Announcing the 2026 Waldo Tobler and TGIS Distinguished Lecture in GIScience

Abstract: Knowledge advances through the accumulation and evaluation of evidence that either corroborates or challenges an existing understanding. Attempting to replicate research is one approach to generating such evidence and using it to evaluate the credibility of existing claims. However, expected variation in social and environmental processes across locations calls into question when a replication performed in one context can be used to make or evaluate claims in another context. While this problem has a long history in the geographic literature, recent work on the reproducibility and replicability of geographic research has not focused on addressing it. In this talk, I identify new directions for reproducibility research in geography focusing on the goal of using replication to make and evaluate claims across locations.

Abstract: In this talk, I will discuss my involvement with Geospatial Artificial Intelligence (GeoAI) from the NSF funded Alexandria Digital Library Project at UCSB in 1998 to the present. I will present my contributions in the context of two themes. One is that spatial data is special in that space (and time) provides a rich context in which to analyze it. The challenge is how to incorporate spatial context into AI methods when adapting or developing them for geographic data—that is, to make them spatially explicit. A second theme is that location is a powerful key (in the database sense) that allows us to associate large amounts of different kinds of data. This can be especially useful, for example, for generating large collections of weakly labeled data when training machine learning models.