Breast Diameter-height Models of Eucalyptus urophylla×E. grandis Mixed Plantations Based on Convolutional Neural Network
Author:
  • Article
  • | |
  • Metrics
  • |
  • Reference [28]
  • |
  • Related [2]
  • | | |
  • Comments
    Abstract:

    The study aimed to predict the tree height of large-diameter mixed plantations of Eucalyptus urophylla×E. grandis using convolutional neural networks (CNN) and provide a theoretical basis for forest resource monitoring and evaluation. The research focused on 24 plots of mixed plantations of Eucalyptus urophylla×E. grandis intercropped with Mytilaria laosensis, Castanopsis hystrix, Manglietia glauca, and Michelia macclure at the Nanning Eucalyptus Field Station. By combining the information of dominant tree species (groups) in the stand and using statistical inference based on sample information and prior information of CNN, suitable model structures for each tree species (group) were obtained through training. Using basically consistent modeling data, traditional tree height equations were solved, and the modeling plots that did not participate in the modeling were used as a validation set for comparative analysis based on six classical models of nonlinear models or nonlinear mixed effects and three CNN models based on activation functions. The results showed that the RMSE (root-mean-square error) values of Näslund, Curtis, Logistic, Weibull, Gomperz, and Korf traditional models and the L-M model (Model I) ranged from 2.5 to 5.6. The CNN model with ReLU activation function (Model II) had a RMSE of 2.304 2 and a R2 of 0.814 9, while the CNN model with Logistic activation function (Model III) had a R2 of 0.958 8. The activation function models of CNN do not rely on empirical model selection. Compared with traditional empirical models, the CNN model of tree height-diameter at breast height (DBH) based on the Logistic equation has a higher determination coefficient and lower root mean square error, with generally higher fitting accuracy. It can better fit the growth patterns of different tree species, improve the accuracy and stability of predictions, and optimize the ecological and economic benefits of forestry.

    Reference
    [1] WANG M L. Effects of Eucalyptus tannin on soil respiration and microbial community structure [D]. Nanning: Guangxi University, 2022. [王妙玲. 桉树单宁对土壤呼吸及微生物群落结构的影响[D]. 南宁: 广西大学, 2022. doi: 10.27034/d.cnki.ggxiu.2022.002451.]
    [2] LIU T, XIE Y J. Studies on the causes of rapid development of Eucaly-ptus plantations in China [J]. Eucalypt Sci Technol, 2020, 37(4): 38-47. [刘涛, 谢耀坚. 中国桉树人工林快速发展动因分析与展望[J]. 桉树科技, 2020, 37(4): 38-47. doi:10.13987/j.cnki.askj.2020.04.07.]
    [3] Forrester D I, Theiveyanathan S, Collopy J J, et al. Enhanced water use efficiency in a mixed Eucalyptus globulus and Acacia mearnsii plantation [J]. For Ecol Manag, 2010, 259(9): 1761-1770. doi: 10.1016/j.foreco.2009.07.035.
    [4] NIU S Y, LIU P J, LEI X D, et al. Average tree height-diameter models of Cunninghamia lanceolata in China based on continuous forest inventory plot data [J]. For Res, 2023, 36(1): 117-123. [牛思圆, 刘鹏举, 雷相东, 等. 基于连清样地数据的全国杉木人工林平均木树高-胸径模型[J]. 林业科学研究, 2023, 36(1): 117-123. doi: 10.12403/j. 1001-1498.20220322.]
    [5] LIANG R T, SUN Y J, LI Y. Comparison of deep learning and trade-tional models to simulate the height-DBH relationship of Chinese fir [J]. For Res, 2021, 34(6): 65-72. [梁瑞婷, 孙玉军, 李芸. 深度学习和传统方法模拟杉木树高-胸径模型比较[J]. 林业科学研究, 2021, 34(6): 65-72. doi: 10.13275/j.cnki.lykxyj.2021.06.008.]
