Forecasting the Natural Forest Stand Age Based on Artificial Neural Network Model

摘要：

Stand age is the average age of trees in the stand. In this paper, the back propagation (BP) artificial neural network, the projection pursuit regression (PPR) artificial neural network and the multiple stepwise regression anatomic models were introduced to predict the nonlinear relation between the natural stand age and the stand factors. At the same time, the author contrasted the forecasting results precision of the BP artificial neural network model, the PPR artificial neural network and the multiple stepwise regression anatomic models. The result indicated that 3 models were available for prediction of natural forest age; the predication average relative error of BP artificial neural network model was 0.1, he predication average relative error of multiple stepwise regression anatomic models was 0.05, the predication average relative error of PPR artificial neural network model was 0.02; the stability of BP artificial neural network model was poor and in other hand the PPR model and the multiple stepwise regression anatomic model with good stability. Therefore, the PPR model was better than the other two models, which can be applied to predict the natural forest stand age.

关键词： BP artificial neural network model PPR artificial neural network mode multiple stepwise regression anatomic models stands age

作者: NING Yang-cui ZHENG Xiao-xian ZHAO Jing JIANG gui-juan

作者单位: The Key Laboratory/or Silviculture and Conservation of Ministry of Education Beijing Forestry University Beijing, China

会议类型: 国际会议

会议名称: 2010 International Conference on Computer and Communication Technologies in Agriculture Engineering(计算机与通信技术在农业工程国际会议 CCTAE 2010)

会议地点: 成都

会议语种:英文

页码: 536-539

在线出版日期: 2010-06-12（万方平台首次上网日期，不代表论文的发表时间）