Engineering Papers⌕ Search

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.

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

At least 163 records · Page 9
All sourcesNASA NTRSDOE OSTI
DOE OSTI2026

A unified large language model–based framework for heterogeneous PV image diagnosis

With advances in imaging technologies, modern photovoltaic (PV) systems generate large volumes of heterogeneous image data, including visible, electroluminescence (EL), and infrared (IR) images. Existing PV image analysis models, particularly deep learning approaches, are typically task-specific and lack cross-modality generalization. To address this limitation, this paper proposes an open-source large language model (LLM)–based unified framework for heterogeneous PV image diagnostics. Through task-aware diagnostic prompting, the framework enables analysis of visible, EL, and IR images within a single pipeline, supporting both zero-shot and few-shot inference and binary and multiclass classification. It is compatible with state-of-the-art multimodal LLMs, including ChatGPT, Gemini, Claude, Qwen, and CLIP. The framework is evaluated on PV module condition classification (clean, soiling, snow, hail, and bird droppings) using visible images, cell crack detection using EL images, and hotspot detection using IR images. GPT-5.1 in few-shot mode achieves the best performance, with classification accuracy exceeding 97.3%. Open-source models such as Qwen and CLIP also deliver competitive results on visible images (around 90% accuracy), though their performance is more limited on EL and IR modalities. On the full ELPV dataset, the framework achieves 83.5% zero-shot accuracy, within 2.8% of the supervised CNN baseline, confirming scalability to larger benchmarks. Practical aspects such as reproducibility, response latency, and confidence estimation are systematically analyzed. The framework operates across PV image modalities without modality- or task-specific training, making it well suited as a rapid pre-screening tool to support downstream detailed diagnostics. A benchmark dataset of diverse labeled PV images is also released.

Li, Baojie↗
DOE OSTI2025

Remote Sensing and Fluxes Upscaling for Real-world Impact (Workshop Report)

The "Remote Sensing and Fluxes Upscaling for Real-world Impact" workshop, held on July 9-10, 2024, at Lawrence Berkeley National Lab, was a collaborative effort led by the AmeriFlux Management Project, NEON, and the Carbon Dew Community of Practice. The event brought together over 200 registrants and approximately 100 attendees each day, including leading experts, researchers, and practitioners. The primary focus was on bridging the gap between cutting-edge research and practical applications in environmental monitoring by integrating remote sensing and flux data. Key themes included the importance of site-level measurements for validating remote sensing products, providing nature-based climate solutions, and addressing challenges such as instrument costs and the need for standardized methods. At the regional scale, discussions centered on addressing spatial heterogeneity and using high-resolution remote sensing and machine learning methods to enhance data interpretation. Global scale challenges included data consistency, gap filling, and accurate emission source identification, with opportunities for international collaboration and standardized practices to improve global carbon budget assessments. The workshop emphasized the critical need for integrating data across local, regional, and global scales through explicit scale-matching and developed a workflow for scaling flux data using "straight shot" and "explicit nesting" approaches. The event highlighted the importance of connecting scientific research with real-world applications in carbon, energy, and water management, ensuring that advancements translate into tangible societal benefits. These insights will guide future research, technology transfer, and collaboration, maximizing the potential of environmental fluxes to address real-world challenges.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2022

Reconfigurable perovskite nickelate electronics for artificial intelligence

Reconfigurable devices offer the ability to program electronic circuits on demand. Here, in this work, we demonstrated on-demand creation of artificial neurons, synapses, and memory capacitors in post-fabricated perovskite NdNiO 3 devices that can be simply reconfigured for a specific purpose by single-shot electric pulses. The sensitivity of electronic properties of perovskite nickelates to the local distribution of hydrogen ions enabled these results. With experimental data from our memory capacitors, simulation results of a reservoir computing framework showed excellent performance for tasks such as digit recognition and classification of electrocardiogram heartbeat activity. Using our reconfigurable artificial neurons and synapses, simulated dynamic networks outperformed static networks for incremental learning scenarios. The ability to fashion the building blocks of brain-inspired computers on demand opens up new directions in adaptive networks.

