Search NASA⌕ Search

SEARCH · Search NASA

Results for “INTERPOLATION”

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 OSTI2024

Thermodynamic modeling of CsF with LiF-NaF-KF for molten fluoride-fueled reactors

Gibbs energy models were developed to describe the thermochemical behavior of CsF in molten FLiNaK (46.5LiF-11.5NaF-42KF mol%), a proposed molten salt reactor (MSR) fuel solvent and coolant, as cesium is of concern due to its high radiotoxicity and volatility. Initially, it was necessary to obtain a more accurate Gibbs energy function for CsF which required fitting parameters to reported vapor pressures over condensed phase CsF. The pseudo-binary systems CsF-LiF, CsF-NaF and CsF-KF were then evaluated utilizing phase equilibria and enthalpy of mixing (Δ mix H) values, together with original differential scanning calorimetry (DSC) measurements performed for the CsF-LiF and CsF-KF systems. The CsF-LiF-NaF, CsF-LiF-KF and CsF-NaF-KF pseudo-ternary system representations were obtained by interpolation of the constituent pseudo-binary systems, with DSC measurements performed for the CsF-LiF-NaF system to corroborate the calculated liquidus temperature. Ultimately, the pseudo-ternary systems were interpolated to obtain Gibbs energy models for the pseudo-quaternary CsF-LiF-NaF-KF system, supported by DSC measurements at low CsF compositions (1–10 mol%), yielding computed equilibria and cesium-containing vapor pressures that compare favorably with reported values. In conclusion, the Molten Salt Thermal Properties Database – Thermochemical (MSTDB-TC) was subsequently expanded to include these Gibbs energy models allowing description of the thermochemical behavior of the CsF-LiF-NaF-KF system.

11 - NUCLEAR FUEL CYCLE AND FUEL MATERIALS↗
DOE OSTI2025

On the effectiveness of neural operators at zero-shot weather downscaling

Machine-learning (ML) methods have shown great potential for weather downscaling. These data-driven approaches provide a more efficient alternative for producing high-resolution weather datasets and forecasts compared to physics-based numerical simulations. Neural operators, which learn solution operators for a family of partial differential equations, have shown great success in scientific ML applications involving physics-driven datasets. Neural operators are grid-resolution-invariant and are often evaluated on higher grid resolutions than they are trained on, i.e., zero-shot super-resolution. Given their promising zero-shot super-resolution performance on dynamical systems emulation, we present a critical investigation of their zero-shot weather downscaling capabilities, which is when models are tasked with producing high-resolution outputs using higher upsampling factors than are seen during training. To this end, we create two realistic downscaling experiments with challenging upsampling factors (e.g., 8x and 15x) across data from different simulations: the European Centre for Medium-Range Weather Forecasts Reanalysis version 5 (ERA5) and the Wind Integration National Dataset Toolkit. While neural operator-based downscaling models perform better than interpolation and a simple convolutional baseline, we show the surprising performance of an approach that combines a powerful transformer-based model with parameter-free interpolation at zero-shot weather downscaling. We find that this Swin-Transformer-based approach mostly outperforms models with neural operator layers in terms of average error metrics, whereas an Enhanced Super-Resolution Generative Adversarial Network-based approach is better than most models in terms of capturing the physics of the ground truth data. We suggest their use in future work as strong baselines.

17 WIND ENERGY↗
DOE OSTI2025

Geospatial modeling of near subsurface temperatures of the contiguous United States for assessment of materials degradation

Abstract Understanding subsurface temperature variations is crucial for assessing material degradation in underground structures. This study maps subsurface temperatures across the contiguous United States for depths from 50 to 3500 m, comparing linear interpolation, gradient boosting (LightGBM), neural networks, and a novel hybrid approach combining linear interpolation with LightGBM. Results reveal heterogeneous temperature patterns both horizontally and vertically. The hybrid model performed best achieving a root mean square error of 2.61 °C at shallow depths (50–350 m). Model performance generally decreased with depth, highlighting challenges in deep temperature prediction. State-level analyses emphasized the importance of considering local geological factors. This study provides valuable insights for designing efficient underground facilities and infrastructure, underscoring the need for depth-specific and region-specific modeling approaches in subsurface temperature assessment.

