DOI QR코드

DOI QR Code

Estimation of Shared Bicycle Demand Using the SARIMAX Model: Focusing on the COVID-19 Impact of Seoul

SARIMAX 모형을 이용한 공공자전거 수요추정과 평가: 서울시의 COVID-19 영향을 중심으로

  • Hong, Jungyeol (Dept. of Transportation Eng., Univ. of Seoul) ;
  • Han, Eunryong (Dept. of Transportation Eng., Univ. of Seoul) ;
  • Choi, Changho (Division of Logistics and International Trade, Chonnam National Univ.) ;
  • Lee, Minseo (Division of Bicycle Policy, Seoul Metropolitan Government) ;
  • Park, Dongjoo (Dept. of Transportation Eng., Univ. of Seoul)
  • 홍정열 (서울시립대학교 교통공학과) ;
  • 한은룡 (서울시립대학교 교통공학과) ;
  • 최창호 (전남대학교 물류통상학부) ;
  • 이민서 (서울시 자전거정책과) ;
  • 박동주 (서울시립대학교 교통공학과)
  • Received : 2020.12.17
  • Accepted : 2021.01.11
  • Published : 2021.02.28

Abstract

This study analyzed how external variables, such as the supply policy of shared bicycles and the spread of infectious diseases, affect the demand for shared bicycle use in the COVID-19 era. In addition, this paper presents a methodology for more accurate predictions. The Seasonal Auto-Regulatory Integrated Moving Average with Exogenous stressors methodology was applied to capture the effects of exogenous variables on existing time series models. The exogenous variables that affected the future demand for shared bicycles, such as COVID-19 and the supply of public bicycles, were statistically significant. As a result, from the supply volume and COVID-19 outbreak according to the scenario, it was estimated that approximately 46,000 shared bicycles would be supplied by 2022, and the COVID-19 cases would continue to be at the current level. In addition, approximately 32 million and 45 million units per year will be needed in 2021 and 2024, respectively.

COVID-19 발병으로 세계는 심각한 위기에 직면해 있으며, 각 국에서는 전염병 확산을 감소시키고 안전한 통행환경을 조성하기 위하여 사회적 거리두기가 가능한 공공자전거 활성화에 대한 관심이 높아지고 있다. 본 연구는 COVID-19 시대에서 공공자전거의 공급정책, 전염병의 확산 등의 외생요인들이 공공자전거 이용수요에 어떠한 영향을 미치는지 분석하고, 이를 반영한 장래수요예측 방법론을 제시하는데 주요 목적이 있다. 기존 시계열 모형이 가지고 있는 외생요인 미반영의 한계점을 보완하기 위하여 SARIMAX 방법론을 제시하였다. 본 분석을 통하여 외생변수인 COVID-19 발병률과 공공자전거 공급량이 공공자전거 이용수요와 양(+)의 관계에 있다는 것이 통계적으로 유의하게 나타났다. 2022년까지 4만5천대의 공공자전거가 공급되고, COVID-19의 발병률이 현재 수준으로 지속될 경우, 서울시 공공자전거는 2021년 연간 약 3천2백만 대, 2024년에 약 4천6백만 대의 이용수요가 발생할 것으로 예측되었다.

