Search NASA⌕ Search

SEARCH · Search NASA

Results for “NN”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 361 records · Page 20
All sourcesNASA NTRSDOE OSTI
DOE OSTI2022

Dynamic calibration of differential equations using machine learning, with application to turbulence models

We present a methodology for calibration of parametric ordinary and partial differential equation models, using off-the-shelf software for back-propagation in Neural Networks (NN). As a prototypical example, we consider calibration of a Reynolds-averaged Navier-Stokes (RANS) turbulence closure model, against ground truth data from direct numerical simulations (DNS) of two different turbulent flows. Numerical time integration is represented as a custom NN, where only the RANS model parameters are trainable. A loss function is defined to quantify the mismatch between the NN prediction and the ground truth over a predefined, finite time integration window. This loss function is then minimized using a gradient descent method utilizing the back-propagation algorithm. Furthermore, this dynamic approach to training is to be contrasted with a static approach, wherein a least square regression estimate for parameters is obtained in the limit of an infinitesimal time integration window. In a first test of static and dynamic approaches against ground truth data generated by the model, the former proves to be significantly faster and more accurate than the latter at recovering the parameters. When both calibration approaches are tested against DNS data, for which it is known that the model cannot achieve a perfect fit, the static approach yields a good prediction only for short times, while the dynamic approach results in physical and stable predictions over the entire integration window. After optimization of the dynamic approach for time step, spatial resolution, stability, and physics-based constraints, we obtain a 50% improvement of outcomes over those obtained from the existing, manually calibrated set of parameters, demonstrating the merits of this systematic and automated procedure.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2022

Physics-informed Karhunen-Loeve and Neural Network Approximations for Solving Inverse Differential Equation Problems

Here we present the PI-CKL-NN method for parameter estimation in differential equation (DE) models given sparse measurements of the parameters and states. In the proposed approach, the space- or time-dependent parameters are approximated by Karhunen-Loeve (KL) expansions that are conditioned on the parameters’ measurements, and the states are approximated by deep neural networks (DNNs). The unknown weights in the KL expansions and DNNs are found my minimizing the cost function that enforces the measurements of the states the DE constraint. Regularization is achieved by adding the l2 norm of the conditional KL coefficients into the loss function. Our approach assumes that the parameter fields are correlated in space or time and enforces the statistical knowledge (the mean and the covariance function) in addition to the DE constraints and measurements as opposed to the physics-informed neural network (PINN) and other similar physics-informed machine learning methods where only DE constraints and data are used for parameter estimation. We use the PI-CKL-NN method for parameter estimation in an ordinary differential equation with an unknown time-dependent parameter and the one- and two-dimensional partial differential diffusion equations with unknown space-dependent diffusion coefficients. We also demonstrate that PI-CKL-NN is more accurate than the PINN method, especially when the observations of the parameters are very sparse

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗
DOE OSTI2025

Neural chaos: A spectral stochastic neural operator

Building surrogate models for operators with uncertainty quantification capabilities is essential for many engineering applications where randomness–such as variability in material properties, boundary conditions, and initial conditions–is unavoidable. Polynomial Chaos Expansion (PCE) is widely recognized as a go-to method for constructing stochastic surrogates in both intrusive and non-intrusive ways, and it has recently been used in the context of operator learning. However, its application becomes challenging for complex or high-dimensional processes, as achieving accuracy requires higher-order polynomials, which can increase computational demand and/or the risk of overfitting. Furthermore, PCE requires specialized treatments to manage random variables that are not independent, and these treatments may be problem-dependent or may fail with increasing complexity. Here, in this work, we adopt the same formalism as the spectral expansion used in PCE; however, we replace the classical polynomial basis functions with neural network (NN) basis functions to leverage their expressivity. To achieve this, we propose an algorithm that identifies NN-parameterized basis functions in a purely data-driven manner, without any prior assumptions about the joint distribution of the random variables involved, whether independent or dependent, or about their marginal distributions. The proposed algorithm identifies each NN-parameterized basis function sequentially, ensuring they are orthogonal with respect to the data distribution. The basis functions are constructed directly on the joint stochastic variables without requiring a tensor product structure or assuming independence of the random variables. This approach may offer greater flexibility for complex stochastic models, while simplifying implementation compared to the tensor product structures typically used in PCE to handle random vectors. This is particularly advantageous given the current state of open-source packages, where building and training neural networks can be done with just a few lines of code and extensive community support. We demonstrate the effectiveness of the proposed scheme through several numerical examples of varying complexity and provide comparisons with classical PCE.

