Study on forest fire danger prediction in plateau mountainous forest area

Abstract

Due to the complex vegetation and topography conditioning the plateau mountainous area, forest fire is difficult to put out in this area once it occurred. The research on forest fire danger prediction is very significant for fire prevention and fire fighting in plateau mountain area. Based on fire dataset from 1997 to 2018 in Lijiang area, this paper applied the spatial overlay analysis, Kriging interpolation analysis and Logistic regression model to study the relationship between forest fire occurrence and elevation, vegetation types and meteorological factors. An optimal Logistic model was selected to predict the probability of forest fire occurrence and fire danger rating in Lijiang area. The results showed that elevation, slope, aspect, daily average temperature and daily average relative humidity were significantly correlated with forest fire occurrence. The prediction accuracy of the Logistic model is averagely 86.9%. According to the results of fire danger prediction, forest fires in Lijiang occurred mainly concentrated in the north of Yulong county, the south of Ninglang county and the central area of Huaping county. The results are of great significance for forest fire prevention in Lijiang area.

Keywords

• Lijiang area
• Fire occurrence
• Fire risk prediction
• Logistic regression