Spatially Disaggregated Car Ownership Prediction Using Deep Neural Networks
Abstract
:1. Introduction
2. Previous Work on Car Ownership Modelling
3. Data
3.1. Hypothesised Predictors of Car Ownership
3.2. Multicollinearity
3.3. Dependent Variable
4. Method
4.1. Advanced Regression Models and Artificial Intelligence
4.2. Comparison to Other Regression Techniques
4.3. Artificial Neural Network
4.4. Preprocessing—Normalisation
4.5. Hyperparameter Tuning
4.5.1. Network Depth and Number of Neurons per Layer
4.5.2. Learning Rate, Weightings Estimator, Batch Size, Activation Function
4.5.3. Training
4.5.4. Optimal Configurations
5. Results and Discussion
5.1. Base Year (2011)
5.2. Change in Car Ownership from 2001 to 2011
6. Conclusions and Future Work
Author Contributions
Funding
Institutional Review Board Statement
Informed Consent Statement
Data Availability Statement
Conflicts of Interest
References
- Department for Business, Energy & Industrial Strategy. 2020 UK Greenhouse Gas Emissions, Provisional Figures; Technical Report; Department for Business, Energy & Industrial Strategy: London, UK, 2021.
- Department for Business, Energy & Industrial Strategy. UK Becomes First Major Economy to Pass Net Zero Emissions Law; Department for Business, Energy & Industrial Strategy: London, UK, 2019.
- Climate Change Committee. Net Zero: The UK’s Contribution to Stopping Global Warming; Technical Report May; Climate Change Committee: London, UK, 2019. [Google Scholar]
- Department for Transport. Decarbonising Transport: Setting the Challenge; Technical Report; Department for Transport: London, UK, 2020.
- Society of Motor Manufacturers & Traders (SMMT). Electric Vehicle and Alternatively Fuelled Vehicle Registrations: Year-to-Date; Society of Motor Manufacturers & Traders (SMMT): London, UK, 2021. [Google Scholar]
- McKerracher, C.; Izadi-Najafabadi, A.; O’Donovan, A.; Albanese, N.; Soulopolous, N.; Doherty, D.; Boers, M.; Fisher, R.; Cantor, C.; Frith, J.; et al. Electric Vehicle Outlook 2020; Technical Report; Bloomberg New Energy Finance: London, UK, 2020. [Google Scholar]
- Climate Change Committee. The Sixth Carbon Budget: The UK’s Path to Net Zero; Climate Change Committee: London, UK, 2020. [Google Scholar]
- National Grid ESO. Future Energy Scenarios; National Grid ESO: London, UK, 2020. [Google Scholar]
- Brand, C.; Götschi, T.; Dons, E.; Gerike, R.; Anaya-Boig, E.; Avila-Palencia, I.; de Nazelle, A.; Gascon, M.; Gaupp-Berghausen, M.; Iacorossi, F.; et al. The climate change mitigation impacts of active travel: Evidence from a longitudinal panel study in seven European cities. Glob. Environ. Chang. 2021, 67, 102224. [Google Scholar] [CrossRef]
- Dixon, J.; Elders, I.; Bell, K. Electric Vehicle Charging Simulations on a Real Distribution Network using Real Trial Data. In Proceedings of the IEEE Transportation Electrification Conference & Expo, Asia-Pacific, Seogwipo, Korea, 8–10 May 2019. [Google Scholar] [CrossRef] [Green Version]
- Neaimeh, M.; Wardle, R.; Jenkins, A.M.; Yi, J.; Hill, G.; Lyons, P.F.; Hübner, Y.; Blythe, P.T.; Taylor, P.C. A probabilistic approach to combining smart meter and electric vehicle charging data to investigate distribution network impacts. Appl. Energy 2015, 157, 688–698. [Google Scholar] [CrossRef] [Green Version]
- Veldman, E.; Verzijlbergh, R.A. Distribution grid impacts of smart electric vehicle charging from different perspectives. IEEE Trans. Smart Grid 2015, 6, 333–342. [Google Scholar] [CrossRef]
- Pieltain Fernández, L.; Gómez San Román, T.; Cossent, R.; Mateo Domingo, C.; Frías, P. Assessment of the impact of plug-in electric vehicles on distribution networks. IEEE Trans. Power Syst. 2011, 26, 206–213. [Google Scholar] [CrossRef]
