Comparative Assessment of Geospatial and Statistical Methods to Estimate Local Road Annual Average Daily Traffic
Publication: Journal of Transportation Engineering, Part A: Systems
Volume 147, Issue 7
Abstract
Collecting traffic data and/or estimating and reporting annual average daily traffic (AADT) is important for planning, designing, building, and maintaining the road infrastructure. However, AADT is not available for most local functionally classified roads (referred to as local roads in this paper), which comprise a major proportion of the roads in the United States. The AADT of a local road depends on geospatial data such as road density, socioeconomic and demographic characteristics, and proximity to the nearest nonlocal road. The suitability of these explanatory variables for modeling local road AADT has not been widely explored, nor have methodological approaches been comprehensively compared in the past. Therefore, the focus of this research is on exploring geospatial and statistical methods and conducting a comparative assessment to estimate local road AADT. The AADT based on traffic counts collected at 12,899 stations on local roads in North Carolina during 2014, 2015, and 2016 was considered in model development and validation. The road, socioeconomic, and demographic characteristics based on the data gathered from the North Carolina Department of Transportation (NCDOT) for 2015 were considered as the explanatory variables. Five different modeling methods were examined and compared to estimate AADT on local road links. They include traditional ordinary least squares (OLS) regression, geographically weighted regression (GWR), and geospatial interpolation methods such as kriging, inverse distance weighting (IDW), and natural neighbor interpolation. The model development and validation results showed that the GWR model performed better compared with the other considered geospatial and statistical methods. The GWR model can better capture the effect of geospatial variations in the data, by geographic location, when estimating local road AADT. Local road AADT estimates help practitioners in planning and prioritizing road infrastructure projects for future improvements and air quality estimates, in addition to Highway Safety Improvement Program (HSIP) and Highway Performance Monitoring System (HPMS) reporting.
Get full access to this article
View all available purchase options and get full access to this article.
Data Availability Statement
Some or all data, models, or code generated or used during the research are available from the authors by request.
Acknowledgments
The paper is based on a research project conducted for the North Carolina Department of Transportation (NCDOT). Special thanks are extended to Kent L. Taylor, Behshad M. Norowzi, Jamie L. Viera, Stephen P. Piotrowski, William S. Culpepper, Brian G. Murphy, and Lisa E. Penny of NCDOT, and Mike Bruff of Capital Area Metropolitan Planning Organization (CAMPO) for providing excellent support, guidance, and valuable input for successful completion of the project. The authors also thank Venkata R. Duddu, Chaitanya M. Bhure, Chandan Mannem, and Sarvani Duvvuri for their help with data processing and analysis.
Disclaimer
The contents of this paper reflect the views of the authors and not necessarily the views of the University of North Carolina at Charlotte (UNC Charlotte) or the NCDOT. The authors are responsible for the facts and the accuracy of the data presented herein. The contents do not necessarily reflect the official views or policies of either UNC Charlotte, NCDOT, or the Federal Highway Administration (FHWA) at the time of publication. This report does not constitute a standard, specification, or regulation.
References
Apronti, D., K. Ksaibati, K. Gerow, and J. J. Hepner. 2016. “Estimating traffic volume on Wyoming low volume roads using linear and logistic regression methods.” J. Traff. Transp. Eng. 3 (6): 493–506. https://doi.org/10.1016/j.jtte.2016.02.004.
Asa, E., M. Saafi, J. Membah, and A. Billa. 2012. “Comparison of linear and nonlinear kriging methods for characterization and interpolation of soil data.” J. Comput. Civ. Eng. 26 (1): 11–18. https://doi.org/10.1061/(ASCE)CP.1943-5487.0000118.
Bartier, P. M., and C. P. Keller. 1996. “Multivariate interpolation to incorporate thematic surface data using inverse distance weighting (IDW).” Comput. Geosci. 22 (7): 795–799. https://doi.org/10.1016/0098-3004(96)00021-0.
Brunsdon, C., S. Fotheringham, and M. Charlton. 1998. “Geographically weighted regression.” J. R. Stat. Soc. Ser. D Stat. 47 (3): 431–443. https://doi.org/10.1111/1467-9884.00145.
Castro, N., Y. Manoel, M. K. Jeong, and L. D. Han. 2009. “AADT prediction using support vector regression with data-dependent parameters.” Expert Syst. Appl. 36 (2): 2979–2986. https://doi.org/10.1016/j.eswa.2008.01.073.
Chang, H. H., and S. H. Cheon. 2019. “The potential use of big vehicle GPS data for estimations of annual average daily traffic for unmeasured road segments.” Transportation 46 (3): 1011–1032. https://doi.org/10.1007/s11116-018-9903-6.
Chowdhury, M., A. Sadek, Y. Ma, N. Kanhere, and P. Bhavsar. 2006. “Applications of artificial intelligence paradigms to decision support in real-time traffic management.” Transp. Res. Rec. 1968 (1): 92–98. https://doi.org/10.1177/0361198106196800111.
Das, S., and I. Tsapakis. 2020. “Interpretable machine learning approach in estimating traffic volume on low-volume roadways.” Int. J. Transp. Sci. Technol. 9 (1): 76–88. https://doi.org/10.1016/j.ijtst.2019.09.004.
Duddu, V. R., and S. S. Pulugurtha. 2013. “Principle of demographic gravitation to estimate annual average daily traffic: Comparison of statistical and neural network models.” J. Transp. Eng. 139 (6): 585–595. https://doi.org/10.1061/(ASCE)TE.1943-5436.0000537.
ESRI (Environmental Systems Research Institute). 2011. ArcGIS Pro 2.5.2. Redlands, CA: ESRI.
FHWA (Federal Highway Administration). 2013. “Highway functional classification concepts, criteria and procedures.” Accessed September 7, 2019. https://www.fhwa.dot.gov/planning/processes/statewide/related/highway_functional_classifications/fcauab.pdf.
FHWA (Federal Highway Administration). 2018. “Highway performance monitoring system field manual.” Accessed December 2, 2018. https://www.fhwa.dot.gov/policyinformation/hpms/fieldmanual/page00.cfm.
Fotheringham, A., C. Brunsdon, and M. Charlton. 2002. Geographically weighted regression: The analysis of spatially varying relationships. West Sussex, UK: Wiley.
Gadda, S., A. Magoon, and K. M. Kockelman. 2007. “Estimates of AADT: Quantifying the uncertainty.” In Proc., 86th Annual Meeting of Transportation Research Board. Washington, DC: Transportation Research Board.
Gross, F. 2017. Highway safety improvement program (HSIP) evaluation guide. Washington, DC: Federal Highway Administration.
Khan, S. M., S. Islam, M. Z. Khan, K. Dey, M. Chowdhury, N. Huynh, and M. Torkjazi. 2018. “Development of statewide annual average daily traffic estimation model from short-term counts: A comparative study for South Carolina.” Transp. Res. Rec. 2672 (43): 55–64. https://doi.org/10.1177/0361198118798979.
Khan, Z., S. M. Khan, K. Dey, and M. Chowdhury. 2019. “Development and evaluation of recurrent neural network-based models for hourly traffic volume and annual average daily traffic prediction.” Transp. Res. Rec. 2673 (7): 489–503. https://doi.org/10.1177/0361198119849059.
Krivoruchko, K. 2012. Empirical bayesian kriging. Redlands, CA: Environmental Systems Research Institute.
Krivoruchko, K., and A. Gribov. 2019. “Evaluation of empirical Bayesian kriging.” Spatial Stat. 32: 100368. https://doi.org/10.1016/j.spasta.2019.100368.
Kusam, P. R., and S. S. Pulugurtha. 2015. “Spatial proximity and dependency to model urban travel demand.” J. Urban Plann. Dev. 142 (2): 04015014. https://doi.org/10.1061/(ASCE)UP.1943-5444.0000281.
Ma, Y., M. Chowdhury, A. Sadek, and M. Jeihani. 2012. “Integration of vehicle infrastructure integration (VII) system and artificial intelligence (AI) for online travel time prediction.” IEEE Trans. Intell. Transp. Syst. 13 (3): 1369–1382. https://doi.org/10.1109/TITS.2012.2198644.
McCord, M. R., and P. K. Goel. 2009. Estimating AADT from combined air photos and ground based data: System design, prototyping, and testing. NEXTRANS Proj. No 002OY01, Final Rep. USDOT Region V Regional Univ. Transportation Center. Columbus, OH: Ohio State University.
McCord, M. R., Y. Yang, Z. Jiang, B. Coifman, and P. K. Goel. 2003. “Estimating annual average daily traffic from satellite imagery and air photos: Empirical results.” Transp. Res. Rec. 1855 (1): 136–142. https://doi.org/10.3141/1855-17.
Mohamad, D., K. C. Sinha, T. Kuczek, and C. F. Scholer. 1998. “Annual average daily traffic prediction model for county roads.” Transp. Res. Rec. 1617 (1): 69–77. https://doi.org/10.3141/1617-10.
Neveu, A. J. 1983. “Quick-response procedures to forecast rural traffic.” Transp. Res. Rec. 944 (1): 47–53.
North Carolina State Data Center. 2018. “The urban and rural faces of North Carolina.” Accessed January 27, 2021. https://files.nc.gov/ncosbm/documents/files/2018ACSNC.pdf.
Pulugurtha, S. S., and P. R. Kusam. 2012. “Modeling annual average daily traffic with integrated spatial data from multiple network buffer bandwidths.” Transp. Res. Rec. 2291 (1): 53–60. https://doi.org/10.3141/2291-07.
Raja, P., D. Mehrnaz, and M. D. Anderson. 2018. “Estimation of average daily traffic on low volume roads in Alabama.” Int. J. Traff. Transp. Eng. 7 (1): 1–6. https://doi.org/10.5923/j.ijtte.20180701.01.
Reksten, J. H., and A. Salberg. 2021. “Estimating traffic in urban areas from very-high resolution aerial images.” Int. J. Remote Sens. 42 (3): 865–883. https://doi.org/10.1080/01431161.2020.1815891.
Robinson, T. P., and G. Metternicht. 2006. “Testing the performance of spatial interpolation techniques for mapping soil properties.” Comput. Electron. Agric. 50 (2): 97–108. https://doi.org/10.1016/j.compag.2005.07.003.
Saha, S. K., and J. D. Fricker. 1986. “Traffic volume forecasting methods for rural state highways.” Transp. Res. Rec. 1203 (1): 10–26.
Seaver, W. L., A. Chatterjee, and M. L. Seaver. 2000. “Estimation of traffic volume on rural local roads.” Transp. Res. Rec. 1719 (1): 121–128. https://doi.org/10.3141/1719-15.
Selby, B., and K. M. Kockelman. 2013. “Spatial prediction of traffic levels in unmeasured locations: Applications of universal kriging and geographically weighted regression.” J. Transp. Geogr. 29: 24–32. https://doi.org/10.1016/j.jtrangeo.2012.12.009.
Shamo, B., E. Asa, and J. Membah. 2015. “Linear spatial interpolation and analysis of annual average daily traffic data.” J. Comput. Civ. Eng. 29 (1): 04014022. https://doi.org/10.1061/(ASCE)CP.1943-5487.0000281.
Sharma, S., P. Lingras, F. Xu, and P. Kilburn. 2001. “Application of neural networks to estimate AADT on low-volume roads.” J. Transp. Eng. 127 (5): 426–432. https://doi.org/10.1061/(ASCE)0733-947X(2001)127:5(426).
Sharma, S. C., P. Lingras, G. X. Liu, and F. Xu. 2000. “Estimation of annual average daily traffic on low-volume roads: Factor approach versus neural networks.” Transp. Res. Rec. 1719 (1): 103–111. https://doi.org/10.3141/1719-13.
Sibson, R. 1981. “A brief description of natural neighbor interpolation.” Chap. 2 in Interpolating multivariate data, 21–36. New York: Wiley.
Smith, B. L., B. M. Williams, and R. J. Oswald. 2002. “Comparison of parametric and nonparametric models for traffic flow forecasting.” Transp. Res. Part C: Emerging Technol. 10 (4): 303–321. https://doi.org/10.1016/S0968-090X(02)00009-8.
Sun, X., and S. Das. 2015. Developing a method for estimating AADT on all Louisiana roads. Baton Rouge, LA: Louisiana Department of Transportation.
Tang, Y. F., W. H. Lam, and P. L. Ng. 2003. “Comparison of four modeling techniques for short-term AADT forecasting in Hong Kong.” J. Transp. Eng. 129 (3): 271–277. https://doi.org/10.1061/(ASCE)0733-947X(2003)129:3(271).
Wang, X., and K. Kockelman. 2009. “Forecasting network data: Spatial interpolation of traffic counts from Texas data.” Transp. Res. Rec. 2105 (1): 100–108. https://doi.org/10.3141/2105-13.
Watson, D. 1992. Contouring: A guide to the analysis and display of spatial data. Tarrytown, NY: Pergamon Press.
Wheeler, D., and M. Tiefelsdorf. 2005. “Multicollinearity and correlation among local regression coefficients in geographically weighted regression.” J. Geogr. Syst. 7 (2): 161–187. https://doi.org/10.1007/s10109-005-0155-6.
Wheeler, D. C., and A. Páez. 2010. “Geographically weighted regression.” In Handbook of applied spatial analysis, 461–486. Berlin: Springer.
Xia, Q., F. Zhao, Z. Chen, L. Shen, and D. Ospina. 1999. “Estimation of annual average daily traffic for nonstate roads in a Florida county.” Transp. Res. Rec. 1660 (1): 32–40. https://doi.org/10.3141/1660-05.
Zhang, X., and M. Chen. 2020. “Enhancing statewide annual average daily traffic estimation with ubiquitous probe vehicle data.” Transp. Res. Rec. 2674 (9): 649–660. https://doi.org/10.1177/0361198120931100.
Zhao, F., and S. Chung. 2001. “Contributing factors of annual average daily traffic in a Florida county: Exploration with geographic information system and regression models.” Transp. Res. Rec. 1769 (1): 113–122. https://doi.org/10.3141/1769-14.
Zhao, F., and N. Park. 2004. “Using geographically weighted regression models to estimate annual average daily traffic.” Transp. Res. Rec. 1879 (1): 99–107. https://doi.org/10.3141/1879-12.
Information & Authors
Information
Published In
Journal of Transportation Engineering, Part A: Systems
Volume 147 • Issue 7 • July 2021
Copyright
© 2021 American Society of Civil Engineers.
History
Received: Oct 26, 2020
Accepted: Feb 19, 2021
Published online: May 13, 2021
Published in print: Jul 1, 2021
Discussion open until: Oct 13, 2021
Authors
Metrics & Citations
Metrics
Citations
Download citation
If you have the appropriate software installed, you can download article citation data to the citation manager of your choice. Simply select your manager software from the list below and click Download.