欢迎访问《应用生态学报》官方网站,今天是 分享到:

应用生态学报 ›› 2022, Vol. 33 ›› Issue (9): 2339-2346.doi: 10.13287/j.1001-9332.202209.007

• • 上一篇    下一篇

基于Landsat 8时间序列数据的翠岗林场森林类型划分

董灵波1, 梁凯富1, 张一帆2, 刘兆刚1*   

  1. 1东北林业大学林学院, 森林生态系统可持续经营教育部重点实验室, 哈尔滨 150040;
    2中船(浙江)海洋科技有限公司, 浙江舟山 316021
  • 收稿日期:2022-02-15 接受日期:2022-04-28 出版日期:2022-09-15 发布日期:2023-03-15
  • 通讯作者: * E-mail: lzg19700602@163.com
  • 作者简介:董灵波, 男, 1988年生, 博士, 副教授。主要从事森林可持续经营研究。E-mail: farrell0503@126.com
  • 基金资助:
    国家自然科学基金项目(32171778)资助。

Classification of forest types in Cuigang Forest Farm based on time series data of Landsat 8

DONG Ling-bo1, LIANG Kai-fu1, ZHANG Yi-fan2, LIU Zhao-gang1*   

  1. 1Ministry of Education Key Laboratory of Sustainable Forest Ecosystem Management, School of Forestry, Northeast Forestry University, Harbin 150040, China;
    2CSSC (ZheJiang) Ocean Technology Co., Ltd., Zhoushan 316021, Zhejiang, China
  • Received:2022-02-15 Accepted:2022-04-28 Online:2022-09-15 Published:2023-03-15

摘要: 探讨增强型植被指数(EVI)时间序列数据对提升森林类型识别精度的实际作用,可以促进光学遥感数据在森林资源调查和监测领域的深层次应用。以大兴安岭新林林业局翠岗林场为对象,以2014—2018年的20景Landsat 8 OLI时间序列数据、2017—2019年的56块固定样地数据和2016年二类调查数据为基础,运用随机森林算法,以光谱特征、纹理特征和EVI时间序列特征为基础构建6种不同的分类方案,实现翠岗林场森林类型的划分,并评估不同分类方案的精度。结果表明: 落叶松林、白桦林、针阔混交林、针叶混交林和阔叶混交林的EVI值在非生长季(36—111日和287—367日)间差异较大,其间针叶混交林EVI值显著高于其他4种森林类型,而阔叶混交林EVI值始终低于其他4种森林类型;在生长季早期(111—143日),白桦林EVI值高于落叶松EVI值,可有效区分白桦林和落叶松林;在6种分类方案中,光谱特征+纹理特征+EVI时间序列特征的分类精度最高,其Kappa达到0.82、分类精度86.1%。对比结果表明,加入植被指数时间序列特征的总体精度比光谱特征的总体精度提高了14.3%。因此,光谱特征、纹理特征及EVI时间序列特征组合下的随机森林算法能够对翠岗林场森林类型进行有效划分,具有良好的识别精度和可信度。

关键词: 时间序列数据, 大兴安岭, 森林类型, 随机森林算法

Abstract: To explore the practical role of enhanced vegetation index (EVI) time series data in improving the accuracy of forest type recognition could promote the deep application of optical remote sensing data in forest resources investigation and monitoring. With Cuigang Forest Farm of Xinlin Forestry Bureau in Daxing’anling as the object, we constructed six classification schemes, using random forest algorithm with spectral feature, texture feature and EVI time series feature. The data sources were 20-view Landsat 8 OLI time series data from 2014 to 2018, 56 fixed plots data from 2017-2019, and the 2016 Class II survey data. Our aims were to realize the classification of forest types in Cuigang Forest Farm and to evaluate the accuracy of different classification schemes. The results showed the EVI values of Larix gmelinii forest, Betula platyphylla forest, coniferous-broadleaved mixed forest, coniferous mixed forest and broadleaved mixed forest were significantly different in non-growing seasons (36-111 days and 287-367 days), with the EVI value of mixed conifer forest being significantly higher, and that of mixed broadleaf forest being always lower than the other four forest types. In the early growing season (111-143 days), the EVI value of B. platyphylla forest were higher than L. gmelinii forest, which could effectively distinguish the two forests. Among the six classification schemes, spectral feature, texture feature, and EVI time series feature had the highest classification accuracy, with a Kappa of 0.82 and a classification accuracy of 86.1%. The comparison results showed that the overall accuracy of adding vegetation index time series feature was improved by 14.3% compared with that of spectral feature. The random forest algorithm with combined spectral, texture and EVI time series features could effectively classify forest stand types in Cuigang Forest Farm, with good recognition accuracy and confidence.

Key words: time series data, Daxing’anling, forest type, random forest algorithm