Artificial Intelligence‐Assisted Target Design for High‐Intensity Laser‐Driven Neutron Sources
Open Access
- 11 May 2025
- journal article
- Published by Wiley in Advanced Intelligent Systems
- Vol. 7 (11)
Abstract
Designing and optimizing target structures is one of the most critical steps in high‐intensity laser experiments, like laser‐driven neutron sources, which are increasingly recognized for their compactness and portability. Herein, an artificial intelligence (AI)‐assisted target design approach that leverages AI algorithms in combination with particle‐in‐cell simulations is proposed. This newly AI‐optimized structure addresses the limitations of conventional approaches, such as foam targets or wire‐array structures. Simulation results demonstrate a neutron yield exceeding three orders of magnitude compared to flat targets and over 18 times greater than that of wire‐array targets. This dramatic result demonstrates that the AI‐assisted target design method can be effectively applied to other high‐intensity laser applications.Keywords
Funding Information
- National Key Research and Development Program of China (2023YFA1606900)
- National Natural Science Foundation of China (12235003)
This publication has 46 references indexed in Scilit:
- Topology optimization of on-chip integrated laser-driven particle acceleratorNuclear Science and Techniques, 2022
- Micro/nano functional devices fabricated by additive manufacturingProgress in Materials Science, 2022
- A gradient ascent algorithm based on possibilistic fuzzy C-Means for clustering noisy dataExpert Systems with Applications, 2022
- Review of accelerator driven heavy ion nuclear fusionMatter and Radiation at Extremes, 2018
- Smilei : A collaborative, open-source, multi-purpose particle-in-cell code for plasma simulationComputer Physics Communications, 2018
- Introduction to Plasma Physics and Controlled Fusion2016
- LMJ/PETAL laser facility: Overview and opportunities for laboratory astrophysicsHigh Energy Density Physics, 2015
- Optimal control of coupled spin dynamics: design of NMR pulse sequences by gradient ascent algorithmsJournal of Magnetic Resonance, 2005
- Multiagent learning using a variable learning rateArtificial Intelligence, 2002
- Compression of amplified chirped optical pulsesOptics Communications, 1985