Development and Evaluation of Recurrent Neural Network-Based Models for Hourly Traffic Volume and Annual Average Daily Traffic Prediction

Abstract

The prediction of high-resolution hourly traffic volumes of a given roadway is essential for transportation planning. Traditionally, automatic traffic recorders (ATR) are used to collect these hourly volume data. These large datasets are time-series data characterized by long-term temporal dependencies and missing values. Regarding the temporal dependencies, all roadways are characterized by seasonal variations that can be weekly, monthly or yearly, depending on the cause of the variation. Traditional time-series forecasting models perform poorly when they encounter missing data in the dataset. To address this limitation, robust, recurrent neural network (RNN)-based, multi-step-ahead forecasting models are developed for time-series in this study. The simple RNN, the gated recurrent unit (GRU) and the long short-term memory (LSTM) units are used to develop the forecasting models and evaluate their performance. Two approaches are used to address the missing value issue: masking and imputation, in conjunction with the RNN models. Six different imputation algorithms are then used to identify the best model. The analysis indicates that the LSTM model performs better than simple RNN and GRU models, and imputation performs better than masking to predict future traffic volume. Based on analysis using 92 ATRs, the LSTM-Median model is deemed the best model in all scenarios for hourly traffic volume and annual average daily traffic (AADT) prediction, with an average root mean squared error (RMSE) of 274 and mean absolute percentage error (MAPE) of 18.91% for hourly traffic volume prediction and average RMSE of 824 and MAPE of 2.10% for AADT prediction.