Standing volume prediction of Pinus sylvestris var. mongolica based on machine learning algorithm

doi:10.12302/j.issn.1000-2006.202104014

JOURNAL OF NANJING FORESTRY UNIVERSITY ›› 2023, Vol. 47 ›› Issue (1): 31-37.doi: 10.12302/j.issn.1000-2006.202104014

Special Issue: 智慧林业之森林参数遥感估测

Previous Articles Next Articles

Standing volume prediction of Pinus sylvestris var. mongolica based on machine learning algorithm

SUN Mingchen(), JIANG Lichun()

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

Received:2021-04-12 Accepted:2021-08-04 Online:2023-01-30 Published:2023-02-01
Contact: JIANG Lichun E-mail:178059314@qq.com;jlichun@nefu.edu.cn

Abstract

Abstract:

【Objective】 Using various, nonlinear machine learning algorithms, different volume models were constructed and compared to provide a theoretical basis for the accurate prediction of the volume of Pinus sylvestris var. mongolica.【Method】 A total of 184 felled Pinus sylvestris var. mongolica trees in the Tuqiang Forestry Bureau of the Greater Khingan Mountains were used to establish a nonlinear binary volume model (NLR). Three optimal machine learning algorithms were obtained using the K-fold cross test and OOB error test, including back propagation neural network (BP), ε-support vector regression (ε-SVR), and random forest (RF). An optimal volume model was obtained by comparing and analyzing the differences between the different models. 【Result】 The results showed that the machine learning algorithm was superior to the traditional binary volume model in the fitting and prediction of standing volume, and the specific order was RF > BP > ε-SVR > NLR. Compared with the traditional model, the R² of RF increased by 2.00%; the RMSE, RMSE% and MAE decreased by 22.95%, 22.93% and 36.34%, respectively; and the absolute value of MRB was lower than the real value, which proved the superiority of RF in volume prediction. 【Conclusion】 Machine learning algorithms can effectively improve the accuracy at which standing volume can be predicted, providing a new solution for the accurate investigation and management of forest resources.

Key words: Pinus sylvestris var. mongolica, binary volume model, BP neural network, ε-support vector regression(ε-SVR), random forest(RF)

CLC Number:

S791.253

SUN Mingchen, JIANG Lichun. Standing volume prediction of Pinus sylvestris var. mongolica based on machine learning algorithm[J]. JOURNAL OF NANJING FORESTRY UNIVERSITY, 2023, 47(1): 31-37.

Figures/Tables 8

Table 1

Table 2

Fig.1

Table 3

Fig.2

Table 4

Fig.3

Table 5

References 29

[1]	MAO P, QIN L J, HAO M Y, et al. An improved approach to estimate above-ground volume and biomass of desert shrub communities based on UAV RGB images[J]. Ecol Indic, 2021, 125: 107494. DOI:10.1016/j.ecolind.2021.107494. doi: 10.1016/j.ecolind.2021.107494
[2]	MUUKKONEN P. Generalized allometric volume and biomass equations for some tree species in Europe[J]. Eur J Forest Res, 2007, 126(2): 157-166. DOI:10.1007/s10342-007-0168-4. doi: 10.1007/s10342-007-0168-4
[3]	廖祖辉. 福建桉树人工林材积表和蓄积量表编制的研究[J]. 福建林业科技, 2005, 32(2):17-20.
	LIAO Z H. Studies of the volume table and stocking table compilations of Eucalyptus plantations[J]. J Fujian For Sci Technol, 2005, 32(2): 17-20. DOI:10.13428/j.cnki.fjlk.2005.02.005. doi: 10.13428/j.cnki.fjlk.2005.02.005
[4]	吕勇, 刘辉, 王才喜. 杉木林分蓄积量不同测定方法的比较[J]. 中南林学院学报, 2001, 21(4): 50-53.
	LV Y, LÜ H, WANG C X. Comparison of the different measurement methods of stand volume[J]. J Central South For Univ, 2001, 21(4): 50-53. DOI:10.3969/j.issn.1673-923X.2001.04.006. doi: 10.3969/j.issn.1673-923X.2001.04.006
[5]	WIANT H V JR, WOOD G B, WILLIAMS M. Comparison of three modern methods for estmating volume of sample trees using one or two diameter measurements[J]. For Ecol Manag, 1996, 83(1/2): 13-16. DOI:10.1016/0378-1127(96)03708-5. doi: 10.1016/0378-1127(96)03708-5
[6]	OZCELIK R, WIANT H, BROOKS J. Accuracy using xylometry of log volume estimates for two tree species in Turkey[J]. Scan J Forest Res, 2008, 23(3): 272-277. DOI: 10.1080/02827580801995323. doi: 10.1080/02827580801995323
[7]	曾伟生. 杉木相容性立木材积表系列模型研建[J]. 林业科学研究, 2014, 27(1): 6-10.
	ZENG W S. Establishment of compatible tree volume equation systems of Chinese fir[J]. For Res, 2014, 27(1): 6-10. DOI:10.13275/j.cnki.lykxyj.2014.01.002. doi: 10.13275/j.cnki.lykxyj.2014.01.002
[8]	许晴, 李晓莎, 许中旗, 等. 塞罕坝地区樟子松立木材积表研究[J]. 林业资源管理, 2017(1): 57-62.
	XU Q, LI X S, XU Z Q, et al. Study on the volume table of scotch pine in Saihanba aera[J]. For Resour Manag, 2017(1): 57-62. DOI:10.13466/j.cnki.lyzygl.2017.01.011. doi: 10.13466/j.cnki.lyzygl.2017.01.011
[9]	雷相东. 机器学习算法在森林生长收获预估中的应用[J]. 北京林业大学学报, 2019, 41(12): 23-36.
	LEI X D. Applications of machine learning algorithms in forest growth and yield prediction[J]. J Beijing For Univ, 2019, 41(12): 23-36. DOI:10.12171/j.1000-1522.20190356. doi: 10.12171/j.1000-1522.20190356
[10]	CUTLER D R, EDWARDS T C J, BEARD K H, et al. Random forests for classification in ecology[J]. Ecology, 2007, 88(11): 2783-2792. DOI:10.1890/07-0539.1. doi: 10.1890/07-0539.1 pmid: 18051647
[11]	GUAN B T, GERTNER G. Modeling red pine tree survival with an artificial neural network[J]. For Sci, 1991, 37(5): 1429-1440. DOI:10.1093/forestscience/37.5.1429. doi: 10.1093/forestscience/37.5.1429
[12]	MARIA J D. Artificial neural networks as an alternative tool in pine bark volume estimation[J]. Comput Electron Agric, 2005, 48(3): 235-244. DOI:10.1016/j.compag.2005.04.002. doi: 10.1016/j.compag.2005.04.002
[13]	MARIA J D, ÖZÇELIK R, YAVUZ H. Tree-bark volume prediction via machine learning: a case study based on black alder’s tree-bark production[J]. Comput Electron Agric, 2018, 151: 431-440. DOI:10.1016/j.compag.2018.06.039. doi: 10.1016/j.compag.2018.06.039
[14]	COLIN J G, JONGHO I. Forest biomass estimation from airborne LiDAR data using machine learning approaches[J]. Remote Sens Environ, 2012, 125: 80-91. DOI: 10.1016/j.rse.2012.07.006. doi: 10.1016/j.rse.2012.07.006
[15]	MARIA J D, MILIOS E. Modelling total volume of dominant pine trees in reforestations via multivariate analysis and artificial neural network models[J]. Biosyst Eng, 2010, 105(3): 306-315. DOI: 10.1016/j.biosystemseng.2009.11.010. doi: 10.1016/j.biosystemseng.2009.11.010
[16]	ÖZCELIK R, MARIA J D, BROOKS J R, et al. Estimating tree bole volume using artificial neural network models for four species in Turkey[J]. J Environ Manag, 2010, 91(3): 742-753. DOI: 10.1016/j.jenvman.2009.10.002. doi: 10.1016/j.jenvman.2009.10.002
[17]	WU J W, YAO W, CHOI S, et al. A comparative study of predicting DBH and stem volume of individual trees in a temperate forest using airborne waveform LiDAR[J]. IEEE Geosci Remote Sens Lett, 2015, 12(11): 2267-2271. DOI:10.1109/LGRS.2015.2466464. doi: 10.1109/LGRS.2015.2466464
[18]	MUSHAR S H, AHMAD S S, KASMIN F, et al. Machine learning approach for estimating tree volume[J]. J Phys: Conf Ser, 2020, 1502(1): 012039. DOI:10.1088/1742-6596/1502/1/012039. doi: 10.1088/1742-6596/1502/1/012039
[19]	BHERING L L, CRUZ C D, DE AZEVEDO P L, et al. Application of neural networks to predict volume in eucalyptus[J]. Crop Breed Appl Biotechnol, 2015, 15(3): 125-131. DOI:10.1590/1984-70332015v15n3a23. doi: 10.1590/1984-70332015v15n3a23
[20]	靳晓东, 姜立春. 基于树干不同形率的樟子松立木材积方程研建[J]. 北京林业大学学报, 2020, 42(3):78-86.
	JIN X D, JIANG L C. Equation construction on standing tree volume of Pinus sylvestris var. mongolica based on different form quotients of trunk[J]. J Beijing For Univ, 2020, 42(3):78-86. DOI:10.12171/j.1000-1522.20190047. doi: 10.12171/j.1000-1522.20190047
[21]	张明铁. 单株立木材积测定方法的研究[J]. 林业资源管理, 2004(1):24-26.
	ZHANG M T. Study on volume measurement of single trees[J]. For Resour Manag, 2004(1): 24-26. DOI:10.13466/j.cnki.lyzygl.2004.01.005. doi: 10.13466/j.cnki.lyzygl.2004.01.005
[22]	RUMELHART D E, HINTON G E, WILLIAMS R J. Learning internal representations by error propagation[J]. Read Cognit Sci, 1988, 323(6088):399-421. DOI:10.1016/B978-1-4832-1446-7.50035-2. doi: 10.1016/B978-1-4832-1446-7.50035-2
[23]	王轶夫, 孙玉军, 郭孝玉. 基于BP神经网络的马尾松立木生物量模型研究[J]. 北京林业大学学报, 2013, 35(2): 17-21.
	WANG Y F, SUN Y J, GUO X Y. Single-tree biomass modeling of Pinus massoniana based on BP neural network[J]. J Beijing For Univ, 2013, 35(2): 17-21. DOI: 10.13332/j.1000-1522.2013.02.018. doi: 10.13332/j.1000-1522.2013.02.018
[24]	徐晓明. SVM参数寻优及其在分类中的应用[D]. 大连: 大连海事大学, 2014.
	XU X M. SVM parameter optimization and its application in the classification[D]. Dalian: Dalian Maritime University, 2014.
[25]	曹正凤. 随机森林算法优化研究[D]. 北京: 首都经济贸易大学, 2014.
	CAO Z F. Study on optimization of random forests algorithm[D]. Beijing: Capital University of Economics and Business, 2014.
[26]	BREIMAN L. Bagging predictors[J]. Mach Learn, 1996, 24(2): 123-140. DOI:10.1007/bf00058655. doi: 10.1007/bf00058655
[27]	DING S, CHANG X H, WU Q H. A study on approximation performances of improved BP neural networks based on LM algorithms[J]. Appl Mech Mater, 2013, 411/412/413/414: 1935-1938. DOI:10.4028/www.scientific.net/amm.411-414.1935. doi: 10.4028/www.scientific.net/amm.411-414.1935
[28]	杜军岗, 魏汝祥, 刘宝平. 基于PSO优化LS-SVM的小样本非线性协整检验与建模研究[J]. 系统工程理论与实践, 2014, 34(9): 2322-2331. doi: 10.12011/1000-6788(2014)9-2322
	DU J G, WEI R X, LIU B P. Nonlinear cointegration test and error correction modeling based on LS-SVM optimized by PSO in small sample[J]. Syst Eng-theory Pract, 2014, 34(9): 2322-2331. DOI: CNKI:SUN:XTLL.0.2014-09-015. doi: CNKI:SUN:XTLL.0.2014-09-015.
[29]	HAJAR A S, AZIZAH A N, HASZLINNA M N. Adoption of machine learning techniques in software effort estimation: an overview[J]. IOP Conf Ser: Mater Sci Eng, 2019, 551(1): 012074. DOI:10.1088/1757-899x/551/1/012074.

