欢迎访问林业资源管理

林业资源管理 ›› 2022, Vol. 0 ›› Issue (3): 54-59.doi: 10.13466/j.cnki.lyzygl.2022.03.009

• 科学研究 • 上一篇    下一篇

基于GF-1数据多尺度遥感特征的森林蓄积量估测研究

黄冰倩1,2(), 岳彩荣1(), 朱泊东1   

  1. 1.西南林业大学,昆明 650224
    2.贵州省林业调查规划院,贵阳 550003
  • 收稿日期:2022-03-03 修回日期:2022-03-15 出版日期:2022-06-28 发布日期:2022-08-04
  • 通讯作者: 岳彩荣
  • 作者简介:黄冰倩(1990-),女,贵州铜仁人,工程师,主要从事林业信息技术研究与应用、林业调查规划等方面的工作。Email: 294918392@qq.com
  • 基金资助:
    云南省科技厅重大科技专项(202002AA100007-015);贵州省森林保护“六个严禁”执法专项行动案件管理信息系统研发(黔林科合J [2018]14号)

Estimation of Forest Volume Based on Multi-Scale Remote Sensing Features of GF-1

HUANG Bingqian1,2(), YUE Cairong1(), ZHU Bodong1   

  1. 1. College of Forestry,Southwest Forestry University,Kunming 650224,China
    2. Forestry Survey & Planning Institute of Guizhou Province,Guiyang 550003,China
  • Received:2022-03-03 Revised:2022-03-15 Online:2022-06-28 Published:2022-08-04
  • Contact: YUE Cairong

摘要:

基于贵州省观山湖区高分1号(GF-1)遥感数据提取的光谱信息、植被指数及纹理特征,结合实测马尾松样地数据,通过多元逐步回归、随机森林算法构建不同窗口遥感特征的森林蓄积量估测模型。结果表明:多元逐步回归、随机森林估测模型最佳窗口均为13×13窗口;选取DI2,B3,EN2,SM2,CO3作为建模特征变量,以最佳窗口建立蓄积估测模型,随机森林模型拟合效果优于多元逐步回归模型。根据遥感影像分辨率选取适宜窗口提取特征变量,可进一步提高森林蓄积估测的建模精度。

关键词: 高分1号, 纹理特征, 多元逐步回归, 随机森林算法, 森林蓄积量

Abstract:

Based on spectral information,vegetation index and texture characteristics extracted from GF-1 remote sensing data in Guanshanhu,Guizhou Province,combined with the measured masson pine plot data,multiple stepwise regression and random forest algorithm were used to construct forest stock estimation models with different windows of remote sensing features.The results indicated that:the optimal windows of multiple stepwise regression and random forest estimation models were both 13×13.When feature variables were extracted as DI2,B3,EN2,SM2,CO3,and the accumulation estimation model was established with the optimal window,the fitting effect of random forest model was better than that of multiple stepwise regression model.According to the resolution of remote sensing image,selecting suitable window to extract characteristic variables can further improve the modeling accuracy of forest stock estimation.

Key words: GF-1, texture features, multiple stepwise regression, random forest algorithm, forest stock

中图分类号: