Estimating annual average daily traffic (AADT) data on low-volume roads with the cokriging technique and census/population data

Abstract

Geostatistical methods such as simple, ordinary, and universal kriging are not multivariate models in the usual statistical function. Notwithstanding, simple, ordinary, and universal kriging techniques utilize random function models that include unlimited random variables while modeling one attribute. The cokriging technique is a multivariate estimation method that can simultaneously model two or more attributes, defined with the same domains as coregionalization. For a successful structural analysis, it is necessary to have a minimum amount of each domain's measured attributes. The assumption is that data integration methods such as cokriging may yield more reliable models because their strength is drawn from multiple variables. This study investigates the impact of the population as a variable on traffic volumes. The investigation adopts the annual average daily traffic (AADT) from Montana, Minnesota, and Washington as one attribute and countywide population as a second attribute (or factor controlling traffic volumes). AADT data for this research span from 2009 to 2016. The cross-validation results of the model types explored with the cokriging technique are successfully used to evaluate the interpolation technique's performance and select optimal models for each state. The investigation results based on the cross-validation confirm the model's usefulness. The interpolation surface maps from the Montana and Minnesota models accurately represent the states' traffic and population density. The Washington model had a few exceptions; therefore, it did not necessarily represent the traffic and population density. An indication that other factors may impact the results. Consequently, it is worth exploring the impact of tourism, shopping, recreation centers, and possible transiting patterns throughout the state.