Stand basal area modelling for Chinese fir plantations using an artificial neural network model

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 backpropagation models using artificial neural networks include determination of the structure of the network and overlearning 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.

Site index for Chinese fir plantations varies with climatic and soil factors in southern China

Chinese fir[Cunninghamia lanceolata(Lamb.)Hook.]has a large native distribution range in southern China.Here,we tested differences in productivity of Chinese fir plantations in different climatic regions and screened the main environmental factors affecting site productivity in each region.Relationships of a Chinese fir site index with climatic factors and the soil physiochemical properties of five soil layers were examined in a long-term positioning observation trial comprising a total of 45 permanent plots in Fujian(eastern region in the middle subtropics),Guangxi(south subtropics)and Sichuan(central region in the middle subtropics)in southern China.Linear mixed effects models were developed to predict the site index for Chinese fir,which was found to vary significantly among different climatic regions.Available P,total N,bulk density and total K were dominant predictors of site index in three climatic regions.The regional linear mixed models built using these predictors in the three climatic regions fit well(R~2=0.86–0.97).For the whole study area,the available P in the 0–20-cm soil layer and total N in the 80–100-cm soil layer were the most indicative soil factors.MAP was the most important climatic variable influencing the site index.The model evaluation results showed that the fitting performance and prediction accuracy of the global site index model using the climatic region as the dummy variable and random parameters and the most important soil factors of the three climatic regions as predictors was higher than that of global site index model using the climatic variable and the most indicative soil variables of the whole study area.Our results will help with further evaluation of site quality of Chinese fir plantations and the selection of its appropriate sites in southern China as the climatic changes.