Season 2, Episode 6 -- Pushing Limits in Computing and Biology
Release Date: 10/26/2022
Science in Parallel
In the second episode in our series on foundation models for science, we discuss Oak Ridge National Laboratory's work and hear about lessons learned from the recent 1000 Scientists AI Jam, a recent event that brought together researchers from several Department of Energy national laboratories, OpenAI and Anthropic. My guest is Prasanna Balaprakash, ORNL's director of AI programs. We talk about how foundation models could help with climate forecasts and his team's 2024 Gordon Bell finalist research and futuristic work that applies principles of swarm intelligence for managing distributed...
info_outlineScience in Parallel
Large language models aren't just powering chatbots like ChatGPT. This type of computational model is an example of a particular flavor of artificial intelligence known as foundation models, which are trained on vast amounts of data to make inferences in new areas. Although text is one rich data source, science offers many more from biology, chemistry, physics and more. Such models open up a tantalizing new set of research questions. How effective are foundation models for science? How could they be improved? Could they help researchers work on challenging questions? And what might they mean...
info_outlineScience in Parallel
Wrapping up our discussion of the 2024 Nobel Prizes in Physics and Chemistry, computer scientist Mansi Sakarvadia and computational structural biologist Josh Vermaas talk about the recent prizes and what they mean for science. You'll hear about how the prizes both break down research barriers and introduce concerns about misinformation and public trust. The research honored with the chemistry prize has already changed how researchers study questions that involve understanding proteins' structures. For more on the 2024 Nobel Prizes, check out . You'll meet: is a Ph.D. student in the and...
info_outlineScience in Parallel
2024 was artificial intelligence’s Nobel Prize year with the physics and chemistry prizes recognizing the underpinnings and application of these algorithms. Science journalist and author Anil Ananthaswamy spent years writing a popular book, Why Machines Learn: The Elegant Math Behind Modern AI, that explores the equations and historical context for this technology. In this conversation, Anil and host Sarah Webb explore that math and history, the significance of these Nobel Prizes for both AI and science, and the challenges that come with this powerful and fast-moving technology. You’ll...
info_outlineScience in Parallel
The annual convenes November 17-22 in Atlanta with the theme of HPC creates, and Science in Parallel previews a special display at the meeting: . Host Sarah Webb interviews Sadie Bartholomew of the United Kingdom's and the about her work as a research software engineer and her passion for creative coding. She submitted several pieces of digital art that will be displayed at SC24. Sadie discussed the many patterns in her work—within weather and climate, in coding and in digital art. She makes her pieces using matplotlib, a visualization tool in Python. She talks about the synergy and...
info_outlineScience in Parallel
Early in her applied math journey, Paulina Rodriguez was a little skeptical of calculators and computers. But her desire to really understand what’s going on under the hood has ultimately led to satisfying research. During her Ph.D., she’s explored the credibility of computational models for medical device applications, making sure that researchers understand the accuracy, validity and uncertainty of simulated results. Paulina shares how she honed her problem-solving skills and creativity as she navigated her education. Her enthusiasm and determination are infectious, and she describes her...
info_outlineScience in Parallel
Science communication often attracts people with diverse interests, who thrive in multiple roles. Paul Sutter is no exception: he’s an astrophysicist, host, author and more. He’s also a visiting professor at Barnard College, Columbia University. Paul’s roots are in computational science, and he shares how his many projects continue to build on that foundation. We also discuss his most recent book: Rescuing Science: Restoring Trust in an Age of Doubt, which critiques today’s scientific enterprise and and offers ideas for supporting a better future. You'll meet: is a theoretical...
info_outlineScience in Parallel
Video games are everywhere, but the fundamental elements that generate human reactions such as suspense or surprise aren’t understood. Instead, game designers start from scratch each time they want to build a new experience for players. Rogelio Cardona-Rivera of the University of Utah wants to understand games and the fundamental elements that make people respond as they do—as a science of games. The research is important for more than just gaming—Rogelio is working on a variety of projects, including artificial intelligence research, technology for Indigenous storytelling and virtual...
info_outlineScience in Parallel
The field of high-performance computing (HPC) currently faces dual challenges: important technical problems that require a skilled workforce and the need to recruit more computational researchers. This conversation with Lois Curfman McInnes of Argonne National Laboratory examines both the complexity in building scientific software and the work needed to build the HPC workforce of the future. You'll meet: is a senior computational scientist in the mathematics and computer science division at . She served as deputy director for the software technology focus are of the U.S. Department of...
info_outlineScience in Parallel
Artificial intelligence is reshaping research to discover new materials for a range of important applications. In this episode, meet of Lawrence Berkeley National Laboratory, a researcher who has been at the forefront of this transition. He uses machine learning and other computational tools as a materials scientist to discover compounds that could store and convert energy and solve other societal problems. Anubhav’s current research path started in graduate school at MIT, where he was supported by a . We discuss how computational tools including AI have moved from a novel idea to a central...
info_outlineScience in Parallel’s season two concludes with a conversation about answering important questions in biology and medicine with leadership class supercomputers, including urgent issues that came up during the COVID-19 pandemic. You’ll hear from Anda Trifan of the University of Illinois, Urbana-Champaign and Amanda Randles of Duke University.
Starting as a chemist, Anda is completing a Ph.D. in biophysics and quantitative biology at the University of Illinois Urbana-Champaign where she has studied molecular strategies that make certain cells turn cancerous. In early 2020, she joined an Argonne National Laboratory team that pivoted to working on the pandemic, and she modeled how SARS-CoV-2 infects cells, how it replicates and how it spreads through aerosols.
Amanda is an assistant professor of biomedical engineering at Duke University with roots in physics and computer science. Much of her work now focuses on large-scale simulations of how blood flows through a person’s unique network of vessels. During the pandemic, her team applied their expertise to calculations that could help physicians figure out how to split ventilators between patients who weren’t exact matches, a critical problem in early 2020 when these devices were in short supply.
Both Anda and Amanda completed Department of Energy Computational Science Graduate Fellowships. Between them, they have worked on a total of five projects that have been finalists for either the ACM Gordon Bell Prize or the Special Prize for COVID-19 research. Adding to the excitement of their pandemic work: They both navigated the at-home adventure of raising very young children during lockdown. They talk about what drives them, the challenge of working at the cutting edge of HPC and biology and medicine, and their advice for other researchers, particularly other women in science.