​The Data Science Institute’s Seed Funds Program supports new collaborations that will lead to longer term and deeper relationships among faculty in different disciplines across campus. Aimed at advancing research that combines data science expertise with domain expertise, the program’s funded research embodies the spirit of the Institute’s mission statement. 

The following research projects and teams have received 2022 awards.

Using Machine Learning to Measure Racial/Ethnic Bias in Obstetric Settings

Veronica Barcelona, Nursing

Kenrick Cato, Nursing

Dena Goffman, Obstetrics and Gynecology

Coretta Green, New York-Presbyterian

Anita Holman, Obstetrics and Gynecology

Janice James Aubey, Obstetrics and Gynecology

Bernadette Khan, New York-Presbyterian

Kenya Robinson, New York-Presbyterian

Maxim Topaz, Nursing

This team will examine the association between linguistic bias and pregnancy-related morbidity among birthing people from 2017-2019 at two hospitals. They will use natural language processing approaches to: 1) identify stigmatizing language in clinical notes, 2) examine patterns of language use by race and ethnicity, and 3) study associations between language use and pregnancy-related morbidity.

Application of Gaussian Mixture Regression to Obtain Useful, Actionable Air Pollution Data from Consumer-Grade, Low-Cost Monitoring Devices

Xiaofan (Fred) Jiang, Electrical Engineering

Daniel Westervelt, Lamont-Doherty Earth Observatory

This team will develop and apply a novel, globally applicable, bias correction algorithm to a fast-growing global network of consumer grade, low-cost air quality sensors. This method will allow users to obtain high-quality data from raw, unvalidated sensor data, thereby empowering communities to better understand their air pollution exposure and take action.

Positioning Energy Storage Technologies with Stochastic Climate Scenarios

Upmanu Lall, Earth and Environmental Engineering

Bolun Xu, Earth and Environmental Engineering

This project combines data-driven renewable energy simulations with model-based storage pricing models to quantify the financial value of various energy storage technologies in integrating renewables and mitigating climate change in a decarbonizing electric power system.

Racial Inequality in Police Violence: Injuries and Fatalities from Police Use of Force

Jeffrey A. Fagan, Law, Public Health

Rajiv Sethi, Barnard, Economics

Elizabeth Ananat, Barnard, Economics 

Morgan C. Williams, Jr., Barnard, Economics

Brendan O’Flaherty, Economics

José Luis Montiel Olea, Economics

This project will create a data archive on non-fatal injuries and fatalities from police encounters—data that may be harmonized and integrated with other increasingly detailed datasets on police killings—and provide estimates of a continuum of police use of force. The new database will provide capacity and research opportunities for departments, schools, laboratories, and students across the university on an urgent public policy issue.

Using Data Science and Causal Inference to Estimate the Community-Level Impact of Police Behavior on Psychological Distress: The Case of No-Knock Search Warrants in Chicago

Gerard Torrats-Espinosa, Sociology

Kara Rudolph, Public Health

This team proposes to create a novel linkage of police administrative records that capture highly detailed information on all search warrants that the Chicago Police Department executed from 2012 to 2020. They will document spatial and temporal patterns of search warrant use across Chicago’s neighborhoods.

Psychology, Organizational Behavior and Neuroscience Literatures: Harnessing Data Science to Unify DEI Findings in Academic Literature and the Popular Press

Valerie Purdie-Greenaway, Psychology

Alfredo Spagna, Psychology

Peter Bearman, Sociology

Jennifer Manly, Neurology

Smaranda Muresan, DSI, Computer Science

This team will develop a shared understanding of how diversity and inclusion (D&I) is conceptualized and studied in the academic literature and compare academic research on D&I to what is found in popular press outlets. The project will draw from social psychology, organizational behavior, and social-cognitive neuroscience to create a baseline for understanding the structure of scientific knowledge related to D&I and to understand what kinds of D&I research finds its way into the popular press.