High-repetition-rate (HRR) laser-driven experiments are transforming high energy density physics by enabling rapid, data-rich exploration of complex plasma phenomena. Real-time control in these systems remains difficult because iterative optimization algorithms and linear feedback loops (e.g., PID) consume shots during convergence and adapt poorly to nonlinear, drifting operating conditions. Here we demonstrate shot-to-shot direct ML control for laser-driven plasmas, implemented with a neural setpoint controller that maps a requested plasma state and measured operating conditions directly to actuator settings. Applied to blast wave position control on a multi-joule platform, the method delivers sub-second inference compatible with 1 Hz operation and maintains the target po- sition with sub-millimeter precision while background pressure varies by more than 400% within the trained pressure bounds. Benchmarking against a hybrid neural-network plus Bayesian-optimization framework shows a substantial gain in response speed and control authority. These results establish a practical route toward retrainable autonomous control for next-generation laser-plasma platforms.

Understanding high energy density physics (HEDP) is critical for advancements in fusion energy and astrophysics. The computational demands of the computer models used for HEDP studies have led researchers to explore deep learning methods to enhance simulation efficiency. This paper introduces HEDP-Gen, a framework for training and evaluating generative models tailored for HEDP. Central to HEDP-Gen is Geom-WAE-a generalized Wasserstein auto-encoder accommodating both Euclidean and non-Euclidean latent spaces. HEDP-Gen establishes a rigorous evaluation standard, assessing not only reconstruction fidelity but also scientific validity, sample diversity, and latent space utility in geodesic interpolation and attribute traversal. A case study using hyperbolic geometry (Poincaréball prior) demonstrates that non-Euclidean priors yield scientifically valid samples and stronger generalization in downstream tasks, advantages often missed by conventional reconstruction metrics. High energy density physics (HEDP) is crucial for advancements in fusion energy and astrophysics, yet its simulations are complex and computationally demanding. The authors introduce HEDP-Gen, a deep learning framework which uses advanced geometry in model design, and show that it enhances simulation efficiency and produces scientifically accurate results.

An inertial confinement fusion experiment, carried out at the National Ignition Facility, has achieved ignition by generating fusion energy exceeding the laser energy that drove the experiment. Prior to the experiment, a generative machine learning model that combines radiation hydrodynamics simulations, deep learning, experimental data, and Bayesian statistics was used to predict, with a probability greater than 70%, that ignition was the most likely outcome for this shot.

Recent experiments conducted at the National Ignition Facility (NIF) within the past 2 years have achieved the burning plasma state and exceeded the Lawson criterion for the first time in the laboratory. Here, we report on a set of experiments where the deuterium and tritium (DT) ice layers were replaced with dudded tritium, hydrogen, and deuterium (THD) fuel mixtures to remove the influence of alpha-heating on hot spot dynamics. The hot spot compression and yield in the absence of alpha particle self-heating were measured to assess the proximity of NIF implosions toward the ignition cliff. We find that the “burn-off” Lawson parameters χnoα inferred from the THD experiments are in good agreement with the inferences from postshot simulations of the DT-layered implosions. The THD for burning plasma shot N210307 yielded χnoα≈0.88±0.03 while the THD for ignition shot N210808 yielded χnoα≈1.04±0.04. These results also provide important context for the observed variability in the repeat attempts of ignition shot N210808 since implosions on the ignition cliff are expected to exhibit very large variations in the fusion yield from small changes in the initial conditions.

Recent advances in inertial confinement fusion (ICF) at the National Ignition Facility (NIF), including ignition and energy gain, are enabled by a close coupling between experiments and high-fidelity simulations. Neither simulations nor experiments can fully constrain the behavior of ICF implosions on their own, meaning pre- and postshot simulation studies must incorporate experimental data to be reliable. Linking past data with simulations to make predictions for upcoming designs and quantifying the uncertainty in those predictions has been an ongoing challenge in ICF research. We have developed a data-driven approach to prediction and uncertainty quantification that combines large ensembles of simulations with Bayesian inference and deep learning. The approach builds a predictive model for the statistical distribution of key performance parameters, which is jointly informed by past experiments and physics simulations. The prediction distribution captures the impact of experimental uncertainty, expert priors, design changes, and shot-to-shot variations. We have used this new capability to predict a 10x increase in ignition probability between Hybrid-E shots driven with 2.05 MJ compared to 1.9 MJ, and validated our predictions against subsequent experiments. We describe our new Bayesian postshot and prediction capabilities, discuss their application to NIF ignition and validate the results, and finally investigate the impact of data sparsity on our prediction results. C2024 Author(s). All article content, except where otherwise noted, is licensed under a Creative Commons Attribution-NonCommercial-NoDerivs 4.0 International (CC BY-NC-ND) license (https://creativecommons.org/licenses/by-nc-nd/4.0/).https://doi.org/10.1063/5.0215962