75 CONDENSED MATTER PHYSICS, SUPERCONDUCTIVITY AND↗
DOE OSTI2026

Online LIBS–ML Framework for Dynamic Characterization of Heterogeneous Waste-Derived Gasification Feedstocks

LIBS−ML framework for real time feedstock characterization during continuous conveyor transport Heterogeneous waste derived feedstocks (e.g., waste coal, biomass and blends) introduce rapid variability in heating value and ash chemistry that affect gasifier operation, yet conventional laboratory characterization techniques are too slow to support proactive control. To address this gap, this study reports on an online, in situ, dynamic characterization framework that couple’s laser-induced breakdown spectroscopy (LIBS) with leakage safe machine learning (ML) regression to deliver real time, decision quality predictions of gasifier relevant properties. A controlled sample matrix spanning two different waste coals, two different biomasses, and engineered blends under two particle size conditions were constructed and benchmarked using standardized laboratory analyses for proximate/ultimate properties and ash composition. LIBS spectra were acquired dynamically as material flowed on a conveyor belt, using high energy 1064 nm laser ablation and shot averaging to improve repeatability and precision. Supervised regression models (multi layer perceptron (MLP) /artificial neural network (ANN), random forest (RF), and support vector regression (SVR)) and an optimized weighted ensemble were trained on emission line feature sets using nested cross validation with Bayesian hyperparameter tuning and validated against an independent hold out set. The proposed LIBS−ML workflow achieves near laboratory predictive fidelity across parametric targets (including higher heating value (HHV), ash content, fixed carbon, sulfur, major ash forming oxides, and initial deformation temperature (IDT)), with the weighted ensemble providing a robust default predictor under dynamic measurement conditions. These results demonstrate a practical pathway for real time feedstock characterization that can enable feedforward adjustments and more resilient gasifier operation for variable quality waste derived fuels.

Biomass↗
DOE OSTI2022

Real-time X-ray phase-contrast imaging using SPINNet—a speckle-based phase-contrast imaging neural network

X-ray phase-contrast imaging has become indispensable for visualizing samples with low absorption contrast. In this regard, speckle-based techniques have shown significant advantages in spatial resolution, phase sensitivity, and implementation flexibility compared with traditional methods. However, the computational cost associated with data inversion has hindered their wider adoption. By exploiting the power of deep learning, we developed a speckle-based phase-contrast imaging neural network (SPINNet) that significantly improves the imaging quality and boosts the phase retrieval speed by at least 2 orders of magnitude compared to existing methods. To achieve this performance, we combined SPINNet with a coded-mask-based technique, an enhanced version of the speckle-based method. Using this scheme, we demonstrate the simultaneous reconstruction of absorption and phase images on the order of 100 ms, where a traditional correlation-based analysis would take several minutes even with a cluster. In addition to significant improvement in speed, our experimental results show that the imaging and phase retrieval quality of SPINNet outperform existing single-shot speckle-based methods. Furthermore, we successfully demonstrate SPINNet application in x-ray optics metrology and 3D x-ray phase-contrast tomography. Our result shows that SPINNet could enable many applications requiring high-resolution and fast data acquisition and processing, such as in situ and in operando 2D and 3D phase-contrast imaging and real-time at-wavelength metrology and wavefront sensing.

36 MATERIALS SCIENCE↗
DOE OSTI2021

Data-Driven Multi-agent Deep Reinforcement Learning for Distribution System Decentralized Voltage Control with High Penetration of PVs

This paper proposes a novel model-free/data-driven centralized training and decentralized execution multi-agent deep reinforcement learning (MADRL) framework for distribution system voltage control with high penetration of PVs. The proposed MADRL can coordinate both the real and reactive power control of PVs with existing static var compensators and battery storage systems. Unlike the existing DRL-based voltage control methods, our proposed method does not rely on a system model during both the training and execution stages. This is achieved by developing a new interaction scheme between the surrogate modeling of the original system and the multi-agent soft actor critic (MASAC) MADRL algorithm. In particular, the sparse pseudo-Gaussian process with a few-shots of measurements is utilized to construct the surrogate model of the original environment, i.e., power flow model. This is a data-driven process and no model parameters are needed. Furthermore, the MASAC enabled MADRL allows to achieve better scalability by dividing the original system into different voltage control regions with the aid of real and reactive power sensitivities to voltage, where each region is treated as an agent. This also serves as the foundation for the centralized training and decentralized execution, thus significantly reducing the communication requirements as only local measurements are required for control. Comparative results with other alternatives on the IEEE 123-nodes and 342-nodes systems demonstrate the superiority of the proposed method.

