Short-Term Road Traffic Flow Prediction Model on Damaged Road Characteristics (Type of Distress Raveling)

Abstract

In the Intelligent Transportation System (ITS) era, several studies related to traffic flow prediction models on the road made it easier to obtain continuous traffic volume data, traffic volume on roads was strongly influenced, one of them by damaged road conditions. This research is related to the development of a traffic flow prediction model due to damaged roads. In developing the traffic flow prediction model for the characteristics of damaged roads (distress raveling type) using the Auto Regressive Integrated Moving Average (ARIMA) and Long Short Term Memory (LSTM) models, these two models are suitable for short-term traffic flow prediction models using Mean Absolute Error (MAE) and Root Mean Square Error (RMSE) evaluation methods. The results obtained in the development of this model are quite promising to provide an overview of the traffic flow prediction model for the characteristics of damaged roads (distress raveling type) at the survey location. The evaluation shows that RMSE or MAE values for SARIMA and LSTM are less than 5%.