We present progress in utilizing a machine learning (ML) assisted optimization framework to study the trends in a parameter space defined by spectrally shaped, high-intensity, petawatt-class (8 J, 45 fs) laser pulses interacting with solid targets and give the first simulation-based overview of predicted trends. A neural network (NN) incorporating uncertainty quantification is trained to predict the number of hot electrons generated by the laser–target interaction as a function of pulse shaping parameters. The predictions of this NN serve as the basis function for a Bayesian optimization framework to navigate this space. For post-experimental evaluation, we compare two separate neural network (NN) models. One is based solely on data from experiments, and the other is trained only on ensemble particle-in-cell simulations. Reviewing the predicted and observed trends across the experiment-capable laser parameter search space, we find that both ML models predict a maximal increase in hot electron generation at a level of approximately 12%–18%; however, no statistically significant enhancement was observed in experiments. On direct comparison of the NN models, the average discrepancy is 8.5%, with a maximum of 30%. Since shot-to-shot fluctuations in experiments affect the observations, we evaluate the behavior of our optimization framework by performing virtual experiments that vary the number of repeated observations and the noise levels. Here, we discuss the implications of such a framework for future autonomous exploration platforms in high-repetition-rate experiments.

Indirect Drive Inertial Confinement Fusion Experiments on the National Ignition Facility (NIF) have achieved a burning plasma state with neutron yields exceeding 170 kJ, roughly 3 times the prior record and a necessary stage for igniting plasmas. The results are achieved despite multiple sources of degradations that lead to high variability in performance. Results shown here, for the first time, include an empirical correction factor for mode-2 asymmetry in the burning plasma regime in addition to previously determined corrections for radiative mix and mode-1. Analysis shows that including these three corrections alone accounts for the measured fusion performance variability in the two highest performing experimental campaigns on the NIF to within error. Here we quantify the performance sensitivity to mode-2 symmetry in the burning plasma regime and apply the results, in the form of an empirical correction to a 1D performance model. Furthermore, we find the sensitivity to mode-2 determined through a series of integrated 2D radiation hydrodynamic simulations to be consistent with the experimentally determined sensitivity only when including alpha-heating. Recent improvements in the indirect-drive inertial confinement fusion experiments include the achievement of burning plasma state. Here the authors report the scaling of neutron yield in a burning plasma of Deuterium-Tritium fusion reaction by including the mode-2 asymmetry.

High performance computing has entered the Exascale Age. Capable of performing over 1018 floating point operations per second, exascale computers, such as El Capitan, the National Nuclear Security Administration's first, have the potential to revolutionize the detailed in-depth study of highly complex science and engineering systems. However, in addition to these kind of whole machine “hero” simulations, exascale systems could also enable new paradigms in digital design by making petascale hero runs routine. Currently, untenable problems in complex system design, optimization, model exploration, and scientific discovery could all become possible. Motivated by the challenge of uncovering the next generation of robust high-yield inertial confinement fusion (ICF) designs, project ICECap (Inertial Confinement on El Capitan) attempts to integrate multiple advances in machine learning (ML), scientific workflows, high performance computing, GPU-acceleration, and numerical optimization to prototype such a future. Built on a general framework, ICECap is exploring how these technologies could broadly accelerate scientific discovery on El Capitan. In addition to our requirements, system-level design, and challenges, we describe some of the key technologies in ICECap, including ML replacements for multiphysics packages, tools for human-machine teaming, and algorithms for multifidelity design optimization under uncertainty. As a test of our prototype pre-El Capitan system, we advance the state-of-the art for ICF hohlraum design by demonstrating the optimization of a 17-parameter National Ignition Facility experiment and show that our ML-assisted workflow makes design choices that are consistent with physics intuition, but in an automated, efficient, and mathematically rigorous fashion.

On December 5, 2022, an indirect drive fusion implosion on the National Ignition Facility (NIF) achieved a target gain G_{target} of 1.5. This is the first laboratory demonstration of exceeding "scientific breakeven" (or G_{target}>1) where 2.05 MJ of 351 nm laser light produced 3.1 MJ of total fusion yield, a result which significantly exceeds the Lawson criterion for fusion ignition as reported in a previous NIF implosion [H. Abu-Shawareb et al. (Indirect Drive ICF Collaboration), Phys. Rev. Lett. 129, 075001 (2022)PRLTAO0031-900710.1103/PhysRevLett.129.075001]. This achievement is the culmination of more than five decades of research and gives proof that laboratory fusion, based on fundamental physics principles, is possible. This Letter reports on the target, laser, design, and experimental advancements that led to this result.

