In order to fulfill the climate commitments outlined in the 2015 Paris Climate Agreement, there is a pressing need to substantially reduce Greenhouse Gas (GHG) emissions worldwide. Among these GHG emissions, CO2 contributes for 75% of the total Greenhouse Gas emissions. The transport sector accounts for 22% of these CO2 emissions. Despite the only 2% of the overall vehicle fleet in Europe, trucks and buses contribute a substantial 28% to the annual CO2 emissions on roads. Decarbonizing the transportation sector can be approached with various solution, with electrification emerging as one viable solution. Electrification involves converting diesel trucks with internal combustion engines into battery trucks. Furthermore, extending this shift to heavy duty trucks can be achieved by implementing an Electric Road System (ERS), utilizing either inductive or conductive charging. Completing an European network for ERS would be optimal, considering the daily cross-border transportation undertaken by heavy-duty trucks. Given the challenges in constructing a full European network at once, it is recommended to start an ERS infrastructure between two major freight handling points to guarantee high initial utilization. Numerous studies and pilot projects have investigated ERS technologies, with the Overhead Catenary Line system currently standing out as the most mature technology. However, existing studies primarily focus on the technical aspects or cost-effectiveness of ERS technology, neglecting a crucial aspect—the Social Cost-Benefit Analysis (SCBA) that evaluates the socio-economic impact of implementing an Overhead Catenary Line system. Moreover, these studies mostly looked into the implementation of a larger ERS network. Consequently, the main research question is formulated: What is the socio-economic feasibility of the implementation of an Electric Road System (ERS), the overhead catenary line system, between two freight handling points?
The shift towards electrification has already begun, with the introduction of battery trucks alongside diesel trucks. Hence, a transitional phase involving a mix of diesel and battery trucks is anticipated in the coming years (the zero alternative). The study has focused on testing one policy measure, namely the implementation of an ERS infrastructure between the ports of Rotterdam and Antwerp. The implementation of an ERS network, extend the truck fleet (consisting of diesel trucks and battery trucks), with a new type: the catenary trucks. This is the so called policy scenario (anticipated completion by 2030), which has been compared with the zero alternative. Three distinct route alternatives between the ports were assessed through SCBA, revealing that implementing an ERS infrastructure proves welfare enhancing for all three route alternatives, thus demonstrating the socio-economic feasibility of the policy measure. Furthermore, among the route alternatives (the Western route, the Middle route and the Eastern route), the Eastern route presents the most favorable Net Present Value outcomes for ERS infrastructure. However, conducting further studies encompassing research variables and non-monetized factors arising from ERS infrastructure implementation is necessary. This comprehensive analysis is crucial for informed decision making regarding the successful implementation of an Electric Road System.

Increased urbanisation has led to significant challenges for public transport operators. Inconsistent demand leads to peaks in passenger activity on the network. Moreover, the COVID-19 pandemic has introduced a need for social distancing as well, limiting the desired capacity of vehicles. To combat this, intelligent real-time and data-driven decision making is required. In many cases, the data required is lacking or not available in real-time. Our research addresses these challenges by providing means to gain insight into the passenger load of public transport vehicles. The focus of this research is to investigate how using in-vehicle sensor data can help in constructing an estimate of the passenger load and evaluate its contribution.

By combining in-vehicle sensor signals with historical passenger flow patterns, a novel fusion model
based on gradient boosting machines is constructed that can make real-time predictions of the passenger load using this data as input features. The evaluation shows that its estimates have a mean absolute error (MAE) score of 7.83, outperforming a random forest model baseline by 37%. Moreover, a crowding indicator analysis demonstrated that when predicting crowding indicators, the model achieves a weighted F1 score of 0.828. An ablation study found that excluding the in-vehicle features from the model reduces the model’s performance significantly, it could reduce the performance by up to 42%. In fact, the same experiment showed that having only the in-vehicle features is preferable to historical passenger flow features. Therefore, we conclude that using in-vehicle sensor data can be a feasible alternative to historical AFC data for predicting the passenger load.

The methodology has been extended by constructing a short-term forecasting model based on Seasonal ARIMA and GARCH that uses real-time signals of the passenger load to update its forecasts. The results show that while the forecasts lack accuracy initially, once the model is updated the forecasts improve up to almost a negligible error. When model predictions are used as update signals, the forecasting model is still able to improve and the results are competitive, despite the error contained in the signals.

Overall, we conclude that the proposed real-time model offers a suitable method for passenger load prediction and clearly demonstrates the effectiveness of using in-vehicle sensor data as input features. Moreover, we have presented a feasible method for using these features in a forecasting setting with a real-time model as an intermediary