AGENDA (2026)
Follows in spring 2026
| 09:00 a.m. | SOFT LANDING |
| 09:30 a.m. | Welcome Address |
| 09:40 a.m. | “AI for Sustainable Mobility: Leveraging New Data Sources for Understanding Mobility Behavior and Optimizing Transportation Systems“ by Prof. Dr. Simone Weikl (OTH Regensburg) Advances in data‑collection technologies create new possibilities for capturing detailed spatiotemporal mobility data. The research group Artificial Intelligence for Infrastructure and Urban Development at OTH Regensburg explores how data science and emerging data sources can improve the understanding and management of mobility systems. The talk highlights recent developments and examples from ongoing projects—ranging from sensor‑equipped bicycles and drone‑based traffic monitoring to smartphone GPS data. It shows how heterogeneous data streams are transformed into meaningful mobility insights using machine‑learning methods for ride‑style detection, safety analysis, traffic prediction, and infrastructure mapping—advancing safer and more sustainable transportation. |
| 10:20 a.m. | “Causal inference for climate data: an example on land-atmosphere Feedbacks by Dr. Oana Popescu (University of Potsdam, TU Berlin) The climate system is highly intricate, shaped by interactions among many components operating across diverse spatial and temporal scales. This complexity makes it challenging to understand, and ultimately to predict weather extremes. However, these events are highly interesting as they have profound impacts on ecosystems, economies, and communities worldwide. In this talk, we explore how causal inference can help disentangle the mechanisms underlying anomalous climate phenomena, particularly focusing on heatwaves. We present how both causal discovery and causal effect estimation can be employed to uncover the influence of land–atmosphere feedbacks on heatwaves. |
| 11:00 a.m. | — COFFEEBREAK |
| 11:20 a.m. | “Data, Science, and AI at OroraTech” by Dr. Alison Merritt (Hochschule Bielefeld) As climate change intensifies wildfires, droughts, and land degradation, the availability of high-quality, high-frequency thermal Earth observation is increasingly vital. OroraTech is working towards creating a thermal digital twin of the Earth, through a global constellation of satellites with a 30 minute revisit time. The first eight are already in orbit and operational, providing data during the critical “late afternoon gap” where wildfires are most likely to ignite or intensify. In this talk, I will present an overview of how we work with our mid- and long-wave infrared data, from data calibration and validation to near real-time fire detection and fire spread modeling. . |
| 12:00 noon | — LUNCHBREAK |
| 01:00 p.m. | Lightning Round & Poster Session (& COFFEE) |
| 03:00 p.m. | „Human AI Alignment in Joint Decision Making and Problem Solving“ von Prof. Dr. Ute Schmid (University of Bamberg) With the advance of highly performant AI systems — deep learning based classifiers and transformer based generative approaches — there is hope that human AI collaboration will support humans to master complex tasks more efficient as well as in high quality. This is especially relevant for critical tasks such as medical diagnostics or generation of program code for scientific tasks. However, a growing number of empirical studies shows that the best of humans or AI systems outperform human AI teams. Possible reasons are on the one hand over-reliance in the output of AI systems and on the other hand a mismatch between human cognitive processes and AI systems. In the talk, I will propose that we need more human aligned methods of explainable AI as well as novel methods to support human agency and oversight. |
| 03:40 p.m. | „Making AI Work for Everyone: NLP in the Era of Large Language Models“ von Prof. Dr. Barbara Plank (LMU) Large Language Models (LLMs) have transformed Natural Language Processing (NLP) research, and enabled systems that appear broadly capable. Yet their success also raises pressing questions: Under what conditions do they work or fail, and how can we ensure progress benefits a wide range of users and languages? In this talk, I will offer a critical yet optimistic perspective on NLP in the era of large language models, arguing that scale alone is not enough to achieve inclusive and reliable language technology. By reflecting on the history of NLP and its long-standing engagement with linguistic and human variation, the goal of this talk is to outline paths forward that integrate variation as a core design and evaluation concern for making AI work for everyone. |
| 04:20 p.m. | “tbd.” by Claudia Hauff (Spotify) coming soon |
| 05:00 p.m. | WiDS 2026 Summary |
| 05:10 p.m. | Get-together No program, just delicious food and plenty of networking opportunity. |
| 06:30 p.m. | Goodbye |