At the National Ignition Facility, inertial confinement fusion experiments aim to burn and ignite a hydrogen plasma to generate a net source of energy through the fusion of deuterium and tritium ions. The energy deposited by α-particles released from the deuterium–tritium fusion reaction plays the central role in heating the fuel to achieve a sustained thermonuclear burn. In the hydrodynamic picture, α-heating increases the temperature of the plasma, leading to increased reactivity because the mean ion kinetic energy increases. Therefore, the ion temperature is related to the mean ion kinetic energy. Here we use the moments of the neutron spectrum to study the relationship between the ion temperature (measured by the variance in the neutron kinetic energy spectrum) and the ion mean kinetic energy (measured by the shift in the mean neutron energy). We observe a departure from the relationship expected for plasmas where the ion relative kinetic energy distribution is Maxwell–Boltzmann, when the plasma begins to burn. Understanding the cause of this departure from hydrodynamic behaviour could be important for achieving robust and reproducible ignition. Inertial confinement fusion experiments reveal a departure from the expected hydrodynamic behaviour of a plasma when the fusion reactions become the primary source of plasma heating.

Data-driven science and technology offer transformative tools and methods to science. This review article highlights the latest development and progress in the interdisciplinary field of data-driven plasma science (DDPS), i.e., plasma science whose progress is driven strongly by data and data analyses. Plasma is considered to be the most ubiquitous form of observable matter in the universe. Data associated with plasmas can, therefore, cover extremely large spatial and temporal scales, and often provide essential information for other scientific disciplines. Thanks to the latest technological developments, plasma experiments, observations, and computation now produce a large amount of data that can no longer be analyzed or interpreted manually. This trend now necessitates a highly sophisticated use of high-performance computers for data analyses, making artificial intelligence and machine learning vital components of DDPS. This article contains seven primary sections, in addition to the introduction and summary. Following an overview of fundamental data-driven science, five other sections cover widely studied topics of plasma science and technologies, i.e., basic plasma physics and laboratory experiments, magnetic confinement fusion, inertial confinement fusion and high-energy-density physics, space and astronomical plasmas, and plasma technologies for industrial and other applications. The final Section before the summary discusses plasma-related databases that could significantly contribute to DDPS. Each primary Section starts with a brief introduction to the topic, discusses the state-of-the-art developments in the use of data and/or data-scientific approaches, and presents the summary and outlook. Despite the recent impressive signs of progress, the DDPS is still in its infancy. This article attempts to offer a broad perspective on the development of this field and identify where further innovations are required.

nuclear plants currently under construction including 10 in China, 8 in India, and 4 in Russia. In the United States, there have been notifications to the Nuclear Regulatory Commission of intentions to apply for combined construction and operating licenses for 27 new units over the next decade. The projected growth in nuclear power has focused increasing attention on issues related to the permanent disposal of nuclear waste, the proliferation of nuclear weapons technologies and materials, and the sustainability of a once-through nuclear fuel cycle. In addition, the effective utilization of nuclear power will require continued improvements in nuclear technology, particularly related to safety and efficiency. In all of these areas, the performance of materials and chemical processes under extreme conditions is a limiting factor. The related basic research challenges represent some of the most demanding tests of our fundamental understanding of materials science and chemistry, and they provide significant opportunities for advancing basic science with broad impacts for nuclear reactor materials, fuels, waste forms, and separations techniques. Of particular importance is the role that new nanoscale characterization and computational tools can play in addressing these challenges. These tools, which include DOE synchrotron X-ray sources, neutron sources, nanoscale science research centers, and supercomputers, offer the opportunity to transform and accelerate the fundamental materials and chemical sciences that underpin technology development for advanced nuclear energy systems. The fundamental challenge is to understand and control chemical and physical phenomena in multi-component systems from femto-seconds to millennia, at temperatures to 1000?C, and for radiation doses to hundreds of displacements per atom (dpa). This is a scientific challenge of enormous proportions, with broad implications in the materials science and chemistry of complex systems. New understanding is required for microstructural evolution and phase stability under relevant chemical and physical conditions, chemistry and structural evolution at interfaces, chemical behavior of actinide and fission-product solutions, and nuclear and thermomechanical phenomena in fuels and waste forms. First-principles approaches are needed to describe f-electron systems, design molecules for separations, and explain materials failure mechanisms. Nanoscale synthesis and characterization methods are needed to understand and design materials and interfaces with radiation, temperature, and corrosion resistance. Dynamical measurements are required to understand fundamental physical and chemical phenomena. New multiscale approaches are needed to integrate this knowledge into accurate models of relevant phenomena and complex systems across multiple length and time scales.

