Estimation of the burned area in forest fires using computational intelligence techniques

Forest fires have environmental impacts that create economic problems as well as ecological damage. Developing a means to predict the possible size of a fire shortly after it first breaks out has the potential to guide proper resource allocation for improved fire control and was the main motivation of this research. In this study, the burned areas resulting from possible forest fires were estimated using historical forest fire records which contained parameters like geographical conditions of the existing environment, date and time when the fire broke out, meteorological data such as temperature, humidity and wind speed, and the type and number of trees in a unit area. The data was from the Department of Forestry in Turkey and contained 7,920 forest fire records from 2000 and 2009. The output from the estimation methods implemented in this work predicted the size of the area lost due to the fire and the corresponding fire size, i.e. big, medium, or small fire. Some of the estimation methods investigated were Multilayer Perceptron (MLP), Radial Basis Function Networks (RBFN), Support Vector Machines (SVM) and fuzzy logic. The results of these estimates are presented and compared to similar studies in literature.