Modeling forest fire risk using the Fuzzy-AHP method in the Belezma National Park (Aures-Algeria)

Wildfires in Belzema National Park (Algeria) pose a real threat, exacerbated by climate change and socio-economic impacts. This necessitates the development of a technique that enables effective management of areas degraded by this disaster. Most current models have shortcomings in assessing fire risks, which results in a lack of distinction between the different elements of risk (hazard and vulnerability) and their direct combination, particularly the degree of combustibility of the plant species. This study presents a new integrated framework based on the fuzzy analytic hierarchy process (FAHP) to assess forest fire risks by combining explicit spatial models of hazard and vulnerability. For hazard, six biophysical factors were considered: flammability index, normalized difference moisture index (NDMI), wind speed and direction, slope, and exposure. For vulnerability, six socio-ecological factors were used: distance from roads and inhabited areas, dry vegetation residue index (NDTI), combustibility index, maximum temperature, and vegetation cover density. The model was validated using the area under curve (AUC) value. The results revealed that 57% of the area was classified as having a high to very high risk, with an AUC of 0.86. High-risk areas coincide with high combustibility and human accessibility levels. This study represents a significant methodological advancement in the assessment of wildfire risk. This process strengthens management efforts to prevent the degradation of protected areas Mediterranean forest.