Spatial Prediction of AADT in Unmeasured Locations by Universal Kriging

摘要: This work explores the application of kriging methods for prediction average daily traffic counts across Texas network. Both results based on both euclidean and roadway network distances (between new count sites existing data-collection sites) are compared, allowing strategic spatial interpolation values, while comparing functional classification, lane numbers, speed limits, other site attributes. Universal is found to reduce errors (in practically statistically significant ways) over non-spatial regression techniques, thought, at some sites, remain quite high, particularly in less dense areas small roads near major highways. Interestingly, estimation parameters by showed no enhanced performance Euclidean distances, which require data much more easily computed.