.issn.1000-6850.casb20200200085

• 农业信息·科技教育 • 上一篇    下一篇

柴达木地区枸杞种植区遥感提取方法对比研究

雷春苗1,3, 肖建设2,3(), 史飞飞2,3, 郭英香1, 赵金龙4, 郑玲1   

  1. 1 青海省气象服务中心,西宁,810001
    2 青海省气象科学研究所,西宁,810001
    3 青海省防灾减灾重点实验室,西宁 810001
    4 中国气象局旱区特色农业气象灾害监测预警与风险管理重点实验室,银川 750002
  • 收稿日期:2020-01-05 修回日期:2020-03-14 出版日期:2020-06-15 发布日期:2020-06-09
  • 通讯作者: 肖建设
  • 作者简介:雷春苗,女,1989年出生,陕西绥德人,工程师,硕士,研究方向为生态气象遥感监测。通信地址:810001青海省西宁市五四大街青海省气象局,E-mail:1447160797@qq.com。
  • 基金资助:
    国家自然科学基金项目“基于多源卫星的青藏高原湿雪判识算法研究”(41761078);中国气象局旱区特色农业气象灾害监测预警与风险管理重点实验室开放研究项目“基于多源遥感数据的柴达木地区枸杞种植信息提取与生长状况遥感监测方法研究”(CAMF-201806);青海省气象局科研项目“多源遥感数据支持的柴达木地区枸杞提取方法对比研究”(QH-2017006)

Extraction Methods of Wolfberry Plantation in Qaidam Region: A Comparative Study

Lei Chunmiao1,3, Xiao Jianshe2,3(), Shi Feifei2,3, Guo Yingxiang1, Zhao Jinlong4, Zheng Ling1   

  1. 1 Qinghai Meteorological Service Center, Xining 810001
    2 Institute of Qinghai Meteorological Science Research, Xining 810001
    3 Key Laboratory of Disaster Prevention and Mitigation of Qinghai Province, Xining 810001
    4 Key Laboratory for Meteorological Disaster Monitoring and Early Warning and Risk Management of Characteristic Agriculture in Arid Regions, Yinchuan 750002
  • Received:2020-01-05 Revised:2020-03-14 Online:2020-06-15 Published:2020-06-09
  • Contact: Xiao Jianshe

摘要:

枸杞作为柴达木地区特色经济作物之一,利用高分辨率遥感影像开展枸杞种植区识别与提取,有利于政府和农业部门开展市场调控和作物精细化管理。以柴达木典型枸杞种植区诺木洪农场为例,利用随机森林、Softmax、支持向量机、BP神经网络和最大似然5种分类器开展农场内不同生长年限枸杞种植区精细化提取,并对结果进行精度验证。结果表明:采用随机森林的分类效果最佳,其总体分类精度达到93.8%,Kappa 0.93,采用Softmax、支持向量机和BP神经网络方法也均获得了较高的分类精度,其总体分类精度均达到了86.6%~87.6%,Kappa系数达到0.84~0.86,而最大似然法分类效果最差,其总体分类精度仅为76.9%,Kappa系数为0.73。通过实验利用国产高分辨率卫星结合较优的分类器能够实现包括枸杞等小宗特色经济作物种植区域和种植结构的精细化识别和监测。

关键词: 柴达木, 枸杞, 随机森林, Softmax, 支持向量机, BP神经网络

Abstract:

In this study, we use high-resolution remote sensing images to identify and extract the planting areas of wolfberry, a special economic crop in Qaidam, to provide evidence for market regulation and fine crop management. Taking Numuhong Farm, a typical wolfberry plantation area in the region as the research area, and using five classifiers of random forest, Softmax, support vector machine, BP neural network and maximum likelihood, we conducted the refined extraction of wolfberry plantation areas with different growth years, and verified the accuracy of the classification results. The results show that the classification effect using the random forest method is the best, with an overall classification accuracy of 93.8% and a Kappa of 0.93. Softmax, support vector and BP neural network methods have also achieved high classification accuracy, and their overall classification accuracy is 86.6%~87.6%, and the Kappa coefficient is 0.84~0.86. The maximum likelihood method has the worst classification effect, its overall classification accuracy is only 76.9%, and the Kappa coefficient is 0.73. Therefore, the use of domestic high-resolution satellites combined with a better classification method can realize the fine identification and monitoring of the planting areas and structures of minor characteristic cash crops such as Chinese wolfberry.

Key words: Qaidam, wolfberry, random forest, Softmax, SVM, BPNN

中图分类号: