Transformer-Powered Surrogates Close the ICF Simulation-Experiment Gap with Extremely Limited Data
This work addresses the simulation-experiment gap in inertial confinement fusion, an incremental improvement for domain-specific applications.
The paper tackles the problem of predicting multi-modal outputs in inertial confinement fusion experiments with extremely limited real-world data (only 10 shots) by using a transformer-powered surrogate model, achieving superior prediction accuracy compared to prior methods.
Recent advances in machine learning, specifically transformer architecture, have led to significant advancements in commercial domains. These powerful models have demonstrated superior capability to learn complex relationships and often generalize better to new data and problems. This paper presents a novel transformer-powered approach for enhancing prediction accuracy in multi-modal output scenarios, where sparse experimental data is supplemented with simulation data. The proposed approach integrates transformer-based architecture with a novel graph-based hyper-parameter optimization technique. The resulting system not only effectively reduces simulation bias, but also achieves superior prediction accuracy compared to the prior method. We demonstrate the efficacy of our approach on inertial confinement fusion experiments, where only 10 shots of real-world data are available, as well as synthetic versions of these experiments.