UCGIS Symposium 2026

The future of Spatial Intelligence - The opportunity for Leadership
In the not-too-distant future, every decision - investment, infrastructure, climate adaptation, real estate, farming, banking - will start with a live conversation with the Earth. In our field, we have surely moved from looking at the Earth to asking it questions building on the maturity of geospatial technology and computing, the explosion of earth observation data, and the proliferation of AI. In an era of 'AI Everywhere,' the path to true spatial intelligence requires more than just technological advancement; it demands a radical shift in how we collaborate.

In her keynote, Marge Cole draws on her global experience working with NASA, OGC and a multitude of startups and innovators over the years. Reflecting on the path towards spatial intelligence, its impact on innovation, research, and business opportunties - underscoring the pivotal need for academia and research to forge more cross-disciplinary, more collaboration, more agility, and more partnerships with industry upfront and throughout the research process, also examining the unique opportunities and challenges this rapid evolution presents for education and research.

Scaling over Space: Advancing the Model and Data Foundations of GeoAI
Advances in deep learning and foundation models are raising expectations for general-purpose learning and creating new opportunities to harness the geospatial data revolution for Earth monitoring and scientific discovery, with broad benefits for agriculture, energy, water, transportation, smart cities, and disaster response. At the same time, major challenges remain for large-scale geospatial applications, including spatial variability that substantially weakens model generalization, limited and localized training data, and high computational demands that constrain and slow scientific discovery. This talk will discuss both AI model and data foundations for scaling geospatial applications, including geo-aware learning, knowledge-guided learning, task-aligned pretraining, and new benchmark datasets.