Science & Technology - Other Topics↗
DOE OSTI2025

A transient near to far field transformation method and verification benchmarking procedure

The numerical calculation of electromagnetic far fields in the time-domain requires a near to far field transformation (NTFF) method. While time-domain NTFF methods for popular finite-difference time-domain (FDTD) approaches are well established, there is little discourse on NTFF methods for finite-element time-domain (FETD) codes. Here, this work is concerned with the development of an NTFF method for the Empire FETD code, which utilizes curl and divergence conforming elements. This discretization presents a difficulty in obtaining the equivalent electric current for the NTFF. Straightforward finite element interpolation of the fields is shown to give poor accuracy. Alternative interpolation methods are recommended. An expanding magnetic quadrupole pulse benchmark problem, which is fully developed in the appendices, provides the basis for quantitative comparison.

FETD↗
DOE OSTI2024

GALIC: hybrid multi-qubitwise pauli grouping for quantum computing measurement

Abstract Observable estimation is a core primitive in NISQ-era algorithms targeting quantum chemistry applications. To reduce the state preparation overhead required for accurate estimation, recent works have proposed various simultaneous measurement schemes to lower estimator variance. Two primary grouping schemes have been proposed: full commutativity (FC) and qubit-wise commutativity (QWC), with no compelling means of interpolation. In this work we propose a generalized framework for designing and analyzing context-aware hybrid FC/QWC commutativity relations. We use our framework to propose a noise-and-connectivity aware grouping strategy: Generalized backend-Aware pauLI Commutation (GALIC). We demonstrate how GALIC interpolates between FC and QWC, maintaining estimator accuracy in Hamiltonian estimation while lowering variance by an average of 20% compared to QWC. We also explore the design space of near-term quantum devices using the GALIC framework, specifically comparing device noise levels and connectivity. We find that error suppression has a more than 10 × larger impact on device-aware estimator variance than qubit connectivity with even larger correlation differences in estimator biases.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗
DOE OSTI2026

Importance of finite-size corrections for accurate ab initio modeling of carrier capture at semiconductor defects: A case study of substitutional C N in GaN

In ab initio studies of carrier-capture processes in defective semiconductor materials, the single-effective-mode formalism and the static-coupling approximation have become the predominant theoretical approaches for determining carrier-capture coefficients. The single-mode formalism relies on accurate nonequilibrium defect energies obtained from density-functional theory (DFT), where required inputs are a series of configurationally displaced, defect-containing supercells obtained using an interpolative ansatz, and where the DFT outputs are corresponding total energies that have traditionally been postprocessed using a long-established ground-state formulation of finite-size corrections and defect-formation energies. This formulation remains commonly used even though the defects that form a configuration-coordinate (CC) diagram typically exist as structures that are displaced from the ground state. To remedy this inconsistency, Kumagai has recently proposed novel methods for implementing finite-size corrections specifically intended for DFT calculations of the defect energies used to construct CC diagrams and implement the single-mode formalism [Y. Kumagai, Phys. Rev. B 107, L220101 (2023)]. Kumagai's approach builds on the latest finite-size-correction methods introduced to describe vertical charge-state transitions for charge-localizing point defects in semiconductors and insulators [T. Gake et al., Phys. Rev. B 101, 020102 (2020); S. Falletta et al., Phys. Rev. B 102, 041115 (2020)]. The newly identified finite-size artifact treated in these studies is the polarization charge induced on a configurationally frozen defect and its subsequent interaction with a vertical transition in charge state. In this work, we evaluate Kumagai's proposed methodology by applying it in a high-precision DFT study of carrier capture by substitutional C N in GaN, a well-characterized and technologically relevant defect and material. We have rigorously calculated C N defect energies across various supercell sizes for each defect configuration and charge state on the hole-capture CC diagram of C N (𝑞=−1), enabling a direct comparison of the slopes of the defect energies versus inverse cell size with those predicted by Kumagai. The most consequential prediction of Kumagai's method is that these slopes distinctly vary as the square of the linear-interpolation parameter used to construct the nonequilibrium defect configurations. Our results quantitatively support this prediction. Moreover, with these new finite-size corrections and multiple-cell-size DFT calculations in place, we find that the classical energy barrier for hole capture by C N (𝑞=−1) in GaN decreases to 0.092–0.127 eV. This finding confirms the recent ≈ 0.1 eV prediction of Reshchikov based on the weak temperature dependence for hole capture observed in photoluminescence experiments [M. A. Reshchikov, J. Appl. Phys. 129, 121101 (2021)]. These results stand in stark contrast to previously calculated barriers of 0.486 and 0.73 eV, which also used the single-mode formalism but were obtained by instead using ground-state-based finite-size corrections. Our reduced classical barrier for capture increases the temperature-dependent hole-capture coefficient of a C N (𝑞=−1) defect by more than two to four orders of magnitude for temperatures of 100–600 K, compared to the previous 0.486 eV results. While other defects may not be as dramatically affected as here, we suggest that incorporating proper finite-size corrections for the vertical-transition-like states embedded within CC diagrams is an essential, yet previously unrecognized, component of accurate modeling of carrier-capture when using the single-effective-mode formalism.

