文献类型：期刊文献

英文题名：Stand basal area modelling for Chinese fir plantations using an artificial neural network model

作者：Che, Shaohui[1,2] Tan, Xiaohong[1] Xiang, Congwei[1] Sun, Jianjun[3] Hu, Xiaoyan[1] Zhang, Xiongqing[1] Duan, Aiguo[1] Zhang, Jianguo[1]

第一作者：Che, Shaohui

通信作者：Duan, AG[1]

机构：[1]Chinese Acad Forestry, Res Inst Forestry, Key Lab Tree Breeding & Cultivat, State Forestry Adm, Beijing 100091, Peoples R China;[2]Beijing Inst Econ & Management, Beijing 100091, Peoples R China;[3]Chinese Acad Forestry, Subtrop Forestry Expt Cent, Fenyi 336600, Peoples R China

年份：2019

卷号：30

期号：5

起止页码：1641-1649

外文期刊名：JOURNAL OF FORESTRY RESEARCH

收录：;Scopus(收录号：2-s2.0-85047401766);WOS:【SCI-EXPANDED(收录号:WOS:000486923500009)】；

基金：The work was supported by the National Scientific and Technological Task in China (Nos. 2015BAD09B0101, 2016YFD0600302), National Natural Science Foundation of China (No. 31570619), and the Special Science and Technology Innovation in Jiangxi Province (No. 201702).

语种：英文

外文关键词：Chinese fir; Basal area; Artificial neural network; Support vector machine; Mixed-effect model

摘要：Artificial neural network models are a popular estimation tool for fitting nonlinear relationships because they require no assumptions about the form of the fitting function, non-Gaussian distributions, multicollinearity, outliers and noise in the data. The problems of back-propagation models using artificial neural networks include determination of the structure of the network and over-learning courses. According to data from 1981 to 2008 from 15 permanent sample plots on Dagangshan Mountain in Jiangxi Province, a back-propagation artificial neural network model (BPANN) and a support vector machine model (SVM) for basal area of Chinese fir (Cunninghamia lanceolata) plantations were constructed using four kinds of prediction factors, including stand age, site index, surviving stem numbers and quadratic mean diameters. Artificial intelligence methods, especially SVM, could be effective in describing stand basal area growth of Chinese fir under different growth conditions with higher simulation precision than traditional regression models. SVM and the Chapman-Richards nonlinear mixed-effects model had less systematic bias than the BPANN.