Commuting flow prediction using OpenStreetMap data

Abstract

Accurately predicting commuting flows is crucial for sustainable urban planning and preventing disease spread due to human mobility. While recent advancements have produced effective models for predicting these recurrent flows, the existing methods rely on datasets exclusive to a few study areas, limiting the transferability to other locations. This research broadens the utility of state-of-the-art commuting flow prediction models with globally available OpenStreetMap data while achieving prediction accuracy comparable to location-specific and proprietary data. We show that the types of buildings, residential and non-residential, are a strong indicator for predicting commuting flows. Consistent with theoretical and analytical models, our experiments indicate that building types, distance, and population are the determining characteristics for mobility related to commuting. Our experiments show that predicted flows closely match ground truth flows. Our work enables accurate flow prediction using building types to support applications such as urban planning and epidemiology.

References

[1] Alessandretti L, Aslak U, Lehmann S. The scales of human mobility Nature, 2020, 587(7834): 402-407.

[2] Alonso, W. (1971). The system of intermetropolitan population flows. Institute of Urban and Regional Development.

[3] Atwal KS, Anderson T, Pfoser D, Züfle A. Predicting building types using openstreetmap Scientific Reports, 2022, 12(1): 19976.

[4] Bakillah M, Liang S, Mobasheri A, Jokar Arsanjani J, Zipf A. Fine-resolution population mapping using openstreetmap points-of-interest International Journal of Geographical Information Science, 2014, 28(9): 1940-1963.

[5] Balcan D, Colizza V, Gonçalves B, Hu H, Ramasco JJ, Vespignani A. Multiscale mobility networks and the spatial spreading of infectious diseases Proceedings of the national academy of sciences, 2009, 106(51): 21484-21489.

[6] Bast, H., Storandt, S., & Weidner, S. (2015). Fine-grained population estimation. In Proceedings of the 23rd SIGSPATIAL International Conference on Advances in Geographic Information Systems (pp. 1–10). New York: Association for Computing Machinery.

[7] Breiman L Random forests. Machine learning, 2001, 45: 5-32.

[8] Cai, M., Pang, Y., & Sekimoto, Y. (2022). Spatial attention based grid representation learning for predicting origin–destination flow. In 2022 IEEE International Conference on Big Data (Big Data) (pp. 485–494). IEEE.

[9] Census Bureau, U. (2010). Population data. https://data.census.gov/table. Accessed 3 June 2024.

[10] Census Bureau, U. (2015). Lodes data. https://lehd.ces.census.gov/data/. Accessed 3 June 2024.

[11] Chen, T. & Guestrin, C. (2016). Xgboost: A scalable tree boosting system. In Proceedings of the 22nd acm sigkdd international conference on knowledge discovery and data mining (pp. 785–794). New York: Association for Computing Machinery.

[12] Chicco D, Warrens MJ, Jurman G. The coefficient of determination r-squared is more informative than smape, mae, mape, mse and rmse in regression analysis evaluation Peerj computer science, 2021, 7: e623.

[13] Credit K, Arnao Z. A method to derive small area estimates of linked commuting trips by mode from open source lodes and acs data Environment and Planning B: Urban Analytics and City Science, 2023, 50(3): 709-722

[14] Delventhal MJ, Kwon E, Parkhomenko A. Jue insight: How do cities change when we work from home? Journal of Urban Economics, 2022, 127: 103331.

[15] F de Arruda, H., Reia, S.M., Ruan, S., Atwal, K.S., Kavak, H., Anderson, T., & Pfoser, D. (2024). An openstreetmap derived building classification dataset for the united states. Scientific Data, 11(1), 1210.

[16] Fairfax County, G. (2024). Fairfax county open geospatial data. https://www.fairfaxcounty.gov/maps/open-geospatial-data. Accessed 3 June 2024.

[17] Feng J, Li Y, Lin Z, Rong C, Sun F, Guo D, Jin D. Context-aware spatial-temporal neural network for citywide crowd flow prediction via modeling long-range spatial dependency ACM Transactions on Knowledge Discovery from Data (TKDD), 2021, 16(3): 1-21.

[18] Ferguson NM, Cummings DA, Fraser C, Cajka JC, Cooley PC, Burke DS. Strategies for mitigating an influenza pandemic Nature, 2006, 442(7101): 448-452.

[19] Fonte C, Minghini M, Antoniou V, Patriarca J, See L. Classification of building function using available sources of vgi ISPRS-International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 2018, 42: 209-215

[20] Gonzalez MC, Hidalgo CA, Barabasi A-L. Understanding individual human mobility patterns Nature, 2008, 453(7196): 779-782.

[21] Hancock GR, Freeman MJ. Power and sample size for the root mean square error of approximation test of not close fit in structural equation modeling Educational and Psychological Measurement, 2001, 61(5): 741-758.

[22] Herfort B, Lautenbach S, Porto de Albuquerque J, Anderson J, Zipf A. A spatio-temporal analysis investigating completeness and inequalities of global urban building data in openstreetmap Nature Communications, 2023, 14(1): 3985.

[23] Horner MW. Spatial dimensions of urban commuting: A review of major issues and their implications for future geographic research The Professional Geographer, 2004, 56(2): 160-173.

[24] Jiang R, Cai Z, Wang Z, Yang C, Fan Z, Chen Q, Tsubouchi K, Song X, Shibasaki R. Deepcrowd: A deep model for large-scale citywide crowd density and flow prediction IEEE Transactions on Knowledge and Data Engineering, 2021, 35(1): 276-290

[25] Koca, D., Schmöcker, J. D., & Fukuda, K. (2021). Origin-destination matrix estimation by deep learning using maps with new york case study. In 2021 7th International Conference on Models and Technologies for Intelligent Transportation Systems (MT-ITS) (pp. 1–6). IEEE.

[26] Kotsubo M, Nakaya T. Kernel-based formulation of intervening opportunities for spatial interaction modelling Scientific Reports, 2021, 11(1): 950.

[27] Layman CC, Horner MW. Comparing methods for measuring excess commuting and jobs-housing balance: Empirical analysis of land use changes Transportation Research Record, 2010, 2174(1): 110-117.

[28] Lee M, Holme P. Relating land use and human intra-city mobility PloS one, 2015, 10(10): e0140152.

[29] Lenormand, M., Huet, S., Gargiulo, F., & Deffuant, G. (2012). A universal model of commuting networks. PLoS ONE, 7(10), 1–7.

[30] Levinson DM. Accessibility and the journey to work Journal of transport geography, 1998, 6(1): 11-21.

[31] Li, M.-H., Chen, B.-Y., & Li, C.-T. (2022). A hybird method with gravity model and nearest-neighbor search for trip destination prediction in new metropolitan areas. In 2022 IEEE International Conference on Big Data (Big Data) (pp. 6553–6560). IEEE.

[32] Liang, Y., Ouyang, K., Sun, J., Wang, Y., Zhang, J., Zheng, Y., Rosenblum, D., & Zimmermann, R. (2021). Fine-grained urban flow prediction. In Proceedings of the Web Conference 2021 (pp. 1833–1845). New York: Association for Computing Machinery.

[33] Liu X, Long Y. Automated identification and characterization of parcels with openstreetmap and points of interest Environment and Planning B: Planning and Design, 2016, 43(2): 341-360.

[34] Liu, Z., Miranda, F., Xiong, W., Yang, J., Wang, Q., & Silva, C. (2020). Learning geo-contextual embeddings for commuting flow prediction. In Proceedings of the AAAI conference on artificial intelligence (vol. 34, pp. 808–816). Washington: AAAI Press.

[35] Lundberg, S. M. & Lee, S.-I. (2017). A unified approach to interpreting model predictions. In Proceedings of the 31st International Conference on Neural Information Processing Systems, NIPS’17 (pp. 4768–4777). Curran Associates Inc.

[36] Luxen, D. & Vetter, C. (2011). Real-time routing with openstreetmap data. In Proceedings of the 19th ACM SIGSPATIAL international conference on advances in geographic information systems (pp. 513–516). New York: Association for Computing Machinery.

[37] Masucci, A. P., Serras, J., Johansson, A., & Batty, M. (2013). Gravity versus radiation models: On the importance of scale and heterogeneity in commuting flows. Physical Review E—Statistical, Nonlinear, and Soft Matter Physics, 88(2), 022812.

[38] Morton, A., Piburn, J., & Nagle, N. (2018). Need a boost? a comparison of traditional commuting models with the xgboost model for predicting commuting flows (short paper). In 10th International Conference on Geographic Information Science (GIScience 2018). Schloss-Dagstuhl-Leibniz Zentrum für Informatik.

[39] NYC, D. o. C. P. (2015). Pluto and mappluto. https://www.nyc.gov/site/planning/data-maps/open-data/dwn-pluto-mappluto.page. Accessed 3 June 2024.

