Enhancing Statewide Annual Average Daily Traffic Estimation with Ubiquitous Probe Vehicle Data

Annual average daily traffic (AADT) is a critical input into many transportation applications, particularly safety reporting. For example, the Highway Safety Improvement Program in the U.S. requires states to make AADT data for all public paved roadways accessible by 2026. Because collecting traffic counts on every network segment is prohibitively expensive, a method capable of accurately estimating AADT on unmonitored segments is of great value to state DOTs. The ubiquitous probe vehicle data present a great opportunity to this end. This paper presents an enhanced method for statewide AADT estimation by leveraging such data in Kentucky. The use of the probe data is explored in two ways. First, an annual average daily probes (AADP) variable is derived from hourly probe counts; second, a betweenness centrality (BC) variable is calculated using probe speeds. Including both variables and using the random forest model results in model performance that exceeds those previously reported for statewide applications. Incorporating AADP and BC improves the accuracy of AADT estimates by 30%–37% for all roads and 23%–43% for highways in functional classes 5–7, compared with only using sociodemographic and roadway characteristics. These results demonstrate the value of the probe data for enhancing AADT estimation. The analysis further shows that on roadways having more than 53 AADP or an average of 2.2 probe counts per hour, the median and the mean absolute percent errors are below 20% and 25%, respectively. These findings have practical implications for state DOTs wanting to maximize the utility of probe vehicle data.

Development of Statewide Annual Average Daily Traffic Estimation Model from Short-Term Counts: A Comparative Study for South Carolina

Annual Average Daily Traffic (AADT) is an important parameter for traffic engineering analysis. Departments of Transportation continually collect traffic count using both permanent count stations (i.e., Automatic Traffic Recorders or ATRs) and temporary short-term count stations. In South Carolina, 87% of the ATRs are located on interstates and arterial highways. For most secondary highways (i.e., collectors and local roads), AADT is estimated based on short-term counts. This paper develops AADT estimation models for different roadway functional classes with two machine learning techniques: Support Vector Regression (SVR) and Artificial Neural Network (ANN). The models predict AADT from short-term counts. The results are first compared against each other, using the 2011 ATR data, to identify the best models. Then, the results of the best models are compared against both the regression-based model and factor-based model. The comparison reveals the superiority of the SVR model for AADT estimation for different roadway functional classes over all other methods. Among models for different roadway functional classes, developed with the 2011 ATR data, the SVR-based models show minimum errors in estimating AADT compared to the ANN-based, regression-based, and factor-based models, depicting the superiority of the SVR-based model for all roadway functional classes over other models in terms of AADT estimation accuracy. SVR models are validated for each roadway functional class using the 2016 ATR data and short-term count data collected by the South Carolina Department of Transportation (SCDOT). The validation results show that the SVR-based AADT estimation models can be used by the SCDOT as a reliable option to predict AADT from the short-term counts.

A Comparison of Short Duration Traffic Counts Methodologies for Estimating Annual Average Daily Traffic

Annual average daily traffic (AADT) serves the important basic data in transportation sector. Future level of service is forecasted, based on design traffic volume. AADT is used as design traffic which is the basic traffic volume in transportation plan. But AADT is estimated using short duration traffic counts at most sites because permanent traffic counts are installed at limited sites. A various of methodologis about short duration traffic counts are used to estimate AADT. This study compared with typical short duration traffic counts methodologies in USA and Korea. Short duration traffic counts in USA typically are defined as stations where 24-hour, 48-hour of data is collected. In Korea, short duration traffic counts are collected at one day (24-hour) or two days (not two consecutive days). So this study compared among each short duration traffic counts methodology: one day (24-hour), two consecutive days (48-hour), not two consecutive days (twice per year). Short duration traffic counts surveyed twice per year is the best method to reduce AADT estimation error among analyzed methodologies. The analysis found that in case adjustment factor is applied to estimate AADT, AADT estimation error is further lowered.

Use of Reduction-Effectiveness Ratios to Evaluate Reduced Traffic Data Collection Plans

Because of budget shortfalls in recent years, state departments of transportation (DOTs) must adjust their traffic data collection plans by reducing data collection locations or extending data collection cycles; however, few studies have been performed to evaluate the cost-effectiveness of various efforts to reduce data collection. This study developed a quantitative method for evaluating the impact of various reduced plans for traffic data collection on the overall accuracy of the annual average daily traffic (AADT) estimation. The mean absolute percentage error is calculated to compare the accuracy of 10 reduced data collection plans with a base plan. In addition, a reduction-effectiveness ratio (i.e., the percentage of reduced data collection cost to the percentage of increased AADT estimation error) is proposed. Results from this study show that the current practice, which randomly selects data collection sites on the basis of different cycles, performs well in maintaining AADT estimation accuracy but may not be the most cost-effective approach. Results also show that certain types of sites, such as rural sites, lower-AADT sites, and sites with higher AADT variation, tend to produce larger errors if they are not counted. The results imply that the proposed method both provides a quantitative means with which to evaluate plans for reduced data collection and suggests ways to enhance current data collection and traffic estimation practices. The method also enriches the information provided to state departments of transportation for effective and informed decision making with limited resources.