Lab Partnering Service Discovery
Use the LPS faceted search filters, or search by keywords, to narrow your results.
Dr. Agarwal's research focuses on scientific tools that enable sharing of scientific experiments, advanced networking infrastructure to support sharing of scientific data, data analysis support infrastructure for eco-science, and cybersecurity infrastructure to secure collaborative environments. Dr. Agarwal is the coordinator for ML4Sci, the Lab-wide machine learning initiative. Dr. Agarwal is a Senior Fellow at the Berkeley Institute for Data Science and an Inria International Chair. Dr. Agarwal also leads teams developing data server infrastructure to significantly enhance data browsing and analysis capabilities and enable eco-science synthesis at the watershed-scale to understand hydrologic and conservation questions and at the global-scale to understand carbon flux. Some of the projects Dr. Agarwal is working on include: Enviromental Systems Science Digital Infrastructure for a Virtual Ecosystem (ESS-DIVE), Watershed Function SFA, AmeriFlux Management Project, FLUXNET, NGEE Tropics, and International Soil Carbon Network. Dr. Agarwal received her Ph.D. in electrical and computer engineering from University of California, Santa Barbara and a B.S. in Mechanical Engineering from Purdue University.
Matthew Reno is a Principal Member of Technical Staff in the Electric Power Systems Research Department at Sandia National Laboratories. His research focuses on distribution system modeling and analysis with big data and high penetrations of photovoltaics by applying cutting edge machine learning algorithms to power system problems. Matthew is also involved with the IEEE Power System Relaying Committee for developing guides and standards for protection of microgrids and systems with high penetrations of inverter-based resources. He received his Ph.D. in electrical engineering from Georgia Institute of Technology.
Gabriel Perdue is a Scientist in Fermilab’s Quantum Institute, where he works on quantum computing for simulation and machine learning, and more generally on machine learning in physics. He also has a long history at Fermilab in neutrino physics and spent the last decade working on the MINERvA experiment and on the GENIE MC event generator.
Areas of expertise: AI Algorithms for Data Analysis and Systems Control
Title: Assistant Computational Scientist
- Scientific literature processing to rapidly find protein-protein interaction candidates
- AI-based platform to accelerate discovery of novel drug compounds
- Querying and filtering interface for users to efficiently scan tens of thousands of sources
Since joining Brookhaven National Laboratory in 2018, Carlos X. Soto has been an active member of the Machine Learning Group, where he has contributed extensively toward large-scale scientific data extraction from published literature using natural language processing (NLP) techniques applied to areas such as functional genomics, drug discovery, and government reports. His contributions to machine learning for the integration of biological genomics data helped prompt an ongoing partnership with Oak Ridge National Laboratory to use NLP techniques to accelerate COVID-19 drug discovery. In 2019, Soto was part of the Brookhaven team awarded one of only two Nuclear Threat Initiative (NTI) Nuclear Security Index Challenge grants. The work, Towards a Predictive Nuclear Security Threat Model, aims to create a predictive model by integrating NTI Index data into machine learning and sentiment analysis. Presently, his work on COVID-related projects focuses on providing domain scientists with powerful new computational tools to identify patterns and insights in large volumes of documents, in particular relating to potential drug compound candidates.