Towards Foundation Model for Spatiotemporal Data Analysis

Abstract

Spatiotemporal data modeling has long been a fundamental task across disciplines such as climate & environmental science, and transportation engineering. A typical goal is to estimate unknown information at specific spatiotemporal points based on partially observed data—for example, interpolating weather conditions at unmeasured locations, reconstructing missing historical records, or forecasting the future trajectories of financial markets. These are all core tasks within the broader scope of spatiotemporal modeling. This tutorial (1 hours) introduces a cohesive view of spatiotemporal data modeling, tracing the evolution from traditional statistical approaches to modern deep learning paradigms. We begin by revisiting Kriging and time series decomposition to highlight the essential assumptions and strengths of these classical methods. Next, we explore low-rank matrix and tensor completion techniques, which leverage the structured patterns of spatiotemporal data. We then elaborate on spatiotemporal graph neural networks, which characterize complex dependencies by integrating graph structures with dynamic temporal features. Finally, we discuss recent advances in applying large foundation models to spatiotemporal tasks, including their capabilities and current limitations. Throughout the tutorial, we emphasize how lessons from traditional methods—such as the importance of locality, periodicity, and smoothness priors—can inspire new directions for developing and fine-tuning foundation models in the spatiotemporal domain. We conclude by outlining key challenges and opportunities in bridging classical wisdom with emerging AI capabilities.