欢迎访问林业资源管理

林业资源管理 ›› 2020, Vol. 0 ›› Issue (4): 127-133.doi: 10.13466/j.cnki.lyzygl.2020.04.018

• 技术应用 • 上一篇    下一篇

基于Boruta和极端随机树方法的森林蓄积量估测

韩瑞1,2,3(), 吴达胜1,2,3(), 方陆明1,2,3, 黄宇玲1,2,3,4   

  1. 1.浙江农林大学 信息工程学院,杭州 311300
    2.林业感知技术与智能装备国家林业和草原局重点实验室,杭州 311300
    3.浙江省林业智能监测与信息技术研究重点实验室,杭州 311300
    4.醴陵市陶瓷烟花职业技术学校,湖南 醴陵 412200
  • 收稿日期:2020-05-03 修回日期:2020-06-03 出版日期:2020-08-28 发布日期:2020-10-10
  • 通讯作者: 吴达胜
  • 作者简介:韩瑞(1995-),男,河南周口人,在读硕士,主要从事资源与环境信息系统研究。Email: 804874277@qq.com
  • 基金资助:
    浙江省科技重点研发计划资助项目(2018C02013)

Estimation of Forest Reserves Based on Boruta and Extra-trees Methods

HAN Rui1,2,3(), WU Dasheng1,2,3(), FANG Luming1,2,3, HUANG Yuling1,2,3,4   

  1. 1. School of Information Engineering,Zhejiang Agriculture and Forestry University,Hangzhou Zhejiang 311300,China
    2. Key Laboratory of State Forestry and Grassland Administration on Forestry Sensing Technology and Intelligent Equipment,Hangzhou Zhejiang 311300,China
    3. Key Laboratory of Forestry Intelligent Monitoring and Information Technology of Zhejiang Province,Hangzhou Zhejiang 311300,China
    4. Ceramics-Fireworks Vocational Technology School of Liling,Hunan 412200,China
  • Received:2020-05-03 Revised:2020-06-03 Online:2020-08-28 Published:2020-10-10
  • Contact: WU Dasheng

摘要:

森林蓄积量是反映森林资源数量的重要指标之一。本研究应用Boruta特征选择方法和极端随机树(Extremely randomized trees,Extra-trees)方法,以小班为研究单元,估测龙泉市部分区域森林资源的每公顷蓄积量,为县域尺度森林蓄积量的估测提供新的方法和思路。基于研究区的森林资源二类调查数据、高分二号(GF-2)遥感影像数据、数字高程模型数据,提取多元特征组成原始特征集。通过Boruta选择方法对原始特征集进行筛选,利用Extra-trees方法建立森林蓄积量估测模型,选用十折交叉验证法对模型进行检验,并与随机森林(Random Forest,RF)方法和梯度提升(Gradient Boosting)方法进行对比分析。研究结果显示:1) 经过Boruta特征选择方法得出的特征有土层厚度、年龄、郁闭度、海拔、坡度和坡向;2) 极端随机树方法采用网格搜索调参得到的最优参数组合为:树的个数为250,树的最大深度为14;3) 基于Boruta和极端随机树方法的森林蓄积量估测模型的测试精度为84.14%,R2为0.92,RMSE为19.65m3/hm2,MAE为13.95m3/hm2,模型优于随机森林方法和梯度提升方法,表明Boruta特征选择方法结合极端随机树方法估测森林蓄积量可取得更好的效果。

关键词: Boruta特征选择, 极端随机树, 随机森林, 森林蓄积量, 机器学习

Abstract:

Forest reserve is an important index to show the quantity of forest resources.In this study,the boruta feature selection method and the extremely randomized trees(Extra-trees) method are used to estimate the forest resources per mu in some areas of Longquan city.The study takes small classes as the research unit to provide new methods for the estimation of forest reserves at the county level.Based on the secondary survey data of forest resources,GF-2 remote sensing image data and digital elevation model data,multiple features are collected to form the original feature set.Through the boruta selection method,the original feature set is screened,the forest volume estimation model is established by extra-trees method,and the ten fold cross validation method is used to test the model,which is compared with the random forest(RF) method and gradient boosting method.The results show that:(1) the features found by the boruta feature selection method are soil thickness,age,canopy density,altitude and slope;(2) the optimal parameter combination obtained by the grid search and parameter adjustment of the Extra-trees method is:the number of tree is 250,and the maximum depth of the tree is 14;(3) the testing accuracy of the forest volume estimation model based on the boruta and extra-trees method is 84.14%,R 2 is 0.92,RMSE is 19.65m3/hm2,and MAE is 13.95m3/hm2.The model is superior to the random forest method and the gradient lifting method.It shows that the boruta feature selection method combined with the Extra-trees method can achieve better results in estimating the forest reserve.

Key words: boruta feature selection, extremely randomized trees, random forest, forest reserves, machine learning

中图分类号: