基于TLS辅助的长白落叶松一级枝条生物量模型构建

doi:10.12302/j.issn.1000-2006.202204037

国家林草科技领军期刊
中国精品科技期刊
中国高校百佳科技期刊
江苏省新闻出版政府奖期刊奖
RCCSE林学权威期刊（A+）
CSCD核心期刊
Scopus数据库收录期刊
中文核心期刊
SCD核心期刊

作者加群：102861116

微信公众号：南京林业大学学报

高级检索

南京林业大学学报（自然科学版） ›› 2023, Vol. 47 ›› Issue (2): 130-140.doi: 10.12302/j.issn.1000-2006.202204037

基于TLS辅助的长白落叶松一级枝条生物量模型构建

唐依人¹(), 贾炜玮¹^,²^,^*(), 王帆¹, 孙毓蔓¹, 张颖¹

1.东北林业大学林学院,黑龙江哈尔滨 150040
2.东北林业大学森林生态系统可持续经营教育部重点实验室,黑龙江哈尔滨 150040

收稿日期:2022-04-15 修回日期:2022-06-13 出版日期:2023-03-30 发布日期:2023-03-28
通讯作者: * 贾炜玮(jiaww2002@163.com),教授。
基金资助:
国家自然科学基金区域联合基金项目(U21A20244)

Constructing a biomass model of Larix olgensis primary branches based on TLS

TANG Yiren¹(), JIA Weiwei¹^,²^,^*(), WANG Fan¹, SUN Yuman¹, ZHANG Ying¹

1. School of Forestry, Northeast Forestry University, Harbin 150040, China
2. Key Laboratory of Sustainable Forest Ecosystem Management, Ministry of Education, Northeast Forestry University, Harbin 150040, China

Received:2022-04-15 Revised:2022-06-13 Online:2023-03-30 Published:2023-03-28

摘要/Abstract

摘要：

【目的】探究利用地基激光雷达(terrestrial laser scanning,TLS)点云数据估测枝条生物量的可行性,构建预测长白落叶松(黄花落叶松)枝条生物量的最优模型。【方法】以利用孟家岗林场26株长白落叶松点云数据提取出的733个一级枝条的特征因子[枝长(L_BL)、弦长(L_BCL)、基径(d_B)、着枝角度(A_B)、弓高(H_BAH)、枝条基部断面积(S_BAB)、相对着枝深度(d_RDINC)]和对应的实测数据为数据源,分别建立枝条水平上的一级枝条生物量基础模型,通过对比基础模型之间的差异来分析利用TLS数据建立枝条生物量模型的可行性。最后利用TLS数据分别对比基础模型、混合效应模型和随机森林模型的预测效果。【结果】基础模型中最终选定的自变量为S_BAB和L_BCL。利用TLS数据建立的枝条生物量基础模型具有更好的预测精度。对比3种模型预测能力结果显示,随机森林模型无论在训练集还是测试集上都表现出最好的效果,具体顺序为:随机森林模型>混合效应模型>基础模型。其中随机森林模型的决定系数(R²)相较于混合模型和基础模型分别提高了1.32%和4.89%,均方根误差(RMSE)分别降低了11.23%和13.60%。【结论】基于TLS利用随机森林算法能够准确对枝条生物量进行估测,不仅为随机森林算法在林分生长模型上的应用奠定了一定的实践基础,也为TLS在树冠结构研究中的应用提供了重要的参考价值。

关键词: 长白落叶松(黄花落叶松), 点云数据, 枝条特征因子, 枝条生物量, 混合模型, 随机森林

Abstract:

【Objective】 To explore the feasibility of using terrestrial laser scanning (TLS) point cloud data to estimate branch biomass and find the optimum model to predict the branch biomass of Larix olgensis. 【Method】 The characteristic factors (branch length (L_BL), branch chord length (L_BCL), branch diameter (d_B), branch angle (A_B), branch arch height (H_BAH), basal area of branches (S_BAB), and relative depth within the crown (d_RDINC)) of 733 first-order branches extracted using point cloud data of 26 artificial larch plants and the corresponding measured data from Mengjiagang Forestry Farm were used as data sources to establish first-level branch biomass base models at the branch level. Additionally, the feasibility of using TLS data to establish branch biomass models by comparing the differences between base models were analyzed. Finally, the prediction effects of the base model, mixed-effects model, and random forest model were compared separately using TLS data. 【Result】 The independent variables selected in the base model were S_BAB and L_BCL. Using TLS data to build the branch biomass base model had a better prediction accuracy. Comparing the results of the three models showed that the random forest model showed the best results both on the training and test sets, in the following order: random forest model > mixed-effects model > base model. The R² of the random forest model improved by 1.32% and 4.89%, and the RMSE decreased by 11.23% and 13.60%, respectively, compared to the mixed model and the base model. 【Conclusion】 The results of this paper proved that the branch biomass can be estimated accurately based on TLS using the random forest algorithm, which not only laid a practical foundation for the application of the random forest algorithm on stand growth models, but also provided an important reference value for the application of TLS in the study of crown structure.

Key words: Larix olgensis, point cloud data, branch characterization factor, branch biomass, mixed-effects model, random forest

中图分类号:

S758

唐依人,贾炜玮,王帆,等. 基于TLS辅助的长白落叶松一级枝条生物量模型构建[J]. 南京林业大学学报（自然科学版）, 2023, 47(2): 130-140.

TANG Yiren, JIA Weiwei, WANG Fan, SUN Yuman, ZHANG Ying. Constructing a biomass model of Larix olgensis primary branches based on TLS[J].Journal of Nanjing Forestry University (Natural Science Edition), 2023, 47(2): 130-140.DOI: 10.12302/j.issn.1000-2006.202204037.

图/表 11

图1

表1

图2

表2

表3

表4

图3

图4

图5

图6

表5

参考文献 32

[1]	董利虎, 李凤日, 贾炜玮. 基于线性混合效应的红松人工林枝条生物量模型[J]. 应用生态学报, 2013, 24(12): 3391-3398.
	DONG L H, LI F R, JIA W W. Linear mixed modeling of branch biomass for Korean pine plantation[J]. Chin J Appl Ecol, 2013, 24(12): 3391-3398.DOI:10.13287/j.1001-9332.2013.0571.
[2]	DELUCIA E H M H C E V. Climate-driven changes in biomass allocation in pines[J]. Glob Change Bio, 2000, 6(5):587-593.
[3]	HELMISAARI H S, MAKKONEN K, KELLOMÄKI S, et al. Below-and above-ground biomass, production and nitrogen use in eastern Finland[J]. For Ecol Manag, 2002, 165(1/2/3):317-326.DOI:10.1016/s0378-1127(01)00648-x.
[4]	MÄKINEN H, MÄKELÄ A. Predicting basal area of Scots pine branches[J]. For Ecol Manag, 2003, 179(1/2/3): 351-362. DOI:10.1016/S0378-1127(02)00551-0.
[5]	GONZALEZ DE TANAGO J, LAU A, BARTHOLOMEUS H, et al. Estimation of above-ground biomass of large tropical trees with terrestrial LiDAR[J]. Methods Ecol Evol, 2018, 9(2): 223-234. DOI: 10.1111/2041-210x.12904.
[6]	STOVALL A E L, VORSTER A G, ANDERSON R S, et al. Non-destructive aboveground biomass estimation of coniferous trees using terrestrial LiDAR[J]. Remote Sens Environ, 2017, 200: 31-42.DOI:10.1016/j.rse.2017.08.013.
[7]	ATKINS J W, BOHRER G, FAHEY R T, et al. Quantifying vegetation and canopy structural complexity from terrestrial Li DAR data using the forest package[J]. Methods Ecol Evol, 2018, 9(10): 2057-2066. DOI:10.1111/2041-210X.13061.
[8]	卢军, 刘宪钊, 孟维亮, 等. 基于地面激光点云数据的单木三维重建方法[J]. 南京林业大学学报(自然科学版), 2021, 45(6): 193-199.
	LU J, LIU X Z, MENG W L, et al. Methodology of individual tree 3D reconstruction based on terrestrial laser scanning point cloud data[J]. J Nanjing For Univ (Nat Sci Ed), 2021, 45(6): 193-199.
[9]	张颖, 贾炜玮. 基于地基激光雷达的落叶松人工林枝条因子提取和建模[J]. 应用生态学报, 2021, 32(7): 2505-2513.
	ZHANG Y, JIA W W. Extraction of branch factors and model construction for Larix plantation using terrestrial laser scanning (TLS)[J]. Chin J Appl Ecol, 2021, 32(7): 2505-2513. DOI:10.13287/j.1001-9332.202107.034.
[10]	范伟伟, 刘浩然, 徐永胜, 等. 基于地基激光雷达和手持式移动激光雷达的单木结构参数提取精度对比[J]. 中南林业科技大学学报, 2020, 40(8): 63-74.
	FAN W W, LIU H R, XU Y S, et al. Comparison of extraction precision of individual tree structure parameters based on terrestrial laser scanning and hand-held mobile laser scanning[J]. J Central South Univ For & Technol, 2020, 40(8): 63-74. DOI:10.14067/j.cnki.1673-923x.2020.08.008.
[11]	MÄKELÄ A. A carbon balance model of growth and self-pruning in trees based on structural relationships[J]. For Sc, 1997, 43(1): 7-24. DOI:10.1093/FORESTSCIENCE/43.1.7.
[12]	MEDHURST J L, BATTAGLIA M, CHERRY M L, et al. Allometric relationships for Eucalyptus nitens (Deane and Maiden) Maiden plantations[J]. Trees, 1999, 14(2): 91-101. DOI: 10.1007/PL00009756.
[13]	LEHTONEN A, MÄKIPÄÄ R, HEIKKINEN J, et al. Biomass expansion factors (BEFs) for Scots pine, Norway spruce and birch according to stand age for boreal forests[J]. For Ecol Manag, 2004, 188(1/2/3): 211-224. DOI: 10.1016/j.foreco.2003.07.008.
[14]	REPOLA J. Biomass equations for Scots pine and Norway spruce in Finland[J]. Silva Fenn, 2009, 43(4): 4-184.DOI: 10.14214/sf.184.
[15]	贾炜玮, 李凤日, 董利虎, 等. 基于相容性生物量模型的樟子松林碳密度与碳储量研究[J]. 北京林业大学学报, 2012, 34(1): 6-13.
	JIA W W, LI F R, DONG L H, et al. Carbon density and storage for Pinus sylvestris var. mongolica plantation based on compatible biomass models[J]. J Beijing For Univ, 2012, 34(1): 6-13. DOI:10.13332/j.1000-1522.2012.01.018.
[16]	曾伟生, 唐守正. 利用度量误差模型方法建立相容性立木生物量方程系统[J]. 林业科学研究, 2010, 23(6): 797-803.
	ZENG W S, TANG S Z. Using measurement error modeling method to establish compatible single-tree biomass equations system[J]. For Res, 2010, 23(6): 797-803. DOI:10.13275/j.cnki.lykxyj.2010.06.004.
[17]	许昊, 孙玉军, 王新杰, 等. 利用线性混合效应模型模拟杉木人工林枝条生物量[J]. 应用生态学报, 2015, 26(10): 2969-2977.
	XU H, SUN Y J, WANG X J, et al. Simulation of the branch biomass for Chinese fir plantation using the linear mixed effects model[J]. Chin J Appl Ecol, 2015, 26(10): 2969-2977. DOI:10.13287/j.1001-9332.20150921.026.
[18]	董灵波, 刘兆刚, 李凤日, 等. 基于线性混合模型的红松人工林一级枝条大小预测模拟[J]. 应用生态学报, 2013, 24(9): 2447-2456.
	DONG L B, LIU Z G, LI F R, et al. Primary branch size of Pinus koraiensis plantation: a prediction based on linear mixed effect model[J]. Chin J Appl Ecol, 2013, 24(9): 2447-2456. DOI:10.13287/j.1001-9332.2013.0490.
[19]	姜立春, 张锐, 李凤日. 基于线性混合模型的落叶松枝条长度和角度模型[J]. 林业科学, 2012, 48(5): 53-60.
	JIANG L C, ZHANG R, LI F R. Modeling branch length and branch angle with linear mixed effects for Dahurian larch[J]. Sci Silvae Sin, 2012, 48(5): 53-60. DOI:10.11707/j.1001-7488.20120508.
[20]	姜立春, 李凤日, 张锐. 基于线性混合模型的落叶松枝条基径模型[J]. 林业科学研究, 2012, 25(4): 464-469.
	JIANG L C, LI F R, ZHANG R. Modeling branch diameter with linear mixed effects for Dahurian larch[J]. For Res, 2012, 25(4): 464-469. DOI:10.13275/j.cnki.lykxyj.2012.04.013.
[21]	HAUGLIN M, ASTRUP R, GOBAKKEN T, et al. Estimating single-tree branch biomass of Norway spruce with terrestrial laser scanning using voxel-based and crown dimension features[J]. Scand J For Res, 2013, 28(5): 456-469. DOI:10.1080/02827581.2013.777772.
[22]	GONZALEZ DE TANAGO J, LAU A, BARTHOLOMEUS H, et al. Estimation of above-ground biomass of large tropical trees with terrestrial LiDAR[J]. Methods Ecol Evol, 2018, 9(2): 223-234. DOI:10.1111/2041-210x.12904.
[23]	LAU A, BENTLEY L P, MARTIUS C, et al. Quantifying branch architecture of tropical trees using terrestrial LiDAR and 3D modelling[J]. Trees, 2018, 32(5): 1219-1231. DOI:10.1007/s00468-018-1704-1.
[24]	陈世林. 激光雷达单木参数提取与生物量估算研究[D]. 北京: 北京林业大学, 2020.
	CHEN S L. Research on extraction of single tree parameters and biomass estimation based on LiDAR[D]. Beijing: Beijing Forestry University, 2020.
[25]	胡靖扬, 贾宝军, 林宽, 等. 辽东山区长白落叶松枝叶生物量模型建立与评估[J]. 西南林业大学学报, 2016, 36(5): 52-57,117.
	HU J Y, JIA B J, LIN K, et al. Establishment and evaluation of biomass models of branches and leaves for Larix olgensis plantation in montane region of eastern Liaoning Province[J]. J Southwest For Univ, 2016, 36(5):52-57,117.
[26]	ASHRAF M I, ZHAO Z Y, BOURQUE C P A, et al. Integrating biophysical controls in forest growth and yield predictions with artificial intelligence technology[J]. Can J For Res, 2013, 43(12): 1162-1171. DOI:10.1139/cjfr-2013-0090.
[27]	BREIMAN L. Random forests[J]. Mach Learn, 2001, 45(1):5-32.DOI:10.1023/A:1010933404324.
[28]	CUTLER D R, EDWARDS T C Jr, BEARD K H, et al. Random forests for classification in ecology[J]. Ecology, 2007, 88(11): 2783-2792. DOI: 10.1890/07-0539.1.
[29]	高若楠, 苏喜友, 谢阳生, 等. 基于随机森林的杉木适生性预测研究[J]. 北京林业大学学报, 2017, 39(12): 36-43.
	GAO R N, SU X Y, XIE Y S, et al. Prediction of adaptability of Cunninghamia lanceolata based on random forest[J]. J Beijing For Univ, 2017, 39(12): 36-43. DOI:10.13332/j.1000-1522.20170260.
[30]	欧强新, 李海奎, 雷相东, 等. 基于清查数据的福建省马尾松生物量转换和扩展因子估算差异解析:3种集成学习决策树模型的比较[J]. 应用生态学报, 2018, 29(6): 2007-2016.
	OU Q X, LI H K, LEI X D, et al. Difference analysis in estimating biomass conversion and expansion factors of Masson pine in Fujian Province, China based on national forest inventory data: a comparison of three decision tree models of ensemble learning[J]. Chin J Appl Ecol, 2018, 29(6): 2007-2016. DOI:10.13287/j.1001-9332.201806.019.
[31]	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.
	OU Q X, LEI X D, SHEN C C, et al. Individual tree DBH growth prediction of larch-spruce-fir mixed forests based on random forest algorithm[J]. J Beijing For Univ, 2019, 41(9): 9-19. DOI:10.13332/j.1000-1522.20180266.
[32]	卢婧, 冯仲科. 运用随机森林模型对北京市林分蓄积生长量的预测[J]. 东北林业大学学报, 2020, 48(5): 7-11.
	LU J, FENG Z K. Forecast of stand volume growth in Beijing by using random forest[J]. J Northeast For Univ, 2020, 48(5): 7-11. DOI:10.13759/j.cnki.dlxb.2020.05.002.

