A Review of Remote Sensing Methods in Identifying and Monitoring Forest Fires

Numerous studies on the phenomenon of fire over the past several decades have provided an extensive set of input data and implementation and evaluation methods. However, this vast array of results and research is structured to provide a roadmap to new users in the field and guidance on various applications and conditions that have not yet been analyzed. In other words, the absence of coherent research on the relative performance of different remote sensing processes in the fire is felt to produce various products or the resulting utilities. To fill this gap, a relatively comprehensive analysis of fire studies in remote sensing publications has been performed in this study. Some of the general factors evaluated in the pre, during, post-fire studies were the manipulation of input data, the review of algorithms, and their development, as these are factors that can be controlled by analysts to improve the Final accuracy of analyzes and results. One of the important issues in the field of fire after the identification and discovery of fire, due to the permanent changes in the structure and composition of vegetation, is to study how vegetation is restored and its growth rate during the years after the fire. According to a study of fire studies in the country, about 48% of them are related to the identification and spread of fire and the remaining 52% are related to resuscitation and recovery. In a review of research related to identification studies, it was found that approximately 5% of its share was done using learning methods and the remaining 43% was done using traditional methods. At the same time, of the study-related share of Resuscitation studies approximately 21% to examine vegetation and 31% of the soil under the fire surface. The findings of this study can be useful in helping researchers to make decisions in the selection of data and algorithms used according to the purpose of study, in different branches of studies associated with fire. However, in addition to these general guidelines, an analyst can consider personal preferences or the benefits of a particular algorithm that may be relevant to a particular program.