Author(s)

Mingxiang Huang, Liang Guo, Jianhua Gong, Weijun Yang

GuangZhou Urban Planning & Design Survey Research Institute, GuangZhou ,China.
State Key Laboratory of Remote Sensing Science, Institute of Remote Sensing Applications, Chinese Academy of Sciences, Beijing ,China.
T Information Center, Ministry of Environmental Protection of China, Beijing ,China.

A Bayesian network (BN) model was developed to predict susceptibility to PWD(Pine Wilt Disease). The distribution of PWD was identified using QuickBird and unmanned aerial vehicle (UAV) images taken at different times. Seven factors that influence the distribution of PWD were extracted from the QuickBird images and were used as the independent variables. The results showed that the BN model predicted PWD with high accuracy. In a sensitivity analysis, elevation (EL), the normal differential vegetation index (NDVI), the distance to settlements (DS) and the distance to roads (DR) were strongly associated with PWD prevalence, and slope (SL) exhibited the weakest association with PWD prevalence. The study showed that BN is an effective tool for modeling PWD prevalence and quantifying the impact of various factors.

Pine Wilt Disease; Bayesian Network; Modeling; Factor Analysis

M. Huang, L. Guo, J. Gong and W. Yang, "Bayesian Network and Factor Analysis for Modeling Pine Wilt Disease Prevalence," Journal of Software Engineering and Applications, Vol. 6 No. 3B, 2013, pp. 13-17. doi: 10.4236/jsea.2013.63B004.