By combining engineering and operations domain expertise and creative integration of advanced hardware and software, we deliver advanced computational solutions that address complex data and analytic challenges. Working in multidisciplinary teams, we connect research to engineering to operations, providing the tools necessary to innovate quickly and field results faster. Our strengths are integrated across the data analytics lifecycle—from data acquisition and management, to analysis, to decision support.
Our mission is to deliver cutting-edge data science solutions that drive innovation and progress across the Department of Energy (DOE) complex by collaborating with subject matter experts at Jefferson Lab, partner laboratories, and universities. We aim to provide tailored data science support for scientific applications relevant to our regional community.
We envision a future where:
- Capacity Building: Our team expands the capabilities and capacity of data science within JLab, fostering a culture of innovation and excellence.
- Collaborative Research Hub: We establish a collaborative research hub that brings together experts from academia, industry, and government to tackle complex scientific challenges.
- Education & Outreach: We foster education and research opportunities with regional universities and industries, promoting knowledge sharing and skill development.
By achieving these goals, we aim to make a lasting impact on the DOE complex while advancing scientific discovery and reducing environmental sustainability.
The scope of the department involves the development and application of advanced Artificial Intelligence (AI) and Machine Learning (ML) techniques to address complex challenges in various research areas.
- Application Research Area:
- Particle Physics, Accelerator, and Detectors
- Environmental Science, Health & Medical Applications
- Computer Science & Advanced and Resource Efficient Algorithms
- Data Science Methods:
- Anomaly Detection & Prediction: Develop AI/ML models for identifying unusual patterns, predicting anomalies, and detecting potential issues in complex systems.
- Uncertainty Quantification: Create methods to quantify uncertainty in predictions, allowing for more informed decision-making under uncertainty.
- Optimization & Control: Apply optimization techniques (e.g., reinforcement learning) to optimize system performance, resource allocation, and process control.
- Continual Learning: Develop algorithms and infrastructure that enable machines to learn continuously from new data, adapting to changing conditions and improving over time.
- HPC Scalable ML: Design AI/ML systems that can execute on super-computers at DOE LCFs
- Generative AI: Leverage and develop new solutions based on existing LLM and generative techniques for scientific discoveries
- Edge ML: Implement Machine Learning solutions for low power edge devices