Polynomial chaos expansion↗
DOE OSTI2020

Beam-energy and collision-system dependence of the linear and mode-coupled flow harmonics from STAR

Recent measurements and hydrodynamic model calculations suggest that the higher-order flow coefficients ν 4 and ν 5 have two contributions: a linear contribution driven by the initial-state eccentricities, εn, and a mode-coupled contribution derived from the lower-order eccentricity coefficients ε 2 and ε 3 . Measurements of these two contributions to ν 4 and ν 5 provide crucial insights to discern initial-state models and to constrain the temperature-dependent specific shear viscosity, η/s, of the plasma produced in heavy-ion collisions. In this work, we have employed the two-subevents cumulant technique to provide the first beam-energy and collision-system dependence of the linear and mode-coupled contributions to the higher-order flow harmonics. Furthermore, our results are shown and discussed for several centrality intervals for U+U collisions at √s NN = 193GeV, Au+Au collisions at √s NN = 200 ,and 54.4GeV and Cu+Au collisions at √s NN = 200GeV. The results are compared with similar studies performed by the ALICE experiment at LHC.

73 NUCLEAR PHYSICS AND RADIATION PHYSICS↗
DOE OSTI2023

Photoproduction of low-p T $J/ψ$ from peripheral to central Pb–Pb collisions at 5.02 TeV

An excess of J/ψ yield at very low transverse momentum (p T < 0.3 GeV/c), originating from coherent photoproduction, is observed in peripheral and semicentral hadronic Pb–Pb collisions at a center-of-mass energy per nucleon pair of $\sqrt{s_{NN}}=$ 5.02 TeV. The measurement is performed with the ALICE detector via the dimuon decay channel at forward rapidity (2.5 < y <4). The nuclear modification factor at very low p T and the coherent photoproduction cross section are measured as a function of centrality down to the 10% most central collisions. These results extend the previous study at $\sqrt{s_{NN}}=$ 2.76 TeV, confirming the clear excess over hadronic production in the p T range 0 – 0.3 GeV/c and the centrality range 70–90%, and establishing an excess with a significance greater than 5σ also in the 50–70% and 30–50% centrality ranges. The results are compared with earlier measurements at $\sqrt{s_{NN}}=$ 2.76 TeV and with different theoretical predictions aiming at describing how coherent photoproduction occurs in hadronic interactions with nuclear overlap.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2023

Neural network ensembles and uncertainty estimation for predictions of inelastic mechanical deformation using a finite element method-neural network approach

The finite element method (FEM) is widely used to simulate a variety of physics phenomena. Approaches that integrate FEM with neural networks (NNs) are typically leveraged as an alternative to conducting expensive FEM simulations in order to reduce the computational cost without significantly sacrificing accuracy. However, these methods can produce biased predictions that deviate from those obtained with FEM, since these hybrid FEM-NN approaches rely on approximations trained using physically relevant quantities. In this work, an uncertainty estimation framework is introduced that leverages ensembles of Bayesian neural networks to produce diverse sets of predictions using a hybrid FEM-NN approach that approximates internal forces on a deforming solid body. The uncertainty estimator developed herein reliably infers upper bounds of bias/variance in the predictions for a wide range of interpolation and extrapolation cases using a three-element FEM-NN model of a bar undergoing plastic deformation. This proposed framework offers a powerful tool for assessing the reliability of physics-based surrogate models by establishing uncertainty estimates for predictions spanning a wide range of possible load cases.

42 ENGINEERING↗
DOE OSTI2025

SchrödingerNet: A Universal Neural Network Solver for the Schrödinger Equation

Recent advances in machine learning have facilitated numerically accurate solution of the electronic Schrödinger equation (SE) by integrating various neural network (NN)-based wave function ansatzes with variational Monte Carlo methods. Nevertheless, such NN-based methods are all based on the Born–Oppenheimer approximation (BOA) and require computationally expensive training for each nuclear configuration. In this work, we propose a novel NN architecture, SchrödingerNet, to solve the full electronic-nuclear SE by defining a loss function designed to equalize local energies across the system. This approach is based on a translationally, rotationally and permutationally symmetry-adapted total wave function ansatz that includes both nuclear and electronic coordinates. Furthermore, this strategy not only allows for an efficient and accurate generation of a continuous potential energy surface at any geometry within the well-sampled nuclear configuration space, but also incorporates non-BOA corrections, through a single training process. Comparison with benchmarks of atomic and small molecular systems demonstrates its accuracy and efficiency.

