SEARCH · Engineering Papers

Results for “Few Shot Learning”

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.

SourceResearch connectionFrom yearThrough year

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

At least 73 records · Page 4

All sources NASA NTRS DOE OSTI

DOE OSTI2025

Temporal Forecasting of Distributed Temperature Sensing in a Thermal Hydraulic System With Machine Learning and Statistical Models

We benchmark performance of long-short term memory (LSTM) network machine learning model and autoregressive integrated moving average (ARIMA) statistical model in temporal forecasting of distributed temperature sensing (DTS). Data in this study consists of fluid temperature transient measured with two co-located Rayleigh scattering fiber optic sensors (FOS) in a forced convection mixing zone of a thermal tee. We treat each gauge of a FOS as an independent temperature sensor. We first study prediction of DTS time series using Vanilla LSTM and ARIMA models trained on prior history of the same FOS that is used for testing. The results yield maximum absolute percentage error (MaxAPE) and root mean squared percentage error (RMSPE) of 1.58% and 0.06% for ARIMA, and 3.14% and 0.44% for LSTM, respectively. Next, we investigate zero-shot forecasting (ZSF) with LSTM and ARIMA trained on history of the co-located FOS only, which is advantageous when limited training data is available. The ZSF MaxAPE and RMSPE values for ARIMA are comparable to those of the Vanilla use case, while the error values for LSTM increase. We show that in ZSF, performance of LSTM network can be improved by training on most correlated gauges between the two FOS, which are identified by calculating the Pearson correlation coefficient. The improved ZSF MaxAPE and RMSPE for LSTM are 4.4% and 0.33%, respectively. Performance of ZSF LSTM can be further enhanced through transfer learning (TL), where LSTM is re-trained on a subset of the FOS that is the target of forecasting. We show that LSTM pre-trained on correlated dataset and re-trained on 30% of testing target dataset achieves MaxAPE and RMSPE values of 2.32% and 0.28%, respectively.

ARIMA↗

DOE OSTI2025

A framework to evaluate machine learning crystal stability predictions

The rapid adoption of machine learning in various scientific domains calls for the development of best practices and community agreed-upon benchmarking tasks and metrics. We present Matbench Discovery as an example evaluation framework for machine learning energy models, here applied as pre-filters to first-principles computed data in a high-throughput search for stable inorganic crystals. We address the disconnect between (1) thermodynamic stability and formation energy and (2) retrospective and prospective benchmarking for materials discovery. Alongside this paper, we publish a Python package to aid with future model submissions and a growing online leaderboard with adaptive user-defined weighting of various performance metrics allowing researchers to prioritize the metrics they value most. To answer the question of which machine learning methodology performs best at materials discovery, our initial release includes random forests, graph neural networks, one-shot predictors, iterative Bayesian optimizers and universal interatomic potentials. We highlight a misalignment between commonly used regression metrics and more task-relevant classification metrics for materials discovery. Accurate regressors are susceptible to unexpectedly high false-positive rates if those accurate predictions lie close to the decision boundary at 0 eV per atom above the convex hull. The benchmark results demonstrate that universal interatomic potentials have advanced sufficiently to effectively and cheaply pre-screen thermodynamic stable hypothetical materials in future expansions of high-throughput materials databases.

Riebesell, Janosh↗

DOE OSTI2025

Accessible, uniform protein property prediction with a scikit-learn based toolset AIDE

Summary Protein property prediction via machine learning with and without labeled data is becoming increasingly powerful, yet methods are disparate and capabilities vary widely over applications. The software presented here, “Artificial Intelligence Driven protein Estimation (AIDE)”, enables instantiating, optimizing, and testing many zero-shot and supervised property prediction methods for variants and variable length homologs in a single, reproducible notebook or script by defining a modular, standardized application programming interface (API), i.e. drop-in compatible with scikit-learn transformers and pipelines. Availability and implementation AIDE is an installable, importable python package inheriting from scikit-learn classes and API and is installable on Windows, Mac, and Linux. Many of the wrapped models internal to AIDE will be effectively inaccessible without a GPU, and some assume CUDA. The newest stable, tested version can be found at https://github.com/beckham-lab/aide_predict and a full user guide and API reference can be found at https://beckham-lab.github.io/aide_predict/. Static versions of both at the time of writing can be found on Zenodo.