- Xydas, E.; Marmaras, C.; Cipcigan, L.M.; Jenkins, N.; Carroll, S.; Barker, M. A data-driven approach for characterising the charging demand of electric vehicles: A UK case study. Appl. Energy 2016, 162, 763–771. [Google Scholar] [CrossRef] [Green Version]
- Dixon, J.; Bukhsh, W.; Edmunds, C.; Bell, K. Scheduling Electric Vehicle Charging to Minimise Carbon Emissions and Wind Curtailment. Renew. Energy 2020, 161, 1072–1091. [Google Scholar] [CrossRef]
- Crozier, C.; Morstyn, T.; McCulloch, M. The opportunity for smart charging to mitigate the impact of electric vehicles on transmission and distribution systems. Appl. Energy 2020, 268, 114973. [Google Scholar] [CrossRef]
- De Jong, G.; Fox, J.; Daly, A.; Pieters, M.; Smit, R. Comparison of car ownership models. Transp. Rev. 2004, 24, 379–408. [Google Scholar] [CrossRef]
- Potoglou, D.; Kanaroglou, P.S. Modelling car ownership in urban areas: A case study of Hamilton, Canada. J. Transp. Geogr. 2008, 16, 42–54. [Google Scholar] [CrossRef]
- Shay, E.; Khattak, A.J. Automobiles, trips, and neighborhood type: Comparing environmental measures. Transp. Res. Rec. 2007, 2010, 73–82. [Google Scholar] [CrossRef]
- Wang, X.; Shao, C.; Yin, C.; Zhuge, C. Exploring the influence of built environment on car ownership and use with a spatial multilevel model: A case study of Changchun, China. Int. J. Environ. Res. Public Health 2018, 15, 1868. [Google Scholar] [CrossRef] [Green Version]
- Fox, J.; Patruni, B.; Daly, A.; Lu, H. Estimation of the National Car Ownership Model for Great Britain: 2011 Base; Technical Report; The National Academies of Sciences, Engineering, and Medicine: Washington, DC, USA, 2017. [Google Scholar] [CrossRef]
- International Transport Forum. Understanding Consumer Vehicle Choice—A New Car Fleet Model for France; Technical Report; International Transport Forum: Paris, France, 2019. [Google Scholar]
- Dargay, J.M. Determinants of car ownership in rural and urban areas: A pseudo-panel analysis. Transp. Res. Part E Logist. Transp. Rev. 2002, 38, 351–366. [Google Scholar] [CrossRef]
- Chatterton, T.J.; Anable, J.; Barnes, J.; Yeboah, G. Mapping household direct energy consumption in the United Kingdom to provide a new perspective on energy justice. Energy Res. Soc. Sci. 2016, 18, 71–87. [Google Scholar] [CrossRef] [Green Version]
- Brand, C.; Goodman, A.; Rutter, H.; Song, Y.; Ogilvie, D. Associations of individual, household and environmental characteristics with carbon dioxide emissions from motorised passenger travel. Appl. Energy 2013, 104, 158–169. [Google Scholar] [CrossRef] [PubMed] [Green Version]
- Wu, N.; Zhao, S.; Zhang, Q. A study on the determinants of private car ownership in China: Findings from the panel data. Transp. Res. Part A Policy Pract. 2016, 85, 186–195. [Google Scholar] [CrossRef]
- Gough, I.; Abdallah, S.; Johnson, V. The Distribution of Total Greenhouse Gas Emissions by Households in the UK, and Some Implications for Social Policy; Technical Report; New Economics Foundation and Centre for Analysis of Social Exclusion: London, UK, 2011. [Google Scholar]
- Cairns, S.; Chatterton, T.; Anable, J.; Wilson, E.; Ball, S.; Emmerson, P.; Barnes, J. MOT data: What scope for understanding car ownership and use at a local level? In Proceedings of the 14th Annual Transport Practitioners Meeting, Nottingham, UK, 29–30 June 2016. [Google Scholar]
- Best, H.; Wolf, C.; Meuleman, B.; Loosveldt, G.; Emonds, V. Regression Analysis: Assumptions and Diagnostics; SAGE: Newcarthon-on-Tyne, UK, 2014; pp. 83–110. [Google Scholar] [CrossRef]
