SEARCH · Engineering Papers

Results for “edge inference”

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 37 records · Page 2

All sources NASA NTRS DOE OSTI

DOE OSTI2025

End-to-end deep learning pipeline for real-time Bragg peak segmentation: from training to large-scale deployment

X-ray crystallography reconstruction, which transforms discrete X-ray diffraction patterns into three-dimensional molecular structures, relies critically on accurate Bragg peak finding for structure determination. As X-ray free electron laser (XFEL) facilities advance toward MHz data rates (1 million images per second), traditional peak finding algorithms that require manual parameter tuning or exhaustive grid searches across multiple experiments become increasingly impractical. While deep learning approaches offer promising solutions, their deployment in high-throughput environments presents significant challenges in automated dataset labeling, model scalability, edge deployment efficiency, and distributed inference capabilities. We present an end-to-end deep learning pipeline with three key components: (1) a data engine that combines traditional algorithms with our peak matching algorithm to generate high-quality training data at scale, (2) a modular architecture that scales from a few million to hundreds of million parameters, enabling us to train large expert-level models offline while deploying smaller, distilled models at the edge, and (3) a decoupled producer-consumer architecture that separates specialized data source layer from model inference, enabling flexible deployment across diverse computing environments. Using this integrated approach, our pipeline achieves accuracy comparable to traditional methods tuned by human experts while eliminating the need for experiment-specific parameter tuning. Although current throughput requires optimization for MHz facilities, our system's scalable architecture and demonstrated model compression capabilities provide a foundation for future high-throughput XFEL deployments.

Wang, Cong↗

DOE OSTI2026

Discovery of Probabilistic Dirichlet-to-Neumann Maps on Graphs

Dirichlet-to-Neumann maps enable the coupling of multiphysics simulations across computational subdomains by ensuring continuity of state variables and fluxes at artificial interfaces. We present a novel method for learning Dirichlet-to-Neumann maps on graphs using Gaussian processes, specifically for problems where the data obey a conservation law arising from an underlying partial differential equation. Our approach combines discrete exterior calculus and nonlinear optimal recovery to infer relationships between vertex and edge values. This framework yields data-driven predictions with uncertainty quantification across the entire graph, even when observations are limited to a subset of vertices and edges. By minimizing the reproducing kernel Hilbert space norm while penalizing kernel complexity through maximum likelihood estimation, our method ensures that the resulting surrogate strictly enforces conservation laws without overfitting. We demonstrate our method on two representative applications: subsurface flow in fracture networks and arterial blood flow. Finally, the results demonstrate that the method maintains high accuracy and well-calibrated uncertainty estimates even under severe data scarcity, highlighting its potential for scientific applications where limited data and reliable uncertainty quantification are critical.

Dirichlet-to-Neumann map↗

DOE OSTI2025

FPGA-accelerated SpeckleNN with SNL for real-time X-ray single-particle imaging

We present the implementation of a specialized version of our previously published unified embedding model, SpeckleNN, for real-time speckle pattern classification in X-ray Single-Particle Imaging (SPI), using the SLAC Neural Network Library (SNL) on an FPGA platform. This hardware realization transitions SpeckleNN from a prototypic model into a practical edge solution, optimized for running inference near the detector in high-throughput X-ray free-electron laser (XFEL) facilities, such as those found at the Linac Coherent Light Source (LCLS). To address the resource constraints inherent in FPGAs, we developed a more specialized version of SpeckleNN. The original model, which was designed for broader classification across multiple biological samples, comprised ~5.6 million parameters. The new implementation, while reducing the parameter count to 64.6K (a 98.8% reduction), focuses on maintaining the model's essential functionality for real-time operation, achieving an accuracy of 90%. Furthermore, we compressed the latent space from 128 to 50 dimensions. This implementation was demonstrated on the KCU1500 FPGA board, utilizing 71% of available DSPs, 75% of LUTs, and 48% of FFs, with an average power consumption of 9.4W according to the Vivado post-implementation report. The FPGA performed inference on a single image with a latency of 45.015 microseconds at a 200 MHz clock rate. In comparison, running the same inference on an NVIDIA A100 GPU resulted in an average power consumption of ~73W and an image processing latency of around 400 microseconds. Our FPGA-accelerated version of SpeckleNN demonstrated significant improvements, achieving an 8.9 × speedup and a 7.8 × reduction in power consumption compared to the GPU implementation. Key advancements include model specialization and dynamic weight loading through SNL, which eliminates the need for time-consuming FPGA design re-synthesis, allowing fast and continuous deployment of models (re)trained online. These innovations enable real-time adaptive classification and efficient vetoing of speckle patterns, making SpeckleNN more suited for deployment in XFEL facilities. This implementation has the potential to significantly accelerate SPI experiments and enhance adaptability to evolving experimental conditions.

