Our research strategy is informed by the observation that the unique challenges found in real-world problems often inspire foundational advances in data science. By partnering with groups around campus, DSI simultaneously supports the research mission of the university and advances the forefront of data science through use-inspired research.
This portfolio includes examples of projects that DSI has contributed to through our Data Science Services, as well as projects led by our staff and affiliates. Our research portfolio is growing, and we regularly add new projects to this page.
Corn Fungicide ROI Calculator
This decision-support tool allows corn growers to estimate the profitability of different fungicide applications based on real-time crop conditions.
Dairy Data Science
This project builds off the DairyBrain infrastructure project that ingests and analyzes data from dairy farms, adapting it to an easily-deployable open-source project.
Ask-xDD
Ask-xDD offers an easy-to-use chat interface for accessing academic information. It helps bridge the gap between complex academic content and users.
AI for Physics
This project uses transformers to precisely calculate scattering amplitudes, which are the mathematical quantities at the heart of many high-energy physics calculations.
Corn Yields and Diseases
DSI supported a meta-analysis to determine whether foliar fungicides were effectively controlling diseases and potentially enhancing the overall health of corn crops.
COVID-19 Research Group
This interdisciplinary coalition was hosted by DSI with partners from UW-Madison, local and state government, industry, and other academic institutions.
ML for Learning to Read
We developed a machine learning model to simulate children's reading learning processes. This digital twin allows us to explore reading mechanisms and could lead to more personalized instruction.
Leaf Image Processing
This project automated the manual process of collecting data from leaf images. DSI data scientists created an app that segments these images into healthy, lesioned, and not-leaf areas.
SoundForestLab Database
The SoundForestLab Database enables the storage and sharing of a large database of ecological soundscape recordings. An audio soundscape is a useful tool for measuring biodiversity.