Bayesian and particle swarm approaches to inertial confinement fusion optimisation

Journal article

The optimisation of laser pulse shapes and target configurations is central to high-performance inertial confinement fusion (ICF) implosions, yet remains challenging due to the high dimensionality of the design space and the substantial computational and experimental cost of evaluation. This work presents, to our knowledge, the first comparison of GP-based Bayesian optimisation and particle swarm optimisation (PSO) frameworks augmented with physics-motivated extensions in full radiation-hydrodynamic ICF optimisation under experimentally relevant constraint handling. These methods are first applied to the reoptimisation of low-convergence-ratio (Low-CR) wetted-foam implosions, providing a benchmark against traditional sequential scan approaches. Both strategies identify improved designs, with Bayesian optimisation achieving the highest final performance using fewer simulations, while PSO converges more rapidly in wall-clock time. The PSO framework is then extended to a 16-dimensional fast ignition design problem, where Gaussian process-based Bayesian optimisation becomes computationally impractical. In this regime, PSO efficiently identifies a compressed fuel assembly with ρR ≈ 1.5 g/cm2 under strict laser intensity and energy constraints. These results demonstrate that the presented optimisation strategies outperform conventional scan-based approaches and provide a scalable platform for high-dimensional ICF optimisation. Beyond numerical design studies, the same frameworks are directly applicable to experimental optimisation campaigns on high-power laser facilities, where limited shot availability and high evaluation cost demand efficient search methodologies.

Authors: Lee, JJ; Coope, D; Redfern, J; Martin, H; Timmis, R

• Publication status: Accepted
• Peer review status: Peer reviewed
• Publisher: American Institute of Physics
• Journal: Physics of Plasmas
• Acceptance date: 2026-05-19
• EISSN: 1089-7674
• ISSN: 1070-664X
• Language: English