数据 data	变量 variable		训练集train
数据 data	变量 variable		平均值 mean		最大值 max	最小值 min	标准差 SD	平均值 mean		最大值 max	最小值 min	标准差 SD
TLS数据 TLS data		单木因子tree factor		n=20					n=6
	树高/m(H)		18.69		25.82	13.12	3.85	19.74		23.05	14.05	3.56
	胸径/cm(D_BH)		19.22		31.10	9.06	5.81	18.31		26.35	12.32	5.53
		枝条因子branch factor		n=601					n=132
	枝长/cm(L_BL)		217.40		525.00	15.80	91.28	198.71		530.59	17.87	93.54
	弦长/cm(L_BCL)		201.20		493.00	14.80	84.21	186.19		500.30	15.03	85.15
	弓高/cm(H_BAH)		26.00		80.00	0.00	12.94	19.97		78.43	1.00	14.80
	基径/mm(d_B)		26.60		69.49	11.10	13.15	28.10		61.56	12.00	13.02
	枝条基部断面积/cm²(S_BAB)		6.81		37.93	1.04	8.05	7.52		29.76	1.14	7.14
	着枝角度/(°)(A_B)		60.00		150.00	15.00	16.02	53.00		104.00	19.00	15.00
	相对着枝深度(d_RDINC)		0.61		1.00	0.10	0.20	0.62		1.00	0.10	0.20
实测数据 real data		单木因子tree factor		n=20					n=6
	树高/m(H)		18.75		26.00	13.17	3.92	19.60		23.22	13.98	3.26
	胸径/cm(D_BH)		19.40		31.00	9.00	5.49	18.58		26.12	12.08	5.13
		枝条因子branch factor		n=601					n=132
	枝长/cm(L_BL)		210.00		532.00	10.00	99.51	182.00		515.00	13.00	92.18
	弦长/cm(L_BCL)		200.00		518.00	8	82.00	180.00		496.00	10.00	83.00
	弓高/cm(H_BAH)		23.00		70.00	0.00	12.00	19.00		81.00	1.00	15.00
	基径/mm(d_B)		27.32		70.12	6.28	14.55	29.48		65.74	8.51	13.74
	枝条基部断面积/cm²(S_BAB)		7.03		38.09	0.85	8.88	7.73		31.29	0.92	7.85
	着枝角度/(°)(A_B)		56.00		135.00	10.00	18.00	59.00		115.00	16.00	17.00
	相对着枝深度(d_RDINC)		0.62		1.00	0.14	0.21	0.62		1.00	0.11	0.20
	枝条生物量/g(W_b)		416.93		4 303.32	3.26	539.97	460.34		3 075.59	4.71	572.88

