Forecasting Network Data: Spatial Interpolation of Traffic Counts Using Texas Data

نویسندگان

  • Xiaokun Wang
  • Kara M. Kockelman
چکیده

Annual average daily traffic (AADT) values have long played an important role in transportation design, operations, planning, and policy making. However, AADT values are almost always rough estimates based on the closest short-period traffic counts, factored up using permanent automatic traffic recorder data. This study develops Kriging-based methods for mining network and count data, over time and space. Using Texas highway count data, the method forecasts future AADT values at locations where no traffic detectors are present. While low-volume road counts remain difficult to predict, available explanatory variables are very few, and extremely high-count outlier sites skew predictions in the data set used here, overall AADT-weighted median prediction error is 31% percent (across all Texas network sites). Here, Kriging performed far better than other options for spatial extrapolation − such as assigning AADT based on a point’s nearest sampling site, which yields errors of 80%. Beyond AADT estimation, Kriging is a promising way to explore spatial relationships across a wide variety of data sets, including, for example, pavement conditions, traffic speeds, population densities, land values, household incomes, and trip generation rates. Further refinements, including spatial autocorrelation functions based on network (rather than Euclidean) distances and inclusion of far more explanatory variables exist, and will further enhance estimation.

برای دانلود رایگان متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Spatial Prediction of Aadt in Unmeasured Locations 3 by Universal Kriging

27 28 ABSTRACT 29 30 This work explores the application of kriging methods for prediction of average daily traffic 31 counts across the Texas network. Results based on Euclidean distances are compared to those 32 using network distances, and both allow for strategic spatial interpolation of count values while 33 controlling for each roadway's functional classification, lane count, speed limit, ...

متن کامل

Traffic Condition Forecasting System by Floating Car Data with Data Mining Method

A traffic condition forecasting system using floating car data in conjunction with a data mining method is proposed. A register network is used to describe the congestion model. The register network denotes the dual graph of the actual road link connections. In this forecasting system, estimation and learning agents alternately calculate the results to improve the forecasting accuracy. To forec...

متن کامل

Natural Gas Price Forecasting using Kriging Interpolation Technique and Neldar-Mead Optimization Algorithm

The prediction of economic series with high volatility and high uncertainty - such as natural gas prices - is always a challenge in econometric models, because the use of traditional linear modeling models does not allow us to predict complex and nonlinear time series. Regarding the prediction of natural gas prices,  findings point to superiority of the neural network compared to regression mod...

متن کامل

Zoning hydraulic conductivity using different geostatistical methods (Case study Shavoor)

In studies of irrigation and drainage projects for drainage, it is necessary to extend the data from the sampling point to the network. Therefore, based on available data from observational wells, estimating the state of hydraulic conductivity (K) in the surrounding area. The estimation process values for locations where there is no information for them based on viewing areas called wells spati...

متن کامل

Traffic Flow Forecasting Based on Combination of Multidimensional Scaling and SVM

Scaling and SVM Zhanquan Sun, Geoffrey Fox a. Key Laboratory for Computer Network of Shandong Province, Shandong Computer Science Center, Jinan, Shandong, 250014, China b. School of Informatics and Computing, Pervasive Technology Institute, Indiana University Bloomington, Bloomington, Indiana, 47408, USA Abstract: Traffic flow forecasting is a popular research topic of Intelligent Transportatio...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2008