36 MATERIALS SCIENCE↗

DOE OSTI2025

A hybrid neural architecture: Online attosecond x-ray characterization

The emergence of high-repetition-rate x-ray free-electron lasers (XFELs), such as SLAC’s LCLS-II, serves as our canonical example for autonomous controls that necessitate high-throughput diagnostics paired with streaming computational pipelines capable of single-shot analysis with extremely low latency. We present the deterministic characterization with an integrated parallelizable hybrid resolver architecture, a hybrid machine learning framework designed for fast, accurate analysis of XFEL diagnostics using angular streaking-based sinogram images. This architecture integrates convolutional neural networks and bidirectional long short-term memory models to denoise input, identify x-ray sub-spike features, and extract sub-spike relative delays with sub-30 attosecond temporal resolution. Deployed on low-latency hardware, it achieves over 10 kHz throughput with 168.3 μs inference latency, indicating scalability to 14 kHz with field-programmable gate array integration. By transforming regression tasks into classification problems and leveraging optimized error encoding, we achieve high precision with low-latency performance that is critical for real-time streaming event selection and experimental control feedback signals. This represents a key development in real-time control pipelines for next-generation autonomous science, generally, and high repetition-rate x-ray experiments in particular.

Accelerator Physics (physics.acc-ph)↗

DOE OSTI2024

Prediction of laser beam spatial profiles in a high-energy laser facility by use of deep learning

We adapt the significant advances achieved recently in the field of generative artificial intelligence/machine-learning to laser performance modeling in multipass, high-energy laser systems with application to high-shot-rate facilities relevant to inertial fusion energy. Advantages of neural-network architectures include rapid prediction capability, data-driven processing, and the possibility to implement such architectures within future low-latency, low-power consumption photonic networks. Four models were investigated that differed in their generator loss functions and utilized the U-Net encoder/decoder architecture with either a reconstruction loss alone or combined with an adversarial network loss. We achieved inference times of 1.3 ms for a 256 × 256 pixel near-field beam with errors in predicted energy of the order of 1% over most of the energy range. It is shown that prediction errors are significantly reduced by ensemble averaging the models with different weight initializations. These results suggest that including the temporal dimension in such models may provide accurate, real-time spatiotemporal predictions of laser performance in high-shot-rate laser systems.

47 OTHER INSTRUMENTATION↗

DOE OSTI2026

Latent Twins

Over the past decade, scientific machine learning has transformed the development of mathematical and computational frameworks for analyzing, modeling, and predicting complex systems. From inverse problems to numerical partial differential equations (PDEs), dynamical systems, and model reduction, these advances have pushed the boundaries of what can be simulated. Yet they have often progressed in parallel, with representation learning and algorithmic solution methods evolving largely as separate pipelines. With Latent Twins, we propose a unifying mathematical framework that creates a hidden surrogate in latent space for the underlying equations. Whereas digital twins mirror physical systems in the digital world, Latent Twins mirror mathematical systems in a learned latent space governed by operators. Through this lens, classical modeling, inversion, model reduction, and operator approximation all emerge as special cases of a single principle. We establish the fundamental approximation properties of Latent Twins for both ordinary differential equations (ODEs) and PDEs and demonstrate the framework across three representative settings: (i) canonical ODEs, capturing diverse dynamical regimes; (ii) a PDE benchmark using the shallow-water equations, contrasting Latent Twin simulations with deep operator network and forecasts with a four-dimensional variational method baseline; and (iii) a challenging real-data geopotential reanalysis dataset, reconstructing and forecasting from sparse, noisy observations. Latent Twins provide a compact, interpretable surrogate for solution operators that evaluate across arbitrary time gaps in a single-shot, while remaining compatible with scientific pipelines such as assimilation, control, and uncertainty quantification. Looking forward, this framework offers scalable, theory-grounded surrogates that bridge data-driven representation learning and classical scientific modeling across disciplines.

Latent Twins↗

DOE OSTI2024

Deep learning based x-ray spectrometer for high repetition rate characterization of betatron radiation

Betatron radiation produced from a laser-wakefield accelerator is a broadband, hard x-ray (>1 keV) source that has been used in a variety of applications in medicine, engineering, and fundamental science. Further development and optimization of stable, high repetition rate (HRR) (>1 Hz) betatron sources will provide a means to extend their application base to include single-shot dynamical measurements of ultrafast processes or dense materials. Recent advances in laser technology used in such experiments have enabled increases in shot-rate and system stability, providing improved statistical analysis and detailed parameter scans. However, unique challenges exist at high repetition rate, where data throughput and source optimization are now limited by diagnostic acquisition rates and analysis. Here, we present the development of a machine-learning algorithm for the real-time analysis of betatron radiation. We report on the fielding of this deep learning algorithm for online source characterization at the Institut National de la Recherche Scientifique's Advanced Laser Light Source. By fine-tuning an algorithm originally trained on a fully synthetic dataset using a subset of experimental data, the algorithm can predict the betatron critical energy with a percent error of 7.2 % with a reconstruction time of 1.5 ms, providing a valuable tool for real-time, multi-objective optimization at HRR.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗

DOE OSTI2025

Predicting fusion ignition at the National Ignition Facility with physics-informed deep learning

Here, 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.

