GIS-Based Traffic Volume Estimation Using Spatial Interpolation Techniques: A Review of Methods, Applications, Validation, and Research Gaps

Author

Mr. Pravej Akhtar, Dr. Arun Kumar Patel


Abstract

 Traffic volume is a fundamental parameter in transportation planning, road design, traffic management, and road-safety assessment. However, traffic counts are generally available at selected monitoring stations, while many road segments remain unmonitored because continuous traffic data collection requires substantial equipment, time, and financial resources. Geographic Information Systems (GIS) provide a spatial framework for integrating traffic counts with road-network characteristics and estimating traffic volumes at locations where direct observations are unavailable. This review examines the application of spatial interpolation techniques for traffic volume estimation, focusing on inverse distance weighting (IDW), ordinary kriging, universal kriging, natural neighbour interpolation, geographically weighted regression (GWR), network-based interpolation, and hybrid geostatistical approaches. Previous studies have demonstrated the potential of these methods for estimating annual average daily traffic and filling gaps in traffic-count datasets. Selby and Kockelman (2013) investigated universal kriging and GWR for predicting traffic levels at unmeasured locations, while Lowry (2014) used network centrality to improve traffic-count estimation. Yang et al. (2018) demonstrated the value of incorporating both spatial and temporal relationships for traffic-volume data imputation. More recent work has explored network regression kriging and machine-learning-based approaches. The review highlights that interpolation accuracy depends on the distribution and representativeness of observed counts, road-network connectivity, temporal consistency, explanatory variables, and validation strategy. Conventional Euclidean-distance interpolation may not adequately represent the structure of a road network. Therefore, network-aware and hybrid methods may be preferable where reliable road-network data and supporting variables are available. The review recommends a GIS-based framework combining traffic-count surveys, road-network attributes, comparative interpolation, independent validation, and uncertainty assessment to produce more reliable traffic-volume estimates for urban road networks.



Keywords

Traffic volume; Geographic Information System; spatial interpolation; inverse distance weighting; kriging; road network; annual average daily traffic; traffic estimation.



Full Text:

Download Paper PDF


References


  • Katayama, H., Yasuda, S., & Fuse, T. (2022). Comparative validation of spatial interpolation methods for traffic density for data-driven travel-time prediction. International Journal of Intelligent Transportation Systems Research, 20, 830–837. https://doi.org/10.1007/s13177-022-00326-0
  • Lowry, M. (2014). Spatial interpolation of traffic counts based on origin–destination centrality. Journal of Transport Geography, 36, 98–105. https://doi.org/10.1016/j.jtrangeo.2014.03.007
  • Selby, B., & Kockelman, K. M. (2013). Spatial prediction of traffic levels in unmeasured locations: Applications of universal kriging and geographically weighted regression. Journal of Transport Geography, 29, 24–32. https://doi.org/10.1016/j.jtrangeo.2012.12.009
  • Shamo, B., Asa, E., & Membah, J. (2015). Linear spatial interpolation and analysis of annual average daily traffic data. Journal of Computing in Civil Engineering, 29(1). https://doi.org/10.1061/(ASCE)CP.1943-5487.0000281
  • Shiode, N. (2011). Street-level spatial interpolation using network-based IDW and ordinary kriging. Transactions in GIS, 15(4), 457–477. https://doi.org/10.1111/j.1467-9671.2011.01278.x
  • Wang, X., & Kockelman, K. M. (2009). Forecasting network data: Spatial interpolation of traffic counts from Texas data. Transportation Research Record: Journal of the Transportation Research Board, 2105(1). https://doi.org/10.3141/2105-13
  • Wu, M., Kwon, T. J., & El-Basyouny, K. (2022). A hybrid geostatistical method for estimating citywide traffic volumes—A case study of Edmonton, Canada. Journal of Geographical Research, 5(2). https://doi.org/10.30564/jgr.v5i2.4513
  • Yang, H., Yang, J., Han, L. D., Liu, X., Pu, L., Chin, S.-M., & Hwang, H. (2018). A kriging based spatiotemporal approach for traffic volume data imputation. PLOS ONE, 13(4), e0195957. https://doi.org/10.1371/journal.pone.0195957

 

Share your valuable work from Social Media Buttons