dielectric properties↗
DOE OSTI2026

Wilson loops with neural networks

Wilson loops are essential objects in QCD and have been pivotal in scale setting and demonstrating confinement. Various generalizations are crucial for computations needed in effective field theories. In lattice gauge theory, Wilson loop calculations face challenges, including excited-state contamination at short times and the signal-to-noise ratio issue at longer times. To address these problems, we develop a new method by using neural networks to parametrize interpolators for the static quark-antiquark pair. We construct gauge-equivariant layers for the network and train it to find the ground state of the system. The trained network itself is then treated as our new observable for the inference. Our results demonstrate a significant improvement in the signal compared to traditional Wilson loops, performing as well as Coulomb-gauge Wilson-line correlators while maintaining gauge invariance. Additionally, we present an example where the optimized ground state is used to measure the static force directly, as well as another example combining this method with the multilevel algorithm. Finally, we extend the formalism to find excited-state interpolators for static quark-antiquark systems. To our knowledge, this work is the first study of neural networks with a physically motivated loss function for Wilson loops.

Bellscheidt, Verena [Massachusetts Inst. of Techno↗
DOE OSTI2025

Single Grid Error Estimation for Neutron Transport Solvers

The method of nearby problems (MNP) is a solution verification technique that does not require the use of multiple spatial grids. To estimate spatial discretization error without requiring a high-fidelity spatial grid, an analytical curve fit is interpolated from the numerical solution. The residual between the curve fit solution and numerical solution is calculated and added as an additional source term to the governing equation. The nearby solution is estimated using the updated source term and boundary conditions to remain consistent with the curve fit interpolation. The nearby solution can be compared to the curve fit solution as a discretization error estimation while using a single spatial grid. Without the use of higher fidelity spatial grids, the MNP is able to approximate the spatial discretization error, a facet of solution verification. The application of the method of nearby problems is presented for one- and two-dimensional neutron transport problems for both fixed source and criticality problems on the spatial variable. The fixed source results demonstrate the effectiveness of nearby problems for spatial error identification using the discrete ordinates method. Criticality results are shown to identify area of high spatial error for the C5G7 problem as well as for the discrete ordinates solver. A novel approach of combining the capabilities of Monte Carlo with the discrete ordinates nearby problems is presented for one- and two-dimensional fixed source problems. In conclusion, the MNP demonstrates its effectiveness at identifying spatial error on a single structured grid with a wide variety of neutron transport problems.