[40] N.Y.C, O. (2024). Nyc opendata. https://data.cityofnewyork.us/Housing-Development/Building-Footprints/nqwf-w8eh. Accessed 3 June 2024.

[41] OSM, c. (2024). Openstreetmap. https://www.openstreetmap.org. Accessed 3 June 2024.

[42] Pourebrahim N, Sultana S, Niakanlahiji A, Thill J-C. Trip distribution modeling with twitter data Computers, Environment and Urban Systems, 2019, 77: 101354.

[43] Ren Y, Ercsey-Ravasz M, Wang P, González MC, Toroczkai Z. Predicting commuter flows in spatial networks using a radiation model based on temporal ranges Nature communications, 2014, 5(1): 1-9.

[44] Robinson, C. & Dilkina, B. (2018). A machine learning approach to modeling human migration. In Proceedings of the 1st ACM SIGCAS Conference on Computing and Sustainable Societies (pp. 1–8). New York: Association for Computing Machinery.

[45] Rodrigue J-P The geography of transport systems, 2020 Routledge.

[46] Rong C, Feng J, Ding J. Goddag: Generating origin-destination flow for new cities via domain adversarial training IEEE Transactions on Knowledge and Data Engineering, 2023, 35(10): 10048-10057.

[47] Rong C, Li T, Feng J, Li Y. Inferring origin-destination flows from population distribution IEEE Transactions on Knowledge and Data Engineering, 2021, 35(1): 603-613

[48] Schneider M. Gravity models and trip distribution theory Papers in Regional Science, 1959, 5(1): 51-56.

[49] Simini F, Barlacchi G, Luca M, Pappalardo L. A deep gravity model for mobility flows generation Nature communications, 2021, 12(1): 6576.

[50] Spadon, G., Carvalho, A.C.d., Rodrigues-Jr, J.F., & Alves, L. G. (2019). Reconstructing commuters network using machine learning and urban indicators. Scientific reports, 9(1), 11801.

[51] Stouffer SA. Intervening opportunities: A theory relating mobility and distance American sociological review, 1940, 5(6): 845-867.

[52] Stouffer SA. Intervening opportunities and competing migrants Journal of regional science, 1960, 2(1): 1-26.

[53] Vargas-Munoz JE, Srivastava S, Tuia D, Falcao AX. Openstreetmap: Challenges and opportunities in machine learning and remote sensing IEEE Geoscience and Remote Sensing Magazine, 2020, 9(1): 184-199.

[54] Yang Y, Herrera C, Eagle N, González MC. Limits of predictability in commuting flows in the absence of data for calibration Scientific reports, 2014, 4(1): 5662.

[55] Yao X, Gao Y, Zhu D, Manley E, Wang J, Liu Y. Spatial origin-destination flow imputation using graph convolutional networks IEEE Transactions on Intelligent Transportation Systems, 2020, 22(12): 7474-7484.

[56] Yin G, Huang Z, Bao Y, Wang H, Li L, Ma X, Zhang Y. Convgcn-rf: A hybrid learning model for commuting flow prediction considering geographical semantics and neighborhood effects GeoInformatica, 2023, 27(2): 137-157.

[57] Zeng, J., Zhang, G., Rong, C., Ding, J., Yuan, J., & Li, Y. (2022). Causal learning empowered od prediction for urban planning. In Proceedings of the 31st ACM International Conference on Information & Knowledge Management (pp. 2455–2464). New York: Association for Computing Machinery.

[58] Zhang, J., Zheng, Y., & Qi, D. (2017). Deep spatio-temporal residual networks for citywide crowd flows prediction. In Proceedings of the AAAI conference on artificial intelligence (vol. 31). Palo Alto: AAAI Press.

[59] Zhou F, Li L, Zhang K, Trajcevski G. Urban flow prediction with spatial-temporal neural odes Transportation Research Part C: Emerging Technologies, 2021, 124: 102912.

[60] Zhou Q, Zhang Y, Chang K, Brovelli MA. Assessing OSM building completeness for almost 13,000 cities globally International Journal of Digital Earth, 2022, 15(1): 2400-2421.

[61] Zipf GK. The p 1 p 2/d hypothesis: On the intercity movement of persons American sociological review, 1946, 11(6): 677-686.

Funding

National Science Foundation(2109647)

RIGHTS & PERMISSIONS

The Author(s)