Current Lab Members
This section introduces the current members of the Mobility Information Engineering lab.
Prof. Dr. Martin Raubal
Martin Raubal is a Professor for Geoinformation Engineering at the Institute of Cartography and Geoinformation, ETH Zurich. He is also an Adjunct Professor at the Department of Geography, University of California, Santa Barbara (UCSB).
More info at raubal.ethz.ch.
Dr. Yanan Xin
Yanan is currently leading the MIE Lab as a postdoctoral researcher at the Chair of Geoinformation Engineering, ETH Zurich. Her research interests lie in the area of computational mobility analysis, mainly focusing on mobility-based anomaly detection and the development of interpretable machine learning methods for analyzing movement data.
Methodological focus: movement data analysis, anomaly detection, interpretable machine learning, and Geographic Information Science (GIScience)
Henry is working as a PhD student in the Mobility Information Engineering Lab (MIE) at the Chair of Geoinformation Engineering at ETH Zürich. Currently, he is involved in the SBB Green Class project.
In general, he is interested in applying modern data analysis methods to spatio-temporal problems and investigating the role of mobility in our way towards a more sustainable energy system.
Methodological focus: Analysis and mining of spatio-temporal data, stochastic modeling, machine learning, and energy systems
More info at https://n.ethz.ch/~martinhe.
Nishant is a PhD student working at the Future Resilient Systems (FRS) at Singapore-ETH Centre. He is involved in exploring the applications of machine learning on spatio-temporal data. Within this paradigm, his focus is on making transportation systems more resilient to continuous and abrupt changes in the system.
He majored in Civil Engineering and studied Computer Science during his master’s, as part of which he worked on the applications of machine learning in computer vision. A comparison of traditional approaches vs machine learning approaches was an important part of his work. His mixed background drew him to Transportation as a domain of work.
Methodological focus: Machine learning for spatio-temporal data, computer vision, detection of weak signals
More info at https://frs.ethz.ch/people/researchers/NishantKUMAR.html.
Ye joined the lab in October 2020 as a Ph.D. student. He holds a B.Sc. in GIS and remote sensing from Sun Yat-sen University, China, and an M.Sc. in Geomatics from ETH Zurich. His current work focuses on understanding human mobility behavior and developing models for mobility prediction.
Methodological focus: Computer vision, Spatio-temporal data mining and analysis, machine learning, and recurrent neural network.
Feel free to get in touch: email@example.com
Former Lab Members
Dr. Dominik Bucher
Dominik was a PhD student at the Chair of Geoinformation Engineering at ETH Zurich. He was working on the SCCER Mobility project GoEco!, which aims at reducing energy usage of personal transportation by changing mobility behavior towards more sustainable alternatives.
Next to GoEco!, he was working on other challenges from the transportation domain, such as facilitating multi-modal routing, respecting personal restrictions and preferences, automatic tracking of movement, inference of transport modes, and analysis of trajectory data. Further, a big part of his research covers location based search, in particular search for spatio-temporal and volatile information, such as search for a carpooling partner.
Methodological focus: Location-based Services (LBS) and location-based search engines, models and algorithms for spatio-temporal information, routing systems and algorithms, linked and realtime spatio-temporal data, mobility tracking systems, and mobile GIS
More info at dominikbucher.com.
Jannik joined the lab in November 2019 as a PhD student. He holds a B.Sc. in Mathematics from FAU Erlangen and a M.Sc. in Statistics from ETH Zurich.
His main project focuses on investigating the potential impact of personalized electric mobility on grid stability.
Methodological focus: Machine learning and reinforcement learning, stochastic modeling of dynamic systems in mobility and energy science
Dr. Pengxiang Zhao
Pengxiang was leading the Mobility Information Engineering Lab (MIE) from 2018 to mid 2020. He was working as a PostDoc researcher at the Chair of Geoinformation Engineering at ETH Zürich. He was involved in COMMIT, SCCER Mobility and SBB Green Class project.
His research interests mainly lie in urban mobility, trajectory data analysis and mining. In particular, he focuses on exploring and analyzing human mobility patterns from massive trajectory data and related contextual data based on machine learning and data mining methods.
Methodological focus: Geographical Information Systems (GIS), movement data analysis, machine learning and data mining
Dr. Christian Sailer
Christian was a PhD student at the Chair of Geoinformation Engineering at ETH Zürich. He was working on the OMLETH project funded by the Innovedum program of ETH, which had the goal of building a learning management system prototype to explore new ways of teaching and learning by location-based mobile learning.
He is mainly interested in mobile human-computer interaction methods of learning and teaching across multiple contexts and locations. He focuses in particular on exploring and understanding the key parameters of designing learning modules, in order to enhance the learning progress.
Methodological focus: Geographical Information Systems (GIS), Educational location-based information and communication technology, visualization and analysis of educational spatio-temporal data
More info at christiansailer.ch.
Dr. David Jonietz
David was leading the Mobility Information Engineering Lab (MIE) from 2016 to 2018. At the time, he was working as a PostDoc researcher at the Chair of Geoinformation Engineering at ETH Zürich. As a spatial data scientist and mobility researcher, his area of expertise lies in the intersection between geoinformatics and GIS, data science and mobility studies. In particular, he focuses on how machine learning and data mining methods can be used and adapted to analyse mobility behaviour based on large trajectory datasets.
Methodological focus: Geographical Information Systems (GIS), movement data analysis, machine learning and data mining, geosimulation, agent-based models (ABM), network analysis and routing, Location-based Services (LBS)