Mobility Information Engineering Lab at ETH Zürich
Category : Uncategorized
We had a very interesting and stimulating Workshop on ‘Reproducibility in tracking data analysis and mobility research’ at the ACM SIGSPATIAL 2023 conference in Hamburg. Featuring an excellent keynote by Edzer Pebesma who highlighted the importance of replicability & reproducibility for Spatial Data Science. Check out our website and tutorial materials.
Category : Uncategorized
Our new paper entitled “Evaluating geospatial context information for travel mode detection” was accepted at Journal of Transport Geography and is now available (open-access!) online.
How much does geospatial context information contribute to travel mode detection?
Our latest study reveals that geospatial network features, such as distance to the road network, are more critical than motion features, such as speed and acceleration, when classifying an extensive list of travel modes. Still, most land-use and land-cover features barely contribute to the task. The results are based on our extensive context representation reviews and the proposed analytical pipeline to assess the contribution of geospatial context information based on a random forest model and the SHapley Additive exPlanation (SHAP) method.
The study provides valuable guidance for feature selection, effective feature design, and building efficient travel mode detection models.
Check out the paper online and the corresponding code on Github!
Category : Uncategorized
Our new paper entitled “Context-aware multi-head self-attentional neural network model for next location prediction” was accepted at Transportation Research Part C: Emerging Technologies and is now available (open-access!) online.
We present a multi-head self-attentional (MHSA) neural network that integrates location features, temporal features, and functional land use contexts for next location prediction. This comprehensive approach effectively captures movement-related spatio-temporal information, leading to state-of-the-art performance on GNSS mobility datasets.
Our analysis demonstrates that training the model on population data yields superior results by learning from collective movement patterns, surpassing the capabilities of individual-level models. Moreover, we emphasize the significance of recent past movements and weekly periodicity, showing that learning from a subset of historical mobility is sufficient to obtain an accurate location prediction result.
The proposed model represents a pivotal advancement in accurate and interpretable individual mobility prediction, and can be readily applied in downstream applications, including planning on-demand transport services, implementing mobility incentives, and suggesting alternative mobility options.
Check out the paper online and the corresponding code on Github!
Category : Uncategorized
This year at the ACM SIGSPATIAL conference, we are hosting a workshop on Reproducibility in Tracking Data Analysis and Mobility Research (https://github.com/mie-lab/reprotrack)!
Considering the fast methodological advances in spatial data science, the topic of reproducibility is more important than ever before. To foster common standards and transparency, we aim to bring researchers together in this session to discuss challenges and future pathways for reproducible spatial data science, with a focus on mobility data. The workshop is planned as a particularly interactive session, including a hands-on tutorial on tracking data preprocessing where you can bring your own data.
Please sign up here if you plan to attend the workshop. We hope to see you there on Monday, November 13th, in Hamburg!
Category : Uncategorized
Our new paper entitled “Incorporating multimodal context information into traffic speed forecasting through graph deep learning” is now online at IJGIS.
In this work, we propose a multimodal context-based graph convolutional neural network (MCGCN) model to fuse context data into traffic speed prediction, including spatial and temporal contexts. The proposed model comprises three modules, i.e., (a) hierarchical spatial embedding to learn spatial representations by organizing spatial contexts from different dimensions, (b) multivariate temporal modeling to learn temporal representations by capturing dependencies of multivariate temporal contexts and (c) attention-based multimodal fusion to integrate traffic speed with the spatial and temporal context representations for multi-step speed prediction. We conduct extensive experiments in Singapore. Compared to the baseline model (STGCN), our results demonstrate the importance of multimodal contexts with the mean-absolute-error improvement of 0.29 km/h, 0.45 km/h and 0.89 km/h in 30-min, 60-min and 120-min speed prediction, respectively. We also explore how different contexts affect traffic speed forecasting, providing references for stakeholders to understand the relationship between context information and transportation systems. Check out the open-access paper online!
Category : Uncategorized
Our paper titled “Influence of tracking duration on the privacy of individual mobility graphs” was published by the Journal of Location Based Services! In this work, we use a GPS tracking dataset and analyze how the tracking duration affects the risk for users to be re-identified; i.e., by matching to previously stored tracking data. It is well known that the tracking data of a user is quite unique and can be matched to stored data easily; however, we study the risk of a representation of tracking data that is already privatised, namely so-called location graphs. Location graphs do not reveal the geocoordinates or time stamps of the places that a user visited, but just the topology of the mobility behaviour. Nevertheless, users can be re-identified with a top-1 accuracy of up to 20%, and the re-identification risk strongly depends on the tracking duration of the user, as well as the duration of the stored data (pool), as shown in the figure below. Check out our paper and code for more information!