数据 data	参数 parameter	预测值 estimate	标准误 SE	t	P	拟合优度 goodness-of-fit statistic
数据 data	参数 parameter	预测值 estimate	标准误 SE	t	P	R²	RMSE/g	MAE/g	RMAE/%	F_p/%
实测数据 real data	a₀	0.069 77	0.025 77	9.951	<0.000 1
	a₁	0.720 14	0.034 74	15.184	<0.000 1	0.849 6	171.79	97.66	39.56	95.71
	a₂	1.350 26	0.084 06	12.975	<0.000 1
TLS数据 TLS data	a₀	0.049 56	0.017 01	12.914	<0.000 1
	a₁	0.788 71	0.033 27	23.708	<0.000 1	0.880 8	156.93	90.07	35.66	96.84
	a₂	1.342 01	0.069 31	19.363	<0.000 1

模型 model	随机效应参数 random effect parameter	参数个数 number of parameter	R²	赤池信息准则 AIC	贝叶斯准则 BIC	对数似然值 Log Likelihood	似然比 LRT	P
12	无	3	0.879	8 455.562	8 509.378	-4 217.56
12.1	a₀	5	0.887	8 433.588	8 455.825	-4 211.79
12.2	a₁	5	0.904	8 364.290	8 386.527	-4 177.15	66.044	<0.000 1
12.3	a₂	5	0.904	8 367.544	8 389.780	-4 178.77
12.4	a₀、a₁	7	0.905	8 437.588	8 468.719	-4 211.79
12.5	a₀、a₂	7	0.904	8 371.544	8 402.675	-4 178.77
12.6	a₁、a₂	7	0.913	8 338.741	8 369.872	-4 162.37	29.549	<0.000 1
12.7	a₀、a₁、a₂	10	不收敛

类型 type	矩阵 matrix	参数个数 parameters number	赤池信息准则 AIC	贝叶斯准则 BIC	对数似然值 Log Likelihood	似然比 LRT	P
方差-协方差 variance-covariance	复合对称矩阵CS	6	不收敛
	对角矩阵UN(1)	6	8 364.832	8 391.516	-4 176.42
	广义正定矩阵	7	8 338.741	8 369.872	-4 162.37	28.090 7	<0.000 1
自相关 autocorrelation	复合对称矩阵CS	8	不收敛
	一阶自回归矩阵AR(1)	8	8 340.194	8 375.773	-4 162.10
	一阶自回归与移动平均矩阵ARMA(1,1)	9	8 342.133	8 382.159	-4 162.07	0.060 7	0.805 4