14 SOLAR ENERGY↗
DOE OSTI2026

Characterization and automated optimization of laser-driven proton beams from converging liquid sheet jet targets

Compact, stable, and versatile laser-driven ion sources hold great promise for applications ranging from medicine to materials science and fundamental physics. While single-shot sources have demonstrated favorable beam properties, including the peak fluxes necessary for several applications, high-repetition-rate operation will be necessary to generate and sustain the high average flux needed for many of the most exciting applications of laser-driven ion sources. Further, to navigate through the high-dimensional space of laser and target parameters toward experimental optima, it is essential to develop ion acceleration platforms compatible with machine learning techniques and capable of autonomous real-time optimization. Here, we present a multi-Hz ion acceleration platform employing a liquid sheet jet target. We characterize the laser-plasma interaction and the laser-driven proton beam across a variety of key parameters governing the interaction using an extensive suite of online diagnostics. We also demonstrate real-time, closed-loop optimization of the ion beam maximum energy by tuning the laser wave front using a Bayesian optimization scheme. This approach increased the maximum proton energy by 11% compared to a manually optimized wave front by enhancing the energy concentration within the laser focal spot, demonstrating the potential for closed-loop optimization schemes to tune future ion accelerators for robust high-repetition-rate operation.

Glenn, G. D. [SLAC National Accelerator Laboratory↗
DOE OSTI2026

Benchmarking the performance of uncertainty quantification methods for neural network-based interatomic potentials

Machine-learned interatomic potentials (ML-IAPs) continue to gain popularity as accurate, computationally efficient replacements for traditional, physics-based interatomic potentials and expensive ab initio methods. Uncertainty quantification (UQ) of ML-IAPs is a growing area of research as UQ is critical in many applications of IAPs, such as developing curated datasets, active learning-based data augmentation, self-improving models, and estimating the uncertainty of molecular dynamics simulations. In this paper, we construct and benchmark a series of different neural network potentials (NNPs) with varying network architectures to determine the performance of these models with respect to both the mean and uncertainty calibration error. Each NNP method is specifically designed to predict either epistemic or aleatoric uncertainty with particular focus on the differences in behavior between the epistemic and aleatoric uncertainty estimates. We benchmark these methods using multiple datasets common in the ML-IAP literature. The results show that the aleatoric uncertainty from single-shot model architectures is a competitive alternative to ensemble-based epistemic uncertainty predictions in regions of sufficient data-density. However, in regions where the representative data is sparse, aleatoric uncertainty models tend to overpredict and epistemic methods tend to underpredict the actual model error. We conclude that the type of UQ is crucial when discussing performance of probabilistic model results as different methods have different performance characteristics depending on the regime in which they are evaluated. Therefore, the type of UQ method should be carefully evaluated against both the data characteristics and requirements for the intended application.

97 MATHEMATICS AND COMPUTING↗
NASA NTRS2006

Providing Housing, Food and Medical Support for 25,000 Katrina Evacuees with 12 Hours Notice: The Harris County Medical Support of the Superdome Evacuees

Hurricane Katrina was responsible for trapping 25,000 people in the New Orleans Superdome and isolating many others throughout Louisiana and Mississippi. The transport of these evacuees to the Reliant Park (Houston, Texas) used 500 buses each containing about 55 people. Processing the arriving evacuees included addressing their health status and medical needs as follows: an initial triage at disembarkation, a secondary triage in the Reliant Astrodome and Center, and definitive clinical care in the Reliant Arena "Katrina" Clinic. Baylor College of Medicine (BCM) physicians boarded buses and identified the sickest for emergency transport to Harris County Hospital District (HCHD) hospitals. BCM departments represented included pediatrics, family and community medicine, internal medicine, radiology, obstetrics and gynecology, orthopedics, surgery, and psychiatry. Astrodome and Center triage was managed by BCM physicians and staffed by HCHD Nurses and volunteers from Texas and beyond. The Reliant Astrodome, Center and Arena reached peak headcounts of 15,000,4500, and 2500, respectively Most evacuees visiting the triage sites in the Astrodome and Center were treated using "over-the-counter" medications with the remaining being transported to the "Katrina" clinic. The clinic was equipped with a lab, pharmacy, digital X-ray, and ultrasound machines in addition to electronic patient records created using 80 computer terminals. The Katrina clinic saw more than 15,000 patients during 15 days of operations (2,000 on the first full day), administered 10,000 tetanus shots, and filled thousands of prescriptions. At the peak of operations, the clinic saw 150 patients/hour with 25 physicians scheduled for each 12-hour shift. Approximately 900 people were transported to hospital emergency rooms. Within 3 weeks of arriving at the Reliant Park facilities, more than 90% of the families found permanent housing, enrolled children in schools, and found work. Using data obtained from manual and electronic medical records, this presentation will document the major milestones and lessons learned from this extraordinary project to help the Katrina evacuees.