Metrics

Comments

www.nldxb.njfu.edu.cn

Edited ＆ Published by Editorial Department of Nanjing Forestry University(Natural Sciences Edition)
Address： No.159 Longpan Road,Nanjing 210037 Jiangsu,P.R.China
E-mail ：xuebao@njfu.edu.cn , xuebao@njfu.com.cn
Telephone +86-25-85428247,85427076
Distributed by China International Book Trading Corporation P.O. Box 399, Beijing ,P.R. China

样本 sample	统计量 statistics	胸径/cm DBH	树高/m tree height	材积/m³ volume
训练样本 train sample	最大值max	50.70	25.70	2.38
	最小值min	6.30	5.80	0.01
	平均值average	27.95	18.28	0.71
	标准差SD	12.12	4.33	0.60
测试样本 test sample	最大值max	50.50	25.60	2.37
	最小值min	7.60	6.30	0.02
	平均值average	28.87	18.85	0.75
	标准差SD	12.16	4.26	0.61

类型 type	算法 algorithm	R²	RMSE	RMSE%	MAE
梯度下降算法 gradient descent algorithms	GDX	0.933 3	0.139 8	19.703 1	0.108 1
	GDA	0.920 4	0.159 5	23.140 5	0.120 8
	RP	0.954 0	0.116 8	16.255 9	0.086 1
共轭梯度算法 conjugate gradient algorithms	CGB	0.954 8	0.110 5	16.128 4	0.076 8
	CGF	0.958 0	0.116 1	16.575 5	0.083 5
	CGP	0.950 2	0.126 6	18.055 4	0.089 0
	SCG	0.947 7	0.119 1	16.918 8	0.090 8
拟牛顿及其他优化算法 quasi Newton and other optimization algorithms	BFG	0.946 6	0.116 6	16.525 3	0.087 5
	OSS	0.932 7	0.132 3	19.482 9	0.098 3
	LM	0.960 8	0.096 0	13.319 9	0.065 3

核函数 kernel function	C	核参数 gamma	R²	RMSE	RMSE%	MAE
线性核函数 line	0.117 0	1.697 4	0.874 9	0.212 6	30.120 5	0.132 0
多项式函数 polynomial	0.122 7	9.854 5	0.954 9	0.127 7	18.083 9	0.079 2
径向基核函数 RBF	12.861 1	3.100 1	0.972 1	0.100 3	14.206 7	0.054 1

模型 model	数据集 dataset	R²	RMSE	RMSE%	MAE	MRB
NLR	训练train	0.963 0	0.115 6	16.380 8	0.076 8	-5.699 5
	测试test	0.953 1	0.130 7	17.503 5	0.091 9	-4.900 3
BP	训练train	0.976 0	0.093 1	13.191 5	0.056 1	-2.090 4
	测试test	0.962 8	0.116 4	15.584 4	0.075 1	-1.636 3
ε-SVR	训练train	0.972 2	0.100 3	14.206 7	0.054 1	-2.594 5
	测试test	0.960 4	0.120 1	16.077 6	0.075 3	1.283 5
RF	训练train	0.996 0	0.037 8	5.358 5	0.021 9	-1.550 8
	测试test	0.972 2	0.100 7	13.489 4	0.058 5	0.169 0

模型 model	数据集 dataset	z值 z value	P	结论 conclusion
NLR	训练train	0.033 3	0.973 5	不存在明显差异
	测试test	0.147 8	0.882 5	不存在明显差异
BP	训练train	0.031 3	0.975 1	不存在明显差异
	测试test	-0.027 3	0.978 2	不存在明显差异
ε-SVR	训练train	-0.222 7	0.823 8	不存在明显差异
	测试test	-0.120 1	0.904 4	不存在明显差异
RF	训练train	0.021 7	0.982 7	不存在明显差异
	测试test	0.085 1	0.932 2	不存在明显差异

Standing volume prediction of Pinus sylvestris var. mongolica based on machine learning algorithm

RichHTML

PDF

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 8

References 29

Related Articles 7

Recommended Articles

Metrics

Comments

Author

Reader

Reviewer

[1]	XU Haishun, QIAN Chen, QIN Xue. Evaluating the social media attributes of urban blue-green open space using a back propagation neural network [J]. JOURNAL OF NANJING FORESTRY UNIVERSITY, 2024, 48(6): 193-200.
[2]	WU Jiong, JIANG Fugen, PENG Shaofeng, MA Kaisen, CHEN Song, SUN Hua. Estimating the tree height and yield of Camellia oleifera by combining crown volume [J]. JOURNAL OF NANJING FORESTRY UNIVERSITY, 2022, 46(2): 53-62.
[3]	FAN Jiahui, ZHANG Yali, LI Mingshi. Comparing four methods for extracting impervious surfaces using spectral information in synergy with spatial heterogeneity of remotely sensed imagery [J]. JOURNAL OF NANJING FORESTRY UNIVERSITY, 2021, 45(1): 212-218.
[4]	SONG Laiping, LIU Bofei, WANG Yuhua, GAO Jingze. Age-dependent-tree-ring growth responses of Pinus sylvestris var. mongolica to climate in Hulunbuir sandy land [J]. JOURNAL OF NANJING FORESTRY UNIVERSITY, 2020, 44(2): 159-164.
[5]	DU Xuehui, MENG Chun, LIU Meishuang. Research on feature selection based on single feature classification accuracy [J]. JOURNAL OF NANJING FORESTRY UNIVERSITY, 2019, 43(04): 109-116.
[6]	SHEN Jianbo, LEI Xiangdong, LI Yutang, LAN Ying. Prediction mean height for Larix olgensis plantation based on Bayesian-regularization BP neural network [J]. JOURNAL OF NANJING FORESTRY UNIVERSITY, 2018, 42(02): 147-154.
[7]	TONG Da, ZHANG Yan,SONG Kuiyan. Comparative to determine the demarcation between juvenile and mature period wood of Juglans mandshurica Maxim. Plantation [J]. JOURNAL OF NANJING FORESTRY UNIVERSITY, 2013, 37(03): 103-109.