Data Science Challenge sees summer surge

Lawrence Livermore welcomed students from four institutions for this year’s Data Science Challenge (DSC) internship program. Hosted by the DSI, the DSC gives undergraduate and graduate students a taste of the multidisciplinary research performed at national laboratories. In addition to UC Merced and UC Riverside, participants hailed from two new partnering institutions: Case Western Reserve University (CWRU) and California State University, Bakersfield (CSUB).

“The DSC gives students an opportunity to engage with the Lab and see the type of impactful work we do,” says program director Omar DeGuchy. “For many of these students, it is their first internship, and our goal is to provide them with an experience where they can develop new data science skills as well as network with the Lab’s scientists and students from other academic institutions.”

Held at the University of California Livermore Collaboration Center, the intensive two-week internship offers students hands-on experience using data science techniques to address real-world computational challenges. Livermore scientists, engineers, and technical staff instruct and mentor students as they navigate challenge problems involving data gathering and analysis.

Expanding the program to include additional schools is a key part of the DSI’s outreach strategy, and this inaugural experience with CWRU and CSUB has been a success. Jane Dong, dean of CSUB’s School of Natural Sciences, Mathematics, and Engineering, says, “As the only four-year public university serving the Kern County community, CSUB takes pride in our mission to support and uplift our diverse student body. Many of our students are first-generation college attendees from low-income families. The prospect of learning from world-class scientists and applying data science principles to drive innovation is incredibly enticing for them. Moreover, the chance to collaborate with peers from major research institutions who share their aspirations is an experience they eagerly anticipate.”

DeGuchy continues, “Since its inception in 2019, the DSC’s challenge problems have ranged from therapeutic drug discovery to asteroid detection. The choice of challenge problem is tied closely with DSI’s Open Data Initiative [ODI].” Through ODI, Livermore curates publicly accessible datasets related to Laboratory research themes such as astronomical surveys, COVID-19 antibody designs, and X-ray images of additively manufactured objects.

This year, led by DSI’s open data science director Kerianne Pruett, DSC participants work with electrocardiogram (ECG) data to model and predict heart health. ECG is a valuable diagnostic tool due to its low cost and noninvasive nature, but the limited data possible using the standard set of twelve electrode leads makes it insufficient for mapping heart activity in high enough detail for many clinical applications.

DSC participants are tasked with applying advanced machine learning techniques to construct electro-anatomical maps of the heart at sufficient resolution to make diagnostic inferences. Undergraduate students take part in all aspects of data analysis while working on a small team led by graduate students. The teams delivered their final presentations on August 2.

“I am very excited that two [of our] computer science students had the opportunity to participate in DSC at an early stage of their college studies,” says Dong. “Exposure to the frontier of biomedical research and the challenge to solve real-world problems empowers students to think outside of the box, inspires them to explore new technologies, and helps them to develop their professional identities.”

CSUB student Noah Gallego adds, “It’s an incredible honor to be selected to represent CSUB, and I’m beyond excited for the opportunity and the experiences that lie ahead!”