Hamilton, Douglas↗
DOE OSTI2022

Foundation Models of Scientific Knowledge for Chemistry: Opportunities, Challenges and Lessons Learned

Foundation models pre-trained on large corpora demonstrate significant gains across many natural language processing tasks and domains e.g., law, healthcare, education, etc. However, only limited efforts have investigated the opportunities and limitations of applying these powerful models to science and security applications. In this work we develop foundation models of scientific knowledge for chemistry to augment scientists with the advanced ability to perceive and reason at scale previously unimagined. Specifically, we build large-scale (1.47B parameter) general-purpose models for chemistry that can be effectively used to perform a wide range of in-domain and out-of-domain tasks. Evaluating these models in a zero-shot setting, we analyze the effect of model and data scaling, knowledge depth, and temporality on model performance in context of model training efficiency. Our novel findings demonstrate that (1) model size significantly contributes to the task performance when evaluated in a zero-shot setting; (2) data quality (aka diversity) affects model performance more than data quantity; (3) similarly, unlike previous work (Luu et al., 2021) temporal order of the documents in the corpus boosts model performance only for specific tasks, e.g., SciQ; and (4) models pre-trained from scratch perform better on in-domain tasks than those tuned from general-purpose models like Open AI’s GPT-2.

Foundation Models, Chemistry↗
DOE OSTI2022

Automatic Detection of Defects in High-Reliability Components

Disastrous consequences can result from defects in manufactured parts—particularly the high consequence parts developed at Sandia. Identifying flaws in as-built parts can be done with nondestructive means, such as X-ray Computed Tomography (CT). However, due to artifacts and complex imagery, the task of analyzing the CT images falls to humans. Human analysis is inherently unreproducible, unscalable, and can easily miss subtle flaws. We hypothesized that deep learning methods could improve defect identification, increase the number of parts that can effectively be analyzed, and do it in a reproducible manner. We pursued two methods: 1) generating a defect-free version of a scan and looking for differences (PandaNet), and 2) using pre-trained models to develop a statistical model of normality (Feature-based Anomaly Detection System: FADS). Both PandaNet and FADS provide good results, are scalable, and can identify anomalies in imagery. In particular, FADS enables zero-shot (training-free) identification of defects for minimal computational cost and expert time. It significantly outperforms prior approaches in computational cost while achieving comparable results. FADS’ core concept has also shown utility beyond anomaly detection by providing feature extraction for downstream tasks.

47 OTHER INSTRUMENTATION↗
DOE OSTI2025

Pointing stabilization of a 1 Hz high-power laser via machine learning

Abstract High-power lasers are vital for particle acceleration, imaging, fusion and materials processing, requiring precise control and high-energy delivery. Laser plasma accelerators (LPAs) demand laser positional stability at focus to ensure consistent electron beams in applications such as X-ray free-electron lasers and high-energy colliders. Achieving this stability is especially challenging for the low-repetition-rate lasers in current LPAs. We present a machine learning method that predicts and corrects laser pointing instabilities in real-time using a high-frequency pilot beam. By preemptively adjusting a correction mirror, this approach overcomes traditional feedback limits. Demonstrated on the BELLA petawatt laser operating at the terawatt level (30 mJ amplification), our method achieved root mean square pointing stabilization of 0.34 and 0.59 $\unicode{x3bc} \mathrm{rad}$ in the x and y directions, reducing jitter by 65% and 47%, respectively. This is the first successful application of predictive control for shot-to-shot stabilization in low-repetition-rate laser systems, paving the way for full-energy petawatt lasers and transformative advances across science, industry and security.

Amodio, Alessio↗
DOE OSTI2023

A flexible proton beam imaging energy spectrometer (PROBIES) for high repetition rate or single-shot high energy density (HED) experiments (invited)

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

3D printing↗
DOE OSTI2025

Stochastic noise can be helpful for variational quantum algorithms

Saddle points constitute a crucial challenge for first-order gradient descent algorithms. In notions of classical machine learning, they are avoided, for example, by means of stochastic gradient descent methods. In this work, we provide evidence that the saddle-points problem can be naturally avoided in variational quantum algorithms by exploiting the presence of stochasticity. We prove convergence guarantees and present practical examples in numerical simulations and on quantum hardware. We argue that the natural stochasticity of variational algorithms can be beneficial for avoiding strict saddle points, i.e., those saddle points with at least one negative Hessian eigenvalue. This insight that some levels of shot noise could help is expected to add a new perspective to notions of near-term variational quantum algorithms. Published by the American Physical Society 2025