In indirect-drive implosions, the final core hot spot energy and pressure and, hence, neutron yield attainable in 1D increase with increasing laser peak power and, hence, radiation drive temperature at the fixed capsule and Hohlraum size. We present simple analytic scalings validated by 1D simulations that quantify the improvement in performance and use this to explain existing data and simulation trends. Extrapolating to the 500 TW National Ignition Facility peak power limit in a low gas-fill 5.4 mm diameter Hohlraum based on existing high adiabat implosion data at 400 TW, 1.3 MJ and 1 × 1016 yield, we find that a 2–3 × 1017 yield (0.5–0.7 MJ) is plausible using only 1.8 MJ of laser energy. Based on existing data varying deuterium–tritium (DT) fuel thickness and dopant areal density, further improvements should be possible by increasing DT fuel areal density, and hence confinement time and yield amplification.

The PROBIES diagnostic is a new, highly flexible, imaging and energy spectrometer designed for laser-accelerated protons. The diagnostic can detect low-mode spatial variations in the proton beam profile while resolving multiple energies on a single detector or more. When a radiochromic film stack is employed for “single-shot mode,” the energy resolution of the stack can be greatly increased while reducing the need for large numbers of films; for example, a recently deployed version allowed for 180 unique energy measurements spanning ∼3 to 75 MeV with <0.4 MeV resolution using just 20 films vs 180 for a comparable traditional film and filter stack. When utilized with a scintillator, the diagnostic can be run in high-rep-rate (>Hz rate) mode to recover nine proton energy bins. We also demonstrate a deep learning-based method to analyze data from synthetic PROBIES images with greater than 95% accuracy on sub-millisecond timescales and retrained with experimental data to analyze real-world images on sub-millisecond time-scales with comparable accuracy.

In order to understand how close current layered implosions in indirect-drive inertial confinement fusion are to ignition, it is necessary to measure the level of alpha heating present. To this end, pairs of experiments were performed that consisted of a low-yield tritium-hydrogen-deuterium (THD) layered implosion and a high yield deuterium-tritium (DT) layered implosion to validate experimentally current simulation-based methods of determining yield amplification. The THD capsules were designed to reduce simultaneously DT neutron yield (alpha heating) and maintain hydrodynamic similarity with the higher yield DT capsules. The ratio of the yields measured in these experiments then allowed the alpha heating level of the DT layered implosions to be determined. The level of alpha heating inferred is consistent with fits to simulations expressed in terms of experimentally measurable quantities and enables us to infer the level of alpha heating in recent high-performing implosions.

This manuscript examines the correlations between the hot-spot velocity (an observable signature of residual kinetic energy), low-mode implosion asymmetries, and burn amplification in inertial confinement fusion implosions on the National Ignition Facility (NIF). Using a combination of two-dimensional axis-symmetric and three-dimensional radiation-hydrodynamic simulations coupled to neutronics, we find that for typical NIF implosions, the stagnation asymmetry multiplies the observed hot-spot velocity anywhere from 80% to 120%, while burn amplification always increases it. Additionally, we find stagnation asymmetry typically deflects the observed hot-spot flow. The two mechanisms (low-mode implosion asymmetries and burn amplification) can be decoupled, and application of a simple model to a database of cryogenic implosions on the NIF infers the total hot-spot velocity amplification. This finding modifies the interpretation of data collected from inertial confinement fusion experiments and impacts the magnitude and origin of low-mode asymmetries.

Deep neural network (DNN) surrogates of expensive physics simulations are enabling a rapid change in the way that common experimental design and analysis tasks are approached. Surrogate models allow simulations to be performed in parallel and separately from downstream tasks, thereby enabling analyses that would be impossible with the simulation in‐the‐loop; surrogates based on DNNs can effectively emulate diverse non‐scalar data of the types collected in fusion and laboratory‐astrophysics experiments. The challenge is in training the surrogate model, for which large ensembles of physics simulations must be run, preferably without wasting computational effort on uninteresting simulations. In this paper, we present an iterative sampling scheme that can preferentially propose simulations in interesting regions of parameter space without neglecting unexplored regions, allowing high‐quality and wide‐ranging surrogate models to be trained using 2–3 times fewer simulations compare to space‐filling designs. Our approach uses an explicit importance function defined on the simulation output space, balanced against a measure of simulation density which serves as a proxy for surrogate accuracy. It is easy to implement and can be tuned to find interesting simulations early in the study, allowing surrogates to be trained quickly and refined as new simulations become available; this represents an important step towards the routine generation of deep surrogate models quickly enough to be truly relevant to experimental work.