Data-Driven Atomic Physics with High Repetition Rate Experiments

Executive Summary

This project will create a transformational set of tools by integrating big data from simulations and experiments to create rapid and accurate surrogate models that are informed by real-world experimental data. The outcome of this work will provide a framework for utilizing high-repetition-rate capable experimental facilities for providing timely answers to key high energy density physics questions.

Publications, Presentations, and Patents

D. A. Mariscal, et al., "Machine-Learning-Guided Pulse-Shaping for Secondary Source Control” (Presentation, LaserNetUS User’s Meeting 2023, College Park, MD, June 27-29, 2023).

B. Z. Djordjević, "Transfer learning and multi-fidelity modeling of laser-driven ion acceleration" (Presentation, Anomalous Absorption 2023, Mammoth Lakes, CA, 2023).

B. Z. Djordjević, “Modeling the effect of spectral phase shaping on laser-driven ion acceleration on ensemble scales” (Presentation, LaserNetUS User’s Meeting 2023, Colllege Park, MD, June 27-29, 2023). 

D. A. Mariscal, et al., “Supporting IFE with High-Repetition-Rate Diagnostics for HED Experiments” (Presentation, US/Japan IFE Workshop 2023).

D. A. Mariscal, et al., “Developing AI-driven High Repetition Rate HED Experiments in support of IFE” (Presentation, IFSA 2023, August 20-23, Daegu, Korea, 2023).

D. A. Mariscal, et al., “Enabling Intelligent High-Repetition-Rate HED Experiments” (Presentation, UCSD HEDP Summer School 2023, San Diego, CA, 2023).

Djordjević, B. Z., J. Kim, S. C. Wilks, J. Ludwig, C. Myers, A. J. Kemp, K. K. Swanson et al. "Transfer learning and multi-fidelity modeling of laser-driven particle acceleration." Physics of Plasmas 30, no. 4 (2023).

Djordjevic, B. Z., P-T. Bremer, G. J. Williams, T. Ma, and D. A. Mariscal. 2023. "Application of Machine Learning to High-Repetition-Rate Laser-Plasma Physics on the Path to Inertial Fusion Energy." No. LLNL-PROC-849644. Lawrence Livermore National Lab. (LLNL), Livermore, CA,