欢迎访问林草资源研究

Forest and Grassland Resources Research >

2020 , Vol. 0 >Issue 4: 127 - 133

DOI: https://doi.org/10.13466/j.cnki.lyzygl.2020.04.018

Technical Application

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

  • Rui HAN ,
  • Dasheng WU ,
  • Luming FANG ,
  • Yuling HUANG
Expand
  • 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 date: 2020-05-03

  Revised date: 2020-06-03

  Online published: 2020-10-10

Fold

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

Cite this article

Rui HAN , Dasheng WU , Luming FANG , Yuling HUANG . Estimation of Forest Reserves Based on Boruta and Extra-trees Methods[J]. Forest and Grassland Resources Research, 2020 , 0(4) : 127 -133 . DOI: 10.13466/j.cnki.lyzygl.2020.04.018

References

[1] 吴达胜. 基于多源数据和神经网络模型的森林资源蓄积量动态监测[D]. 杭州:浙江大学, 2014.
[2] 尤静妮. 基于高分遥感纹理信息的森林蓄积量估测研究[D]. 西安:西安科技大学, 2017.
[3] 姚新华, 金佳, 徐飞飞, 等. 太湖流域果树提取的光谱和纹理特征选择研究[J]. 中国生态农业学报, 2019,27(10):1596-1606.
[4] 刘明艳, 王秀兰, 冯仲科, 等. 基于主成分分析法的老秃顶子自然保护区森林蓄积量遥感估测[J]. 中南林业科技大学学报, 2017,37(10):80-83.
[5] 周如意. 基于Landsat-8遥感影像的森林蓄积量估测[D]. 杭州:浙江农林大学, 2019.
[6] 王海宾, 彭道黎, 高秀会, 等. 基于GF-1 PMS影像和k-NN方法的延庆区森林蓄积量估测[J]. 浙江农林大学学报, 2018,35(6):1070-1078.
[7] Wu Dasheng. Estimation of forest volume base on LM-BP neural network model[J]. Comput.Model.New Technol, 2014,18(4):131-137.
[8] 汪康宁, 马婷, 吕杰. 基于随机森林算法的凉水自然保护区蓄积量反演研究[J]. 西南林业大学学报, 2016,36(5):125-129.
[9] 郭海山, 高波涌, 陆慧娟. 基于Boruta-PSO-SVM的股票收益率研究[J]. 传感器与微系统, 2018,37(3):51-53.
[10] Wei Jing, Huang Wei, Li Zhanqing, et al. Estimating 1-km-resolution PM 2.5 concentrations across China using the space-time random forest approach[J]. Remote Sensing of Environment, 2019,231:111221.
[11] Djavan De Clercq, Wen Zongguo, Fei Fan. Determinants of efficiency in anaerobic bio-waste co-digestion facilities:A data envelopment analysis and gradient boosting approach[J]. Applied Energy, 2019,253:113570.
[12] 洪汝锋. 龙泉市林权制度改革研究[D]. 杭州:浙江农林大学, 2012.
[13] 杨永恬. 基于多源遥感数据的森林蓄积量估测方法研究[D]. 北京:中国林业科学研究院, 2010.
[14] 姚啸. 面向对象的高分遥感影像分类在森林蓄积量估测中的应用研究[D]. 西安:西安科技大学, 2015.
[15] 王雪军. 基于多源数据源的森林资源年度动态监测研究[D]. 北京:北京林业大学, 2013.
[16] Kursa M B, Rudnicki W R. Feature selection with the Boruta package[J]. Journal of Statistical Software. 2010,36(11):1-13.
[17] Geurts P, Ernst D, Wehenkel L. Extremely randomized trees[J]. Machine Learning, 2006,63(1):3-42.
[18] 李世波, 林辉, 王光明, 等. 基于GF-1的森林蓄积量遥感估测[J]. 中南林业科技大学学报, 2019,39(8):70-75.
[19] 罗蜜, 孙玉军, 张博, 等. 应用衍生纹理指数对杉木林分蓄积量的估测[J]. 东北林业大学学报, 2019,47(7):43-49.
[20] 李亚东, 曹明兰, 李长青, 等. 无人机森林航摄影像三维点云估测林分蓄积量研究[J]. 中南林业科技大学学报, 2019,39(3):56-60.
[21] 郎晓雪, 许彦红, 舒清态, 等. 香格里拉市云冷杉林蓄积量遥感估测非参数模型研究[J]. 西南林业大学学报:自然科学, 2019,39(1):146-151.
[22] 陈新云, 李利伟, 刘承芳, 等. 热带原始森林类型分类和蓄积量遥感反演研究[J].林业资源管理, 2019(2):39-46.
[23] 曹霖, 彭道黎, 王雪军, 等. 应用Sentinel-2A卫星光谱与纹理信息的森林蓄积量估算[J]. 东北林业大学学报, 2018,46(9):54-58.
Options
Outlines

/

〈 〉