Category : news
Yatao Zhang presented how to measure and analyze urban resilience using nighttime light data at ICRS 2023. ICRS is the International Conference on Resilient Systems held in Mexico City from 28th to 30th June.
Category : news
Ayda Grisiute joins MIE Lab on May 1st as a Ph.D. student. Before joining MIE Lab, Ayda worked as a researcher at Singapore-ETH Centre for the Cities Knowledge Graph project. Ayda has a background in architecture and city planning. She received her master’s degree in Architecture from Aalto University, Finland, and her bachelor’s degree in Architecture from Vilnius Academy of Arts, Lithuania. In her previous studies, Ayda focused on algorithmic and data-driven design methodologies. Ayda is excited about urban knowledge management and representation with graphs and she is looking forward to an amazing journey at MIE Lab. We are happy to have her join the team!
Category : news
On March 30th the kick-off event for the project “An Open Digital Twin Platform for Research on the Swiss Mobility System” (ODTPR-SMS) took place at the LEE building together with our research partners at the Institute for Transport Planning and Systems, the Swiss Data Science Center and the Center for Sustainable Future Mobility. In the latter, the Geoinformation-Engineering group is a key stakeholder. The project is part of the Swiss National Strategy and Action Plan for Open Research Data and funded by swissuniversities through a Swiss Open Research Data Grant and has been acquired by our lab member Jascha Grübel. ODTPR-SMS has been funded with 1.5 million CHF (matched funding) to develop an Open Digital Twin Platform to underpin development on a mobility-specific Digital Twin “CH on the move”. In the kick-off meeting, all involved parties agreed on the timeline, distributed tasks, discussed the licensing of the software and got to know each other. Everybody was thrilled to contribute to strategically important tool chain that will be developed in the coming 24 months. As part of the project, 2 postdocs will join us at the Center for Sustainable Future Mobility to develop key features of the system.
The Open Digital Twin Platform (ODTP) is bringing together cloud computing, data semantics, licensing, access control and visualisation to enable a holistic processing of data covering data acquisition, data representation, data processing, data analysis and data visualisation. Known tools for mobility research can be automated within ODTP to provide (micro-)services and apply to new scenarios with less overhead than ever before. ODTP takes care of the provisioning and deployment of software allowing researchers to focus on their scientific questions rather than how to get the technology working. To quickly assemble a new Digital Twin, ODTP makes use of a “Digital Twin Zoo” that hosts key software as containers readied to be micro-services. Throughout our project ODTPR-SMS, we will develop a first set of mobility related micro-services that include well-known tools such as MATSim, eqasim and our own trackintel. We are also making available as many data sources on Swiss mobility as possible starting with the National Data Infrastructure for Mobility (NaDIM).
Figure: Overview of ODTP for end users. ODTP facilitates access to open-source software and data through a container-based backend and hosting infrastructure.
ODTP will be accompanied by an open standard for digital twinning. We are looking for experts to evaluate our platform and if you are interested in mobility, digital twins or a combination thereof, please contact Jascha Grübel (jgruebel@ethz.ch) for details on how to join our evaluation board which will be published at the Center of Sustainable Future Mobility’s website. We are also looking forward to add more mobility related software tools to ODTP and we are interested to discuss potential new services, again please contact Jascha Grübel for more details (jgruebel@ethz.ch).
Reference: Grübel, J., C. Vivar Rios, M. Balać, Y. Xin, R. M. Franken, S. Ossey, M. Raubal, K. W. Axhausen and O. Riba-Grofnuz (2023a) “CH on the move”: Introducing the Prototype Digital Twin of The Swiss Mobility System, paper presented at the Swiss Transport Research Conference 2023.
Category : Uncategorized
Over the past years, MIE lab has been developing an open-source Python library for analyzing human mobility data. Trackintel provides a standardized pipeline for loading, preprocessing, and analyzing tracking data, as shown in the graphic below. In the paper titled “Trackintel: An open-source Python library for human mobility analysis”, we describe the functionality of the library and demonstrate it in a case study on several datasets.
The paper is available open-access.
