Keywords
Viễn thám
GIS
Mô hình hóa
Random Forest
Tỉnh Phú Yên Forest fire risk prediction
Remote sensing
GIS
Modeling
Random Forest
Phu Yen province
Working Languages
How to Cite
Abstract
Forest fires are one of the causes of great economic and ecological losses, reducing the area and quality of forests. Due to the effects of climate change and human activities, the trend and frequency of forest fires have increased and reached alarming levels in many areas in Vietnam. Many models of forest fire risk prediction by remote sensing and GIS data have been proposed and tested for regions with different natural and socio-economic conditions. This paper presents the results of building a model to predict forest fire risk in Phu Yen province using remote sensing and GIS data. In the study, 10 input layers were extracted from remote sensing and GIS data, including the NDVI index, NDWI index, land cover/land use, distance to roads, relative humidity, land surface temperature, average monthly rainfall, aspect, slope and elevation are used to build a forest fire risk prediction map based on the Random Forest algorithm. The results obtained in the study are an effective solution in early forecasting the risk of forest fires as well as minimising damage caused by forest fires