模型model	数据集data	R²	RMSE/g	MAE/g	RMAE/%	F_p/%
基础模型 base model	训练集train	0.879	162.14	93.51	38.13	96.51
	测试集test	0.880	156.93	90.07	35.66	96.84
混合模型 mixed model	训练集train	0.913	150.49	83.65	31.58	97.02
	测试集test	0.911	152.75	86.86	32.59	96.99
随机森林模型 random forest model	训练集train	0.930	130.23	67.23	24.30	97.83
	测试集test	0.923	135.59	76.33	28.52	97.65

基于TLS辅助的长白落叶松一级枝条生物量模型构建

Constructing a biomass model of Larix olgensis primary branches based on TLS

RichHTML

PDF

可视化

摘要/Abstract

引用本文

使用本文

图/表 11

参考文献 32

相关文章 15

编辑推荐

Metrics

本文评价

作者

读者

审稿

[1]	赵凌霄, 李智扬, 屈磊磊. 基于EMD和CatBoost算法的改进时间序列模型——以大连市PM_2.5预测为例[J]. 南京林业大学学报（自然科学版）, 2024, 48(3): 268-274.
[2]	周友锋, 谢秉楼, 李明诗. 基于随机森林协同克里金法的区域森林地上生物量制图——以粤北森林为例[J]. 南京林业大学学报（自然科学版）, 2024, 48(1): 169-178.
[3]	路文燕, 董灵波, 田园, 汪莎杉, 曲宣怡, 魏巍, 刘兆刚. 基于树种组成的大兴安岭天然林主要树种树高-胸径曲线研究[J]. 南京林业大学学报（自然科学版）, 2023, 47(4): 157-165.
[4]	宋磊, 金星姬, PUKKALA Timo, 李凤日. 长白落叶松人工林多目标经营模式研究[J]. 南京林业大学学报（自然科学版）, 2023, 47(2): 150-158.
[5]	王帆, 贾炜玮, 唐依人, 李丹丹. 基于TLS的红松树冠半径提取及其外轮廓模型构建[J]. 南京林业大学学报（自然科学版）, 2023, 47(1): 13-22.
[6]	孙铭辰, 姜立春. 基于机器学习算法的樟子松立木材积预测[J]. 南京林业大学学报（自然科学版）, 2023, 47(1): 31-37.
[7]	王甜, 王雪峰, 刘嘉政. 基于RFE_RF算法的幼龄沉香叶片含水率预估模型[J]. 南京林业大学学报（自然科学版）, 2022, 46(4): 177-184.
[8]	聂璐毅, 董利虎, 李凤日, 苗铮, 谢龙飞. 基于两水平非线性混合效应模型的长白落叶松削度方程构建[J]. 南京林业大学学报（自然科学版）, 2022, 46(3): 194-202.
[9]	吴炅, 蒋馥根, 彭邵锋, 马开森, 陈松, 孙华. 结合树冠体积的油茶树高与产量估测研究[J]. 南京林业大学学报（自然科学版）, 2022, 46(2): 53-62.
[10]	卢军, 刘宪钊, 孟维亮, 李红军. 基于地面激光点云数据的单木三维重建方法[J]. 南京林业大学学报（自然科学版）, 2021, 45(6): 193-199.
[11]	花伟成, 田佳榕, 孙心雨, 徐雁南. 基于TLS数据的杨树削度方程建立及材积估算[J]. 南京林业大学学报（自然科学版）, 2021, 45(4): 41-48.
[12]	周泽宇, 杨绕华, 张玉珍, 黄选瑞, 张志东, 王冬至, 李大勇. 华北落叶松人工林直径分布预测模型构建[J]. 南京林业大学学报（自然科学版）, 2020, 44(2): 117-124.
[13]	纪烨琳, 苏喜友, 于治军. 基于随机森林模型的美国白蛾在中国的潜在生境预测[J]. 南京林业大学学报（自然科学版）, 2019, 43(6): 121-128.
[14]	贾炜玮, 梁玉钊, 李凤日. 落叶松人工林树皮厚度预测模型[J]. 南京林业大学学报（自然科学版）, 2019, 43(6): 97-104.
[15]	赵颖慧, 张大力, 甄贞. 基于非参数分类算法和多源遥感数据的单木树种分类[J]. 南京林业大学学报（自然科学版）, 2019, 43(5): 103-112.