Brazilian Flights Dataset

Citation Author(s):
Claudio
Teixeira
CEFET-RJ
Lucas
Tavares
CEFET-RJ
Jorge
Soares
CEFET-RJ
Joel
dos Santos
CEFET-RJ
Glauco
Amorim
CEFET-RJ
Eduardo
Ogasawara
CEFET-RJ
Submitted by:
Claudio Teixeira
Last updated:
Wed, 10/28/2020 - 15:25
DOI:
10.21227/k10b-qn21
Data Format:
Links:
License:
1579 Views
Categories:
Keywords:
5
1 rating - Please login to submit your rating.

Abstract 

This webpage provides information about the Brazilian Flight Dataset (BFD). The description includes the data sources from regular flights (VRA) and weather data. The VRA is provided by ANAC (Agência Nacional de Aviação Civil) and contains all Brazilian flights. The weather data is provided by ASOS (Automated Surface Observing Systems). ASOS is managed by IOWA University (USA). It contains weather data collected by sensors installed at airports around the world.
Instructions: 

The final result of the work consists of a single dataset called bfd with 15,505,922 observations or tuples and 45 characteristics or variables, described below:

1. flight_id - ANAC flight identifier;

2. airline_icao - ICAO acronym of the airline. Ex: GLO, TAM, ONE;

3. airline_name - Full name of the airline;

4. lynetype_code - (N) National, (I) International, (R) Regional, (H) Sub-regional, (E) Special, (C) Freight / Cargo, (G) International Freight / Cargo and (L) Postal Network;

5. origin_icao - ICAO code of the flight origin airport;

6. origin_country - ISO Country Name where the origin airport is located;

7. origin_name - Full name of the airport of origin of the flight;

8. expected_depart_date - Expected flight departure date in YYYYMMDD format where YYYY = year, MM = month and DD = day;

9. expected_depart_hour - Estimated flight departure hour in HH format where HH = full hour;

10. real_depart_date - Flight departure date in YYYYMMDD format where YYYY = year, MM = month and DD = day;

11. real_depart_hour - Flight departure in HH format where HH = full hour;

12. expected_duration - Difference in minutes between expected departure and arrival datetime;

13. departure_delay - Difference in minutes between expected and real departure datetime;

14. depart_temperature - Temperature in degrees Celsius at the airport of origin, at the time of flight departure;

15. depart_dew_point - Dew point, in degrees Celsius at the airport of origin, at the time of flight departure;

16. depart_humidity - Percentage of relative humidity in the airport of origin;

17. depart_pressure - Atmospheric pressure, in mbar, at the airport of origin;

18. depart_visibility - Visibility, in miles, at the airport of origin;

19. depart_wind_speed - Wind speed, in knots, at the airport of origin;

20. depart_wind_direction - Wind direction, based on Wind Rose, at the airport of origin;

21. destination_icao - ICAO code of the destination airport of the flight;

22. destination_name - Full name of the airport of destination of the flight;

23. destination_country - ISO country name where the destination airport is located;

24. expected_arrival_date - Estimated date and time of flight arrival in YYYYMMDD format where YYYY = year, MM = month and DD = day;

25. expected_arrival_hour - Estimated flight arrival hour in HH format where HH = full hour;

26. real_arrival_date - Flight arrival date in YYYYMMDD format where YYYY = year, MM = month and DD = day;

27. real_arrival_hour - Flight arrival hour in HH format where HH = full hour;

28. real_duration - Difference in minutes between real departure and arrival datetime;

29. arrival_delay - Difference in minutes between expected and real arrival datetime;

30. arrival_temperature - Temperature in degrees Celsius at the destination airport, at the time of flight arrival;

31. arrival_dew_point - Dew point, in degrees Celsius at the destination airport, at the time of flight arrival.

32. arrival_humidity - Percentage of relative humidity in the destination airport;

33. arrival_pressure - Atmospheric pressure, in mbar, at the destination airport;

34. arrival_visibility - Visibility, in miles, at the destination airport;

35. arrival_wind_speed - Wind speed in knots at the destination airport;

36. arrival_wind_direction - Wind direction, based on Wind Rose, at the airport of destination;

37. situation_type - Flight status;

38. justification_code - Flight delay or cancellation justification code;

39. justification_description - Description of justification for flight delay or cancellation;

Discretized fields (ds_):

40. ds_depart_wind_speed - The wind classification based on Belfourt Scale at the origin airport;

41. ds_arrival_wind_speed - The wind classification based on Belfourt Scale at the destination airport;

42. ds_depart_wind_direction - The acronymn for the wind direction at destination airport;

43. ds_arrival_wind_direction - The acronymn for the wind direction at destination airport;

44. ds_depart_day_period - Period of the day on real departure. and

45. ds_arrival_day_period - Period of the day on real arrival.

Comments

Figure adapted from Couto, Guilherme & Silva, Ana Paula & Ruiz, Linnyer & Benevenuto, Fabrício. (2015). Structural Properties of the Brazilian Air Transport Network. Proceedings of the Brazilian Academy of Sciences. 87. 10.1590 / 0001-3765201520140155.

Submitted by Claudio Teixeira on Fri, 09/11/2020 - 16:41

This is a very usefull dataset that is helping me a lot in my ressearch.

Submitted by Gabriela Otaviano on Sun, 09/20/2020 - 15:08

This dataset is been used in academical work at Data Analyics Lab (DAL)

Please see... https://eic.cefet-rj.br/~dal/brazilian-flight-dataset-description/

Submitted by Claudio Teixeira on Thu, 10/01/2020 - 14:30