Traffic flow prediction is one of the point research contents of transportation engineering. Accurate ship traffic flow prediction is the value to ensure the safety of ship navigation and smooth channel. In order to predict the port ship traffic flow more accurately, aiming at the shortcomings of the traditional prediction model, a port ship traffic flow prediction model based on long-term and short-term memory network (LSTM) is proposed. Finally, Qingdao port is taken as an example to predict and compare with ARIMA model. The results show that, compared with ARIMA model, the mean absolute percentage error (MAPE) of LSTM model is as low as 3.476%, which indicates that the prediction accuracy of LSTM model is higher and it can be well applied to the field of ship traffic flow prediction. According to the prediction results, it can provide basic basis for channel planning and design and ship navigation management, maximize the navigation capacity of the channel, and optimize the allocation of port resources.
Ship traffic flow forecast of Qingdao port based on LSTM
Sixth International Conference on Electromechanical Control Technology and Transportation (ICECTT 2021) ; 2021 ; Chongqing,China
Proc. SPIE ; 12081
2022-02-07
Conference paper
Electronic Resource
English
Ship traffic flow forecast of Qingdao port based on LSTM
British Library Conference Proceedings | 2022
|BP neural network based on Qingdao City air logistics demand forecast
British Library Conference Proceedings | 2023
|