Air pollution-ecosystem feedbacks: Unmanned aerial vehicles and ecosystem models to quantify ozone-forest interactions
This project is investigating ozone emissions and photosynthesis rates by using the eddy-covariance (EC) technique, which is a statistical method used to measure trace exchange rates and gases in an environment and an unmanned aerial vehicle (UAV), or drone.
Mothers, Infants, Microbiome and Mental Health (MIMMs): A social neuroscience perspective of maternal-child health to unlock the potential of bio-banked data
This project explores the interplay between the intestinal microbiome, anxiety and depression during pregnancy, and subsequent maternal-child attachment.
This project, using a dataset consisting of 3.8 million Twitter users and 150 million tweets and an additional dataset containing more than 40 million tweets corresponding to 45 keywords centered around the Black Lives Matter movement, explores online political discourse from the perspective of those engaged in it.
This project uses high dimensional graphical models to explicitly model the joint distribution of the abundances of all bacteria species in the human gut microbiome, which is more comprehensive than previous approaches, in an effort to develop novel methods and tools that will allow us to synthesize the overarching principles governing the microbial stability and make broad and meaningful predictions that will improve human health.
This project explores the design of an algorithm that can push back against an individual’s immediate desires (i.e., act paternalistically) in an ethically defensible manner using statistical analysis and Inverse Reinforcement Learning to distinguish between a person’s values and desires and developing a recommendation app.
Faculty Advisors: Talbot Brewer (College of Arts and Sciences) and Matthew Gerber (School of Engineering)
Censorship and Detecting Deception: A Data-Driven Look at Obfuscation in Soviet Dissident Writing Versus Misinformation in the USSR and Post-Truth Journalism in America
This project explores how well machine learning and other data science approaches work in detecting fake news in the ideologically distinct environments of the United States and the Soviet-era USSR.
Faculty Advisor: Dariusz Tolczyk (College of Arts and Sciences)