Modelling brussels bike-sharing open data using spatial regression models

Research output: Chapter in Book/Report/Conference proceedingConference contribution

4 Downloads (Pure)

Abstract

In recent years there has been a renewed interest in utilitarian cycling due to its recognized potential in the reduction of energy consumption and pollution in the cities. Bike-sharing systems generate a large amount of data which can be used to improve the systems themselves, or to improve the body of knowledge on urban mobility. The open data automatically generated by the Brussel's bike-sharing system (Villo) is explored through spatial regression models of the number of bicycle trips at stations. The main goal of the modelling process is to understand if socio-economic, infrastructure and land use factors influence mobility patterns in peak periods and weekdays. The first step of the modelling process consists in setting up exploratory Ordinary Least Squares (OLS) models in order to identify potential explanatory variables. Finally, Geographically Weighted Poisson Regression (GWPR) models and semi-parametric versions of GWPR models are parametrised using the previously identified variables. The results show that the relationships between the dependent and independent variables are complex and spatially varying. Furthermore, the results show hidden patterns that enable further local investigation on these relationships. The weaknesses and strengths of our approach are discussed, particularly its implementation in other geographic contexts and its potential of generalisation for all bicycle trips.

Original languageEnglish
Title of host publication19th International Multidisciplinary Scientific GeoConference, SGEM 2019
Subtitle of host publicationConference proceedings. Informatics, geoinformatics and remote sensing
Pages923-930
Number of pages8
Volume19
Edition2.2
DOIs
Publication statusPublished - 1 Jan 2019
Event19th International Multidisciplinary Scientific Geoconference, SGEM 2019 - Albena, Bulgaria
Duration: 30 Jun 20196 Jul 2019

Publication series

NameInternational Multidisciplinary Scientific GeoConference Surveying Geology and Mining Ecology Management, SGEM
PublisherInternational Multidisciplinary Scientific Geoconference
ISSN (Print)1314-2704

Conference

Conference19th International Multidisciplinary Scientific Geoconference, SGEM 2019
CountryBulgaria
CityAlbena
Period30/06/196/07/19

Fingerprint

spatial data
Bicycles
modeling
Land use
Pollution
Energy utilization
infrastructure
land use
pollution
Economics
bicycle

Keywords

  • Bike-sharing systems
  • Geographically weighted poisson regression
  • Mobility
  • Spatial regression
  • Spatial statistics

Cite this

Pina, T. D. C., & Costa, A. C. (2019). Modelling brussels bike-sharing open data using spatial regression models. In 19th International Multidisciplinary Scientific GeoConference, SGEM 2019: Conference proceedings. Informatics, geoinformatics and remote sensing (2.2 ed., Vol. 19, pp. 923-930). (International Multidisciplinary Scientific GeoConference Surveying Geology and Mining Ecology Management, SGEM). https://doi.org/10.5593/sgem2019/2.2/S11.114
Pina, Tiago Daniel Costa ; Costa, Ana Cristina. / Modelling brussels bike-sharing open data using spatial regression models. 19th International Multidisciplinary Scientific GeoConference, SGEM 2019: Conference proceedings. Informatics, geoinformatics and remote sensing. Vol. 19 2.2. ed. 2019. pp. 923-930 (International Multidisciplinary Scientific GeoConference Surveying Geology and Mining Ecology Management, SGEM).
@inproceedings{ff4233f6340c457e87b52e678988d6dc,
title = "Modelling brussels bike-sharing open data using spatial regression models",
abstract = "In recent years there has been a renewed interest in utilitarian cycling due to its recognized potential in the reduction of energy consumption and pollution in the cities. Bike-sharing systems generate a large amount of data which can be used to improve the systems themselves, or to improve the body of knowledge on urban mobility. The open data automatically generated by the Brussel's bike-sharing system (Villo) is explored through spatial regression models of the number of bicycle trips at stations. The main goal of the modelling process is to understand if socio-economic, infrastructure and land use factors influence mobility patterns in peak periods and weekdays. The first step of the modelling process consists in setting up exploratory Ordinary Least Squares (OLS) models in order to identify potential explanatory variables. Finally, Geographically Weighted Poisson Regression (GWPR) models and semi-parametric versions of GWPR models are parametrised using the previously identified variables. The results show that the relationships between the dependent and independent variables are complex and spatially varying. Furthermore, the results show hidden patterns that enable further local investigation on these relationships. The weaknesses and strengths of our approach are discussed, particularly its implementation in other geographic contexts and its potential of generalisation for all bicycle trips.",
keywords = "Bike-sharing systems, Geographically weighted poisson regression, Mobility, Spatial regression, Spatial statistics",
author = "Pina, {Tiago Daniel Costa} and Costa, {Ana Cristina}",
note = "Pina, T. D. C., & Costa, A. C. (2019). Modelling brussels bike-sharing open data using spatial regression models. In International Multidisciplinary Scientific GeoConference Surveying Geology and Mining Ecology Management, SGEM (2.2 ed., Vol. 19, pp. 923-930). (International Multidisciplinary Scientific GeoConference Surveying Geology and Mining Ecology Management, SGEM). https://doi.org/10.5593/sgem2019/2.2/S11.114",
year = "2019",
month = "1",
day = "1",
doi = "10.5593/sgem2019/2.2/S11.114",
language = "English",
isbn = "978-619-7408-80-5",
volume = "19",
series = "International Multidisciplinary Scientific GeoConference Surveying Geology and Mining Ecology Management, SGEM",
publisher = "International Multidisciplinary Scientific Geoconference",
pages = "923--930",
booktitle = "19th International Multidisciplinary Scientific GeoConference, SGEM 2019",
edition = "2.2",

