Research on Individual Tree Volume Estimation Using Backpack LiDAR

doi:10.11873/j.issn.1004-0323.2022.5.1071

Remote Sensing Technology and Application

2022, Vol. 37

Issue (5): 1071-1083 DOI: 10.11873/j.issn.1004-0323.2022.5.1071

Research on Individual Tree Volume Estimation Using Backpack LiDAR

Chao Ma¹(

),Huaguo Huang¹,Xin Tian²(

),Bingjie Liu¹,Kunjian Wen¹,Pengjie Wang²

^1.Beijing Forestry University Forest Resources and Environmental Management National Forest and Grass Bureau Key Laboratory，Beijing 100083，China
^2.Institute of Forest Resource Information Techniques，Chinese Academy of Forestry，Beijing 100091，China

Download:

HTML

PDF (3049KB)
Export: BibTeX | EndNote (RIS)

Abstract

Backpack Laser Scanning （BLS） is a potential tool in forest resource survey， but shows much uncertainty for the extraction accuracy of single-tree volume and forest stand volume in complex topographic circumstances. Using BLS point cloud data from the Gaofeng Forest Farm in Guangxi Province， this study implemented the estimation of single-tree volume and sample plot volume by random forest approach. First， individual tree segmentation was conducted using the BLS point cloud data， 8 characteristic parameters were extracted including Diameter at Breast Height （DBH）， Tree Height （Htree）， Crown Diameter （CD）， Crown Area （CA）， Crown Volume （CV）， Canopy Cover （CC）， Gap Fraction （GF）， and Leaf Area Index （LAI）， and 56 stratification height indicators were calculated （height percentage， cumulative height percentage， coefficient of variation， canopy undulation rate， etc.）. Then， an individual treee volume estimation model was developed using the random forest technique， and the prediction accuracy of various parameter combinations was investigated. The results showed that：（1） modeling with only 8 characteristic parameters of an individual tree structure indicated an estimated accuracy of R2=0.83、RMSE=0.097 m³；（2） modeling estimation accuracy was improved with the addition of the layered height index： R2=0.87、RMSE=0.087 m³；（3） the Boruta algorithm for variable screening reduced the input parameters from 64 to 52， with little difference in estimation accuracy： R²=0.87， RMSE=0.087 m³；（4） the estimation accuracy of sample plot volume was R²=0.97， RMSE=0.703 m³·ha^-1. The results suggested the application potential to use the BLS point cloud for individual tree volume estimation and the sample volume by random forest algorithm.

Key words: Volume Backpack laser scanning Random forest Boruta algorithm

Received: 08 December 2021 Published: 13 December 2022

ZTFLH:

TN958.98

Corresponding Authors: Xin Tian E-mail: machao31@126.com;tianxin@ifrit.ac.cn

	Service
	E-mail this article
	Add to my bookshelf
	Add to citation manager
	E-mail Alert
	RSS
	Articles by authors
	Chao Ma
	Huaguo Huang
	Xin Tian
	Bingjie Liu
	Kunjian Wen
	Pengjie Wang

Cite this article:

Chao Ma,Huaguo Huang,Xin Tian,Bingjie Liu,Kunjian Wen,Pengjie Wang. Research on Individual Tree Volume Estimation Using Backpack LiDAR. Remote Sensing Technology and Application, 2022, 37(5): 1071-1083.

URL:

http://www.rsta.ac.cn/EN/10.11873/j.issn.1004-0323.2022.5.1071 OR http://www.rsta.ac.cn/EN/Y2022/V37/I5/1071

Fig.1 Distribution map of sample plots in the study area

Table 1 Sample plots information summary table

Table 2 LiBackpack DGC50 scanning system

Fig.2 Collection route planning

Fig.3 Flow chart of individual tree stock volume estimation

变量名称	含义	计算公式
H_cv	变异系数	$H c v = (H s t d / H m e a n) × 100 %$ (5)
H_add	平均绝对偏差	$H a a d = 1 n ∑ i = 1 n Z i - H m e a n$ (6)
H_crr	冠层起伏率	$H c r r = (H m e a n - H m i n) / (H m a x - H m i n)$ (7)
H_AIHIQR	累积高度百分位数四分位数间距	$H A I H I Q R = H A I H 75 % - H A I H 25 %$ (8)
H_IQR	高度百分位数四分位数间距	$H I Q R = H 75 % - H 25 %$ (9)
H_sq	二次幂平均	$H s q = (∑ i = 1 n Z i 2) / n$ (10)
H_cmc	三次幂平均	$H c m c = (∑ i = 1 n Z i 3) / n 3$ (11)
H_k	峰度	$H k = ∑ i = 1 n (Z i - H m e a n) 4 (n - 1) H s t d 4$ (12)
H_ske	偏斜度(偏态)	$H k = ∑ i = 1 n (Z i - H m e a n) 3 (n - 1) H s t d 3$ (13)

