Five UMSI faculty earn 2025 MIDAS PODS awards

Five researchers at the University of Michigan School of Information have earned grants from the 2025 Michigan Institute for Data and AI in Society (MIDAS) Propelling Original Data Science (PODS) program. 

Their projects will spur innovations in healthcare, environmental sustainability and education through the use of data science and artificial intelligence. The PODS tracks have been organized in five categories: Data science and AI methodology and applications; Accelerating responsible AI research ecosystems; AI innovations in Clinical & Translational Sciences; AI impact and governance for health policy and healthcare; Data science and AI for health science and healthcare research

UMSI awardees and their tracks:

Track 1: Data science and AI methodology and applications

The As-If Machine (AIM): A Multi-Agent RAG System for Reducing Psychological Distance Through Personalized Narrative Simulations

UMSI assistant professor Ceren Budak and Stephanie Preston (College of Literature, Science, and the Arts). 

This project is an interactive multi-agent system that creates personalized "what-if" stories to help people step into experiences beyond their own. The approach helps people empathize with issues outside their immediate lives, fostering support for inclusive policies and proactive engagement. 

“The PODS award will enable us to rigorously test AIM across these topical areas and to develop a production-ready web application, empowering a diverse set of researchers to deploy their own scalable and customizable interventions with minimal technical requirements,” Budak says. 

SAGE: A Scalable GeoAI Framework for Zero-Shot Mapping of Lithium Mines

Joshua Newell (School for Environment and Sustainability) and UMSI associate professor Paramveer Dhillon. 

This project will help address environmental concerns from lithium mining by building SAGE (Scalable AI for Geospatial Extraction), a generative GeoAI system that converts raw satellite imagery into the first open, high-precision global atlas of lithium-extraction sites.

“This data will let policymakers enforce environmental safeguards, scientists quantify climate and ecosystem impacts and industry verify responsible sourcing,” Dhillon says. “The MIDAS PODS award accelerates this vision by funding our proof-of-concept deployment and validating a scalable approach we can next apply to the full suite of critical minerals."

Harnessing AI for Advancing Data Collection and Population-Scale Causal Inference

William Axinn (Ford School of Public Policy), UMSI associate professor David Jurgens and James Wagner (Institute for Social Research). 

This project is designed to revolutionize general population causal inference by simultaneously accounting for all components of data creation errors while calculating causal associations. This new approach has the potential to advance U-M’s position as the leaders in data collection science as AI increases the breadth of data creation errors we can measure and address. Ultimately, the findings have the potential to drive both improvements in data quality and causal inference.

Track 2: Accelerating responsible AI research ecosystems 

AI Systems to Combat Non-Consensual Intimate Media (NCIM)
UMSI professors Sarita Schoenebeck and Eric Gilbert. 

Non-consensual intimate content, including sexual deepfakes and “revenge porn”, is a large-scale and growing societal crisis. Victim-survivors face relentless violations of their privacy and dignity and must manually report content across hundreds of websites, often with little success. This project builds web-based AI agents that act on behalf of victim-survivors to locate, report, and monitor non-consensual content across the web.

RELATED

Learn more about the Michigan Institute for Data and AI in Society by visiting their website.

See the full list of current and past PODS Awardees.