Mobility Information Engineering Lab at ETH Zürich
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.
Professor Martin Raubal and Thomas Hettinger from SBB will give the first Center for Sustainable Future Mobility (CSFM) seminar talk on spatial data and data analytics for sustainable mobility on 23 March 2023, 17:00-18:10 at ETH Zentrum CAB G 51, ETH Zurich. For more information, please check here.
Our new paper entitled “Conserved quantities in human mobility: From locations to trips” was accepted at Transportation Research Part C: Emerging Technologies and is now available online.
We use two high-resolution user-labelled datasets from ~3800 individuals to analyse individuals’ activity–travel behaviour over the long term. We find that individuals maintain a conserved quantity in the number of essential travel mode and activity location combinations over time. A typical individual maintains 15 mode–location combinations, of which 7 are travelled with a private vehicle every 5 weeks. The dynamics of this stability reveal that the exploration speed of locations is faster than the one for travel modes, and they can both be well-modelled using a power-law fit that slows down over time.
Our findings enrich the understanding of the long-term intra-person variability in activity–travel behaviour and open new possibilities for designing mobility simulation models.
Check out the open-access paper online!
Our new paper on “Graph based mobility profiling” was accepted at Computers, Environment and Urban Systems (CEUS) and is now available online. We propose a graph based workflow to identify groups of persons with similar mobility behavior based on person specific graphs that describe the mobility behavior. Our approach is privacy friendly, does not depend on a specific clustering algorithm, is robust against the choice of hyperparameters, does not require specific labels in the dataset, and is not limited to specific types of tracking data. We show in the paper how this can be used to evaluate the impact of new mobility offers.
The paper is open access and the source code of the project is available on our Github.
Our new paper entitled “Street-level traffic flow and context sensing analysis through semantic integration of multisource geospatial data” by Yatao Zhang and Martin Raubal is now online at TGIS.
Sensing urban spaces from multisource geospatial data is vital to understanding the transportation system in the urban context. However, the complexity of urban context and its indirect interaction with traffic flow deepen the difficulty of exploring their relationship. This study proposes a geo-semantic framework first to generate semantic representations of multi-hierarchical urban context and street-level traffic flow, and then investigate their mutual correlation and predictability using a novel semantic matching method. The results demonstrate that each street is associated with its multi-hierarchical spatial signatures of urban context and street-level temporal signatures of traffic flow. The correlation between urban context and traffic flow displays higher values after semantic matching than those in multi-hierarchies. Moreover, we found that utilizing traffic flow to predict urban context results in better accuracy than the reversed prediction. The results of signature analysis and relationship exploration can contribute to a deeper understanding of context-aware transportation research.
What if 50% of the existing urban road space was allocated to e-bikes and the slow modes? Seven chairs at the department for civil engineering at ETH join forces to analyze the opportunities and effects of an urban future giving priority to cycling, micromobility and public transport. Our group will contribute with the developement of spatial optimization methods for redistributing the street lanes to design the new bike lane network, considering constraints such as (multi-modal) accessibility and exposure levels of the lanes.
Our paper “Causal Inference for Interpretable and Robust Machine Learning in Mobility Analysis” won the Best Vision Paper Award at the 30th ACM SIGSPATIAL Conference in Seattle, USA. This year’s vision paper selection has been very competitive given the large number of submissions. Among the six selected vision papers invited for presentation, our paper, presented by Dr. Yanan Xin, received the best vision paper award. In this paper, we envision opportunities for utilizing causal inference to enhance the interpretability and robustness of deep learning methods and address challenges in mobility analysis. This direction will help us build safer, more efficient, and more sustainable future transportation systems. For more information, check out our paper and a pre-recorded video presentation.
The vision paper also highlights what we aim to achieve through our project “Interpretable and Robust Machine Learning for Mobility Analysis”. Stay tuned for more exciting results coming from the project!
We are delighted to announce that our paper “How do you go where? Improving next location prediction by learning travel mode information using transformers” by MIE Lab members Ye Hong, Henry Martin, and Martin Raubal is now online at arXiv and will be presented at ACM SIGSPATIAL, November 1–4, 2022, Seattle, WA, USA conference.
In this work, we propose a transformer decoder-based neural network to predict the next location an individual will visit based on her historical locations, time, and travel modes. In particular, we design an auxiliary task to jointly predict the next travel mode, with the aim of guiding the learning process of the network. We conduct extensive experiments on two real-world GPS tracking datasets and conclude that considering additional aspects of travel behaviour significantly increases the performance of next location prediction. The overall architecture of the proposed model is shown below.
We participated at the largest Hackathon in Europe, HackZurich 2022, with a team of former and current PhD student of our group, and our app was awarded the challenge price by the company Sensirion! We developed a tool that utilises temperature sensors and building floor plans to serve as a digital energy consultant (for details, see here).
The resilience of a road network refers to its ability to bounce back to the desired level of serviceability after a disruption. After an accident, a more resilient transportation network can restore the flow of traffic faster than a less-resilient network. At the WCS Science of Cities Symposium, researchers from MIE-lab presented the preliminary findings from their recent research in which they used incidence clearance duration as a proxy for road network resilience. Does scale matter while modelling incidence clearance time? Should we use uniform or heterogeneous grids while modelling incidence clearance time? Questions like these and several others were addressed using real incident and congestion data from road networks in Singapore. Their findings reveal that incidence clearance duration is better modelled by splitting the road network into connected regions of similar topology. The notions of connected regions and urban topologies have a special place in urban road network planning because, on one hand, connected regions of similar topologies allow for the spread of traffic congestion, whereas on the other hand, these present an opportunity to share accident clearance resources within the connected region. The abstract proceedings can be found here. Look out for their upcoming pre-print!