Chemical calculations↗
DOE OSTI2021

Selective Removal of Perfluorobutyric Acid Using an Electroactive Ion Exchanger Based on Polypyrrole@Iron Oxide on Carbon Cloth

Perfluorabutyric acid (PFBA) is one classify of perfluoroalkyl and polyfluoroalkyl substances (PFASs), which is applied to wide-spread industry compounds. The removal of PFBA has attracted considerable scientific interest in recent decades because it caused environmental pollutions and human diseases. For removing PFASs from wastewater, the adsorption method has been commonly used for the remediation of PFASs. However, it is usually limited by the inevitable “secondary waster” produced in this treatment process. In this work, PFBA can be removed effectively by synergizing the electrically switched ion exchange (ESIX) and a novel nanostructured ion exchanger. Herein, the nanostructured ion exchanger is designed by coating polypyrrole (PPy) @ Fe 2 O 3 nanoneedle on carbon cloth (PPy@Fe 2 O 3 NN-CC). Overall, results show that PPy@Fe 2 O 3 NN-CC film enhances ion exchange speed and efficiency, which endures its high-capacity adsorption ability and rapid regeneration property, thereby reducing secondary waste. Moreover, ESIX based on PPy@Fe 2 O 3 NN-CC has high selectivity for adsorption of PFBA over Cl - , SO 4 2- and NO 3 - .

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2022

Single-Photon-Induced Electron Spin Polarization of Two Exchange-Coupled Stable Radicals

Transient electron paramagnetic resonance spectroscopy has been used to probe photoinduced electron spin polarization of a stable exchange-coupled organic biradical in a Pt(II) complex comprising 4,4'-di-tert-butyl-2,2'-bipyridine (bpy) and 3,6-bis(ethynyl-para-phenyl-nitronyl nitroxide)-o-catecholate (CAT(o-C$\equiv$C-Ph-NN) 2 ). Photoexcitation results in four unpaired spins in excited states of this complex, with spins being localized on each of the two radicals, CAT •+ and bpy •– . The four spins are all exchange-coupled in these excited states, and an off-diagonal matrix element in the CAT •+ -NN exchange allows for exchange-enhanced intersystem crossing to the 3 T 1a state, which possesses (bpy •– )Pt(CAT •+ ) chromophoric triplet character. Further, fast mixing between this 3 T 1a state and other thermally accessible excited LL'CT state(s) followed by fast relaxation provides spin polarization of the exchange-coupled NN radicals in the 3 S 0 ground state of the complex. Our results demonstrate that well-defined quantum states of a ground-state biradical can be initialized with single-photon excitation and have the potential for further spin manipulation directed toward quantum information science applications.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2024

Improving River Routing Using a Differentiable Muskingum‐Cunge Model and Physics‐Informed Machine Learning

Recently, rainfall-runoff simulations in small headwater basins have been improved by methodological advances such as deep neural networks (NNs) and hybrid physics-NN models—particularly, a genre called differentiable modeling that intermingles NNs with physics to learn relationships between variables. However, hydrologic routing simulations, necessary for simulating floods in stem rivers downstream of large heterogeneous basins, had not yet benefited from these advances and it was unclear if the routing process could be improved via coupled NNs. We present a novel differentiable routing method (δMC-Juniata-hydroDL2) that mimics the classical Muskingum-Cunge routing model over a river network but embeds an NN to infer parameterizations for Manning's roughness (n) and channel geometries from raw reach-scale attributes like catchment areas and sinuosity. The NN was trained solely on downstream hydrographs. Synthetic experiments show that while the channel geometry parameter was unidentifiable, n can be identified with moderate precision. With real-world data, the trained differentiable routing model produced more accurate long-term routing results for both the training gage and untrained inner gages for larger subbasins (>2,000 km2) than either a machine learning model assuming homogeneity, or simply using the sum of runoff from subbasins. The n parameterization trained on short periods gave high performance in other periods, despite significant errors in runoff inputs. The learned n pattern was consistent with literature expectations, demonstrating the framework's potential for knowledge discovery, but the absolute values can vary depending on training periods. The trained n parameterization can be coupled with traditional models to improve national-scale hydrologic flood simulations.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2020