47 OTHER INSTRUMENTATION↗

DOE OSTI2024

Bayesian inference of electron density and ion temperature profiles from neutral beam and halo Balmer- α emission at Wendelstein 7-X

By employing Bayesian inference techniques, the full electron density profile from the plasma core to the edge of Wendelstein 7-X (W7-X) is inferred solely from neutral hydrogen beam and halo Balmer- α (H α ) emission data. The halo is a cloud of neutrals forming in the vicinity of the injected neutral beam due to multiple charge exchange reactions. W7-X is equipped with several neutral hydrogen beam heating sources and an H α spectroscopy system that views these sources from different angles and penetration depths in the plasma. As the beam and halo emission form complex spectra for each spatial point that are non-linearly dependent on the plasma density profile and other parameters, a complete model from the neutral beam injection and halo formation through to the spectroscopic measurements is required. The model is used here to infer electron density profiles for a range of common W7-X plasma scenarios. The inferred profiles show good agreement with profiles determined by the Thomson scattering and interferometry diagnostics across a broad range of absolute densities without any changes to the input or fitting parameters. The time evolution of the density profile in a discharge with continuous core density peaking is successfully reconstructed, demonstrating sufficient spatial resolution to infer strongly shaped profiles. Furthermore, it is shown as a proof of concept that the model is also able to infer the main ion temperature profile using the same data set.

forward modeling↗

DOE OSTI2022

Beam-pointing verification using x-ray pinhole cameras on the 60-beam OMEGA laser

On the OMEGA laser system, the beam-pointing accuracy is verified by irradiating a 4 mm diameter Au-coated spherical target with ~23 kJ of laser energy. Up to ten x-ray pinhole cameras record the x-ray emission from all 60-beam spots. A new set of algorithms has been developed to improve the accuracy of the pointing evaluation. An updated edge-finding procedure allows one to infer the center of the sphere with subpixel accuracy. A new approach was introduced to back-propagate the pixel locations on the 2D image to the 3D surface of the sphere. Furthermore, a fast Fourier transform-based de-noising method significantly improves the signal-to-noise of the data. Based on the beam-pointing analysis, hard-sphere calculations of the laser-drive illumination uniformity on the target surface and the decomposition of the illumination distribution into lower order modes (1–10) are evaluated.

47 OTHER INSTRUMENTATION↗

DOE OSTI2022

EdgeAI: Machine learning via direct attached accelerator for streaming data processing at high shot rate x-ray free-electron lasers

We present a case for low batch-size inference with the potential for adaptive training of a lean encoder model. We do so in the context of a paradigmatic example of machine learning as applied in data acquisition at high data velocity scientific user facilities such as the Linac Coherent Light Source-II x-ray Free-Electron Laser. We discuss how a low-latency inference model operating at the data acquisition edge can capitalize on the naturally stochastic nature of such sources. We simulate the method of attosecond angular streaking to produce representative results whereby simulated input data reproduce high-resolution ground truth probability distributions. By minimizing the mean-squared error between the decoded output of the latent representation and the ground truth distributions, we ensure that the encoding layers and resulting latent representation maintains full fidelity for any downstream task, be it classification or regression. We present throughput results for data-parallel inference of various batch sizes, some with throughput exceeding 100 k images per second. We also show in situ training below 10 s per epoch for the full encoder–decoder model as would be relevant for streaming and adaptive real-time data production at our nation’s scientific light sources.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2022

NREL Stratus - Enabling Workflows to Fuse Data Streams, Modeling, Simulation, and Machine Learning

Integrating cloud services into advanced computing facilities provides significant new capabilities over focusing solely on traditional high performance computing (HPC) workloads. This brings complementary capabilities as well as enabling new focused roles for HPC. They are especially potent for workflows that fuse data streams, modeling and simulation ('modsim') and machine learning. A key challenge to adopting a hybrid edge-cloud-HPC model is to align optimal capability, data, and user intent on the right resources for each step in a workflow.?The NREL Stratus service provides a basis for this: Stratus layers capabilities needed to make?cloud services accessible to a lab-based scientific community on commercial offerings, and; currently supports upwards of 200 projects ranging from IOT integration to traditional modeling and simulation. This provides a real-world inventory of scientific workflow elements. A growing knowledge base enables placing these elements appropriately between the edge, cloud, and traditional HPC. This paper outlines a vision via reference architecture and the application of that architecture in a typical workflow highlighting multiple components: sensor data intake, cleaning and transforming (edge/cloud suitable); generation of synthetic data through modsim, computationally heavy ML training and hyperparameter optimization (HPC suitable), and; inference and deployment (cloud ideal). Every step in such a workflow involves a cost-benefit analysis regarding the data movement, computational efficiency, availability, latency, and resource capabilities. The reference architecture and examples outlined allow for understanding new opportunities in the context of emerging workflows that combine IOT, cloud, and HPC to bolster scientific productivity.

