Sandeep Datla

Imputation of Missing Traffic Data during Holiday Periods

Abstract Highway and transportation agencies implement large-scale traffic monitoring programs to fulfill the planning, operation and management needs of highway systems. These monitoring programs typically use inductive loops as detectors to collect traffic data. Because of the harsh environment in which they operate, they are highly prone to malfunctioning and providing erroneous or missing data. If this occurs during holiday periods when the increase in highway traffic is often substantial, there is a good chance that traffic peaking and variation will be underestimated. This paper discusses the adaptability of available imputation techniques for holiday traffic and then introduces a new procedure using non-parametric regression – the k-nearest neighbor (k-NN) method. It is found that the performance of the k-NN method is consistent and reasonable for different holidays and types of highway. In addition, it is also concluded that the data requirements for this method are flexible.

Variation of Impact of Cold Temperature and Snowfall and Their Interaction on Traffic Volume

This paper presents a detailed investigation of highway traffic variations with severity of cold, the amount of snow, and various combinations of cold and snow intensities. Separate analyses for starting, middle, and ending months of winter seasons are conducted to study the variations in traffic-weather relationships within the winter season. The study is based on hourly traffic flow data from 350 permanent traffic counter sites located on the provincial highway system of Alberta, Canada, and weather data obtained from nearby Environment Canada weather stations, from 1995 to 2005. Multiple regression analysis is used in the modeling process. The model parameters include three sets of variables: the amount of snowfall as a quantitative variable, categorized cold as a dummy variable, and an interaction variable formed by the product of these two variables. The study results indicate that the association of highway traffic flow with cold and snow varies with day of week, hour of day, and severity of weather conditions. A reduction of 1% to 2% in traffic volume for each centimeter of snowfall is observed when the mean temperature is above 0°C. For the days with zero precipitation, reductions in traffic volume due to mild and severe cold are 1% and 31%, respectively. An additional reduction of 0.5% to 3% per centimeter of snowfall results when snowfall occurs during severe cold conditions. Study results show lesser impact of adverse weather conditions on traffic during severe winter months (mid-November to mid-March) and the months thereafter compared with early (starting) winter months.

Statistical Investigations of Snowfall and Temperature Interaction with Passenger Car and Truck Traffic on Primary Highways in Canada

AbstractWinter weather conditions such as extremely cold temperatures, heavy snowfall, and high wind chills are common occurrences in Canada. Impacts of such adverse weather conditions on total highway traffic volume have been the subject of several research studies in the past. However, none of the past studies investigated thoroughly the impacts of severe cold and heavy snowfall on temporal and spatial variations of truck traffic on Canadian highways. Impacts of weather on route choice behavior of truck and passenger car drivers have also not been addressed in the past. This paper presents an in-depth analysis of the winter weather impacts on classified traffic volume in terms of passenger cars and trucks with considerations of highway types. This study is based on large traffic and weather data sets from weigh-in-motion sites and weather stations in Alberta, Canada. The data were collected from six sites located on two primary highways: Highway 2 and Highway 2A, in Alberta. Winter-weather traffic model...

The impact of cold and snow on weekday and weekend highway total and passenger cars traffic volumes

Presented in this paper is an investigation of the impact of cold and snow on daily traffic volumes of total traffic and passenger cars. It is based on a detailed case study of five years of Weigh-In-Motion data recorded continuously at a highway site in Alberta, Canada. Dummy-variable regression models are used to relate daily traffic volumes with snowfall and categorized cold variables. The importance of all the independent variables used in the model are established by conducting tests of statistical significance. The total traffic and passenger car volumes are influenced by both the snowfall and the cold categories. Plots of the partial effect of each independent variable on the dependent variable are generated. It is found that a daily snowfall of 10 cm may cause a 25% reduction in the daily volume of passenger cars, and temperatures below -25°C may reduce the passenger car volumes by 10% or more. It is believed that the developed traffic-weather models of this study can benefit highway agencies in developing more advanced imputation method or identifying weather adjustment factors for accurate estimation of AADT from short duration traffic counts. Language: en

Consideration of Weather Conditions to Estimate Missing Traffic Data

Estimating missing traffic data is an essential task for transportation agencies. Several imputation methods have been developed in the literature to estimate the missing traffic volumes. However, none have considered the variation in traffic patterns caused by severe winter weather conditions. Highway traffic volumes are highly influenced by weather conditions; therefore, a detailed investigation was carried out to develop relationships between weather and highway traffic volumes and to use them for reliable estimation of missing traffic volumes. The study was based on hourly traffic data from permanent traffic counter sites located on provincial highways of Alberta, Canada, using 11 years of data from 1995 to 2005. Weather data were obtained from Environment Canada weather stations located within 10 mi of the chosen permanent traffic counter sites. Cold and snowfall represented the winter conditions. Multiple regression analysis was used to develop relationships between hourly traffic volumes, categorized cold, and total snowfall. The study models showed a strong association between traffic volumes and weather conditions. Weekend traffic was more susceptible to weather than weekday traffic. In cases of extreme cold (≤25°C), the peak hours experienced fewer reductions in traffic (6% to 13%) than off-peak hours (10% to 17%). The amount of reduction in traffic volume caused by each centimeter of snowfall varied from 0.5% to 2.0%. The traffic–weather relationships developed were used to estimate missing hourly volumes. The errors were 30% to 75% less than the traditional methods used by highway agencies.