Please wait a minute...
浙江大学学报（农业与生命科学版）
浙江大学学报（农业与生命科学版）  2015, Vol. 41 Issue (2): 205-212    DOI: 10.3785/j.issn.1008-9209.2014.05.191
资源与环境科学     
基于反向传播神经网络的退化红壤区杉木树干液流模拟
涂洁1*， 刘琪璟2， 危骏1， 胡良1
1.南昌工程学院生态与环境科学研究所，南昌 330099；2.北京林业大学林学院，北京 100083
Sap flow simulation of Cunninghamia lanceolata in degraded red soil region based on back propagation neural network.
Tu Jie1*, Liu Qijing2, Wei Jun1, Hu Liang1
(1. Research Institute of Ecology & Environmental Sciences, Nanchang Institute of Technology, Nanchang 330099, China; 2. Department of Forest Sciences, Beijing Forestry University, Beijing 100083, China)
 全文: PDF(1222 KB)   HTML ( ) 
摘要： 以江西退化红壤区杉木人工林为研究对象，采用MATLAB工具箱中的log-sigmoid型函数（tansig）为神经元作用函数，以空气温度、空气相对湿度、平均净辐射、水汽压亏缺为输入变量，液流速率为输出变量，运用贝叶斯正则化算法和Levenberg-Marquardt算法对4 000组气象数据和液流数据进行网络训练和检验，构建拓扑结构为4101的杉木树干液流反向传播(back propagation, BP)神经网络模型。结果表明：在2种算法下训练样本和检验样本模型输出值与实测值之间线性回归的拟合程度均较高，回归方程的相关系数在0.93以上；训练样本的拟合精度分别为83.57%和83.06%，检验样本的仿真精度分别为82.87%和82.15%。说明该网络模型能够很好地反映液流速率与气象因子之间的非线性函数关系，可为杉木人工林的可持续经营和林地水资源的科学管理提供有效手段。
关键词： 杉木;  树干液流;  贝叶斯正则化算法;  Levenberg-Marquardt算法;  反向传播神经网络    
Abstract: Cunninghamia lanceolate is commonly considered to be one of the most important tree species for forest restoration and reconstruction in subtropical area of China, owing to its advantages of rapid growth, good quality and high yield per unit area. However, they also consume certain amount of water during the course of growth and play roles of ecological benefits. Therefore, quantitative research on tree water consumption characteristics by transpiration has become a hot issue in the field of tree physiological ecology in recent years.
Taking the C. lanceolata plantation in degraded red soil of Jiangxi Province as the research object, the log-sigmoid type function (tansig) of MATLAB toolbox was selected as the transmission function for the role of neurons. Four main factors including air temperature, relative air humidity, average net radiation and vapor pressure deficit were chosen as the input variables, and the sap flow velocity was selected as the output variable to train and examine the neural network model with Bayesian regularization algorithm and Levenberg-Marquardt algorithm. The optimum network model of C. lanceolata sap flow velocity was built with the topological structure of 4-10-1.
Based on Bayesian regularization algorithm and Levenberg-Marquardt algorithm, good fitting results were obtained from the linear regression between predictive and measured values with correlation coefficients both higher than 0.93. The fitting accuracies of training samples were 83.57% and 83.06%, and the simulation accuracies of testing samples were 82.87% and 82.15% respectively.
Inconclusion the BP network model can well reflect the non-linear relationship between the meteorological factors and the sap flow velocity, thus may provide an effective tool for sustainable developing strategy of C. lanceolata plantations and scientific management of the associated water resource in the future.
Key words: Cunninghamia lanceolate    sap flow    Bayesian regularization algorithm    Levenberg-Marquardt algorithm    back propagation neural network
出版日期: 2015-03-20
CLC:  S 718  
服务　　
把本文推荐给朋友
加入引用管理器
E-mail Alert
RSS
作者相关文章　　
涂洁
刘琪璟
危骏
胡良

引用本文:

涂洁，刘琪璟，危骏，胡良. 基于反向传播神经网络的退化红壤区杉木树干液流模拟[J]. 浙江大学学报（农业与生命科学版）, 2015, 41(2): 205-212.

Tu Jie, Liu Qijing, Wei Jun, Hu Liang. Sap flow simulation of Cunninghamia lanceolata in degraded red soil region based on back propagation neural network.. Journal of Zhejiang University (Agriculture and Life Sciences), 2015, 41(2): 205-212.

链接本文:

http://www.zjujournals.com/agr/CN/10.3785/j.issn.1008-9209.2014.05.191    或    http://www.zjujournals.com/agr/CN/Y2015/V41/I2/205

null
[1] 岑益郎,宋韬,何勇,鲍一丹. 基于可见/近红外漫反射光谱的土壤有机质含量估算方法研究[J]. 浙江大学学报(农业与生命科学版), 2011, 37(3): 300-306.
[2] 刘丹丹,冯利华,王宁. 基于反向传播神经网络的区域水资源需求量预测——以金华市为例[J]. 浙江大学学报(农业与生命科学版), 2011, 37(2): 231-236.