The task of anomaly detection in geospatial data is to find data points in space and time that deviate so much from other observations as to arouse suspicion that it was generated by a different mechanism. Most of the existing work in geospatial data analysis relies on supervised machine learning, which involves training models on labeled datasets, allowing them to learn and make accurate predictions. Anomalies, by definition, are rare events that occur infrequently and unpredictably. As a result, labeled datasets for these events are either non-existent or extremely limited. Consequently, anomaly detection research calls for new strategies that can identify rare and unexpected events based on patterns and distributions within the data itself in an unsupervised fashion. These anomalies may manifest as unexpected changes in environmental conditions, natural disasters, unusual human activities, or irregular patterns in spatiotemporal distributions. To answer this call, we organized the 1st ACM SIGSPATIAL International Workshop on Geospatial Anomaly Detection (GeoAnomalies'24) at SIGSPATIAL'24. In this Newsletter Article, we report our first findings and map future research directions.
The ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems 2025 (ACM SIGSPATIAL 2025), the thirty-second edition, will be held in Minneapolis, MN, USA, from November 3 to November 6, 2025 (https://sigspatial2025.sigspatial.org/org/). The conference began as a series of symposia and workshops starting in 1993 with the aim of bringing together researchers, developers, users, and practitioners in relation to novel systems based on geospatial data and knowledge, and fostering interdisciplinary discussions and research in all aspects of geographic information systems. The conference provides a forum for original research contributions covering all conceptual, design, and implementation aspects of geospatial data ranging from applications, user interfaces, and visualization to data storage and query processing and indexing. The conference is the premier annual event of the ACM Special Interest Group on Spatial Information (ACM SIGSPATIAL).
Urban AI is an interdisciplinary field that integrates artificial intelligence, spatial computing, and urban science to tackle the multifaceted challenges of urbanization. The proliferation of urban data and the rapid digitization of city infrastructures have created unprecedented opportunities for leveraging data-driven machine learning approaches in urban science. Urban AI addresses innovative applications of AI techniques to urban problems, the development of AI-ready urban data infrastructures, and a wide array of practical urban applications. These applications span diverse areas, including urban planning, traffic forecasting, energy optimization, public safety, urban agriculture, and land use management.
Geospatial simulation is an effective tool to experience physical and/or cyber space (e.g., the metaverse). New experiences gained from geospatial simulations can bring significant benefits, including situational awareness, insight into environments, and entertainment. To take advantage of such simulations, it is crucial to advance the methodology of modeling and simulation, develop plausible models, and apply them to various domains, leveraging big data and evolving technologies.
The ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems held a half-day workshop on Sustainable Urban Mobility. This was the second Workshop of this series, after a successful initial event at ACM SIGSPATIAL in 2023 in Hamburg [1]. The workshop explicitly considers urban mobility as an open, complex system, and hence points to a wicked problem: estimating the global impact of any intervention to a mobility system that is aiming for less emissions, less vehicles on the road and less single-person cars, or any other sustainability goal. Often, such interventions show unintended consequences. For example, efficiency gains in one mode of mobility may show rebound effects on that mode as well as feedback loops with other modes. While we typically ignore such interrelations as "too difficult", the workshop set out to explore what the spatial computing community can contribute.
