1 College of Mining Engineering, North China University of Science and Technology, Tangshan 063210, China
2 Hebei Industrial Technology Institute of Mine Ecological Remediation, Tangshan 063210, China
3 Tangshan Key Laboratory of Resources and Environmental Remote Sensing, Tangshan 063210, China
Show less
文章历史+
Received
Published
Revised
2025-08-20
2026-07-28
2026-01-14
Online Date
2026-08-14
PDF (6696K)
摘要
为提高复杂林分阔叶林单木生物量估测精度和效率,基于无人机激光雷达(light detection and ranging,LiDAR)点云估测杨树和榆树的单木生物量。通过单木分割提取单木树高、冠幅作为基础自变量,另引入树冠参数树冠投影面积、树冠体积协助设计不同变量组合。采用恒定异速生长比(constant allometric ratio,CAR)模型和随机森林(random forest,RF)、极端梯度提升树(extreme gradient boosting,XGBoost)和分类特征梯度提升树(categorical features gradient boosting,CatBoost)构建单木生物量估测模型,对比分析不同变量组合和模型估测单木生物量的精度。结果表明,提取杨树和榆树的单木参数与实测值进行拟合,R2分别为0.84和0.89,分割树高与实测树高具有较高的一致性,可以采取提取值构建估测模型;引入树冠参数可以有效提高生物量估测模型的精度,引入树冠参数后,杨树和榆树的估测R2分别比引入前提升了0.02、0.10、0.06、0.04和0.03、0.10、0.05、0.07;与CAR模型相比,机器学习模型估测单木生物量的效果更佳,杨树和榆树的RF模型拟合效果最好,拟合的R2分别为0.53和0.63。可见无人机LiDAR数据能够通过单木分割提取单木参数估测单木生物量,引入树冠参数的机器学习模型估测单木生物量能取得较好的模型拟合优度和较高的估测精度。
Abstract
In order to improve the accuracy and efficiency of individual tree biomass estimation in broadleaf forests in complex stands, the biomass of Populus L. and Ulmus pumila L. trees was estimated by UAV LiDAR point clouds. The height and crown width of individual trees were extracted as the basic independent variables through individual tree segmentation, assisted by tree canopy parameters such as crown parameters such as crown area and crown volume to design different variable combinations. Biomass estimation models were constructed using the constant allometric ratio(CAR) model and random forest(RF), extreme gradient boosting(XGBoost), and categorical features gradient boosting(CatBoost), and the accuracy of different variable combinations and models in estimating individual tree biomass was compared and analyzed. The results show that the individual tree parameters of Populus L. and Ulmus pumila L. are fitted with the measured values, with R2 values of 0.84 and 0.89 respectively. The extracted values have a good consistency with the measured values, and the estimation model can be constructed by using the extracted values. The results indicate that adding tree canopy parameters can effectively improve the accuracy of biomass estimation models. After the addition of tree canopy parameters, the predicting R2 of Populus L. and Ulmus pumila L. increases by 0.02, 0.10, 0.06, 0.04 and 0.03, 0.10, 0.05, 0.07 respectively compared with before the addition. Compared with the CAR model, the machine learning models have better performance in estimating individual tree biomass. The RF models of Populus L. and Ulmus pumila L. have the best performances, with the fitting R2 being 0.53 and 0.63 respectively. It is concluded that the UAV LiDAR data can estimate the biomass of individual tree through the extracted parameters of individual tree segmentation. The machine learning model adding tree canopy parameters can achieve better fit and higher prediction accuracy in estimating the biomass of individual trees.
CAI Yu-zhi, LI Fu-ping, MAN Wei-dong, LIU Ming-yue, ZHANG Yong-bin, LI Xiao-guang, CHI Xiao-jie, SONG Li-jie, WANG Jian.
Individual Tree Biomass Estimation in Broadleaf Forests of Complex Stands Based on UAV LiDAR[J].
Science Technology and Engineering, 2026, 26(21): 9054-9063 DOI:10.12404/j.issn.1671-1815.2506080
对无人机LiDAR点云数据进行预处理,包括对原始点云进行重采样、去噪、滤波,采用改进的渐进加密三角网滤波算法(improved progressive TIN densification,IPTD)将点云数据分为地面点与非地面点两类[16],根据地面点对点云进行地面高度归一化处理,以此消除地形起伏对点云数据高程值的影响,避免影响单木结构参数的提取精度。将预处理完成的LiData格式文件的点云转为las格式。
利用层次密度聚类算法(hierarchical density- based spatial clustering of applications with noise,HDBSCAN)直接对点云进行单木分割[17],取树冠顶点高度到地面的距离,即树高。通过二维凸包的顶点坐标计算各方向极值差提取东西和南北方向冠幅平均值,即冠幅(crown width,CW)[18]。
取生物量实测值的80%作为训练样本、20%作为验证样本,以决定系数R2、均方根误差(root mean square error,RMSE)、相对均方根误差(relative root mean square error,rRMSE)和总相对误差(total relative error,TRE)评价模型的拟合精度和估测能力。计算公式为
ZhuJinqi, XiongYuanqiao, YiYang, et al. Composition and influencing factors of carbon storage and sequestration in subtropical forests: a case study of Wuning Country[J]. Journal of Soil and Water Conservation, 2025, 39(3): 256-267, 277.
WeiXiaobo, LiZhiqiang, ChenZhaoguang, et al. Single tree segmentation of mangrove trees of different species based on UAV-LiDAR[J]. Science Technology and Engineering, 2024, 24(3): 963-969.
[5]
ZhangQ, CaiS, LiangX. Individual tree segmentation in occluded complex forest stands through ellipsoid directional searching and point compensation[J]. Forest Ecosystems, 2024, 11(6): 832-847.