}

Pina, TDC & Costa, AC 2019, Modelling brussels bike-sharing open data using spatial regression models. in 19th International Multidisciplinary Scientific GeoConference, SGEM 2019: Conference proceedings. Informatics, geoinformatics and remote sensing. 2.2 edn, vol. 19, International Multidisciplinary Scientific GeoConference Surveying Geology and Mining Ecology Management, SGEM, pp. 923-930, 19th International Multidisciplinary Scientific Geoconference, SGEM 2019, Albena, Bulgaria, 30/06/19. https://doi.org/10.5593/sgem2019/2.2/S11.114

Modelling brussels bike-sharing open data using spatial regression models. / Pina, Tiago Daniel Costa; Costa, Ana Cristina.

19th International Multidisciplinary Scientific GeoConference, SGEM 2019: Conference proceedings. Informatics, geoinformatics and remote sensing. Vol. 19 2.2. ed. 2019. p. 923-930 (International Multidisciplinary Scientific GeoConference Surveying Geology and Mining Ecology Management, SGEM).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Modelling brussels bike-sharing open data using spatial regression models

AU - Pina, Tiago Daniel Costa

AU - Costa, Ana Cristina

N1 - Pina, T. D. C., & Costa, A. C. (2019). Modelling brussels bike-sharing open data using spatial regression models. In International Multidisciplinary Scientific GeoConference Surveying Geology and Mining Ecology Management, SGEM (2.2 ed., Vol. 19, pp. 923-930). (International Multidisciplinary Scientific GeoConference Surveying Geology and Mining Ecology Management, SGEM). https://doi.org/10.5593/sgem2019/2.2/S11.114

PY - 2019/1/1

Y1 - 2019/1/1

N2 - In recent years there has been a renewed interest in utilitarian cycling due to its recognized potential in the reduction of energy consumption and pollution in the cities. Bike-sharing systems generate a large amount of data which can be used to improve the systems themselves, or to improve the body of knowledge on urban mobility. The open data automatically generated by the Brussel's bike-sharing system (Villo) is explored through spatial regression models of the number of bicycle trips at stations. The main goal of the modelling process is to understand if socio-economic, infrastructure and land use factors influence mobility patterns in peak periods and weekdays. The first step of the modelling process consists in setting up exploratory Ordinary Least Squares (OLS) models in order to identify potential explanatory variables. Finally, Geographically Weighted Poisson Regression (GWPR) models and semi-parametric versions of GWPR models are parametrised using the previously identified variables. The results show that the relationships between the dependent and independent variables are complex and spatially varying. Furthermore, the results show hidden patterns that enable further local investigation on these relationships. The weaknesses and strengths of our approach are discussed, particularly its implementation in other geographic contexts and its potential of generalisation for all bicycle trips.

AB - In recent years there has been a renewed interest in utilitarian cycling due to its recognized potential in the reduction of energy consumption and pollution in the cities. Bike-sharing systems generate a large amount of data which can be used to improve the systems themselves, or to improve the body of knowledge on urban mobility. The open data automatically generated by the Brussel's bike-sharing system (Villo) is explored through spatial regression models of the number of bicycle trips at stations. The main goal of the modelling process is to understand if socio-economic, infrastructure and land use factors influence mobility patterns in peak periods and weekdays. The first step of the modelling process consists in setting up exploratory Ordinary Least Squares (OLS) models in order to identify potential explanatory variables. Finally, Geographically Weighted Poisson Regression (GWPR) models and semi-parametric versions of GWPR models are parametrised using the previously identified variables. The results show that the relationships between the dependent and independent variables are complex and spatially varying. Furthermore, the results show hidden patterns that enable further local investigation on these relationships. The weaknesses and strengths of our approach are discussed, particularly its implementation in other geographic contexts and its potential of generalisation for all bicycle trips.

KW - Bike-sharing systems

KW - Geographically weighted poisson regression

KW - Mobility

KW - Spatial regression

KW - Spatial statistics

UR - http://www.scopus.com/inward/record.url?scp=85073367887&partnerID=8YFLogxK

U2 - 10.5593/sgem2019/2.2/S11.114

DO - 10.5593/sgem2019/2.2/S11.114

M3 - Conference contribution

SN - 978-619-7408-80-5

VL - 19

T3 - International Multidisciplinary Scientific GeoConference Surveying Geology and Mining Ecology Management, SGEM

SP - 923

EP - 930

BT - 19th International Multidisciplinary Scientific GeoConference, SGEM 2019

ER -

Pina TDC, Costa AC. Modelling brussels bike-sharing open data using spatial regression models. In 19th International Multidisciplinary Scientific GeoConference, SGEM 2019: Conference proceedings. Informatics, geoinformatics and remote sensing. 2.2 ed. Vol. 19. 2019. p. 923-930. (International Multidisciplinary Scientific GeoConference Surveying Geology and Mining Ecology Management, SGEM). https://doi.org/10.5593/sgem2019/2.2/S11.114