BADI: A NOVEL BURNED AREA DETECTION INDEX FOR SENTINEL-2 IMAGERY USING GOOGLE EARTH ENGINE PLATFORM

Abstract. Forest fires are natural events that occur in numerous ecosystems worldwide and cause significant damage to human, ecological socio-economic factors. It is also crucial obtain useful information on the distribution density of burned areas large scale. An efficient way map regions through remote sensing (RS). Nevertheless, complex scenario similar spectral signature features multispectral bands can lead many false positives, making it difficult extract accurately. Multispectral data from Sentinel-2 satellite images allow development novel area indices, as more recorded Red-Edge region. This research aims develop a new detection index (BADI) at 20 m spatial resolution google earth engine platform detect wildfire-affected southwest Iran using imagery. The BADI has been specially designed take benefit use combination reasonable for post-fire detection. final results indicated proposed by applying post-processing stage works well case study identify areas. At same time, satisfactorily suppress complicated irrelevant changes scene. Furthermore, rapid provide near real-time. According Copernicus Emergency Management Service (EMS) reference data, maps were produced with kappa coefficient 0.92 an overall accuracy 92.15%, which demonstrated good result comparison indices.