An ETA Prediction Model for Intermodal Transport Networks Based on Machine Learning

Abstract

Transparency in transport processes is becoming increasingly important for transport companies to improve internal processes and to be able to compete for customers. One important element to increase transparency is reliable, up-to-date and accurate arrival time prediction, commonly referred to as estimated time of arrival (ETA). ETAs are not easy to determine, especially for intermodal freight transports, in which freight is transported in an intermodal container, using multiple modes of transportation. This computational study describes the structure of an ETA prediction model for intermodal freight transport networks (IFTN), in which schedule-based and non-schedule-based transports are combined, based on machine learning (ML). For each leg of the intermodal freight transport, an individual ML prediction model is developed and trained using the corresponding historical transport data and external data. The research presented in this study shows that the ML approach produces reliable ETA predictions for intermodal freight transport. These predictions comprise processing times at logistics nodes such as inland terminals and transport times on road and rail. Consequently, the outcome of this research allows decision makers to proactively communicate disruption effects to actors along the intermodal transportation chain. These actors can then initiate measures to counteract potential critical delays at subsequent stages of transport. This approach leads to increased process efficiency for all actors in the realization of complex transport operations and thus has a positive effect on the resilience and profitability of IFTNs.

Literature review and comparative analysis of inland waterways transport: “Container on Barge”

“…For instance, four articles implement game theory and Nash equilibrium to study the behavior of market players in COB-involved intermodal transportation networks (Douma et al 2012;Bouchery et al 2020;Roukouni et al 2020;Caris et al 2012). Three papers published in 2020 apply machine learning to predict estimated time of arrival and market demands in COB transportation (Balster et al 2020;Bouchery et al 2020;Radonjic et al 2020).…”

“…Wiegmans and Konings (2015) and Seo et al (2017) 2 Meers et al (2018), Maras (2011), Konings (2006), Konings et al (2010), Konings and Priemus (2008), Guo et al (2020), Ramaekers et al (2017), Jourquin et al (2014), and Kotowska et al (2018) 13 Konings and Maras (2011), Konings (2006), Konings et al (2010), Konings and Priemus (2008), Grobarcikova and Sosedova (2016), Notteboom et al (2020), Notteboom (2007), Guo et al (2020), Kotowska et al (2018), Yang et al (2021), Balster et al (2020), Kemme (2012), andWagener (2014) 13 10 France Zehendner and Feillet (2014),…”

Predicting the Costs of Forwarding Contracts: Analysis of Data Mining Competition Results

“…The income of the freight forwarder is largely based on a commission from the profit of successfully finding transportation services for the cargo that needed moving. Freight forwards operate on online freight exchanges, such as Timocom 2 , Trans.eu 3 or Teleroute 4 , seeking the most profitable contracts for which they can find a transportation service. The accurate transportation cost prediction is one of the key problems that need to be solved by freight forwarders to be successful.…”

“…Other ML-based approaches focus on finding estimated time of arrival (ETA) or predict fuel consumption. In [4] a random forest is used to predict ETA for intermodal transportation (i.e. including sea and/or railway transport).…”

On the quality of ship arrival predictions

“…Late applications focus on the use of real-time location data, and machine learning techniques, such as in Flapper (2020). 1 For an application in air transport, see Wang et al (2020), and for intermodal transport, Balster et al (2020). The above literature focuses on the development of prediction methods, using rather straightforward forecasting performance indicators to assess the quality of the predictions.…”