Category: Uncategorized

We welcome Juliette Sikking who will start her PhD at the MIE Lab on the topic of GeoAI and spatial machine learning for human mobility and geospatial data. Juliette is interested in the interplay between machine learning methods and geospatial patterns in urban systems. She is excited about applying spatial machine learning to improve our understanding of human mobility. Before joining ETH, she received her master’s degree in Mathematics from EPFL, with a minor in Quantum Science & Engineering, where her research experience spanned geospatial machine learning, large language models, quantum information theory, and quantum machine learning. She received her bachelor’s degree from EPFL in Mathematics.

Our paper “UrbanFusion: Stochastic Multimodal Fusion for Contrastive Learning of Robust Spatial Representations” was accepted to the International Conference on Machine Learning (ICML 2026)!

In the paper that was led by Dominik Mühlematter as his master thesis at the MIE lab, we are presenting a new method to learn general embeddings of spatial locations that can be used for a variety of downstream tasks. We propose to train with a contrastive loss on masked modality subsets, combined with a reconstruction loss. This scheme not only results in improved performance on downstream tasks such as inferring land use, health indicators or sociodemographics, but is also theoretically shown to retain more information than baseline methods.

The paper will be presented at the ICML conference in Seoul, South Korea, July 6th-11th.

Paper: https://arxiv.org/abs/2510.13774
Code: https://github.com/DominikM198/UrbanFusion

We welcome Wolin Jiang who will start his PhD at the MIE Lab on the topic of causal inference for car sharing interventions. Wolin is interested in the interplay between individual travel behavior and mobility stakeholders in urban systems. He is excited about applying causal inference to improve shared mobility. Before joining ETH, he received his master’s degree from UC Berkeley, where he focused on using reinforcement learning and game theory to optimize on-demand shared ride operations. He received his bachelor degree in Civil Engineering at Tongji University, Shanghai.

Nina Wiedemann, a postdoctoral researcher at the MIE Lab, has been awarded the Förderpreis Geoinformatik by Runder Tisch GIS e.V. for her dissertation titled “Spatio-temporal effects in GeoAI: from predictability to evaluation.”
She presented her work at the Münchner GI Runde on March 19, where she was selected as the award recipient by an independent jury.

A new paper, titled “Spatial Nudging: Converging Persuasive Technologies, Spatial Design, and Behavioral Theories”, was presented at the 16th International Conference on Spatial Information Theory (COSIT 2024).

This paper introduces the Spatial Nudging framework—a theory-driven approach that maps out nudging strategies in the mobility domain, with a focus on cycling. The framework integrates physical and digital interventions to promote sustainable mobility, drawing from behavioral theories such as Nudge Theory and the Theory of Affordances. Additionally, we propose a graph-based workflow that uses cognitive graphs and the Fine-to-Coarse heuristic to model how cyclists perceive their environment. This method generates cognitive routes that align perceived affordances with the physical environment, closely resembling real-world cycling trajectories.

For more details, check out our paper!

Ayda Grisiute gave a talk at the 8th Cycling Research Board Meeting (CRBAM). The presentation, titled “Conceptualizing Spatial Nudging: A Theoretical Framework for Integrating Interventions to Promote Cycling“ introduced Spatial Nudging framework that delineates nudging practices in the mobility domain and offers a theoretically integrated perspective on promoting cycling through spatial interventions.

In addition, Ayda presented a poster titled “Building a Planning Tool for the E-Bike City Vision,” which showcased a web application created by two geomatics students. The tool helps urban planners reallocate road space for bike lanes using various optimization strategies.

Check out the poster here!

As the ecosystem of transport planning and evaluation metrics, tools, methods, and services grows, there is a pressing need to enhance domain interoperability and interpretability. In our new paper, titled “An ontology-based approach for harmonizing metrics in bike network evaluations“ , we construct a formal ontology, VeloNEMO, a formal ontology designed to capture the key attributes of bike network evaluation metrics and resolve terminological inconsistencies across them. We also introduce a machine-readable knowledge graph that compiles existing metrics, allowing for more efficient meta-analyses of various evaluation strategies. To further enhance transparency, we offer recommendations for making metric descriptions more comparable across different evaluation approaches.

For more details, check out our paper!

What is the potential for integrating vehicle-to-grid with car sharing in the future? As part of the V2G4Carsharing project, we simulated scenarios for 2030 and quantified the benefits in terms of monetary savings and peak shaving effect. In our case study done in collaboration with the swiss car sharing provider Mobility, we found that Mobility could offer flexibilities between 12 to 50 MW, dependent on the scenario. There is a sweet spot where both car sharing and power grid operators benefit.

Our paper titled Vehicle-to-grid for car sharing – A simulation study for 2030 was now published in Applied Energy! Check out the paper here.

Get in touch if you are interested to learn more, or checkout our project code base and the car sharing simulator.

Our paper on “Quantifying the dynamic predictability of train delay with uncertainty-aware neural networks” has been published in Transportation Research Part C!

In light of the importance of accurate delay prediction for transport services and passengers, many predictive methods have been proposed. However, they hardly account for the involved uncertainty and there is a lack of work analysing the dynamic predictability over time. We fill this gap with an uncertainty-aware neural network and a framework for describing the predictability by the prediction horizon. The results on Swiss train delay data show 1) an exponential decay of the predictability by the horizon, 2) a significant portion of (aleatoric) data uncertainty in contrast to model uncertainty, and clear advantages of the NN compared to MC models.

For more details, check out our paper! This work was done in collaboration with the Institute for Trans­port Plan­ning and Sys­tems at ETH Zurich.