73 NUCLEAR PHYSICS AND RADIATION PHYSICS↗
DOE OSTI2024

On Compatible Transfer Operators in Nonsymmetric Algebraic Multigrid

The standard goal for an effective algebraic multigrid (AMG) algorithm is to develop relaxation and coarse-grid correction schemes that attenuate complementary error modes. In the nonsymmetric setting, coarse-grid correction Π will almost certainly be nonorthogonal (and divergent) in any known standard product, meaning ∥Π∥ > 1. This introduces a new consideration, that one wants coarse-grid correction to be as close to orthogonal as possible, in an appropriate norm. In addition, due to nonorthogonality, Π may actually amplify certain error modes that are in the range of interpolation. Relaxation must then not only be complementary to interpolation, but also rapidly eliminate any error amplified by the nonorthogonal correction, or the algorithm may diverge. Here this paper develops analytic formulae on how to construct “compatible” transfer operators in nonsymmetric AMG such that ∥Π∥ = 1 in some standard matrix-induced norm. Discussion is provided on different options for the norm in the nonsymmetric setting, the relation between “ideal” transfer operators in different norms, and insight into the convergence of nonsymmetric reduction-based AMG.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2025

Gaussian Process Regression under Computational and Epistemic Misspecification

Gaussian process regression is a classical kernel method for function estimation and data interpolation. In large data applications, computational costs can be reduced using low-rank or sparse approximations of the kernel. This paper investigates the effect of such kernel approximations on the interpolation error. We introduce a unified framework to analyze Gaussian process regression under important classes of computational misspecification: Karhunen-Loève expansions that result in low-rank kernel approximations, multiscale wavelet expansions that induce sparsity in the covariance matrix, and finite element representations that induce sparsity in the precision matrix. Furthermore, our theory also accounts for epistemic misspecification in the choice of kernel parameters.

Gaussian process regression↗
DOE OSTI2026

HITMAN

HITMAN (Hermite Interpolation of Trajectories and Measurement Synthesis for Analysis of Navigators) interpolates—or estimates the unknown values between known values—flight trajectories and generates synthetic inertial measurement unit (IMU) data using Hermite splines. This Python library provides modeling and simulation capabilities to synthesize inertial measurements from discrete trajectory points, enabling researchers to create exemplar datasets for evaluating navigation algorithms in various applications, including consumer devices like smartphones and vehicles. Sandia National Laboratories is a multimission laboratory managed and operated by National Technology & Engineering Solutions of Sandia, LLC, a wholly owned subsidiary of Honeywell International Inc., for the U.S. Department of Energy’s National Nuclear Security Administration under contract DE-NA0003525.

Walker II, Michael [Sandia National Lab. (SNL-CA),↗
DOE OSTI2024

Machine Learning Approach for Spatiotemporal Multivariate Optimization of Environmental Monitoring Sensor Locations

Abstract Long-term environmental monitoring is critical for managing the soil and groundwater at contaminated sites. Recent improvements in state-of-the-art sensor technology, communication networks, and artificial intelligence have created opportunities to modernize this monitoring activity for automated, fast, robust, and predictive monitoring. In such modernization, it is required that sensor locations be optimized to capture the spatiotemporal dynamics of all monitoring variables as well as to make it cost-effective. The legacy monitoring datasets of the target area are important to perform this optimization. In this study, we have developed a machine-learning approach to optimize sensor locations for soil and groundwater monitoring based on ensemble supervised learning and majority voting. For spatial optimization, Gaussian process regression (GPR) is used for spatial interpolation, while the majority voting is applied to accommodate the multivariate temporal dimension. Results show that the algorithms significantly outperform the random selection of the sensor locations for predictive spatiotemporal interpolation. While the method has been applied to a four-dimensional dataset (with two-dimensional space, time, and multiple contaminants), we anticipate that it can be generalizable to higher-dimensional datasets for environmental monitoring sensor location optimization.

