Johann Hartleb
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Johann Hartleb has a total of 10 co-authors. Here are the top co-authors by number of shared publications:
Christopher Szymula
1 shared publicationDennis Huisman
Econometric Institute and Erasmus Center for Optimization in Public Transport, Erasmus University, Rotterdam 3062PA, Netherlands
1 shared publication- Emely Richter
Technische Universität Dresden
1 shared publication Marie Schmidt
1 shared publication- Marie Schmidt
Department for Computer Science University of Würzburg Am Hubland 97074 Würzburg Germany
1 shared publication Markus Friedrich
Institute for Road and Transport Science, University of Stuttgart, Stuttgart 70569, Germany
1 shared publication
Latest Publications
- Open Access
- 25 March 2026
- Published by Elsevier in SSRN Electronic Journal
Learning-based scope reduction for real-time train rescheduling optimization in station areas
Real-time train rescheduling requires the rapid generation of revised train timetables in response to unforeseen disruptions. Solving such problems using exact methods is computationally challenging, especially in case of infrastructure blockages at complex station areas with dense traffic. This paper introduces a Learning-based Scope Reduction (LSR) framework for local train rescheduling that effectively prunes the search space by fixing a subset of decision variables prior to optimization. The approach fixes nominal routing decisions of trains that are predicted to be unaffected by infrastructure disruptions. Logistic Regression, Random Forest, and Neural Network classifiers are trained on generated disruption scenarios and their corresponding high-quality rescheduling solutions obtained by solving a Mixed Integer Linear Programming model. To balance the trade-off in computation time savings and potential solution quality degradation, we propose an effective tuning method that strengthens prediction robustness to improve computational efficiency. We evaluate the proposed LSR framework on a real-world medium-sized station area in Germany. Results show that LSR achieves computation time reductions of up to 97%, while largely preserving solution quality in comparison to the full scope solutions. In the best configuration, the approach solves 95% of the most complex instances in real time, with only minor solution quality degradation of 2.3%. This work demonstrates the potential of a hybrid train rescheduling approach that combines supervised learning with exact optimization and offers a promising tool for intelligent real-time dispatching support.
- 25 March 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessLearning-based scope reduction for real-time train rescheduling optimization in station areas
Real-time train rescheduling requires the rapid generation of revised train timetables in response to unforeseen disruptions. Solving such problems using exact methods is computationally challenging, especially in case of infrastructure blockages at complex station areas with dense traffic. This paper introduces a Learning-based Scope Reduction (LSR) framework for local train rescheduling that effectively prunes the search space by fixing a subset of decision variables prior to optimization. The approach fixes nominal routing decisions of trains that are predicted to be unaffected by infrastructure disruptions. Logistic Regression, Random Forest, and Neural Network classifiers are trained on generated disruption scenarios and their corresponding high-quality rescheduling solutions obtained by solving a Mixed Integer Linear Programming model. To balance the trade-off in computation time savings and potential solution quality degradation, we propose an effective tuning method that strengthens prediction robustness to improve computational efficiency. We evaluate the proposed LSR framework on a real-world medium-sized station area in Germany. Results show that LSR achieves computation time reductions of up to 97%, while largely preserving solution quality in comparison to the full scope solutions. In the best configuration, the approach solves 95% of the most complex instances in real time, with only minor solution quality degradation of 2.3%. This work demonstrates the potential of a hybrid train rescheduling approach that combines supervised learning with exact optimization and offers a promising tool for intelligent real-time dispatching support.
- 1 March 2023
- Published by Institute for Operations Research and the Management Sciences (INFORMS) in Transportation Science
- Vol. 57 (2) , 336-350
Modeling and Solving Line Planning with Mode Choice
We present a mixed-integer linear program (MILP) for line planning with mode and route choice. In contrast to existing approaches, the mode and route decisions of passengers are modeled depending on the line plan and commercial solvers can be applied to solve the corresponding MILP. The model aims at finding line plans that maximize the profit for the railway operator while estimating the corresponding passenger demand with aggregate choice models. Hence, the resulting line plans are not only profitable for operators but also attractive to passengers. By suitable preprocessing we are able to apply any aggregate choice model for mode choices using linear constraints. We provide and test means to improve the computational performance. Our experiments on the Intercity network of the Randstad, a metropolitan area in the Netherlands, show that models which assume a fixed passenger assignment to modes cannot attract the passenger numbers they were designed for and therefore lead to inferior profit compared with our new model. Supplemental Material: The online appendices are available at https://doi.org/10.1287/trsc.2022.1171 .
- 1 March 2023
- Published by Institute for Operations Research and the Management Sciences (INFORMS) in Transportation Science
- Vol. 57 (2) , 336-350
Modeling and Solving Line Planning with Mode Choice
We present a mixed-integer linear program (MILP) for line planning with mode and route choice. In contrast to existing approaches, the mode and route decisions of passengers are modeled depending on the line plan and commercial solvers can be applied to solve the corresponding MILP. The model aims at finding line plans that maximize the profit for the railway operator while estimating the corresponding passenger demand with aggregate choice models. Hence, the resulting line plans are not only profitable for operators but also attractive to passengers. By suitable preprocessing we are able to apply any aggregate choice model for mode choices using linear constraints. We provide and test means to improve the computational performance. Our experiments on the Intercity network of the Randstad, a metropolitan area in the Netherlands, show that models which assume a fixed passenger assignment to modes cannot attract the passenger numbers they were designed for and therefore lead to inferior profit compared with our new model. Supplemental Material: The online appendices are available at https://doi.org/10.1287/trsc.2022.1171 .
- Open Access
- 1 May 2022
- Published by Elsevier in European Journal of Operational Research
- Vol. 298 (3) , 953-966
Railway timetabling with integrated passenger distribution
- 1 May 2022
- Published by Elsevier in European Journal of Operational Research
- Vol. 298 (3) , 953-966
Open AccessRailway timetabling with integrated passenger distribution
- Open Access
- 2 July 2021
- Published by Springer Nature in Transportation
- Vol. 49 (4) , 1133-1155
Vehicle scheduling for on-demand vehicle fleets in macroscopic travel demand models
The planning of on-demand services requires the formation of vehicle schedules consisting of service trips and empty trips. This paper presents an algorithm for building vehicle schedules that uses time-dependent demand matrices (= service trips) as input and determines time-dependent empty trip matrices and the number of required vehicles as a result. The presented approach is intended for long-term, strategic transport planning. For this purpose, it provides planners with an estimate of vehicle fleet size and distance travelled by on-demand services. The algorithm can be applied to integer and non-integer demand matrices and is therefore particularly suitable for macroscopic travel demand models. Two case studies illustrate potential applications of the algorithm and feature that on-demand services can be considered in macroscopic travel demand models.
- 2 July 2021
- Published by Springer Nature in Transportation
- Vol. 49 (4) , 1133-1155
Open AccessVehicle scheduling for on-demand vehicle fleets in macroscopic travel demand models
The planning of on-demand services requires the formation of vehicle schedules consisting of service trips and empty trips. This paper presents an algorithm for building vehicle schedules that uses time-dependent demand matrices (= service trips) as input and determines time-dependent empty trip matrices and the number of required vehicles as a result. The presented approach is intended for long-term, strategic transport planning. For this purpose, it provides planners with an estimate of vehicle fleet size and distance travelled by on-demand services. The algorithm can be applied to integer and non-integer demand matrices and is therefore particularly suitable for macroscopic travel demand models. Two case studies illustrate potential applications of the algorithm and feature that on-demand services can be considered in macroscopic travel demand models.