Projected Statewide Traffic Forecast Parameters using Artificial Neural Networks

Abstract

Design-hour volume (DHV) and directional DHV (DDHV) are important traffic forecast parameters for both planning and operational studies. They are used for roads and intersection design and operational analysis. Estimating these two parameters requires a record of hourly volumes for every hour in a year. Therefore, permanent traffic counters are usually used to keep a record of those hourly volumes. The use of permanent counters faces several challenges because of adjacent construction activities and hardware or communication failure. These challenges result in the missing part of the collected data. Moreover, estimating DHV and DDHV based on short-term traffic counts is often needed. In this research, an artificial intelligence approach is used to estimate DHV and DDHV for roadways with different functional classifications. An artificial neural network model, which utilises historical records of annual average daily traffic along with other road characteristics, such as number of lanes and functional classification, is developed. Results show that the model was able to achieve a highly accurate and reliable DHV and DDHV estimates.