EPSCoR Research Fellows: NSF: Physics-Informed Machine Learning for Accelerated Discovery and Dynamics Analysis in Ultrafast X-Ray Diffraction

About This Grant

This Research Infrastructure Improvement EPSCoR Research Fellows project provides a fellowship to an Assistant Professor and training for a graduate student at the University of Hawaii at Mānoa. This work is conducted in collaboration with researchers at the SLAC National Accelerator Laboratory. Through the fellowship, the principal investigator (PI) will develop artificial intelligence (AI) tools to interpret vast volumes of data generated by SLAC’s powerful X-ray light source. These tools will help researchers better understand the dynamics of matter at atomic spatial and temporal scales by identifying hidden patterns in ultrafast X-ray scattering data and linking these patterns to the physical processes governing matter’s properties. The outcomes will impact real-world applications, such as improving solar panel and battery efficiency, biomedical imaging, radiation therapies, and the design of new materials and precision drugs. More broadly, this work addresses growing challenges in data-intensive science and engineering and will strengthen research capacity in AI and imaging in Hawaii while supporting local STEM workforce development. This project will investigate the use of foundation models and physics-informed machine learning to interpret and simulate large-scale X-ray coherent diffraction data. It will develop a scalable, generalizable framework that integrates vision-language models (VLMs), physical constraints, and both simulation and experimental data to extract dynamic signatures from high-throughput X-ray speckle patterns. In collaboration with SLAC’s Linac Coherent Light Source (LCLS), the PI will access the state-of-the-art ultrafast imaging facilities and data critical to building the proposed framework. The project will enhance the PI’s expertise and support the development of an AI-driven computational imaging program at the University of Hawaii. Broader impacts include graduate student training, workforce development in AI and imaging science, and strengthened research infrastructure. This effort will combine technical innovation with institutional capacity building, positioning Hawaii as a future leader in data-enabled science and engineering. This project is supported by the EPSCoR Research Infrastructure Improvement Program: EPSCoR Research Fellows (ERF), which supports early- and mid-career investigators in eligible jurisdictions to develop collaborations at the nation’s private, government or academic research institutions. This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.