Prediction of Stand Diameter Distribution with Artificial Neural Network

  • Authors:
  • Jiarong Huang;Junhui Zhao;Guangqin Gao;Xianyu Meng;Yuxiu Guan

  • Affiliations:
  • -;-;-;-;-

  • Venue:
  • ICNC '09 Proceedings of the 2009 Fifth International Conference on Natural Computation - Volume 02
  • Year:
  • 2009

Quantified Score

Hi-index 0.00

Visualization

Abstract

An artificial neural network model forecasting diameter distribution of stands was created by using artificial neural network modeling technology, in Masson pine planted forest. Through training and optimum seeking, the idea model was created, in which the model structure is 3:6:6:1, the training error is 0.000281, and the total fitting accuracy is 98 %. Concretely, the mean frequency fitting accuracy of 82 training plots and its cumulated frequency fitting accuracy is 87 % and 98 %, respectively. While the mean frequency fitting accuracy of 18 testing plot and its cumulated frequency fitting accuracy is 88 % and 98%, respectively. The created model has very high fitting accuracy and very strong prediction ability so that it can be used in Masson pine planted forest from 10 to 30 years of age. The results indicate the artificial neural network technology can be applied in modeling diameter distribution of trees.