Siddiquee, Masudur R.↗
DOE OSTI2026

Learning genetic perturbation effects with variational causal inference

Advances in sequencing technologies have enhanced the understanding of gene regulation in cells. In particular, Perturb-seq has enabled high-resolution profiling of the transcriptomic response to genetic perturbations at the single-cell level. This understanding has implications in functional genomics and potentially for identifying therapeutic targets. Various computational models have been developed to predict perturbational effects. While deep learning models excel at interpolating observed perturbational data, they tend to overfit in the lack of enough data and may not generalize well to unseen perturbations. In contrast, mechanistic models, such as linear causal models based on gene regulatory networks, hold greater potential for extrapolation, as they encapsulate regulatory information that can predict responses to unseen perturbations. However, their application has been limited to small studies due to overly simplistic assumptions, making them less effective in handling noisy, large-scale single-cell data. We propose a hybrid approach that combines a mechanistic causal model with variational deep learning, termed Single Cell Causal Variational Autoencoder (SCCVAE). The mechanistic model employs a learned regulatory network to represent perturbational changes as shift interventions that propagate through the learned network. SCCVAE integrates this mechanistic causal model into a variational autoencoder, generating rich, comprehensive transcriptomic responses. Our results indicate that SCCVAE exhibits superior performance over current state-of-the-art baselines for extrapolating to predict unseen perturbational responses. Additionally, for the observed perturbations, the latent space learned by SCCVAE allows for the identification of functional perturbation modules and simulation of single-gene knockdown experiments of varying penetrance, presenting a robust tool for interpreting and interpolating perturbational responses at the single-cell level.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2025

Evaluation of data driven low-rank matrix factorization for accelerated solutions of the Vlasov equation

Low-rank methods have shown success in accelerating simulations of a collisionless plasma described by the Vlasov equation, but still rely on computationally costly linear algebra every time step. We propose a data-driven factorization method using artificial neural networks, specifically with convolutional layer architecture, that trains on existing simulation data. At inference time, the model outputs a low-rank decomposition of the distribution field of the charged particles, and we demonstrate that this step is faster than the standard linear algebra technique. Numerical experiments show that the method achieves comparable reconstruction accuracy for interpolation tasks, generalizing to unseen test data in a manner beyond just memorizing training data; patterns in factorization also inherently followed the same numerical trend as those within algebraic methods (e.g., truncated singular-value decomposition). However, when training on the first 70% of a time-series data and testing on the remaining 30%, the method fails to meaningfully extrapolate. Despite this limiting result, the technique may have benefits for simulations in a statistical steady-state or otherwise showing temporal stability. These results suggest that while the model offers a computationally efficient alternative for datasets with temporal stability, its current formulation is best suited for interpolation rather than for predicting future states in time-evolving systems. This study thus lays the groundwork for further refinement of neural network-based approaches to low-rank matrix factorization in high-dimensional plasma simulations.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2025

Quality-Controlled Meteorological Data from the Flood Control District of Maricopa County (FCDMC) Network, Phoenix, Arizona (1987-2024)

This dataset contains 15- or 30-minute interval meteorological data from the Flood Control District of Maricopa County (FCDMC), Arizona, USA, covering eight key variables across multiple sensor stations between 1987 and 2024. Each variable is stored as a separate CSV file, containing time-series data that have undergone rigorous quality control (QC) procedures and, where appropriate, short-gap interpolation for consistency. The quality control (QC) pipeline consisted of four sequential tests: (1) a range test to ensure all values fall within physically realistic limits, (2) a step test to identify abrupt and implausible changes between consecutive records, (3) a proximity test that validates flagged values from step test using data from nearby stations and exceedance probability thresholds, and (4) a persistence test to detect and remove periods of unrealistically constant readings. These thresholds were calibrated to Arizona’s environmental conditions and sensor specifications. After QC, short gaps (≤2 hours) were linearly interpolated to ensure consistent temporal resolution, except for wind variables. Due to a major upgrade in FCDMC’s data transmission system, only ALERT-2 protocol data (2016–2024) for wind variables are included; earlier ALERT-1 data were excluded because of irregular sampling and high missing rates. This dataset supports regional climate and infrastructure resilience studies by providing standardized, high-resolution meteorological data for the greater Phoenix metropolitan area.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2026

