Throughout the world, the intensity and frequency of wildfires has been dramatically increasing over the years. Therefore, understanding the significant factors leading to such events is critical for developing better strategies in preventing fires. In this project, I conducted joint work between the Department of Mathematics & Statistics and the Department of Geopgraphy & Planning at the University at Albany, SUNY. We conducted an analysis of an extensive list of climatic, anthropogenic, and topographic variables to determine the most significant factors leading to wildfires in East Siberia from 2001-2017. Our work includes the use of both statistical and machine learning methods.
The initial findings for this project have been published in Environmental Advances.
Tools: R (randomForest, kernlab, rJava, maxent, dismo, sp, maptools, ggplot2, readxl, lubridate, spdep, rgdal, PerformanceAnalytics, BBmisc), RStudio