Socio-economic dataset at 1 km grid cell for fire prediction in 1980s and 2000s Madrid (Spain)

This data gathers socioeconomic drivers at 1km2 grid cell spatial resolution to predict forest fires in a region in Spain (Madrid) for two periods of time (1980 and 2000s. The response variable was exact located fires by grid cell. The resulting work was published at Vilar, L., Gómez, I., Martínez-Vega, J., Echavarría, P., Riaño, D., & Martín, M. P. (2016). Multitemporal modelling of socio-economic wildfire drivers in central Spain between the 1980s and the 2000s: comparing generalized linear models to machine learning algorithms. PLoS One, 11(8), e0161344. .-Description of the data and file structure The data set is an excel file with columns for these variables: VARIABLES DESCRIPTION CellCode ID of the 1*1km cell X X cell coordinate Y Y cell coordinate POP population density AGRI agriculture workforce density SERV services workforce density FAI 200 m Forest Agriculture Interface buffer WUI 12.5m Wildland Urban Interface buffer FGI 200 m Forest Grassland Interface buffer RAILWAYS 70 and 100 m railway buffers ROADS 15, 25 and 50 m road buffers TRACKS 300 m tracks buffer NPA Natural Protected Area FIRE_PRESENCE Response variable. Fire presence/absence