Keywords

References

  1. Chai X., Guo X., Xiao J. and Jiang J.(2020), "Spatiotemporal Analysis of Share Bike Usage during the COVID-19 Pandemic: A Case Study of Beijing," Physics and Society, arXiv preprint arXiv:2004.12340.
  2. Cho H., Yun S. and Jeong Y.(2020), "Seoul Transportation Changes and Strategies After COVID-19," Transportation Technology and Policy, vol. 17, no. 3, pp.46-51.
  3. Cho K. M., Lee S. S. and Nam D.(2020), "Forecasting of Rental Demand for Public Bicycles Using a Deep Learning Model," The Journal of the Korea Institute of Intelligent Transport Systems, vol. 19, no. 3, pp.28-37. https://doi.org/10.12815/kits.2020.19.3.28
  4. Cho M. and Baik D.(2013), "A Study on Demand Forecasting Model for the Passengers of Marine Traffic using Time-Series Analysis Techniques," Journal of the Korea Society for Simulation Conference 2013, pp.56-93.
  5. Choi M. and Jung H.(2020), "A Study on the Influencing Factor of Intention to Use Personal Mobility Sharing Services," The Journal of Korean Society of Transportation, vol. 38, no. 1, pp.1-13. https://doi.org/10.7470/jkst.2020.38.1.001
  6. Coya, https://www.coya.com/bike/index-2019, 2020.11.05.
  7. Fournier N., Christofa E. and Knodler M. A.(2017), "A sinusoidal model for seasonal bicycle demand estimation," Transportation Research Part D: Transport and Environment, vol. 50, pp.154-169. https://doi.org/10.1016/j.trd.2016.10.021
  8. Hamilton J.(1994), Time series econometric, Princeton U. Press, p.816.
  9. Hong J.(2019), "Air Demand Forecasting using Time Series Data: Focusing on Daegu International Airport," International Journal of Tourism and Hospitality Research, vol. 34, no. 3, pp.61-77. https://doi.org/10.21298/ijthr.2020.3.34.3.61
  10. Kaltenbrunner A., Meza R., Grivolla J., Codina J. and Banchs R.(2010), "Urban cycles and mobility patterns: Exploring and predicting trends in a bicycle-based public transport system," Pervasive and Mobile Computing, vol. 6, no. 4, pp.455-466. https://doi.org/10.1016/j.pmcj.2010.07.002
  11. Kim C. and Han A.(2020), "Since Corona 19, transportation policy has changed from efficiency to safety," Issue & Analysis, Vol. 2020, no. 417, pp.1-26.
  12. Kim J. and Jang K.(2017), "Subway Demand Forecast using Seasonal Autoregressive Integrated Moving Average," Korean Society of Transportation, the 76th Academic Conference, pp.450-453.
  13. Kim S. and Park M.(2016), "A Comparison of Accuracy among Tourism Demand Forecasting Models: Suwon-City, Gyeonggi-Do," Northeast Asia Tourism Research, vol. 12, no. 4, pp.121-142.
  14. Lim H. and Chung K.(2019), "Development of Demand Forecasting Model for Seoul Shared Bicycle," Journal of Korea Contents Association, vol. 19, no. 1, pp.132-140. https://doi.org/10.5392/JKCA.2019.19.01.132
  15. Musselwhite C., Avineri E. and Susilo Y.(2020), "Editorial JTH 16-The Coronavirus Disease COVID-19 and implications for transport and health," Journal of Transport & Health, vol. 16, 100853.
  16. O'brien O., Cheshire J. and Batty M.(2014), "Mining bicycle sharing data for generating insights into sustainable transport systems," Journal of Transport Geography, vol. 34, pp.262-273. https://doi.org/10.1016/j.jtrangeo.2013.06.007
  17. Rudloff C. and Lackner B.(2014), "Modeling demand for bikesharing systems: Neighboring stations as source for demand and reason for structural breaks," Transportation Research Record, vol. 2430, no. 1, pp.1-11. https://doi.org/10.3141/2430-01
  18. Seoul Open Data Portal, http://data.seoul.go.kr, 2020.11.01.
  19. Teixeira J. F. and Lopes M.(2020), "The link between bike sharing and subway use during the COVID-19 pandemic: The case-study of New York's Citi Bike," Transportation Research Interdisciplinary Perspectives, vol. 6, 100166.
  20. Tirachini A. and Cats O.(2020), "COVID-19 and public transportation: Current assessment, prospects, and research needs," Journal of Public Transportation, vol. 22, no. 1, pp.1-21.
  21. Tsay R. S.(2005), Analysis of financial time series, John Wiley & Sons, p.720.
  22. Vogel P., Greiser T. and Mattfeld D. C.(2011), "Understanding bike-sharing systems using data mining: Exploring activity patterns," Procedia-Social and Behavioral Sciences, vol. 20, pp.514-523. https://doi.org/10.1016/j.sbspro.2011.08.058
  23. Wilbur M., Ayman A., Ouyang A., Poon V., Kabir R., Vadali A. and Dubey A.(2020), "Impact of COVID-19 on Public Transit Accessibility and Ridership," Physics and Society, arXiv preprint arXiv:2008.02413.
  24. Zheng R., Xu Y., Wang W., Ning G. and Bi Y.(2020), "Spatial transmission of COVID-19 via public and private transportation in China," Travel Medicine and Infectious Disease, vol. 34, 101626.