2026 Projects
Understanding how the brain’s physical wiring relates to its functional activity remains a major open question in neuroscience. This project investigates how structural connectivity (mapped using diffusion MRI) aligns with functional connectivity (derived from resting-state fMRI), with a focus on underexplored signals in white matter. Using large-scale datasets from the...
This data expedition focused on biological senses, in particular, musicality. The students read and summarized four scientific articles in discussion groups to build their background knowledge when it comes to how humans and animals use pitch and rhythm in music, language, and songs. We then had each student use headphones...
Accurate forecasting of weather variables -including humidity, temperature, dew point, cloud cover, and wind speed and direction- is critical for improving predictions of both renewable energy generation and electricity demand, and for managing emerging challenges associated with the rapid growth of data centers energy needs. In this project, we analyze...
A student team led by Henry Pfister’s research group will develop and evaluate an AI-powered “visual assistant” that pairs smart glasses with modern visual language models to assist people with visual impairment. We’ll start by benchmarking models on the VisAssistDaily dataset and then prototype a real-time system using open-source multimodal...
How do elites maintain power when the world around them is being radically transformed? Between the late sixteenth and early eighteenth centuries, England was reshaped by the explosive growth of global trade. Political and socio-economic elites had to adapt—or risk losing power. Who benefited from these changes, who lost out,...
A team of students led by researchers in the Division of Marine Science and Conservation within the Nicholas School of the Environment will explore environmental data collected at North Carolina oyster farms in combination with oyster RNA sequencing data. This project will enhance environmental data and biological samples collected by...
Duke Baseball Analytics team is looking to create a metric called Pitcher WAR. This metric is widely used throughout Major League Baseball to evaluate talent and use as evidence during contract negotiations. WAR stands for Wins Above Replacement, which allows you to see what the value of each player is...
A team of students led by Pratt professor Rachel Beaudoin will develop generalizable models to quantify the greenhouse gas footprint of Durham organizations and to assess the impacts of decarbonization projects. Students will work with a dataset of Durham Public Schools’ historical energy and procurement data to develop a model...
Explore Climate and Health Equity with Duke’s REGAL Lab! Join the Research to Eliminate Global Cancer Disparities (REGAL) Lab at the Duke University School of Medicine for a hands-on research experience on climate and health equity. Students will compile and analyze North Carolina county-level environmental indicators, such as air quality,...
A team of students will combine cutting-edge, high-resolution satellite imagery with a state-of-the-art AI and pattern-recognition framework to improve restoration outcomes across sub-Saharan Africa. Students will map trees both inside forests and across farms and villages using a deep learning model, then link those maps to socioeconomic factors and biophysical...
Duke undergraduate students interested in global health or data science along with Drs. Thuy Le and Tom Carpino from the Duke School of Medicine and Duke Global Health Institute, and a group of investigators from the Kilimanjaro Christian Medical Centre in Moshi, Tanzania, will investigate how real-world climate factors impact...
A team of students led by researchers in the Nicholas School of the Environment will use satellite imagery and spatial data in Google Earth Engine (GEE) to determine how a quarter-million smallholder farmers across East Africa and India have successfully scaled tree planting as a natural climate solution over the...
A team of students led by researchers in the Duke University Critical Minerals Hub will use data-driven methods to develop machine learning models that predict critical mineral presence and abundance in mine waste and acid mine drainage. Students will integrate large geological and geochemical datasets, identify key indicators of critical...
A team of students led by Dr. Tananun Songdechakraiwut (Computer Science) and Dr. Michael Lutz (Neurology) will use a newly released dataset from the Alzheimer’s Disease Sequencing Project Phenotype Harmonization Consortium (ADSP-PHC) to study relationships among cognitive measures, brain imaging, biomarkers, and clinical features of Alzheimer’s disease and related dementias...
A team of students led by researchers in English and Computer Science will investigate a fundamental question about artificial intelligence: can machines be truly creative? Students will design experiments comparing human and AI storytelling, build datasets and computational tools to measure originality and surprise, and explore what current language models...
Showing 1-20 of 28 results