Lab Partnering Service Discovery
Use the LPS faceted search filters, or search by keywords, to narrow your results.
Daniel is Head of the Machine Learning (ML) Initiative at SLAC National Accelerator Laboratory. The ML initiative coordinates the application of ML techniques across the range of science at the lab, with special focus in autonomous facility and experimental control, edge-ML, sparse and irregular data sets, prognostics, and new approaches to data analysis. Previously, Daniel led the Accelerator Directorate’s ML department, as well as working in the Linac Coherent Light Source Laser Division. Prior to joining SLAC, Daniel worked as a conservation scientist at the Museum of Modern Art in New York, and as a data analyst for WhenU.com. Daniel received his PhD in Applied Physics from Stanford, and his AB in Physics from Harvard.
Dr. David Stracuzzi is a Principal Member of Technical Staff at Sandia National Laboratories and has been studying machine learning and artificial intelligence for 20 years. He currently leads several projects that apply data-driven modeling and uncertainty analysis methods to tasks related to remote sensing data, pattern-of-life data, geophysical data, and data related to physics-based simulations. Prior to joining Sandia in 2010, Dr. Stracuzzi was a member of the research faculty at Arizona State University working on computational cognitive architectures for developing intelligent agents.
Haruko Wainwright received her MS in nuclear engineering (2006), MA in statistics (2010), and PhD in nuclear engineering (2010) at University of California, Berkeley. Her initial research interest was to investigate the environmental impact of nuclear waste and nuclear weapon productions. Her PhD dissertation focused on Bayesian geostatistical inverse modeling for subsurface characterization at the uranium-contaminated DOE Hanford site. Since then, she has broadened her research interest to various environmental problems, including Arctic ecosystem responses to climate change, groundwater contamination, and deep-subsurface CO2 storage. In addition to working in many interdisciplinary projects, she is a deputy lead of the site application thrust in the Advanced Simulation Capability for Environmental Management project, leading the site application at the Savannah River Site F-Area. She is also on the leadership team of Institute for Resilient Communities, which aims to prepare communities for radiological and other disasters through research, education and outreach activities.
For more information: https://eesa.lbl.gov/profiles/haruko-murakami-wainwright/
COVID-19-related research: "Using Machine Learning to Estimate COVID-19âs Seasonal Cycle"
Eoin Brodie is a Senior Scientist in Berkeley Labâs Earth and Environmental Sciences Area (EESA). Dr. Brodie serves as the Deputy Director of the Climate and Ecosystem Sciences Division, Program Domain Lead for Environmental and Biological Systems Sciences and co-lead of the labwide Microbes-to-Biomes initiative. At the University of California, Berkeley, Dr. Brodie is an Associate Adjunct Professor in the Department of Environmental Science, Policy and Management. His research group develops approaches to observe, sense and simulate the distribution and activities of microorganisms in natural and managed ecosystems.
For more information: https://eesa.lbl.gov/profiles/eoin-brodie/
COVID-19-related research: "Using Machine Learning to Estimate COVID-19's Seasonal Cycle". Other principal investigators include: Ben Brown, Nicola Falco, Dan Feldman, Zhao Hao, Chaincy Kuo, Joshua Ladau, and Haruko Wainwright.
Dr. Marius Stan is the Intelligent Materials Design Lead in the Argonne National Laboratory’s Applied Materials division. Stan is a computational physicist and chemist interested in complexity, non-equilibrium thermodynamics, heterogeneity, and materials design for energy and electronics applications. He uses artificial intelligence, machine learning, and multi-scale computer simulations to understand and predict properties and evolution of complex physical systems.
Stan came to Argonne and the University of Chicago in 2010, from Los Alamos National Laboratory. He is a Senior Fellow at the University of Chicago’s Computation Institute (CI) and a senior Fellow of the Northwestern-Argonne Institute for Science and Engineering (NAISE).
The goal of Stan’s research is to discover or design materials, structures, and device architectures for energy applications, such as nuclear energy and energy storage, and for the new generation computers. To that end, he develops theory-based (as opposite to empirical) mathematical models of thermodynamic and chemical properties of imperfect materials. The imperfection comes from defects or deviations from stoichiometry (e.g., in battery electrodes), from irradiation (e.g. in nuclear fuels), or doping (e.g. computer memory devices). Then Stan uses the models in computer simulations of coupled heat and chemical transport, micro(nano)-structure evolution, phase-stability, and phase transformations. To analyze large and complex experimental and computational data sets, Stan uses Bayesian analysis and machine learning methods based on regression and evolutionary (genetic) algorithms that can produce robust data screening and sampling. In parallel, Stan designs experiments to validate the models and simulations.
He is a computational biologist staff scientist in the Biological Systems and Engineering Division within Berkeley Lab’s Biosciences Area. The goal of his research is to understand the functional organization and dynamic coordination of sensorimotor networks underlying learned, skilled behaviors. His lab’s research will address the question of how distributed neural circuits gives rise to coordinated behaviors. To address this question, his lab combines multi-scale electrophysiology with optical manipulations in reaching rodents and advanced computational methods to investigate the functional organization and dynamic coordination of sensorimotor networks. He also develop software to analyze this data, including novel machine learning algorithms and deep learning approaches.