    [6] CHEN R B, ZHU N N, MEI S H, et al. Individual diameter-height and crown-height prediction models for Pinus massoniana and Eucalyptus in Guangxi [J]. Geom Spat Inf Technol, 2022, 45(7): 70-73. [陈瑞波, 朱宁宁, 梅树红, 等. 广西桉树和马尾松单木胸径/冠幅-树高模型构建[J]. 测绘与空间地理信息, 2022, 45(7): 70-73. doi: 10.3969/j. issn.1672-5867.2022.07.020.]
    [7] ZHENG Y P, LI G Y, LI Y. Survey of application of deep learning in image recognition [J]. Comput Eng Appl, 2019, 55(12): 20-36. [郑远攀, 李广阳, 李晔. 深度学习在图像识别中的应用研究综[J]. 计算机工程与应用, 2019, 55(12): 20-36. doi: 10.3778/j.issn.1002-8331.1903-0031.]
    [8] QIAN H M, MAO Q L, CHEN S, et al. TCSNGAN: Image generation model based on transformer and CNN with spectral normalization [J]. Appl Res Comput, 2024, 41(4): 1221-1227. [钱惠敏, 毛邱凌, 陈实, 等. TCSNGAN: 基于Transformer和谱归一化CNN的图像生成模型[J]. 计算机应用研究, 2024, 41(4): 1221-1227. doi: 10.19734/j.issn. 1001-3695.2023.07.0357.]
    [9] ZHANG L Y, SUN H H, SHI B B. Review of node classification methods based on graph convolutional neural networks [J]. Comput Sci, 2024, 51(4): 95-105. [张丽英, 孙海航, 石兵波. 基于图卷积神经网络的节点分类方法研究综述[J]. 计算机科学, 2024, 51(4): 95-105. doi: 10.11896/jsjkx.230600071.]
    [10] CEN J Y, LI Q Y, ZENG W S et al. Curve models of relative tree height for Eucalyptus plantations in Guangxi [J]. J CS Univ For Technol, 2007, 27(4): 23-27. [岑巨延, 李巧玉, 曾伟生, 等. 广西速丰桉人工林相对树高曲线模型研究[J]. 中南林业科技大学学报, 2007, 27(4): 23-27. doi: 10.3969/j.issn.1673-923X.2007.04.005.]
    [11] WANG M L, TANG S Z. Research on universal height diameter curves [J]. For Res, 1997, 10(3): 259-264. [王明亮, 唐守正. 标准树高曲线的研制[J]. 林业科学研究, 1997, 10(3): 259-264.]
    [12] Salas-Eljatib C, Mehtätalo L, Gregoire T G. et al. Growth equations in forest research: Mathematical basis and model similarities [J]. Curr For Rep, 2021, 7(4): 230-244. doi: 10.1007/s40725-021-00145-8.
    [13] Huang S M, Price D, Titus S J. Development of ecoregion-based height-diameter models for white spruce in boreal forests. [J]. For Ecol Manag, 2000, 129(1/2/3): 125-141. doi: 10.1016/S0378-1127(99)00151-6.
    [14] Pearl R, Reed L J. On the rate of growth of the population of the United States since 1790 and its mathematical representation [J]. Proc Nat Acad Sci USA, 1920, 6(6): 275-288. doi: 10.1073/pnas.6.6.275.
    [15] Teimouri M, Hoseini S M, Nadarajah S. Comparison of estima-tion methods for the Weibull distribution [J]. Statistics, 2013, 47(1): 93-109. doi: 10.1080/02331888.2011.559657.
    [16] Nzei L C, Eghwerido J T, Ekhosuehi N. Topp-leone gompertz distribution: Properties and applications [J]. J Data Sci, 2020, 18(4): 782-794. doi:10.6339/JDS.202010_18(4)_0012.
    [17] Pretzsch H, Steckel M, Heym M. et al. Stand growth and structure of mixed-species and monospecific stands of Scots pine (Pinus sylvestris L.) and oak [Q. robur L., Quercus petraea (Matt.) Liebl.) analysed along a productivity gradient through Europe [J]. Eur J For Res, 2020, 139(3): 349-367. doi: 10.1007/s10342-019-01233-y.