Spears, Brian K. [Lawrence Livermore National Labo↗

NASA NTRS2006

Impact Testing of Orbiter Thermal Protection System Materials

This viewgraph presentation reviews the impact testing of the materials used in designing the shuttle orbiter thermal protection system (TPS). Pursuant to the Columbia Accident Investigation Board recommendations a testing program of the TPS system was instituted. This involved using various types of impactors in different sizes shot from various sizes and strengths guns to impact the TPS tiles and the Leading Edge Structural Subsystem (LESS). The observed damage is shown, and the resultant lessons learned are reviewed.

Kerr, Justin↗

DOE OSTI2025

Real-time inference and extrapolation with Time-Conditioned UNet: Applications in hypersonic flows, incompressible flows, and global temperature forecasting

Neural Operators are fast and accurate surrogates for nonlinear mappings between functional spaces within training domains. Extrapolation beyond the training domain remains a grand challenge across all application areas. We present Time-Conditioned UNet (TC-UNet) as an operator learning method to solve time-dependent PDEs continuously in time without any temporal discretization, including in extrapolation scenarios. TC-UNet incorporates the temporal evolution of the PDE into its architecture by combining a parameter conditioning approach with the attention mechanism from the Transformer architecture. After training, TC-UNet makes real-time inferences on an arbitrary temporal grid. We demonstrate its extrapolation capability on a climate problem by estimating the global temperature for several years and also for inviscid hypersonic flow around a double cone. We propose different training strategies involving temporal bundling and sub-sampling. We demonstrate performance improvements for several benchmarks, performing extrapolation for long time intervals and zero-shot super-resolution time.

Deep learning↗

DOE OSTI2024

Source localization for neutron imaging systems using convolutional neural networks

The nuclear imaging system at the National Ignition Facility (NIF) is a crucial diagnostic for determining the geometry of inertial confinement fusion implosions. The geometry is reconstructed from a neutron aperture image via a set of reconstruction algorithms using an iterative Bayesian inference approach. An important step in these reconstruction algorithms is finding the fusion source location within the camera field-of-view. Currently, source localization is achieved via an iterative optimization algorithm. In this paper, we introduce a machine learning approach for source localization. Specifically, we train a convolutional neural network to predict source locations given a neutron aperture image. We show that this approach decreases computation time by several orders of magnitude compared to the current optimization-based source localization while achieving similar accuracy on both synthetic data and a collection of recent NIF deuterium–tritium shots.

47 OTHER INSTRUMENTATION↗

DOE OSTI2025

Optimization of simulated high-field side lower hybrid current drive coupling using machine learning predictions of scrape-off layer density

Lower hybrid current drive (LHCD) is a potential source of non-inductive off-axis current drive (CD) for tokamaks. Although LHCD has been successfully deployed on a number of tokamaks, it is highly sensitive to the scrape-off layer (SOL) conditions local to the LHCD launcher. Large gaps between the launcher and plasma core, SOL turbulence, or edge density perturbations due to edge-localized modes can hamper CD or cause large reflected power. These coupling issues in part motivated the installation of an LHCD launcher on the high-field side (HFS) of DIII-D. On the HFS, the SOL is less turbulent and more controllable compared to the low-field side. This quiescence may result in more predictable edge conditions and thus a more predictable CD. Here, in this work, HFS SOL reflectometry measurements are predicted from global plasma parameters using machine learning models. The SOL predictions coupled with the full-wave simulation of the LHCD launcher allow for the prediction of reflected power, directivity, and arcing risk before the discharge. Launcher performance is then optimized using multi-objective Bayesian optimization, finding the shot parameters that result in an optimal SOL density that maximizes CD while minimizing the risk of arcing. The predictions and optimizations of LHCD performance are then accelerated using a surrogate model of the full-wave LHCD simulation.

Bayesian optimization↗

DOE OSTI2024

Data-driven prediction of scaling and ignition of inertial confinement fusion experiments

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 10× 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.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗

DOE OSTI2024

Source localization for neutron imaging systems using convolutional neural networks

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗

DOE OSTI2024

Developing time-resolved x-ray diffraction diagnostics at the National Ignition Facility (invited)

