Workshops

August 26, 2025

  1. Home
  2. Workshops

Mobile Brain Body Imaging Techniques for Spatial Cognition and Human Navigation

Description

With the advent of high-frequency mobile wearable sensors, it is now feasible to research areas pertaining to cognitive maps of the human brain and its interaction with the spatial world. This workshop is designed to provide you with theoretical background on human spatial navigation, give you hands-on experience with Mobile Brain Body Imaging using an electroencephalograph (EEG) and other biometrics, subsequently showcasing frontiers in analysis of data to uncover insights into spatial cognition.

Whether you’re a beginner or have some experience in GIScience or neuroscience, this workshop will equip you with valuable skills and knowledge. Get ready to dive into the fascinating world of spatial cognition and EEG!

Mapping with Communities, international workshop

  • Category: Half day workshop (Morning)
  • Organizers:
  • Anne Schauss, HeiGIT Heidelberg Institute for Geoinformation Technology
  • Erika Upegui, Universidad Distrital Francisco José de Caldas, Bogotá (UDISTRITAL)
  • Diego Pajarito, University of Glasgow

Description

Are you working with communities in LMIC to map their interests and priorities? Are you developing methodologies to engage vulnerable communities in mapping? Or are you using digital technologies to support communities in generating and analysing geospatial data?

Join us for an interactive and engaging workshop where we will explore the challenges and opportunities of participatory mapping in GIScience. This is a space to exchange experiences, discuss qualitative and mixed-method approaches, and reflect on key issues such as fairness, accountability, and transparency in research.

We invite submissions describing efforts in participatory mapping, covering topics such as community engagement, data co-production, validation, modelling, and enabling technologies. Send an abstract (1000 to 1500 words) to mappingwithcomm@glasgow.ac.uk by 30 June. Selected contributions will be featured in the workshop and deposited in our Zenodo digital community. We will share innovative approaches, foster collaboration, and explore the diverse intersections between participatory methodologies and geospatial research.

Through a hands-on session and project showcases, and collaborative discussions, we aim to strengthen the participatory mapping community and shape a future research agenda. Let’s connect, learn from each other, and shape the future of participatory mapping together.

Geospatial Data Representation Learning

Description

Representation learning has revolutionised machine learning by enabling models to extract meaningful features from raw data automatically. This workshop explores its potential in GIScience, focusing on geospatial data’s unique challenges and opportunities. We invite contributions on topics including but not limited to:

  • - Spatial and spatiotemporal representation learning methods.
  • - Applications of representation learning in urban analytics, environmental science, and mobility studies.
  • - Multimodal representation learning for integrating heterogeneous geospatial data.
  • - Theoretical advancements and model interpretability in geospatial contexts.

We welcome research papers, position papers, and practical demonstrations. Join us in advancing geospatial AI through representation learning!

For abstract submissions, please email fanzhanggis@pku.edu.cn. Further information on the workshop is available at: https://carnelian-parmesan-a70.notion.site/Title-of-the-Workshop-Geospatial-Data-Representation-Learning-1b03522f3fbe804295e6c565cb635d14.

Spatiotemporal Causal Analysis (#STCausal2025)

  • Category: Half day workshop (Afternoon)
  • Organizers:
  • Martin Tomko, The University of Melbourne
  • Cecile de Bezenac, The Alan Turing Institute, University of Leeds/ Centre Borelli, ENS Paris-Saclay
  • Grant McKenzie, McGill University
  • Website: stcausal2025.spatial-causal.org

Description

Causal analysis, including causal discovery, causal inference and causal representation learning, is fundamental to understanding the behaviors of a natural and societal system, and for our ability to intervene into the outcomes of such systems. The majority of spatial sciences and spatial statistical research has, for a long time, remained at the level of describing, or predicting (forecasting) outcomes of spatial processes and systems, but has shied away from making causal claims, and therefore also from efforts to design causally-informed interventions. Recent advances in causal analysis make strong assumptions about I.I.D data, fundamentally violated in spatial processes.

We invite researchers interested in the ability to make causal claims based on analyses in spatial disciplines incl. Earth science, epidemiology, transportation, urban planning, and economics, interested in forming a shared conceptual, terminological, and methodological understanding of spatial causal analysis and methods to communicate outcomes of causal analysis to the public to a seminar at GIScience 2025.

This workshop is a part of a concerted effort triggered by a Dagstuhl Seminar on Causal Inference for Spatial Data Analytics in 2024 to build a community meeting along with selected geospatial, computational, and statistical conferences to reach the disparate communities and individuals contributing to spatial causal research. According to literature, there is still a lack of research in causal inference.

