Mobility Information Engineering Lab at ETH Zürich
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 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!
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!
MIE-Lab members attended the Zürich Mobility Data Workshop sponsored by IARAI at the University of Zürich on July 20th. The workshop brought together researchers based in Zurich that work on different mobility research topics to discuss the results and insights learned in the NeurIPS Traffic4cast competition series organized by IARAI. The workshop sparked a lively discussion on the challenges and opportunities of open mobility data. The workshop is co-organized by Yanan Xin, Cheng Fu (GIScience Center, UZH), together with Christian Eichenberger and Moritz Neun (Institute of Advanced Research in Artificial Intelligence, IARAI).
Our new project “Interpretable and Robust Machine Learning for Mobility Analysis” officially starts today! The project aims to bring together the knowledge of GIScience and Machine Learning, advancing our understanding of how interpretable and robust machine learning methods (especially deep learning methods) can be tailored to mobility analysis with the support of causal inference. This research is funded by the Hasler Foundation and is in collaboration with the Swiss Data Science Center. Please check out our project page for more information.
We launched our MIE Lab LinkedIn page! Follow our updates on LinkedIn here.
Dr. Esra Suel joins our team as a Senior Assistant. She is a Research Fellow (part-time) at the School of Public Health, Imperial College London. Since 2018, she also held a Senior Data Scientist position at the Swiss Data Science Center, ETH Zurich where she collaborated with MIE Lab. She obtained her PhD from the Centre for Transport Studies, Imperial College London. Esra’s current research focuses on using emerging sources of large-scale data (e.g., remote sensing, aerial imagery from drones, street-level imagery, mobile phones, and crowd-sourced data) coupled with advances in deep learning methods, along with traditional (e.g., survey-based) data to advance how we make measurements in urban settings and quantify change, ultimately aiming for advanced data-driven policy and behaviour changes for improving urban life.
A paper titled “Anomaly Detection for Volunteered Geographic Information: A Case Study of Safecast Data” by Dr. Yanan Xin is recently published online.
Volunteered Geographic Information (VGI) is a promising new data source for scientific research. However, many scientists are concerned about the quality of VGI data for research, given the lack of rigorous and systematic quality control procedures. This study contributes to the improvement of VGI quality by proposing a Cross-Volunteer Referencing Anomaly Detection (CVRAD) method to filter anomalous measurements in mobile environmental sensing data, using the crowdsourced Safecast radiation data set as a case study. The method is validated using both official KURAMA car-borne survey data and filtered measurements by Safecast moderators. The validation results demonstrate that the anomaly detection method can successfully identify abnormal values and reduce errors in the VGI data when sufficient volunteers are present; thereby increasing the overall accuracy of the data. The code developed to support the findings of the paper is available in figshare.com.
Our new project “V2G4CarSharing” in collaboration with Hive Power and Mobility is funded by the Swiss Federal Office of Energy (SFOE) mobility research program. The project aims to develop and evaluate optimal strategies to integrate car-sharing and Vehicle-to-Grid (V2G). By integrating car-sharing and V2G, our research will tackle core issues related to the stability of the Swiss power grid and the electrification of the transportation system, thus supporting the fulfillment of the Swiss Energy Strategy 2050.
Nina Wiedemann joins MIE-Lab as a Ph.D. student. She completed her Master’s degree in Data Science at ETH Zürich and Bachelor’s degree in Cognitive Science from the University of Osnabrück, Germany. We welcome Nina to our team!
