Statistics Based Predictive Geo-spatial Data Mining: Forest Fire Hazardous Area Mapping Application

摘要: In this paper, we propose two statistics based predictive geo-spatial data mining methods and apply them to predict the forest fire hazardous area. The proposed prediction models used in are likelihood ratio conditional probability methods. these approaches, estimation procedures depend on basic quantitative relationships of sets relevant with respect selected areas previous ignition. order make map for area using evaluate performance power, applied a FHR (Forest Fire Hazard Rate) PRC (Prediction Rate Curve) respectively. When power is compared, method more powerful than method. model would be helpful increase efficiency management such as prevention occurrences effective placement monitoring equipment manpower.