Table 3 Calculation formula of height variable

Table 4 Input individual tree structure variable

Fig.4 Evaluation indicators of model 1

Fig.5 Optimal ntree Parameter of model 1

Fig.6 Estimation individual tree stock volume with model 1

Fig.7 Box plot of variable importance

Table 5 Results of variable filtering

Fig.8 The importance of filtering variables

Fig.9 Evaluation indicators of modeling

Fig.10 Optimal ntree parameter of modeling

Fig.11 Estimation individual tree stock volume with Model 2

Fig.12 Estimation individual tree stock volume with Model 3

Table 6 Results of Ten-fold modeling

Fig.13 Results of Ten-fold modeling

Table 7 Sample field volume estimation

1	Yan Fei. Research of technology and method of forest resource inventory［D］. Beijing： Beijing Forestry University， 2014.
1	闫飞. 森林资源调查技术与方法研究［D］. 北京：北京林业大学， 2014.
2	Wang Jinliang， Cheng Feng， Wang Cheng， et al. Primary discussion on the potential of forest volume estimating using ICESat-GLAS data in complex terrain area： A case study of Shangri-la， Yunnan Province［J］. Remote Sensing Technology and Application， 2012， 27（1）：45-50.
2	王金亮，程峰，王成，等.基于ICESat-GLAS数据估算复杂地形区域森林蓄积量潜力初探——以云南香格里拉县为例［J］. 遥感技术与应用， 2012， 27（1）：45-50.
3	Gang C， Hay G J， St-Onge B. A GEOBIA framework to estimate forest parameters from LiDAR transects， QuickBird imagery and machine learning： A case study in Quebec， Canada［J］. International Journal of Applied Earth Observations and Geoinformation， 2012， 15：28-37.
4	Liang Zhifeng， Ling Feilong， Wang Xiaoqin. Correlation analysis between L-band SAR and forest stem volume in Northeast China［J］. Remote Sensing Technology and Application，2013，28（5）：871-878.
4	梁志锋，凌飞龙，汪小钦. L波段SAR与中国东北森林蓄积量的相关性分析［J］. 遥感技术与应用， 2013， 28（5）：871-878.
5	Li Shibo， Lin Hui， Wang Guangming，et al.Estimation of forest volume based on GF-1［J］. Journal of Central South University of Forestry and Technology， 2019， 39（8）：70-75，86.
5	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）：70-75，86.
6	Pearse G D， Morgenroth J， Watt M S， et al. Optimising prediction of forest leaf area index from discrete airborne LiDAR［J］. Remote Sensing of Environment，2017，200（3）：220-239.
7	Bian Rui， Yanyun Nian， Gou Xiaohua， et al. Analysis of forest canopy height based on UAV LiDAR： A case study of Picea Crassifolia in the east and central of the Qilian Mountains［J］. Remote Sensing Technology and Application， 2021， 36（3）：511-520.
7	边瑞，年雁云，勾晓华，等. 基于无人机激光雷达的森林冠层高度分析［J］. 遥感技术与应用， 2021， 36（3）：511-520.
8	Li Wenjuan， Zhao Chuanyan， Bie Qiang， et al. Retrieval of the forest structural parameters using airborne LiDAR data［J］. Remote Sensing Technology and Application，2015，30（5）：917-924.
8	李文娟，赵传燕，别强，等.基于机载激光雷达数据的森林结构参数反演［J］.遥感技术与应用，2015，30（5）：917-924.
9	Tang Xuguang. Estimation of forest aboveground biomass by integrating ICESat/GLAS waveform and TM data［D］. Changchun： Graduate University of Chinese Academy of Sciences （Northeast Institute of Geography and Agroecology）， 2013.
9	汤旭光. 基于激光雷达与多光谱遥感数据的森林地上生物量反演研究［D］. 长春：中国科学院研究生院（东北地理与农业生态研究所）， 2013.
10	Zhao Xun， Yue Cairong， Li Chungan， et al. Estimation of forest canopy density based on airborne LiDAR point cloud data［J］. Remote Sensing Technology and Application， 2020， 35（5）：1136-1145.
10	赵勋，岳彩荣，李春干，等. 基于机载LiDAR点云数据森林郁闭度估测［J］. 遥感技术与应用， 2020， 35（5）：1136-1145.
11	Wang Xiangyu， Xie Donghui， Wang Yan， et al. 3D reconstruction of an individual tree from terrestrial laser scanner data［J］. Remote Sensing Technology and Application， 2015， 30（3）：455-460.
11	王向玉，谢东辉，汪艳，等. 基于地面激光雷达点云数据的单木三维重建［J］. 遥感技术与应用， 2015， 30（3）：455-460.
12	Cai Shuo. Extraction of tree diameter at breast height based on terrestrial laser scanning and backpack baser scanning［D］. Harbin： Northeast Forestry University， 2021.
12	蔡硕. 基于地基激光雷达和背包式激光雷达林木胸径提取［D］. 哈尔滨：东北林业大学， 2021.
