欢迎访问林草资源研究

林草资源研究 ›› 2024›› Issue (1): 82-87.doi: 10.13466/j.cnki.lczyyj.2024.01.011

• 科学研究 • 上一篇    下一篇

基于深度神经网络的杉木树高-胸径模型研建

王贵林1,2(), 谭伟1,2(), 陈波涛3   

  1. 1.贵州大学 林学院,贵阳 520025
    2.贵州大学 林业信息工程研究中心,贵阳 520025
    3.贵州省林科院,贵阳 520025
  • 收稿日期:2023-12-26 修回日期:2024-02-02 出版日期:2024-02-28 发布日期:2024-03-22
  • 通讯作者: 谭伟,教授,主要研究方向:森林可持续经营、林业信息和3S。Email:wtan@gzu.edu.cn
  • 作者简介:王贵林,硕士研究生,主要研究方向:森林可持续经营。Email:1320474920@qq.com
  • 基金资助:
    贵州省科技计划项目“杉木高世代多性状新品种选育研究”(黔科合支撑合[2018]2301号)

Height-diameter Model of Cunninghamia lanceolata Based on Deep Neural Network

WANG Guilin1,2(), TAN Wei1,2(), CHEN Botao3   

  1. 1. College of Forestry,Guizhou University,Guiyang 550025,China
    2. Forestry Information Engineering Research Center of Guizhou University,Guiyang 550025,China
    3. Guizhou Academy of Forestry Science,Guiyang 550025,China
  • Received:2023-12-26 Revised:2024-02-02 Online:2024-02-28 Published:2024-03-22

摘要:

利用深度神经网络(DNN)模型建立杉木的树高-胸径模型,寻求一种更加高效的杉木树高预测方法。以贵州省清镇市国有林场49块样地中杉木的胸径、树高数据为研究对象,分成不同比例的训练集和测试集,训练集占比分别为20%,30%,40%,50%,60%,70%,80%;对应的测试集占比分别为80%,70%,60%,50%,40%,30%,20%。利用DNN构建树高-胸径模型,并将其与11个传统基础模型进行比较,通过R2、RMSE和MAE对比选出预测效果最好的模型,并根据最优模型添加林木胸径与优势木平均胸径比(DDH),以提高模型的预测精度。利用DNN模型建立的树高-胸径模型在训练集占比为20%的情况下,加入DDH因子后其预测精度R2达到0.89。利用DNN构建杉木树高-胸径模型对杉木树高进行预测,在使用较小数据量的前提下加入DDH因子能够提高对杉木树高的预测效果。

关键词: 杉木, 深度神经网络, 林木胸径与优势木平均胸径比, 树高-胸径模型

Abstract:

By using the deep Neural Network (DNN) model to establish the tree height-diameter model of Cunninghamia lanceolata, we are seeking a more efficient method for predicting the tree height of Cunninghamia lanceolata.The diameter at breast height and tree height data of Cunninghamia lanceolata in 49 plots of state-owned forest farm in Qingzhen City,Guizhou Province were studied,and divided into different proportions of training set and test set data.This consists of training set data(20%,30%,40%,50%,60%,70%,80%,respectively)and test set data(80%,70%,60%,50%,40%,30%,20%,respectively).DNN was used to build a tree height-diameter model,and the model was compared with 11 traditional basic models.Select the model with the best predictive performance by comparing the results of R2,RMSE and MAE.Adding the ratio of diameter at breast height to average diameter at breast height(DDH)of dominant trees based on the optimal model to improve the prediction accuracy.When the training set proportion of the DNN model is 20%,the prediction accuracy of the tree height-diameter model can reach more than 0.89 after adding DDH factor.DNN was used to build a height-diameter model to predict the height of Cunninghamia lanceolata,and adding DDH factor could improve the prediction accuracy of Cunninghamia lanceolata height with a smaller dataset.

Key words: Cunninghamia lanceolata, DNN, DDH, height-diameter model

中图分类号: