Browse > Article
http://dx.doi.org/10.11108/kagis.2010.13.4.138

A Geostatistical Approach for Improved Prediction of Traffic Volume in Urban Area  

Kim, Ho-Yong (Department of Civil, Architecture and Environment, Missouri University of Science and Technology)
Publication Information
Journal of the Korean Association of Geographic Information Studies / v.13, no.4, 2010 , pp. 138-147 More about this Journal
Abstract
As inaccurate traffic volume prediction may result in inadequate transportation planning and design, traffic volume prediction based on traffic volume data is very important in spatial decision making processes such as transportation planning and operation. In order to improve the accuracy of traffic volume prediction, recent studies are using the geostatistical approach called kriging and according to their reports, the method shows high predictability compared to conventional methods. Thus, this study estimated traffic volume data for St. Louis in the State of Missouri, USA using the kriging method, and tested its accuracy by comparing the estimates with actual measurements. In addition, we suggested a new method for enhancing the accuracy of prediction by the kriging method. In the new method, we estimated traffic volume data: first, by applying anisotropy, which is a characteristic of traffic volume data appearing in determining variogram factors; and second, by performing co-kriging analysis using interstate highway, which is in a high spatial correlation with traffic volume data, as a secondary variable. According to the results of the analysis, the analysis applying anisotropy showed higher accuracy than the kriging method, and co-kriging performed on the application of anisotropy produced the most accurate estimates.
Keywords
AADT; Variogram; Ordinary Kriging; Co-Kriging; Anisotropy;
Citations & Related Records
Times Cited By KSCI : 3  (Citation Analysis)
연도 인용수 순위
1 감사원. 2009. 도로부문 교통기초자료 구축사업의 현황 및 문제점: 교통수요 예측 자료를 중심으로. pp.19-30.
2 국토해양부. 2009. 도로 교통량 통계연보 : 고속국도.일반국도.지방도 교통량 2008. 국토해양부 [편]. pp.3-4.
3 김강수. 2007. SOC 투자의사결정 합리화 방안 -도로부문 교통량 추정위험분석을 중심으로. 한국개발원. pp.1-8.
4 김호용. 2010. 공간통계기법을 이용한 태양열발전시설 입지 정확성 향상 방안. 한국지리정보학회지 13(2):146-156.
5 박노욱, 장동호. 2008. 수치표고모델과 다변량 크리깅을 이용한 기온 및 강수 분포도 작성. 대한지리학회지 43(6):1002-1015.   과학기술학회마을
6 정선영. 2005. 인프라 21 세미나 - 교통량 예측을 위한 공간통계학의 응용. 국토 285:151-154.
7 최종근. 2002. 공간정보모델링: 크리깅과 최적화 기법. 구미서관, 서울. pp.125-163.
8 Eom, J.K., M.S. Park, T.Y. Heo and L.F. Huntsinger. 2006. Improving the prediction of annual average daily traffic for nonfreeway facilities by applying a spatial statistical method. Journal of the Transportation Research Board 1968:20-29.   DOI
9 ESRI. 2001. ArcGIS Geostatistical Analyst Tutorial. 26pp.
10 Issacx, E.H. and M. Sivastava. 1989. An Introduction to Applied Geostatistics, New York: Oxford University Press, 146pp.
11 Park, S. 2009. Estimating air temperature over mountainous terrain by combining hypertemporal satellite LST data and multivariate geostatistical methods. Journal of the Korean Geographical Society 44(2):105-121.   과학기술학회마을
12 Tang, Y.F., W.H.K. Lam and P.L.P. Ng. 2003. Comparison of four modeling techniques for short-term AADT forecasting in Hong Kong. Journal of Transportation Engineering 129(3):271-277.   DOI   ScienceOn
13 Wang X. and K.M. Kocklman. 2009. Forecasting network data: spatial interpolation of traffic counts from Texas data. Journal of the Transportation Research Board 2105:100-108.   DOI
14 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. Journal of the Transportation Research Board 1796:113-122.