- Ding, C.; Cao, X. How does the built environment at residential and work locations affect car ownership? An application of cross-classified multilevel model. J. Transp. Geogr. 2019, 75, 37–45. [Google Scholar] [CrossRef]
- De Gruyter, C.; Truong, L.T.; Taylor, E.J. Can high quality public transport support reduced car parking requirements for new residential apartments? J. Transp. Geogr. 2020, 82, 102627. [Google Scholar] [CrossRef]
- Zhong, L.; Lee, B. Carless or Car Later?: Declining Car Ownership of Millennial Households in the Puget Sound Region, Washington State. Transp. Res. Rec. J. Transp. Res. Board 2017, 2664, 69–78. [Google Scholar] [CrossRef]
- Candanedo, L.M.; Feldheim, V.; Deramaix, D. Data driven prediction models of energy use of appliances in a low-energy house. Energy Build. 2017, 140, 81–97. [Google Scholar] [CrossRef]
- Kim, T.Y.; Cho, S.B. Predicting residential energy consumption using CNN-LSTM neural networks. Energy 2019, 182, 72–81. [Google Scholar] [CrossRef]
- Chen, K.; Jiang, J.; Zheng, F.; Chen, K. A novel data-driven approach for residential electricity consumption prediction based on ensemble learning. Energy 2018, 150, 49–60. [Google Scholar] [CrossRef]
- Kaewwichian, P.; Tanwanichkul, L.; Pitaksringkarn, J. Car Ownership Demand Modeling Using Machine Learning: Decision Trees and Neural Networks. Int. J. 2019, 17, 219–230. [Google Scholar] [CrossRef]
- Office for National Statistics. Lower Layer Super Output Area (LSOA) Boundaries; Office for National Statistics: London, UK, 2016.
- Scottish Government. Data Zone Boundaries 2011; Scottish Government: St Andrew’s House, UK, 2019.
- UK Data Service. Infuse—Access 2011 and 2001 UK Census Data; UK Data Service: Colchester, UK, 2011. [Google Scholar]
- Department for Transport. Accessibility Statistics; Department for Transport: London, UK, 2014.
- UK Data Service. Experian Demographic Data, 2004–2005 and 2008–2011; UK Data Service: Colchester, UK, 2011. [Google Scholar]
- Experian. Experian’s Mosaic Public Sector Citizen Classification for the United Kingdom; Technical Report; Experian: Dublin, Ireland, 2011. [Google Scholar]
- Brand, C.; Anable, J.; Morton, C. Lifestyle, efficiency and limits: Modelling transport energy and emissions using a socio-technical approach. Energy Effic. 2019, 12, 187–207. [Google Scholar] [CrossRef] [Green Version]
- Anowar, S.; Eluru, N.; Miranda-Moreno, L.F. Alternative Modeling Approaches Used for Examining Automobile Ownership: A Comprehensive Review. Transp. Rev. 2014, 34, 441–473. [Google Scholar] [CrossRef]
- Office for National Statistics. Regional Gross Disposable Household Income: Local Authorities by NUTS1 Region; Office for National Statistics: London, UK, 2020.
- Office for National Statistics. Regions (December 2017) Boundaries in England; Office for National Statistics: London, UK, 2019.
- Office for National Statistics. Rural Urban Classification (2011) of Lower Layer Super Output Areas in England and Wales; Office for National Statistics: London, UK, 2018.
- Scottish Government. Urban Rural Classification 2011–2012; Scottish Government: St Andrew’s House, UK, 2012.
- Office for National Statistics. Lower Layer Super Output Area Population Estimates; Office for National Statistics: London, UK, 2019.
- National Records of Scotland. Detailed Data Zone Tables—Mid-2011; National Records of Scotland: Edinburgh, UK, 2015.
- Office for National Statistics. Lower Layer Super Output Area (2001) to Lower Layer Super Output Area (2011) to Local Authority District (2011) Lookup in England and Wales; Office for National Statistics: London, UK, 2018.
