Forecast of domestic air travel demand change by opening the high speed rail

Abstract

In Korea, the Seoul-Busan High Speed Rail (HSR) of which length is 430.7 km is under construction with plan to complete at the end of 2011. Therefore, there will be great change at modal split of this corridor travel, especially at air travel denand. This study forecasted the air travel demand changes of Seoul-Busan and Seoul-Daegu airlines which are competitive with the HSR. The result of this study can be used for airline companies to prepare the impact and for government to adjust the domestic air transportation planning. First, studies were conducted to establish a modal split model of regional transit travel by using the travel data between Seoul and 8 regional cities where the airplane, express train and express bus are mutually competitive. For the model, abstract, Logit and neural network models were analyzed, and the best result was obtained at the neural network model. The model has an input layer, 4 hidden layers and an output layer. The input units consists of travel time, travel cost, number of service frequency and number of seats of regional transit modes such as express bus, express train and airplane, and the hidden layers have 8 neurons. Using the neural network model, the travel demands of Seoul-Busan and Seoul-Daegu airlines in the horizon year when the HSR would begin service were estimated. Due to the HSR opening, the demand of Seoul-Busan airline is forecasted to decrease by 69.5% and the demand of the Seoul-Daegu airline is forecasted to decrease by 59.0%.