[6]
DengS, XuQ, YueY, et al. Individual tree detection and segmentation from unmanned aerial vehicle-LiDAR data based on a trunk point distribution indicator[J]. Computers and Electronics in Agriculture, 2024, 218: 108717.
XuTianyi. Estimation of individual tree parameters of larch plantations based on UAV-LiDAR and error-invariable regression[D]. Harbin: Northeast Forestry University, 2023.
[11]
DuL M, PangY, WangQ, et al. A LiDAR biomass index-based approach for tree- and plotlevel biomass mapping over forest farms using 3D point clouds[J]. Remote Sensing of Environment, 2023, 290: 113543.
[12]
PintoC R, GorgensB E, AlmeidaD A R D, et al. The recovery of forest structure 30 years after timber harvesting: a comparison of harvesting methods using field inventories and drone-based LiDAR data[J]. Forest Ecology and Management, 2026, 60: 1123342.
[13]
BenjaminB, LouiseT, NicolasB, et al. Non-destructive estimation of individual tree biomass: allometric models, terrestrial and UAV laser scanning[J]. Remote Sensing of Environment, 2022, 280: 113180.
WuXiaokang, WangHaoyu, FengBaokun, et al. Individual tree biomass estimation based on UAV airborne LiDAR[J]. Science Technology and Engineering, 2022, 22(34): 15028-15035.
BaoLiyang, WangXiangjun, LiShaoda, et al. Estimation of individual tree above-ground biomass of rubber tree based on UAV-LiDAR[J]. Chinese Journal of Tropical Crops, 2023, 44(6): 1266-1275.
WangLiangsong, LiNing, WangCheng, et al. Effect of canopy morphological characteristics on individual tree biomass estimation based on airborne LiDAR[J]. Science Technology and Engineering, 2024, 24(31): 13304-13311.
[20]
EstornellJ, MartíJ, HadasE, et al. Biomass estimation of abandoned orange trees using UAV-SFM 3D points[J]. International Journal of Applied Earth Observation and Geoinformation, 2024, 130: 103931.
[21]
吴舒尧. 基于生态系统服务的生态修复效果与可持续性研究[D]. 北京: 北京大学, 2019.
[22]
WuShuyao. Ecological restoration effects and sustainability based on ecosystem services: a case study of the Dashihe mine ecological restoration project in Hebei[D]. Beijing: Peking University, 2019.
[23]
FangJ, WangM Z. Forest biomass estimation at regional and global levels, with special reference to China’s forest biomass[J]. Ecological Research, 2001, 16(3): 587-592.
[24]
ZhaoX, GuoQ, SuY, 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.
[25]
CampelloR J G B, MoulaviD, SanderJ, et al. Hierarchical density estimates for data clustering, visualization, and outlier detection[J]. ACM Transactions on Knowledge Discovery from Data, 2015, 9(3): 1-51.
[26]
华周阳. 基于激光点云数据的单木分割与结构参数提取研究[D]. 南京: 南京林业大学, 2023.
[27]
HuaZhouyang. Research on individual tree segmentation and structural parameter extraction based on laser point cloud data[D]. Nanjing: Nanjing Forestry University, 2023.
LiWenbo. The application of individual tree segmentation in plantation coniferous forest based on high density UAV-LiDAR point cloud[D]. Harbin: Northeast Forestry University, 2023.
YuDonghai, FengZhongke. Tree crown volume measurement method based on oblique aerial images of UAV[J]. Transactions of the Chinese Society of Agricultural Engineering, 2019, 35(1): 90-97.
LiuHaoran, FanWeiwei, XuYongsheng, et al. Single tree biomass estimation based on UAV LiDAR point cloud[J]. Journal of Central South University of Forestry & Technology, 2021, 41(8): 92-99.
[34]
胥辉. 两种生物量模型的比较[J]. 西南林学院学报, 2003(2): 36-39.
[35]
XuHui. A comparison between CAR and VAR Biomass models[J]. Journal of Southwest Forestry College, 2003(2): 36-39.
ChenRiqiang, LiChangchun, YangGuijun, et al. Extraction of crown information from individual fruit tree by UAV LiDAR[J]. Transactions of the Chinese Society of Agricultural Engineering, 2020, 36(22): 50-59.
[38]
EysnL, HollausM, LindbergE, et al. A benchmark of LiDAR-based single tree detection methods using heterogeneous forest data from the Alpine space[J]. Forests, 2015, 6(5): 1721-1747.
OuJiande, OuJialin, WuHaoyu, et al. Selection of single tree biomass model and canopy structure regulation of Taxus yunnanensis[J]. Journal of Northwest Forestry University, 2022, 37(5): 194-201.
[41]
LeiL, ChaiG, YaoZ, et al. A novel self-similarity cluster grouping approach for individual tree crown segmentation using multi-features from UAV-based LiDAR and multi-angle photo grammetry data[J]. Remote Sensing of Environment, 2025, 318: 114588.
[42]
JiangP, HeH, MaoZ, et al. Canopy properties predominately explain above-ground biomass stock in temperate forests[J]. Journal of Plant Ecology, 2025, 18(2): 226-239.
[43]
ShiY, ShenX, HuM, et al. An advanced approach for multiscale aboveground biomass estimation by integrating UAV, backpack LiDAR and high-resolution imageries: a case study in Liriodendron sino-americanum mixed forests[J]. Computers and Electronics in Agriculture, 2025, 239: 110898.
SiNian, ZhengYili, ShiFuxi, et al. Individual tree biomass estimation from UAV LiDAR using combined CCE and MCW approaches[J/OL]. Journey of Forestry Engineering, 1-10[2026-05-08]. https://doi.org/10.13360/j.issn.2096-1359.202505010.32.1862.S.20251127.1426.005.