- D’Angelo, G.; Pilla, R.; Tascini, C.; Rampone, S. A proposal for distinguishing between bacterial and viral meningitis using genetic programming and decision trees. Soft Comput. 2019, 23, 11775–11791. [Google Scholar] [CrossRef]
- Alvi, R.H.; Rahman, M.H.; Khan, A.A.S.; Rahman, R.M. Deep learning approach on tabular data to predict early-onset neonatal sepsis. J. Inf. Telecommun. 2021, 5, 226–246. [Google Scholar] [CrossRef]
- Bodenhofer, U.; Haslinger-Eisterer, B.; Minichmayer, A.; Hermanutz, G.; Meier, J. Machine learning-based risk profile classification of patients undergoing elective heart valve surgery. Eur. J. Cardio-Thorac. Surg. 2021, 1–8. [Google Scholar] [CrossRef]
- Babagoli, M.; Aghababa, M.P.; Solouk, V. Heuristic nonlinear regression strategy for detecting phishing websites. Soft Comput. 2019, 23, 4315–4327. [Google Scholar] [CrossRef]
- Sang, B. Application of genetic algorithm and BP neural network in supply chain finance under information sharing. J. Comput. Appl. Math. 2021, 384, 113170. [Google Scholar] [CrossRef]
- Dulebenets, M.A. A novel memetic algorithm with a deterministic parameter control for efficient berth scheduling at marine container terminals. Marit. Bus. Rev. 2017, 2, 302–330. [Google Scholar] [CrossRef] [Green Version]
- Brahmia, I.; Wang, J.; Xu, H.; Wang, H.; De Oliveira, L. Robust Data Predictive Control Framework for Smart Multi-Microgrid Energy Dispatch Considering Electricity Market Uncertainty. IEEE Access 2021, 9, 32390–32404. [Google Scholar] [CrossRef]
- Pasha, J.; Dulebenets, M.A.; Kavoosi, M.; Abioye, O.F.; Wang, H.; Guo, W. An Optimization Model and Solution Algorithms for the Vehicle Routing Problem with a ‘Factory-in-a-Box’. IEEE Access 2020, 8, 134743–134763. [Google Scholar] [CrossRef]
- Panda, N.; Majhi, S.K. How Effective is the Salp Swarm Algorithm in Data Classification. In Advances in Intelligent Systems and Computing; Springer: Singapore, 2020; Volume 999, pp. 579–588. [Google Scholar] [CrossRef]
- Liu, Z.Z.; Wang, Y.; Huang, P.Q. AnD: A many-objective evolutionary algorithm with angle-based selection and shift-based density estimation. Inf. Sci. 2020, 509, 400–419. [Google Scholar] [CrossRef] [Green Version]
- Zhao, H.; Zhang, C. An online-learning-based evolutionary many-objective algorithm. Inf. Sci. 2020, 509, 1–21. [Google Scholar] [CrossRef]
- Pedregosa, F.; Varoquaux, G.; Gramfort, A.; Michel, V.; Thirion, B.; Grisel, O.; Blondel, M.; Prettenhofer, P.; Weiss, R.; Dubourg, V.; et al. Scikit-learn: Machine Learning in Python. J. Mach. Learn. Res. 2011, 12, 2825–2830. [Google Scholar]
- Sharifzadeh, M.; Sikinioti-Lock, A.; Shah, N. Machine-learning methods for integrated renewable power generation: A comparative study of artificial neural networks, support vector regression, and Gaussian Process Regression. Renew. Sustain. Energy Rev. 2019, 108, 513–538. [Google Scholar] [CrossRef]
- Friedman, J.; Hastie, T.; Tibshirani, R. The Elements of Statistical Learning; Springer Series in Statistics New York; Springer: New York, NY, USA, 2001; Volume 1. [Google Scholar]
- Sibi, P.; Allwyn Jones, S.; Siddarth, P. Analysis of different activation functions using back propagation neural networks. J. Theor. Appl. Inf. Technol. 2013, 47, 1344–1348. [Google Scholar]
- Kingma, D.P.; Ba, J.L. Adam: A method for stochastic optimization. In Proceedings of the 3rd International Conference on Learning Representations, ICLR 2015—Conference Track Proceedings, San Diego, CA, USA, 7–9 May 2015; pp. 1–15. [Google Scholar]
- Chollet, F. Keras. 2015. Available online: https://github.com/fchollet/keras (accessed on 8 March 2021).
- Department for Transport. Household Car Ownership by Region and Rural-Urban Classifcation: England, 2002/03 and 2018/19 (Table NTS9902); Department for Transport: London, UK, 2020.