As part of a program to measure phase transition timescales in materials under dynamic compression, we have designed new x-ray imaging diagnostics to record multiple x-ray diffraction measurements during a single laser-driven experiment. Our design places several ns-gated hybrid CMOS (hCMOS) sensors within a few cm of a laser-driven target. The sensors must be protected from an extremely harsh environment, including debris, electromagnetic pulses, and unconverted laser light. Another key challenge is reducing the x-ray background relative to the faint diffraction signal. Building on the success of our predecessor (Target Diffraction In Situ), we implemented a staged approach to platform development. First, we built a demonstration diagnostic (Gated Diffraction Development Diagnostic) with two hCMOS sensors to confirm we could adequately protect them from the harsh environment and also acquire acceptable diffraction data. This allowed the team to quickly assess the risks and address the most significant challenges. Here, we also collected scientifically useful data during development. Leveraging what we learned, we recently developed a much more ambitious instrument (Flexible Imaging Diffraction Diagnostic for Laser Experiments) that can field up to eight hCMOS sensors in a flexible geometry and participate in back-to-back shots at the National Ignition Facility (NIF). The design also allows for future iterations, such as faster hCMOS sensors and an embedded x-ray streak camera. The enhanced capabilities of the new instrument required a much more complex design, and the unexpected issues encountered on the first few shots at NIF remind us that complexity has consequences. Our progress in addressing these challenges is described herein, as is our current focus on improving data quality by reducing x-ray background and quantifying the uncertainties of our diffraction measurements.

36 MATERIALS SCIENCE↗

DOE OSTI2026

Lighting a Star on Earth—Again and Again

At Lawrence Livermore National Laboratory’s (LLNL) National Ignition Facility (NIF), scientists are learning what it takes to keep a fusion reaction burning. Their latest experiments, presented this week at the American Physical Society’s Division of Plasma Physics annual meeting, build on a series of successful ignition shots to reveal how capsule design and laser precision can sustain record-setting performance. At NIF, researchers are consistently producing plasmas dominated by self-heating from fusion reactions, achieving target gain greater than two — meaning the fusion output energy exceeds twice the energy used to initiate the reaction. Using the world’s most energetic laser to create these conditions, LLNL scientists can explore the detailed physics of ignition and burn that underpin the Laboratory’s stockpile modernization mission. “It’s a bit like lighting a campfire with a match and a single breath,” said LLNL physicist David Schlossberg, who is co-leading the work. “If you have too little fuel, it burns out quickly; too much, and it won’t light at all. We’ve found the balance between capsule mass and drive strength that starts the burn and keeps it going efficiently.” NIF is the only laboratory in the world to have achieved fusion ignition, a historic breakthrough first realized in December 2022. Since then, the facility has repeated ignition ten times, most recently in October 2025, demonstrating the robustness of the experimental platform and the reproducibility of ignition physics.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗

DOE OSTI2025

AI foundation models for experimental fusion tasks

Artificial Intelligence (AI) foundation models, while successful in various domains of language, speech, and vision, have not been adopted in production for fusion energy experiments. This brief paper presents how AI foundation models can be used for fusion energy diagnostics, enabling, for example, visual automated logbooks to provide greater insights into chains of plasma events in a discharge, in time for between-shot analysis.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗

DOE OSTI2025

Exploring scenarios for enhanced fuel compression and performance on the National Ignition Facility with machine-learning-aided design techniques

Recent fusion experiments on the National Ignition Facility (NIF) have achieved ignition, producing multi-MJ fusion yields for input laser energies of roughly 2 MJ [Abu-Shawareb et al., Phys. Rev. Lett. 132, 065102 (2024)]. Building on the success of the target designs that have achieved ignition, we explore new implosion scenarios predicted to generate significantly more compression of the dense DT ice layer and correspondingly higher yields while preserving many of the key physics characteristics of present-day ignition designs. Our main result is a novel 3-shock implosion scheme that effectively minimizes the shock-induced entropy in the dense, accelerating DT shell and maximizes the resulting fuel compression subject to a fixed leading shock strength consistent with present-day ignition experiments, which is necessary to melt the crystalline high-density carbon ablator. Compared to the first NIF experiment to fulfill Lawson's ignition criterion, shot N210808 [Abu-Shawareb et al., Phys. Rev. Lett. 129, 075001 (2022)], our design exhibits a 40% increase in simulated peak areal density (ρR) and a 5× increase in 1D fusion yield using a 4% lighter ablator and identical DT payloads. We also present a complete integrated 2D hohlraum design and laser pulse specifications capable of generating the desired 3-shock drive and maintaining control of the low-mode capsule implosion symmetry, where the increase in simulated 2D yield relative to N210808 is > 10×. This new implosion regime was discovered with help from a machine-learning-enabled capsule design optimization framework. We outline the workflow this automated tool uses to identify improved design candidates by running several rounds of capsule simulations, constructing a surrogate model mapping input variations to key physics output quantities, and querying the resulting statistical model to propose adjustments to the x-ray drive and capsule to reach a set of physics objectives prescribed by the designer.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