/Forest-Fires-prediction

This is a difficult regression task, where the aim is to predict the burned area of forest fires, in the northeast region of Portugal, by using meteorological and other data

Primary LanguageJupyter Notebook

Data Info :

  • i could find alot of useful info at this link

  • This dataset was first introduced in datamining paper by Paulo Cortez and An´ıbal Morais, and the data was published at at this website

  • The forest Fire Weather Index (FWI) is the Canadian system for rating fire danger and it includes six components :

1- Fine Fuel Moisture Code (FFMC) which denotes the moisture content surface litter and influences ignition and fire spread

2,3- Duff Moisture Code (DMC) and Drought Code (DC) which represent the moisture content of shallow and deep organic layers

5- Initial Spread Index (ISI) which is is a score that correlates with fire velocity spread

6- Buildup Index (BUI) which represents the amount of available fuel (ex. grass and leaves)

  • the first three components are calculated using dataset features like rain, temprature, wind and relative humidity

  • ISI is calculated from wind and FFMC

  • the rest was dropped by the dataset provider the reason he has suggested : "The BUI and FWI were discarded since they are depen-dent of the previous value"

  • X and Y represent a square region of 9x9 grids which represents Montesinho Natural Park

    The Following table was privided in the paper:

Attribute Description
X x-axis coordinate (from 1 to 9)
Y y-axis coordinate (from 1 to 9)
month Month of the year (January to December)
day Day of the week (Monday to Sunday)
FFMC FFMC code
DMC DMC code
DC DC code
ISI ISI inde
temp Outside temperature (in ◦C)
RH Outside relative humidity (in %)
wind Outside wind speed (in km/h)
rain Outside rain (in mm/m2)
area Total burned area (in ha) ha = 100 m2