Algerian forest fires dataset

Citation Author(s):
Faroudja
ABID
Submitted by:
Faroudja ABID
Last updated:
Tue, 10/24/2023 - 06:10
DOI:
10.21227/31na-kz23
Data Format:
*.csv
Research Article Link:
Predicting Forest Fire in Algeria Using Data Mining Techniques: Case Study of the Decision Tree Algorithm
Links:
10.24432/C5KW4N
License:
Creative Commons Attribution
488 Views
Categories:
Weather
Keywords:
Algerian wildfire dataset; meteorological observations; FWI system components.
0
0 ratings - Please login to submit your rating.
ACCESS DATASET CITE SHARE/EMBED

Abstract 

The first Algerian forest fires dataset consist of data on forest fires occurrence in Algeria related to meteorological observations and the fire weather indices. Our dataset includes mainly the daily meteorological observations and the Fire Weather Index (FWI) system components. Given the lack of publically available datasets on data on forest fires occurrence in Algeria we have created this one to study the feasibility of the appliance of machine learning algorithms as models for forest fires prediction in the context of Algeria. This dataset is valuable for researchers working on forest fires forecasting and monitoring systems in Algeria and also over the word, in particular the Mediterranean countries that have similar climate. This dataset is publically available in several repositories for research. It was elaborated in 2018 and first donated to the UCI online repository on October 2019.

 

Instructions: 

Subject: Environmental Science, Ecology

Specific subject area : This dataset involves the area of forest fires data related to meteorological observations and the fire danger rating system indices.

Brief description : This data article presents the first Algerian forest fires dataset that consists of 244 instances, which includes 12 variables (attributes), namely the meteorological observations (four weather parameters), the six components of the FWI Canadian system , the fire classes (“fire” and “not fire”) and the date variable ((DD/MM/YYYY): Day/month ('June' to 'September')/ year (2012)).

 

Table : Algerian forest fires dataset features description

Data Type

Attributes/variablesname

Description

       Values interval

Sidi-Bel-Abbes region

Values interval

Bejaia region

Values intervals

The two regions

 

 

 

Meteorological observations

Temperature

temperature in Celsius     degrees

24 to 42

22 to 37

22 to 42

RH

relative humidity in %

21 to 90

45 to 89

21 to 90

WS

wind speed in km/h

6 to 29

11 to 26

6 to 29

Rain

outside rain in mm/m2

0 to 16.8

0 to 8.7

      0  to 16.8

 

 

 

 

 

 

FWI components

FFMC

Fine Fuel Moisture Code

41.1 to 94.3

28.6 to 90.3

             28.6 to 94.3

DMC

Duff Moisture Code

0.9 to 65.9

0.7 to 54.2

             1.1 to 65.9

DC

Drought Code

7.3 to 177.3

7.4 to 220.4

               7 to 220.4

ISI

Initial Spread Index

0.1 to 18.5

0.1 to 19

                 0.1 to 19

BUI

Buildup Index

1.4 to 68

3.3 to 67.4

                1.1 to 68

FWI

Fire Weather Index

0 to 31.1

0 to 30.2

0 to 31.1

       

This dataset was first donated to the UC Irvine Machine Learning Repository  : https://archive.ics.uci.edu/dataset/547/algerian+forest+fires+dataset

 

Dataset Files

LOGIN TO ACCESS DATASET FILES

QUESTIONS?