Liu, Junyu↗
DOE OSTI2024

On the connection between least squares, regularization, and classical shadows

Classical shadows (CS) offer a resource-efficient means to estimate quantum observables, circumventing the need for exhaustive state tomography. Here, we clarify and explore the connection between CS techniques and least squares (LS) and regularized least squares (RLS) methods commonly used in machine learning and data analysis. By formal identification of LS and RLS ``shadows'' completely analogous to those in CS---namely, point estimators calculated from the empirical frequencies of single measurements---we show that both RLS and CS can be viewed as regularizers for the underdetermined regime, replacing the pseudoinverse with invertible alternatives. Through numerical simulations, we evaluate RLS and CS from three distinct angles: the tradeoff in bias and variance, mismatch between the expected and actual measurement distributions, and the interplay between the number of measurements and number of shots per measurement. Compared to CS, RLS attains lower variance at the expense of bias, is robust to distribution mismatch, and is more sensitive to the number of shots for a fixed number of state copies---differences that can be understood from the distinct approaches taken to regularization. Conceptually, our integration of LS, RLS, and CS under a unifying ``shadow'' umbrella aids in advancing the overall picture of CS techniques, while practically our results highlight the tradeoffs intrinsic to these measurement approaches, illuminating the circumstances under which either RLS or CS would be preferred, such as unverified randomness for the former or unbiased estimation for the latter.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗
NASA NTRS2015

Strain Gage Loads Calibration Testing with Airbag Support for the Gulfstream III SubsoniC Research Aircraft Testbed (SCRAT)

This paper describes the design and conduct of the strain-gage load calibration ground test of the SubsoniC Research Aircraft Testbed, Gulfstream III aircraft, and the subsequent data analysis and results. The goal of this effort was to create and validate multi-gage load equations for shear force, bending moment, and torque for two wing measurement stations. For some of the testing the aircraft was supported by three airbags in order to isolate the wing structure from extraneous load inputs through the main landing gear. Thirty-two strain gage bridges were installed on the left wing. Hydraulic loads were applied to the wing lower surface through a total of 16 load zones. Some dead-weight load cases were applied to the upper wing surface using shot bags. Maximum applied loads reached 54,000 lb. Twenty-six load cases were applied with the aircraft resting on its landing gear, and 16 load cases were performed with the aircraft supported by the nose gear and three airbags around the center of gravity. Maximum wing tip deflection reached 17 inches. An assortment of 2, 3, 4, and 5 strain-gage load equations were derived and evaluated against independent check cases. The better load equations had root mean square errors less than 1 percent. Test techniques and lessons learned are discussed.

flight tests↗
DOE OSTI2021

Autonomous reinforcement learning agent for stretchable kirigami design of 2D materials

Abstract Mechanical behavior of 2D materials such as MoS 2 can be tuned by the ancient art of kirigami. Experiments and atomistic simulations show that 2D materials can be stretched more than 50% by strategic insertion of cuts. However, designing kirigami structures with desired mechanical properties is highly sensitive to the pattern and location of kirigami cuts. We use reinforcement learning (RL) to generate a wide range of highly stretchable MoS 2 kirigami structures. The RL agent is trained by a small fraction (1.45%) of molecular dynamics simulation data, randomly sampled from a search space of over 4 million candidates for MoS 2 kirigami structures with 6 cuts. After training, the RL agent not only proposes 6-cut kirigami structures that have stretchability above 45%, but also gains mechanistic insight to propose highly stretchable (above 40%) kirigami structures consisting of 8 and 10 cuts from a search space of billion candidates as zero-shot predictions.

36 MATERIALS SCIENCE↗
DOE OSTI2024

Transformer-powered surrogates close the ICF simulation-experiment gap with extremely limited data

Abstract Recent advances in machine learning, specifically transformer architecture, have led to significant advancements in commercial domains. These powerful models have demonstrated superior capability to learn complex relationships and often generalize better to new data and problems. This paper presents a novel transformer-powered approach for enhancing prediction accuracy in multi-modal output scenarios, where sparse experimental data is supplemented with simulation data. The proposed approach integrates transformer-based architecture with a novel graph-based hyper-parameter optimization technique. The resulting system not only effectively reduces simulation bias, but also achieves superior prediction accuracy compared to the prior method. We demonstrate the efficacy of our approach on inertial confinement fusion experiments, where only 10 shots of real-world data are available, as well as synthetic versions of these experiments.

97 MATHEMATICS AND COMPUTING↗