We invite participants to lodge brief, max two page position statements to address the above topics in spatial causal analysis, as a starting point to a discussion that will result in an effort to synthesize, and articulate a joint position/vision paper.

Further information and submission criteria are available on the workshop website: stcausal2025.spatial-causal.org.

Engaging in Spatial Data Collection through Participatory Science

  • Category: Half day workshop (Afternoon)
  • Organizers:
  • Dr. Shane Orchard, Dr. Sarah McSweeney, and Dr. Carolynne Hultquist at the University of Canterbury
  • in collaboration with the Citizen Science Association of Aotearoa | New Zealand #CitSciNZ https://citsci.nz/

Description

Participatory science offers a wealth of opportunities for the collection and interpretation of spatial data while also engaging with stakeholders and communities at scales from local to global. In this interactive workshop we will combine a demonstration of two international approaches to data collection (iNaturalist and CoastSnap) with a field tour of local study sites and contexts in which they are applied. These sites feature rich biodiversity, strong cultural values and notable environmental changes including severe effects from the Canterbury earthquakes and ongoing coastal processes.

This workshop provides an opportunity to engage in discussions in the field and consider applications of GIScience to real-world contexts to develop a better understanding of local environments and how they are captured in citizen science data. It will be of particular interest to researchers and practitioners involved in disaster recovery / risk reduction, climate change and monitoring long-term change.

Evaluating, Interpreting and Mitigating Geo-Bias of GeoAI Models

  • Category: Half day workshop (Afternoon)
  • Organizers:
  • Zhangyu Wang, University of California, Santa Barbara

Description

GeoAI models are often evaluated using geo-agnostic metrics such as accuracy, which overlooks the spatial disparity of model performance. A model that is 90% accurate all over the world is preferable to a model that is 99% accurate in most regions but completely fails in certain locations, because this geo-bias may cause user experience degradation and fairness issues. This workshop covers the topics including theories, methods and practical tools for evaluating, interpreting and mitigating geo-bias. We will invite speakers to give presentations on the mathematical foundations, the social/ethical implications, and the broader impacts of geo-bias on the reliability/fairness/sustainability of GeoAI. We will also offer seminars discussing how to understand and address geo-bias. Most importantly, we will give a comprehensive tutorial on a recent geo-bias evaluation and analysis toolbox called PyGBS and GBS-Analysis, making researchers even with the least possible coding skills to easily evaluate and report geo-bias of GeoAI models.

For abstract submissions of 200 words please email zhangyuwang@ucsb.edu.

AI in ArcGIS: Innovations in GeoAI and GenAI

Description

This tutorial workshop covers a wide range of AI methodologies that have been integrated into the ArcGIS workflow. We will provide links to the examples and datasets, so that people can have a try during and after the session. But for logistical reasons it is not hands-on per se.

Time permitting (including Q&A) we plan to cover the following:

  1. Data Engineering- how to do it, how the tools have improved over the years (2D and 3D data)
  2. Training models (Model types, backbone, architectures that are available), how to import weights
  3. Accuracy assessment report, train with focused metrics, validation, generate metrics
  4. Inferencing in different products, and sharing the model
  5. Integrate Open Source AI platform Hugging Face
  6. Integration ( Bringing models in and out of ArcGIS Ecosystem)
  7. Deep Learning pre-trained models freely available (imagery, NZ examples)
  8. The breadth of statistical, ML, and DL tools in ArcGIS to solve problems
    • - Pattern analysis/clustering
    • - Prediction and Classification
    • - Time-series Forecasting
    • - New tools for modelling Uncertainty
  9. Generative AI: where we are at
  10. Discussion: what geospatial analysis problems are most amenable to Gen AI?

Mastering Reproducible Research in Geoscience and Remote Sensing

  • Category: Full day workshop
  • Organizer: Alejandro C. Frery, Victoria University of Wellington

Description

Reproducibility is the backbone of credible science, yet studies reveal a crisis: 70% of researchers fail to reproduce others’ experiments, and 50% struggle to reproduce their own. In Geoscience and Remote Sensing, only 4% of IEEE editorial members believe there’s no crisis.

This hands-on workshop will equip you with the tools and skills to produce rigorous, reproducible research. You’ll:

  1. Learn the foundations of reproducibility and its role in empirical science.
  2. Explore tools like RMarkdown/Quarto to create dynamic, reproducible documents.
  3. Analyse a fully reproducible journal article and draft your own.
  4. Master version control with Git to track changes and collaborate effectively.
By the end, you’ll have a reproducible article draft and the skills to ensure your research stands the test of time.

Who Should Attend?

Researchers, students, and professionals in Geoscience, Remote Sensing, GIScience, and related fields.