13	Cai Shuo， Xing Yanqiu， Duanmu jialong， et al. Extraction of DBH from filtering out low intensity point cloud by backpack laser scanning［J］. Forest Engineering， 2021， 37（5）：12-19.
13	蔡硕，邢艳秋，端木嘉龙. 背包式激光雷达滤除低强度点云提取林木胸径［J］. 森林工程， 2021， 37（5）：12-19.
14	Duanmu jialong. A study of planted forest DBH estimation algorithms using backpack laser scanning data［D］. Harbin： Northeast Forestry University， 2020.
14	端木嘉龙. 基于背包激光雷达数据的人工林林木胸径提取算法研究［D］. 哈尔滨：东北林业大学， 2020.
15	Xza B， Qga C， Ys C， et al. Improved progressive TIN densification filtering algorithm for airborne LiDAR data in forested areas［J］. ISPRS Journal of Photogrammetry and Remote Sensing， 2016， 117：79-91.
16	Lee H， Slatton K C， Roth B E， et al. Adaptive clustering of airborne LiDAR data to segment individual tree crowns in managed pine forests［J］. International Journal of Remote Sensing， 2010， 31（1）：117-139.
17	Li W， Guo Q， Jakubowski M K， et al. A new method for segmenting individual trees from the LiDAR point cloud［J］. Photogrammetric Engineering and Remote Sensing， 2012， 78（1）：75-84.
18	Qin M， Su Y， Guo Q. Comparison of canopy cover estimations from airborne LiDAR， aerial imagery， and satellite imagery［J］. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing， 2017， 10（9）：4225-4236.
19	Richardson J J， Monika Moskal L， Kim S H. Modeling approaches to estimate effective Leaf Area Index from aerial discrete-return LiDAR［J］. Agricultural and Forest Meteorology， 2009， 149（6-7）：1152-1160.
20	Li Y， Guo Q， Tao S， et al. Derivation， validation， and sensitivity analysis of terrestrial laser scanning-based leaf area index［J］. Canadian Journal of Remote Sensing， 2016， 42（6）：719-729.
21	Shao Z， Zhang L， Wang L. Stacked sparse autoencoder modeling using the synergy of airborne LiDAR and satellite optical and SAR data to map forest above-ground biomass［J］. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing， 2017，10（12）：5567-5582.
22	Garcia-Gutierrez J， Martinez-Alvarez F， Troncoso A， et al. A comparison of machine learning regression techniques for LiDAR-derived estimation of forest variables［J］. Neurocomputing， 2015， 167（1）：24-31.
23	Breiman L. Random forests［J］. Machine Learning， 2001， 45：5-32.
24	Franklin J. The elements of statistical learning： Data mining， inference and prediction［J］. The Mathematical Intelligencer， 2005， 27（2）：83-85.
25	Qiangxin Ou， Lei Xiangdong， Shen Chenchen， et al. Individual tree DBH growth prediction of larch-spruce-fir mixed forests based on random forest algorithm［J］. Journal of Beijing Forestry University，2019，41（9）：9-19.
25	欧强新，雷相东，沈琛琛，等. 基于随机森林算法的落叶松-云冷杉混交林单木胸径生长预测［J］. 北京林业大学学报，2019，41（9）：9-19.
26	Lim K， Treitz P， Wulder M， et al. LiDAR remote sensing of forest structure［J］. Progress in Physical Geography， 2003， 27（1）：88-106.
27	Hu Y， Xu X， Wu F， et al. Estimating forest stock volume in Hunan Province， China， by integrating in situ plot data， Sentinel-2 images， and linear and machine learning regression models［J］. Remote Sensing，2020， 12（1）：186. DOI： . doi: 10.3390/rs 12010186
28	Sun Zhongqiu， Gao Jinping， Wu Fayun， et al. Estimating forest stock volume via small-footprint LiDAR point cloud data and random forest algorithm［J］. Forestry Science， 2021， 57（8）：68-81.
28	孙忠秋，高金萍，吴发云，等. 基于机载激光雷达点云和随机森林算法的森林蓄积量估测［J］. 林业科学， 2021， 57（8）：68-81.
29	Pang Yong， Huang Kebiao， Li Zengyuan， et al. Forest aboveground biomass analysis using remote sensing in the Greater Mekong Subregion［J］. Resources Science， 2011， 33（10）：1863-1869.
29	庞勇，黄克标，李增元，等. 基于遥感的湄公河次区域森林地上生物量分析［J］. 资源科学， 2011， 33（10）：1863-1869.
30	Cao Lin， Dai Jinsong， Xu Jianxin， et al. Optimized extraction of forest parameters in subtropical forests based on airborne small footprint LiDAR technology［J］. Journal of Beijing Forestry University， 2014， 36（5）：13-21.
30	曹林，代劲松，徐建新，等. 基于机载小光斑LiDAR技术的亚热带森林参数信息优化提取［J］. 北京林业大学学报， 2014， 36（5）：13-21.

No Suggested Reading articles found!

Viewed

Full text

Abstract

Cited

Shared

Discussed