Nitrogen Fertilization Restructured Spatial Patterns of Soil Organic Carbon and Total Nitrogen in Switchgrass and Gamagrass Croplands in Tennessee USA

Nitrogen (N) fertilizers can potentially alter spatial distribution of soil organic carbon (SOC) and total nitrogen (TN) concentrations in croplands such as switchgrass (SG: Panicum virgatum L.) and gamagrass (GG: Tripsacum dactyloides L.), but it remains unclear whether these effects are the same between crops and under different rates of fertilization. 13 C and 15 N are two important proxy measures of soil biogeochemistry, but they were rarely examined as to their spatial distributions in soil. Based on a three-year long fertilization experiment in Middle Tennessee, USA, the top mineral horizon soils (0–15 cm) were collected using a spatially explicit design within two 15-m 2 plots under three fertilization treatments in SG and GG croplands. A total of 288 samples were collected based on 12 plots and 24 samples in each plot. The fertilization treatments were no N input (NN), low N input (LN: 84 kg N ha -1 in urea) and high N input (HN: 168 kg N ha -1 in urea). The SOC, TN, SOC/TN (C: N), δ 13 C and δ 15 N were quantified and their within-plot variations and spatial distributions were achieved via descriptive and geostatistical methods. Results showed that SG generally displayed 10~120% higher plot-level variations in all variables than GG, and the plot-level variations were 20~77% higher in NN plots than LN and HN plots in SG but they were comparable in unfertilized and fertilized plots in GG. Relative to NN, LN and HN showed more significant surface trends and spatial structures in SOC and TN in both croplands, and the fertilization effect appeared more pronounced in SG. Spatial patterns in C: N, δ 13 C and δ 15 N were comparable among different fertilization treatments in both croplands. The descending within-plot variations were also identified among variables (SOC > TN > δ 15 N > C: N > δ 13 C). This study demonstrated that N fertilizations generally reduced the plot-level variance and simultaneously re-established spatial structures of SOC and TN in bioenergy croplands, which little varied with fertilization rate but was more responsive in switchgrass cropland.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2024

Neutral rhenium( i ) tricarbonyl complexes with sulfur-donor ligands: anti-proliferative activity and cellular localization

Rhenium(I) tricarbonyl complexes are widely studied for their cell imaging properties and anti-cancer and anti-microbial activities, but the complexes with S-donor ligands remain relatively unexplored. A series of six fac-[Re(NN)(CO) 3 (SR)] complexes, where (NN) is 2,2'-bipyridyl (bipy) or 1,10-phenanthroline (phen), and RSH is a series of thiocarboxylic acid methyl esters, have been synthesized and characterized. Cellular uptake and anti-proliferative activities of these complexes in human breast cancer cell lines (MDA-MB-231 and MCF-7) were generally lower than those of the previously described fac-[Re(NN)(CO) 3 (OH 2 )]+ complexes; however, one of the complexes, fac-[Re(CO) 3 (phen)(SC(Ph)CH 2 C(O)OMe)] (3b), was active (IC 50 ~ 10 μM at 72 h treatment) in thiol-depleted MDA-MB-231 cells. Moreover, unlike fac-[Re(CO) 3 (phen)(OH 2 )]+, this complex did not lose activity in the presence of extracellular glutathione. Taken together these properties show promise for further development of 3b and its analogues as potential anti-cancer drugs for co-treatment with thiol-depleting agents. Conversely, the stable and non-toxic complex, fac-[Re(bipy)(CO) 3 (SC(Me)C(O)OMe)] (1a), predominantly localized in the lysosomes of MDA-MB-231 cells, as shown by live cell confocal microscopy (λ ex = 405 nm, λ em = 470–570 nm). It is strongly localized in a subset of lysosomes (25 μM Re, 4 h treatment), as shown by co-localization with a Lysotracker dye. Longer treatment times with 1a (25 μM Re for 48 h) resulted in partial migration of the probe into the mitochondria, as shown by co-localization with a Mitotracker dye. These properties make complex 1a an attractive target for further development as an organelle probe for multimodal imaging, including phosphorescence, carbonyl tag for vibrational spectroscopy, and Re tag for X-ray fluorescence microscopy.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2023

Inference of the optical depth to reionization τ from Planck CMB maps with convolutional neural networks

