Empowering researchers to better design and tackle data-rich projects.

Project DATA (Digital Ad Tracking & Analysis)
Project DATA (Digital Ad Tracking & Analysis)

This collaborative project investigates the sponsors, content, and targets of digital political campaigns across multiple platforms with a user-based, real-time, ad tracking tool that reverse engineers the algorithms of political campaigns. “The Stealth Media? Groups and Targets behind Divisive Issue Campaigns on Facebook,” presents the first empirical study that demonstrated election interference by “suspicious groups” including Russian groups—in real time. Featured in nearly 400 national and international media (e.g., New York Times, BBC5, and WIRED), the outcomes of the project were discussed in testimony before the Federal Election Commission and presented at the Congressional briefings on foreign interference in elections.

Want to Know More?

GeoDeepDive
GeoDeepDive

GeoDeepDive combines library science, computer science, and geoscience to dive into repositories of published text, tables, and figures and return valuable information. by building a comprehensive digital library, supported by a reliable high-throughput computing infrastructure, geoscientists can more efficiently discover and use the hard-earned data locked in the scientific literature to answer important scientific questions about the evolution of organisms and changes in climate.

Want to know more?

Library of Stains
Library of Stains

Stains on medieval manuscripts indicate a past laden with human interactions. Reading stains using multispectral imaging—in concert with conventional information adds to our understanding of a manuscript’s history and use.  The Library of Stains project has published 220 Gb of imaging data in a stain database, generated methodology for using multispectral imaging for the study of stains, and provided a model for public-facing interdisciplinary collaboration. Visualizations are hosted on the Digital Mappa platform, a UW Madison homegrown and funded Digital Humanities resource for annotating and linking data.  

Want to know more?

 

Saving the Amazon Rainforest
Saving the Amazon Rainforest

Overgrazing is a leading cause of deforestation in the Amazon rainforest. Major global companies are committed to eliminate farmers involved in deforestation from their supply chains, but cattle are often moved among several ranches making it difficult to trace them. Databases exist that provide information on millions of cattle transactions involving thousands of properties in Brazil, along with two decades worth of annual deforestation maps, but these data are not linked. Merging the databases allows companies to track the buying and selling transactions involving any given animal, map all of the ranches an animal has moved through, and assess deforestation on them.

Want to learn more?

Computational Plant Sciences (ComPS) Group
Computational Plant Sciences (ComPS) Group

A common problem plant scientists face is that advances in high-throughput measurement platforms have outpaced the ability to readily analyze the datasets produced. Thus, researchers in Plant Sciences formed a Community of Practice, a peer-to-peer mentoring network working across lab, departmental, and college boundaries to help build computational and data science skillsets.

Want to know more?

 

Monitoring the Health of US Lakes
Monitoring the Health of US Lakes

Assessing the health of the nation’s six million lakes and reservoirs at the continental-scale is limited because of data usability. By making large data repositories easier to use for the freshwater research community, we can explore such questions as: What is the state of surface water in the United States? How do continental-scale changes in climate and land use drive water quality? How might global food and water networks influence the ecosystem services that surface waters provide?

Want to know more?

Contact US


Office Hours

Join us in Hub Central in the Discovery Building to learn about data science training opportunities, identify campus data and computing resources, and establish collaborations with data scientists and other researchers on campus.

Open Office Hours:
Wednesdays, 9:30-11:30
Thursdays, 3:00-5:00 

Training

The Data Science Hub hosts training to help researchers learn the skills they need to reproducibly write software and analyze data. For more information about these workshops and others offered elsewhere on campus, click here

Newsletter

The Data Science Hub publishes a bi-monthly newsletter with updates on data and computing news and events for UW-Madison researchers.

Email: