摘要
根据支持向量机（SVM）原理,通过大兴安岭地区1990 ～ 2009年20年间森林火灾数据,得到该地区森林火灾预测模型,并利用此模型对2010 ～2012年3年间的火灾数据进行验证,发现总判对率为84.5％,着火案例判对率为81.4％,说明该回归模型较符合实际情况,具有较好的预测效果,能够为当地林业部门制定防火策略提供参考.
According to the principle of support vector machine （ SVM）, fire from 1990 to 2009 in the Greater Hinggan Mountains Area data, get the forest fire forecast model, and use this model for three years from 2010 to 2012 fire data verification, found that the total sentence of rate was 84.5%, the fire case given the rate of 81.4% , indicating that the regression model is in line with the actual situation and has good prediction effect, which can provide reference for the local forestry department of fire prevention strategies.
出处
《安徽农业科学》
CAS
2014年第12期3684-3684,3754,共2页
Journal of Anhui Agricultural Sciences
基金
黑龙江省留学归国人员基金项目(LC2012C06)
关键词
SVM
森林火险
气象因子
SVM model
Forest fire danger
Meteorological factor