Data-Driven Modeling and Correction of Vehicle Dynamics

We develop a data-driven framework for learning and correcting nonautonomous vehicle dynamics. Physics-based vehicle models are often simplified for tractability and therefore exhibit inherent model-form uncertainty, motivating the need for data-driven correction. Moreover, nonautonomous dynamics are governed by time-dependent control inputs, which pose challenges in learning predictive models directly from temporal snapshot data. To address these, we reformulate the vehicle dynamics via a local parameterization of the time-dependent inputs, yielding a modified system composed ofa sequence of local parametric dynamical systems. Here, we approximate these parametric systems using two complementary approaches. First, we employ the dimension reduction and interpolation in parameter space (DRIPS) methodology to construct efficient linear surrogate models, equipped with lifted observable spaces and manifold-based operator interpolation. This enables data-efficient learning of vehicle models whose dynamics admit accurate linear representations in the lifted spaces. Second, for more strongly nonlinear systems, we employ flow map learning (FML), a deep neural network (DNN) approach that approximates the parametric evolution map without requiring special treatment of nonlinearities. We further extend FML with a transfer-learning-based model correction procedure, enabling the correction of misspecified prior models using only a sparse set of high-fidelity or experimental measurements, without assuming a prescribed form for the correction term. Through a suite of numerical experiments on unicycle, simplified bicycle, and slip-based bicycle models, we demonstrate that DRIPS offers robust and highly data-efficient learning of nonautonomous vehicle dynamics, while FML provides expressive nonlinear modeling and effective correction of model-form errors under severe data scarcity.

data-driven modeling↗
DOE OSTI2024

Plan Position Indicator Hydrometeor Field Statistics (PPIHYD) Evaluation Data Product Version 1.0

The PPIHYD evaluation data product provides distinct hydrometeor field statistics calculated from U.S. Department of Energy Atmospheric Radiation Measurement (ARM) user facility scanning radar plan position indicator (PPI) scans. These statistics include the equivalent reflectivity factor and Doppler spectral width percentiles, min/max values, and first four moments (mean, standard deviation, skewness, and kurtosis) of distinct hydrometeor features (clustered hydrometeor fields). Statistics also include morphological properties, water content and precipitation rate parameterization-based estimates, and thermodynamic properties interpolated using the Interpolated Sonde value-added product (INTERPSONDE VAP). The data set is organized in tabular form and is accompanied by mask arrays with corresponding indices. This straightforward file structure simplifies scanning radar data processing and renders this data set useful for process understanding and model evaluation studies. This report describes the data set and its processing algorithm and provides some examples.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2025

