Gene expression programming and ensemble methods for bushfire susceptibility mapping: a case study of Victoria, Australia

Bushfire susceptibility mapping helps the government authorities predict and provide required disaster management plans to reduce adverse impacts from bushfires. In this paper, we investigated Gene Expression Programming (GEP) ensemble methods create bushfire maps for Victoria, Australia, as a case study. indicate that eastern part of Victoria where forests are predominant has highest probability bushfire. Western which is covered by cropland, shrubland grassland lowest probability. Two methods, namely an GEP Frequency Ratio (GEPFR) Logistic Regression (LRFR), were proposed compared with stand-alone (FR) methods. The evaluated Area Under Curve (AUC). AUCs GEPFR, LRFR, FR 0.860, 0.852, 0.850, 0.840, respectively. It can be concluded GEPFR outperforms other three outperform LRFR produced accuracy in range 90.79%?92.27%, therefore they equally useful policy makers managers have better natural hazard plans.