    [18] TIAN X M, ZHANG X L. Estimation of forest aboveground biomass by remote sensing [J]. J Beijing For Univ, 2021, 43(8): 137-148. [田晓敏, 张晓丽. 森林地上生物量遥感估算方法[J]. 北京林业大学学报, 2021, 43(8): 137-148. doi:10.12171/j.1000-1522.20200166.]
    [19] MOU G X, TAN W, CHAI Z Z, et al. Diameter-height model for Pinus massoniana plantations based on BP neural network [J]. J Zhejiang A&F Univ, 2020, 37(4): 752-760. [卯光宪, 谭伟, 柴宗政, 等. 基于BP神经网络的马尾松人工林胸径-树高模型预[J]. 浙江农林大学学报, 2020, 37(4): 752-760. doi: 10.11833/j.issn.2095-0756.20190486.]
    [20] LIU X, WANG H Y, LEI X D, et al. Generalized height-diameter model for natural mixed spruce-fir coniferous and broadleaf forests based on BP neural network [J]. For Res, 2017, 30(3): 368-375. [刘鑫, 王海燕, 雷相东等. 基于BP神经网络的天然云冷杉针阔混交林标准树高-胸径模型[J]. 林业科学研究, 2017, 30(3): 368-375. doi: 10. 13275/j.cnki.lykxyj.2017.03.002. ]
    [21] CHEN J Q, ZHAO P X, QI N, et al. Establishment of tree height model of Pinus tabuliformis plantation based on BP neural network [J]. J NE For Univ, 2020, 35(1): 212-217. [陈佳琦, 赵鹏祥, 祁宁, 等. 基于BP神经网络的油松人工林树高模型研究[J]. 西北林学院学报, 2020, 35(1): 212-217. doi: 10. 3969/j.issn.1001-7461.2020.01.32.]
    [22] Peng C, Zhang L, Liu J. Developing and validating nonlinear height-diameter models for major tree species of Ontario’s boreal forests [J]. N J Appl For, 2001, 18(3): 87-94. doi: 10.1093/njaf/18.3.87.
    [23] Meter A V. Evaluating height-diameter models for mixed conifer forests in the Sierra Nevada [J]. For Sci, 2021, 67(3): 245-257. doi: 10.1093/forsci/fxab003.
    [24] Torres-Sánchez J, Peña J M, De Castro A I, et al. Multi-temporal mapping of the vegetation fraction in early-season wheat fields using images from UAV [J]. Comp Ele Agric, 2014, 103: 104113. doi: 10.1016/j.compag.2014.02.009.
    [25] Pretzsch H. Transitioning towards ecological forestry embraces the complexity of natural forests [J]. Forests, 2020, 11: 1092. doi: 10.3390/f11101092.
    [26] Hakamada R, Robert M, Hubbard, et al. Biomass production in relation to resource availability in Eucalyptus monocultures and mixed-species plantations along a rainfall gradient in Brazil [J]. For Ecol Management, 2021, 491: 119207. doi: 10.1016/j.foreco.2021. 119207.
    [27] Porte A, Arbellay E, MEREDIEU C, et al. Spatial dynamics of Eucalyptus grandis in mixed-species plantations: Competition drives early dynamics but environmental filtering determines composition in later stages [J]. For Ecol Manag, 2020, 473: 118309. doi: 10.1016/j. foreco.2020.118309.
    [28] Dong T L, Beadle c l, THOMAS D, et al. Growth and biomass partitioning of three Eucalyptus species in monoculture and mixed-species plantations in sub-tropical Queensland [J]. Forests, 2021, 12: 421. doi: 10.3390/f12040421.
    Cited by
    Comments
    Comments
    分享到微博
    Submit
Get Citation

任一平,杨梅,任世奇,朱慧,韦振道,伍琪.基于卷积神经网络的尾巨桉混交林胸径-树高模型[J].热带亚热带植物学报,2025,33(2):140~148

Copy
Share
Article Metrics
  • Abstract:38
  • PDF: 65
  • HTML: 69
  • Cited by: 0
History
  • Received:November 21,2023
  • Revised:March 12,2024
  • Online: April 03,2025
Article QR Code