Master's thesis: Enhancing Train Traffic Management through AI and Optimization

We are looking for two dedicated master’s students to join us in the Systems Engineering Unit at RISE.

The Systems Engineering Unit is part of RISE Mobility and Systems, focusing on Resource Optimization, System of Systems and Cyber-physical systems. The unit conducts projects together with industry and academic partners from Sweden and across the world. The research focus for the proposed thesis topics is within Resource Optimization and Decision support.

Background and Purpose
Transportation systems need continuous development to meet future demands for sustainable transport. Expectations on these systems are constantly increasing regarding reliability, predictability, transparency, and efficiency. The railway system has several advantages but also significant challenges, necessitating improvements in various areas. One crucial field is traffic management, where trains are coordinated to create efficient traffic flows.

Thesis Descriptions
We are offering two master’s thesis opportunities aimed at enhancing train traffic management through AI and optimization:

1. Further Development of an AI Model for Predicting Train Arrival Times
   • Objective: Advance an existing AI model to improve real-time predictions of train arrival times.
   • Description: This thesis focuses on enhancing machine learning algorithms for short-term predictions of train movements. The student will work on improving prediction accuracy, handling real-time data streams, and ensuring continuous updates for high-quality forecasts. The goal is to facilitate more efficient train operations with reduced energy consumption and increased punctuality
   • Qualifications: Strong knowledge of AI and machine learning, good programming skills (mostly in Python), and an interest in solving complex problems involving real-time data.

2. Further Development of an Optimization Model for Real-Time Timetable Adjustment
   • Objective: Develop an optimization model for real-time finetuning of real-time train timetables.
   • Description: This thesis includes development of an optimization model for finetuning of operational train timetables in a real-time setting. Further, it includes integrating the optimization system into a framework where it takes input data, including AI-generated train runtime predictions (from thesis opportunity number 1), and deliver a result to a communication channel. The student will work on optimization model development, model integration with surrounding systems and input and output data handling.

Qualifications 
Solid background in optimization modelling and skills in programming (mostly in Python or Java), and an interest in solving complex problems involving real-time data.

Collaboration
The thesis students will work closely with researchers at RISE in a project in collaboration with Trafikverket. You will have the opportunity to engage with industry partners and contribute to real-world challenges in railway traffic management.

Terms
Start Time: Preferably January or February
Scope: 30 hp.
Location: RISE Mobility and Systems, Västerås or Stockholm. Option to partially work remotely.
Compensation: Compensation will be paid on satisfactory oral and written thesis defence.

Who are you?
We expect you to have a strong and solid knowledge of machine learning and/or optimization, good programming skills (mostly in Python or Java) and an interest in solving complex problems. Preferably you enjoy working both on your own and together with team members.

Application
We welcome applications from students passionate about making a significant impact on the future of transportation systems. Please specify in your application which thesis opportunity you are interested in.

Welcome with your application!
To know more, please contact Zohreh Ranjbar zohreh.ranjbar@ri.se, 070 627 85 98 or Martin Joborn martin.joborn@ri.se, 070 570 99 92. Applications should include a brief personal letter, CV, recent transcript of records, and a code excerpt (example of a code file written by you, or your GitHub repository link). Candidates are encouraged to send in their application as soon as possible but at the latest by the 15th of January 2025. Suitable applicants will be interviewed as soon as applications are received.

Join us in shaping the future of railway traffic management through innovation and cutting-edge research!

Keywords: Master thesis, Machine Learning, deep learning, optimization, Mobility, Systems Engineering, RISE, Stockholm