Hybrid approaches for container traffic forecasting in the context of anomalous events: The case of the Yangtze River Delta region in the COVID-19 pandemic

Research and application of a novel grey multivariable model in port scale prediction under the impact of Free Trade Zone

“…In terms of the artificial intelligence model, Cuong et al (2022) utilized a neural network predictive controller and adaptive fractional-order supervision sliding mode control to handle throughput under external disturbances. In the meantime, some scholars have also used the decomposition integration method (Du et al, 2019;Jin et al, 2023), SARIMA and machine learning hybrid method (Huang et al, 2022;Mo et al, 2018) for forecasting container throughput prediction. In fact, port cargo throughput data is usually provided by port authorities, customs, shipping companies, etc., and its availability is limited especially when some ports may be unwilling or unable to disclose it.…”

Multi-port container traffic analysis using Data Science tools: an application to Yangtze River Delta (China)

“…In terms of methodology, DS tools used in port throughput prediction include traditional statistical methods, Machine Learning models (ML) and hybrid models. From the perspective of forecasting accuracy, hybrid models have the best performance, the ML models are second only to hybrid models, and the last are traditional statistical models (Huang et al 2022b). At the same time, the prediction issue in the port includes many aspects, such as port container traffic prediction, truck demand prediction and cargo throughput, which are all benefits for the port schedule and port investment.…”

“…One of the hottest research topics is container traffic prediction. Predictive analytics can provide more foresight suggestions, which is more efficient and effective in port management (Filom et al 2022) (Huang et al 2022b). The hybrid models have two forms, the first is the combination of two or more forecasting models to predict the container traffic, such as Huang et al (2022b) combined SARIMA with SVR and LSTM to predict the container traffic, they found that the hybrid model is more accurate than single models.…”

“…Predictive analytics can provide more foresight suggestions, which is more efficient and effective in port management (Filom et al 2022) (Huang et al 2022b). The hybrid models have two forms, the first is the combination of two or more forecasting models to predict the container traffic, such as Huang et al (2022b) combined SARIMA with SVR and LSTM to predict the container traffic, they found that the hybrid model is more accurate than single models. Another form is using an algorithm to optimize the parameters of a forecasting model, such as Ping and Fei (2013) applied Genetic Algorithms (GA) to optimize the Back-Propagation…”