The optical depth to reionization, τ, is the least constrained parameter of the cosmological Λ cold dark matter (ΛCDM) model. To date, its most precise value is inferred from large-scale polarized cosmic microwave background (CMB) power spectra from the High Frequency Instrument (HFI) aboard the Planck satellite. These maps are known to contain significant contamination by residual non-Gaussian systematic effects, which are hard to model analytically. Therefore, robust constraints on τ are currently obtained through an empirical cross-spectrum likelihood built from simulations. In this paper, we present a likelihood-free inference of τ from polarized Planck HFI maps which, for the first time, is fully based on neural networks (NNs). NNs have the advantage of not requiring an analytical description of the data and can be trained on state-of-the-art simulations, combining the information from multiple channels. By using Gaussian sky simulations and Planck SRoll2 simulations, including CMB, noise, and residual instrumental systematic effects, we trained, tested, and validated NN models considering different setups. We inferred the value of τ directly from Stokes Q and U maps at ~4° pixel resolution, without computing angular power spectra. On Planck data, we obtained τ NN = 0.0579 ± 0.0082, which is compatible with current EE cross-spectrum results but with a ~30% larger uncertainty, which can be assigned to the inherent nonoptimality of our estimator and to the retraining procedure applied to avoid biases. While this paper does not improve on current cosmological constraints on τ, our analysis represents a first robust application of NN-based inference on real data, and highlights its potential as a promising tool for complementary analysis of near-future CMB experiments, also in view of the ongoing challenge to achieve the first detection of primordial gravitational waves.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2026

Impact of in situ nuclear networks and atomic opacities on neutron star merger ejecta dynamics, nucleosynthesis, and kilonovae

Context. Binary neutron star merger (BNSM) ejecta are key sites of rapid neutron capture (r-process) nucleosynthesis and they produce kilonovae powered by the radioactive decay of freshly synthesized nuclei. Modeling their evolution requires multi-physics simulations involving hydrodynamics, nuclear reactions, and radiative processes. The impact of nuclear burning and atomic opacity is poorly understood and often treated with simplified prescriptions. Aims. We systematically investigate different treatments of nuclear heating, particle thermalization, and atomic opacities in radiation-hydrodynamics simulations of BNSM ejecta and kilonova light curves. Methods. Ejecta profiles from long-term numerical-relativity simulations of asymmetric neutron star binaries with a massive neutron star remnant were evolved to ∼30 days using a 2D ray-by-ray approach. We compared simplified heating-rate and thermalization prescriptions with in situ Nuclear reaction Network (NN) calculations that track nuclear energy deposition and include a composition-dependent thermalization scheme. We also contrasted various gray opacity models with a frequency-dependent treatment based on atomic calculations. Results. Coupling NN and hydrodynamics significantly affects nucleosynthesis and kilonova emission. Assuming homologous expansion alters abundance evolution and produces a narrower, less populated second r-process peak and a third peak shifted to higher mass numbers. The back-reaction of nuclear heating affects the temperature evolution enough to delay and redden the early (t∼ hours) kilonova peaks. A constant thermalization efficiency underestimates and reddens the early emission while overestimating the late-time luminosity compared to the composition-dependent treatment. Analytical opacity prescriptions yield a more extended, colder photosphere, resulting in dimmer, redder kilonovae at early times (t≲ hour), while the delayed recession of the photosphere prolongs the red emission at t ≳ 5 days. Conclusions. Coupling hydrodynamics to an in situ NN is crucial for reliable nucleosynthesis and kilonova predictions. Resolving the first several hundred milliseconds of the hydrodynamics is essential for robust nucleosynthesis calculations. Composition-dependent thermalization and frequency-dependent, atomic-physics-based opacities are needed to accurately capture the temperature evolution of the ejecta and the brightness and color evolution of the kilonova. Calibrated analytic nuclear-power fits with simplified thermalization and opacity prescriptions can still reproduce the density and temperature evolution of the ejecta.

