Gabriel Agostini, PhD candidate at Cornell Tech, will present the EEEP Seminar Series, “Inferring Fine-Grained Migration Patterns across the United States” on April 1, 2026.
Abstract:
Fine-grained migration data illuminate demographic, environmental, and health phenomena. However, United States migration data have serious drawbacks: public data lack spatial granularity, and higher-resolution proprietary data suffer from multiple biases. Through harmonization of high-resolution yet biased proprietary data with coarse yet reliable Census data, we create and release MIGRATE: annual migration matrices capturing flows between 47.4 billion US Census Block Group pairs—approximately four thousand times the spatial resolution of current public data. Our estimates are highly correlated with external ground-truth datasets and improve accuracy relative to raw proprietary data. We use MIGRATE to analyze national and local migration patterns. Nationally, we document demographic and temporal variation in homophily, upward mobility, and moving distance—for example, rising moves into top-income-quartile block groups and racial disparities in upward mobility. Locally, MIGRATE reveals patterns such as wildfire-driven out-migration that are invisible in coarser previous data. In this talk, I will discuss our new data-fusion method to build MIGRATE, our efforts to validate it, and outline findings and potential applications in future migration research.
Bio:
Gabriel Agostini is a PhD student in Information Science at Cornell Tech. Agostini’s research leverages spatial machine learning methods and creates novel datasets to inform more equitable urban policies. Agostini focuses on addressing challenges related to sparse and biased spatial data: specifically, how to transform coarse, crowdsourced, and irregularly collected information into actionable insights for improved city resource allocation.