Abstract

Recently, due to the effects of climate change and human activities, forest fires tend to develop complicatedly. Many forest fire risk prediction models based on remote sensing and GIS data have been proposed to assess the risk of forest fires in different areas. The input data set plays a very important role, determining the accuracy and performance of the forest fire risk prediction model. This article presents the results of research on building an input data set for a forest fire risk prediction model in the western region of Nghe An province. Information on terrain, cover, climate-meteorology, and socio-economics is collected and evaluated for importance to the ability to cause forest fires, from which input data sets are selected for the models., including 9 layers : (1) elevation, (2) slope, (3) aspect, (4) vegetation cover density, (5) population density, (6) land surface temperature, (7) evapotranspiration, (8) wind speed, (9) average monthly rainfall