MPEX AI Digital Twins

All magnetically confined plasma fusion power plant concepts (Tokamak, Spherical Tokamak, Stellarator, Mirror, ...) must exhaust the heat and plasma from the core confinement region to the material walls. The primary channel for this exhaust is through a plasma divertor which directs plasma along open magnetic field lines to a material target. The Material Plasma Exposure eXperiment (MPEX) illustrated in Figure 1, is a high-power, steady-state linear plasma device designed to produce the plasma material interaction (PMI) conditions of the divertor of future magnetic confinement fusion power plants: energy flux 20MW/m 2 , ion fluence 1031/m 2 , pulse duration 106 sec. These goals of plasma exposure in MPEX are well beyond those achieved in magnetic fusion experimental devices. Successfully achieving these high power steady state conditions for long pulses requires operational control of the heating and particle sources and the plasma flux to the walls and target. The MPEX AI Hot Spot Controller, proposed in this project, will help achieve the operational milestones of MPEX. The MPEX device will begin commissioning at the end of FY26. A smaller proto-MPEX was operated for 14,666 plasma discharges and will resume operation in September of 2025 as proto-MPEX-lite, with reduced capability, to test a new window for the Helicon plasma source. The proto-MPEX data has undergone surrogate modeling with machine learning methods (R. Archibald, 2022 IEEE International Conference on Big Data). This proto-MPEX data will be used to begin development of the AI digital twins described in this white paper. The scientific mission of MPEX is to qualify materials of different composition for use in the high energy and plasma flux conditions of a fusion power plant. The materials exposed in MPEX will in some cases be exposed to high neutron fluxes at other ORNL facilities to measure the changes to their PMI properties. The targets exposed in MPEX will be transported under vacuum to a Surface Analysis Station (SAS). The SAS will be equipped with the following diagnostics: Focused Ion Beam (FIB) for trench milling, 100-400 angstrom resolution scanning electron microscope (SEM), surface mapping x-ray spectrometer, high resolution camera, and a future upgrade to a laser induced breakdown spectroscopy quadruple mass spectrometer (LIBS-QMS). The MPEX experiments will generate diverse pre- and post-exposure measurement data of detailed material properties down to the crystal grain level in 3D for post-exposure assessment of PMI damage (e.g. cracking, melting, erosion and redeposition of the material). Physics models for the PMI, and how the material composition and manufacturing impact its performance under high energy plasma exposure, need to be validated with MPEX data to guide the selection of new candidate materials. Our vision for the MPEX AI Digital Twins project is to supply experimental and physics model simulation data to train Artificial Intelligence (AI) models for data processing, analysis, operational control, PMI and materials simulation to maximize the scientific output of the MPEX device. Ultimately, an AI digital twin of MPEX material assessment metrics for tested and synthetic material types with simulated PMI will be trained by the AI Modeling Teams on the experimental and physics simulation data submitted to the American Science Cloud by this project. A purely empirical search for the best material is inefficient given the finite number of samples that can be tested on MPEX. In order to expand the material properties database for training the MPEX Material Assessment AI Digital Twin, and to gain physics understanding of the PMI processes, physics models of the material properties and PMI processes are required. The physics simulations provide detailed simulation data, like impact angles for plasma ions, sputtering yields, transport of the ionized sputtered target material in the plasma, and redeposition locations. This simulation data expands the measurement data for deeper physics understanding. The experimental data is essential to validate the PMI and material structure simulation models. The validated models can then be used to generate new simulation data of MPEX material assessments for synthetic material compositions that have not been exposed in MPEX. These predictive simulations, plus the whole experimental dataset, will be used to train the MPEX Material Assessment AI Digital Twin allowing a rapid generative AI search for new materials with reduced PMI damage by interpolating the domain of the training set. These new optimum materials can be simulated with the physics codes and/or tested in MPEX. The ability of AI neural networks to interpolate multi-dimensional parameter spaces and generate virtual data is exploited for a more efficient search for optimum materials. The advent of the Transformational AI Models Consortium (TAIMC) is an opportunity to engage with state of the art private and public AI developers to achieve the goals of the AI digital twins and AI accelerated physics models proposed in this project. Our partners at ORNL from the Advance Scientific Computing Research (ASCR) organization will collaborate in accelerating the integrated plasma material interaction simulation framework. This simulation framework will provide a platform for generating simulation data across a range of physical fidelities, including hybrid methods that produce multi-fidelity results. This data will be leveraged for AI model development, both for generation of surrogates and the automation of simulation campaigns. A part of the research below will include collaborative efforts with the TAIMC to (i) adapt data storage approaches to ensure AI-readiness, (ii) provide a protypical exemplar to inform and exercise constructed workflows, and (iii) generate and share data, using the TAIMC unified AI data standard, for foundational models that will be trained from multiple sources across the DOE complex. We will also collaborate with the TAIMC, as well as the planned AI modeling teams, to develop approaches for reducing the cost of data generation. These include tailored multi-fidelity approaches as well as fine-tuning strategies to augment general, large-scale foundational models.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