- Wiseman, Y. COVID-19 Along with Autonomous Vehicles will Put an End to Rail Systems in Isolated Territories. IEEE Intell. Transp. Syst. Mag. 2021. [Google Scholar] [CrossRef]
- Beck, M.J.; Hensher, D.A.; Wei, E. Slowly coming out of COVID-19 restrictions in Australia: Implications for working from home and commuting trips by car and public transport. J. Transp. Geogr. 2020, 88, 102846. [Google Scholar] [CrossRef] [PubMed]
Variable Category | Source | Region | Years |
---|---|---|---|
Demographic and Socio-Economic Data | |||
Economic activity | UK Census | GB | 2001; 2011 |
NSSec social classification | UK Census | GB | 2001; 2011 |
Household composition | UK Census | GB | 2001; 2011 |
Tenure | UK Census | GB | 2001; 2011 |
Means of travel to work | UK Census | GB | 2001; 2011 |
Distance travelled to work | UK Census | GB | 2001; 2011 |
Accessibility Data | |||
Bus service frequency indicator (1–100) to nearest amenity s in set of amenities | DfT | England | 2007–2013 |
Travel time by mode t in set of modes to nearest s in | DfT | England | 2007–2013 |
Number of users within travel time m in set of travel times (in minutes) by t in to nearest s in | DfT | England | 2007–2013 |
Experian Mosaic Public Sector Classification Data | |||
Number of individuals in Mosaic Public Sector groups (‘A’–‘O’) | Experian | GB | 2004–2005; 2008–2011 |
Gross Disposable Household Income | |||
Gross disposable household income per Local Authority | ONS | GB | 1997–2017 |
Geographic Data | |||
English region (9 levels; e.g., ‘North West’) | ONS | England | - |
Urban/rural classification (England & Wales, 8 levels) | ONS | England & Wales | 2001; 2011 |
Urban/rural classification (Scotland, 6 levels) | Scottish Government | Scotland | 2001; 2011 |
Population density (England & Wales) | ONS | England & Wales | 2001; 2011 |
Population density (Scotland) | Scottish Government | Scotland | 2001; 2011 |
Regression | OLS | RF | SGD | SVR | NN |
---|---|---|---|---|---|
Cars per LSOA, England | 24.66 (3.18%) | 30.17 (3.89%) | 48.89 (6.30%) | 72.83 (9.39%) | 17.55 (2.23%) |
Cars per LSOA, Wales | 21.06 (2.54%) | 33.62 (4.05%) | 22.39 (2.70%) | 154.21 (18.59%) | 17.03 (2.05%) |
Cars per LSOA, Scotland | 13.27 (3.76%) | 16.71 (4.73%) | 13.43 (3.81%) | 34.07 (9.65%) | 10.38 (2.94%) |
Change in cars per LSOA, England & Wales | 21.54 (25.08%) | 23.37 (27.21%) | 21.78 (25.36%) | 36.38 (42.36%) | 19.62 (22.85%) |
Regression | Hidden Layers | Hidden Layer Dimensions | Weightings Estimator | Activation Function | Batch Size (% of Input Data) | Learning Rate |
---|---|---|---|---|---|---|
Cars per LSOA—England | 2 | [100,60] | Normal | ReLU | 1 | 0.001 |
Cars per LSOA—Wales | 2 | [40,30] | Normal | ReLU | 10 | 0.001 |
Cars per LSOA—Scotland | 2 | [50,50] | Normal | ReLU | 10 | 0.001 |
Change in cars per LSOA—England & Wales | 2 | [40,40] | Normal | ReLU | 1 | 0.001 |
Region/Country | Mean Error (%) |
---|---|
London | +3.05 |
North West | +1.99 |
Yorkshire & The Humber | +1.39 |
North East | +1.96 |
West Midlands | +2.22 |
South East | +1.03 |
East of England | +0.97 |
East Midlands | +0.98 |
South West | +1.37 |
Scotland | +0.11 |
Wales | +0.02 |
Region/Country | Mean Error (%) |
---|---|
London | −15.29 |
North West | −0.12 |
Yorkshire & The Humber | +1.26 |
North East | +3.95 |
West Midlands | −1.10 |
South East | −2.15 |
East of England | −2.29 |
East Midlands | +1.50 |
South West | +2.26 |
Wales | +5.12 |
Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations. |
© 2021 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Dixon, J.; Koukoura, S.; Brand, C.; Morgan, M.; Bell, K. Spatially Disaggregated Car Ownership Prediction Using Deep Neural Networks. Future Transp. 2021, 1, 113-133. https://doi.org/10.3390/futuretransp1010008
Dixon J, Koukoura S, Brand C, Morgan M, Bell K. Spatially Disaggregated Car Ownership Prediction Using Deep Neural Networks. Future Transportation. 2021; 1(1):113-133. https://doi.org/10.3390/futuretransp1010008
Chicago/Turabian StyleDixon, James, Sofia Koukoura, Christian Brand, Malcolm Morgan, and Keith Bell. 2021. "Spatially Disaggregated Car Ownership Prediction Using Deep Neural Networks" Future Transportation 1, no. 1: 113-133. https://doi.org/10.3390/futuretransp1010008