Related papers: Machine-learned trends in mirror configurations in…
Materials synthesis platforms that are designed for autonomous experimentation are capable of collecting multimodal diagnostic data that can be utilized for feedback to optimize material properties. Pulsed laser deposition (PLD) is emerging…
Thanks to advances in plasma science and enabling technology, mirror machines are being reconsidered for fusion power plants and as possible fusion volumetric neutron sources. However cross-field transport and turbulence in mirrors remains…
This paper shows how data-driven machine learning approaches can improve growth control, reproducibility, and physical insight in the pulsed laser deposition (PLD) growth of correlated oxides. Despite well-known relationships between growth…
Diffusion-based posterior sampling (PS) is a leading framework for imaging inverse problems, combining learned priors with measurement constraints. Yet, its standard formulations rely on instantaneous data-consistent estimates, which induce…
The interest in combining model-based control approaches with diffusion models has been growing. Although we have seen many impressive robotic control results in difficult tasks, the performance of diffusion models is highly sensitive to…
The electron density is a key parameter to characterize any plasma. Most of the plasma applications and research in the area of low-temperature plasmas (LTPs) are based on the accurate estimations of plasma density and plasma temperature.…
Exceptional pulse contrast can be critical for ultraintense laser experiments, particularly when using solid density targets, and their use is becoming widespread. However, current plasma mirror technology is becoming inadequate for the new…
Magnetospheres are a ubiquitous feature of magnetized bodies embedded in a plasma flow. While large planetary magnetospheres have been studied for decades by spacecraft, ion-scale "mini" magnetospheres can provide a unique environment to…
Accurate and efficient plasma models are essential to understand and control experimental devices. Existing magnetohydrodynamic or kinetic models are nonlinear, computationally intensive, and can be difficult to interpret, while often only…
Currently, machine learning (ML) methods are widely used to process the results of physical experiments. In some cases, due to the limited amount of experimental data, ML-models can be pre-trained on synthetic data simulated based on the…
One of the fundamental problems is the understanding of physics of electrostatic and electromagnetic fluctuations in multi-scale plasma turbulence. Especially so, in continuously connected plasma regions with varying degree of…
We demonstrate the application of the Dynamic Mode Decomposition (DMD) for the diagnostic analysis of the nonlinear dynamics of a magnetized plasma in resistive magnetohydrodynamics. The DMD method is an ideal spatio-temporal matrix…
A system of automated computerized Langmuir probe measurements is used in order to determine the plasma parameters in a plasma reactor constructed for cleaning of metallic artifacts by RF discharge. A compensated probe insures the…
Implicit visual knowledge in a large latent diffusion model (LLDM) pre-trained on natural images is rich and hypothetically universal to natural and medical images. To test this hypothesis from a practical perspective, we propose a novel…
We explore the applications of machine learning techniques in relativistic laser-plasma experiments beyond optimization purposes. We predict the beam charge of electrons produced in a laser wakefield accelerator given the laser wavefront…
Numerical simulation of plasma turbulence in the Large Plasma Device (LAPD) [Gekelman et al, Rev. Sci. Inst., 62, 2875, 1991] is presented. The model, implemented in the BOUndary Turbulence (BOUT) code [M. Umansky et al, Contrib. Plasma…
The present study explores combining machine learning (ML) algorithms with standard optical diagnostics (such as time-integrated emission spectroscopy and imaging) to accurately predict operating conditions and assess the emission…
Recent progress in imitation learning has been enabled by policy architectures that scale to complex visuomotor tasks, multimodal distributions, and large datasets. However, these methods often rely on learning from large amount of expert…
A supervised machine learning algorithm, called locally adaptive discriminant analysis (LADA), has been developed to locate boundaries between identifiable image features that have varying intensities. LADA is an adaptation of image…
Based on deep neural networks (DNNs), deep learning has been successfully applied to many problems, but its mechanism is still not well understood -- especially the reason why over-parametrized DNNs can generalize. A recent statistical…