74 ATOMIC AND MOLECULAR PHYSICS↗
DOE OSTI2024

Statistical data analysis of x-ray spectroscopy data enabled by neural network accelerated Bayesian inference

Bayesian inference applied to x-ray spectroscopy data analysis enables uncertainty quantification necessary to rigorously test theoretical models. However, when comparing to data, detailed atomic physics and radiation transfer calculations of x-ray emission from non-uniform plasma conditions are typically too slow to be performed in line with statistical sampling methods, such as Markov Chain Monte Carlo sampling. Furthermore, differences in transition energies and x-ray opacities often make direct comparisons between simulated and measured spectra unreliable. Here, we present a spectral decomposition method that allows for corrections to line positions and bound–bound opacities to best fit experimental data, with the goal of providing quantitative feedback to improve the underlying theoretical models and guide future experiments. In this work, we use a neural network (NN) surrogate model to replace spectral calculations of isobaric hot-spots created in Kr-doped implosions at the National Ignition Facility. The NN was trained on calculations of x-ray spectra using an isobaric hot-spot model post-processed with Cretin, a multi-species atomic kinetics and radiation code. The speedup provided by the NN model to generate x-ray emission spectra enables statistical analysis of parameterized models with sufficient detail to accurately represent the physical system and extract the plasma parameters of interest.

47 OTHER INSTRUMENTATION↗
DOE OSTI2020

Neural network based prediction of no-wall β N limits due to ideal external kink instabilities

Multi-layer perceptron based neural networks (NNs) are trained to predict the Troyon no-wall beta limits due to the onset of low-n (n = 1 – 3, n is the toroidal mode number) ideal external kink instabilities in tokamak plasmas. It is revealed that a well-trained NN can predict the n = 1 no-wall beta limit within 10% relative error. The NN performance is somewhat worse for the n = 2 and 3 no-wall beta limits, but still a relative error within 20% is achievable. The trained NNs well reproduce the known dependences of the no-wall beta limits on the plasma pressure (pressure peaking factor) and current (plasma internal inductance) profiles. Other scalings are further easily established with NNs, for parametric dependences such as on the aspect ratio, the elongation and triangularity of the plasma boundary shape. These NN-based Troyon beta limit predictors can be incorporated into integrated modeling platforms, or directly implemented as a real time stability estimator for the purpose of disruption avoidance or mitigation during experiments.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
DOE OSTI2026

Dynamics of argon metastables in Ar–CH 4 radio frequency capacitively-coupled plasma: real-time monitoring with neural network-augmented broadband optical emission spectroscopy

In moderate-pressure radio frequency (RF) capacitively coupled plasmas generated in argon–methane mixtures, the density of argon metastable atoms (Ar 1 s 5 ) exhibits a non-monotonic dependence on methane (CH 4 ) concentration. Laser-induced fluorescence (LIF) was used to measure and compare local Ar 1 s 5 densities in Ar and Ar–CH 4 plasmas at 2.6 Torr and RF powers of 17–117 W. The addition of 1% CH 4 increases the metastable density, and 2% CH 4 triggers a strong depletion by an order of magnitude, compared to 1% CH 4 case. This non-monotonic behavior demonstrates the sensitivity of metastable populations to small gas admixtures, which is critical for processes where metastables drive precursor dissociation. For real-time monitoring of metastable population, broadband optical emission spectroscopy (OES) is augmented with a feedforward neural network (NN) to predict Ar s1 5 densities from spectral features. When trained on LIF data, the NN replicates the absolute densities and the dynamic trends of Ar 1 s 5 density variation. The NN-augmented broadband OES approach can be used as a simple and cost-effective tool for tracking Ar metastables in Ar-rich plasmas, facilitating industrial-scale optimization.

Yatom, Shurik [Princeton Plasma Physics Laboratory↗
DOE OSTI2024

Initial testing of Alfvén eigenmode feedback control with machine-learning observers on DIII-D

A first of its kind fully data-driven system has been developed and implemented into the DIII-D plasma control system to detect and control Alfvén eigenmodes (AE) in real-time. Susceptibility to fast ion-induced AE is a challenge in fully non-inductive tokamak operation, which significantly reduces fast-particle confinement and results in degraded fusion gain. Controlling AEs in real-time to improve fast-ion confinement is, hence, important for future advanced tokamak fusion reactors. The models were implemented and tested in experiments which showed that neural networks (NN) are highly effective in detecting 5 types of AE (BAE, EAE, LFM, RSAE, TAE) using high resolution ECE. To estimate the neutron deficit, a NN has been trained that outputs the classical neutron rate using similar inputs to NUBEAM. Also a preliminary ML-based proportional control has been designed and gone through initial testing in experiment to use feedback-control on the neutral beam power to achieve desired amplitude of AE modes and neutron deficits. The effect of AEs on fast-ion confinement is measured by analysing the gap in classical neutron rate from the proposed NN-based NUBEAM and the measured neutron rate.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