AI↗

DOE OSTI2022

28 NREL Stratus - Enabling Workflows to Fuse Data Streams, Modeling, Simulation, and Machine Learning: Preprint

AI↗

DOE OSTI2025

Considerations for Distributed Edge Data Centers and Use of Building Loads to Support Large Interconnections

The rapid expansion of artificial intelligence (AI) and machine learning is driving unprecedented electricity demand from data centers. It is predicted that by 2030, 90% of AI workloads will be inference-based, requiring interconnection of multiple low-latency edge data centers (<20 MW) sited closer to end users - often on already constrained distribution feeders. Although individually small, these loads can aggregate to large loads per feeder, straining infrastructure, creating multi-year interconnection delays, and driving up customer costs. This paper proposes a data center-focused grid-integration framework that combines feeder hosting capacity analysis with building energy efficiency, building load flexibility, and waste heat reuse to expand effective feeder and substation headroom. Such approaches can reduce interconnection delays, lower costs for ratepayers, and accelerate AI-ready infrastructure deployment.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗

DOE OSTI2023

Spectroscopic identification of Ca-bearing uranyl silicates formed in C–S–H systems

Portland cement-based grouts used for radioactive waste immobilisation contain a Ca- and Si-rich binder phase, known as calcium–silicate–hydrate (C–S–H). Depending on the blend of cement used, the Ca/Si ratio can vary considerably. A range of C–S–H minerals with Ca/Si ratios from 0.6 to 1.6 were synthesised and contacted with aqueous U(VI) at 0.5 mM and 10 mM concentrations. Solid-state 29 Si MAS-NMR spectroscopy was applied to probe the Si coordination environment in U(VI)-contacted C–S–H minerals and, in conjunction with U L III -edge X-ray absorption spectroscopy analysis, inferences of the fate of U(VI) in these systems were made. At moderate or high Ca/Si ratios, uranophane-type uranyl silicates or Ca-uranates dominated, while at the lowest Ca/Si ratios, the formation of a Ca-bearing uranyl silicate mineral, similar to haiweeite (Ca[(UO 2 ) 2 Si 5 O 12 (OH) 2 ]·3H 2 O) or Ca-bearing weeksite (Ca 2 (UO 2 ) 2 Si 6 O 15 ·10H 2 O) was identified. This study highlights the influence of Ca/Si ratio on uranyl sequestration, of interest in the development of post-closure safety models for U-bearing radioactive waste disposal.

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗

DOE OSTI2024

Neural network methods for radiation detectors and imaging

Recent advances in image data proccesing through deep learning allow for new optimization and performance-enhancement schemes for radiation detectors and imaging hardware. This enables radiation experiments, which includes photon sciences in synchrotron and X-ray free electron lasers as a subclass, through data-endowed artificial intelligence. We give an overview of data generation at photon sources, deep learning-based methods for image processing tasks, and hardware solutions for deep learning acceleration. Most existing deep learning approaches are trained offline, typically using large amounts of computational resources. However, once trained, DNNs can achieve fast inference speeds and can be deployed to edge devices. A new trend is edge computing with less energy consumption (hundreds of watts or less) and real-time analysis potential. While popularly used for edge computing, electronic-based hardware accelerators ranging from general purpose processors such as central processing units (CPUs) to application-specific integrated circuits (ASICs) are constantly reaching performance limits in latency, energy consumption, and other physical constraints. These limits give rise to next-generation analog neuromorhpic hardware platforms, such as optical neural networks (ONNs), for high parallel, low latency, and low energy computing to boost deep learning acceleration (LA-UR-23-32395).

edge computing↗

DOE OSTI2021

Experimental inference of neutral and impurity transport in Alcator C-Mod using high-resolution x-ray and ultra-violet spectra

We present experimental inferences of cross-field impurity transport coefficients for AlcatorC-Mod plasmas without edge-localized modes, leveraging a novel forward model for the entire Ca Kα spectrum, including satellite lines within the spectral range, to compare to high-resolution x-ray imaging crystal spectroscopy (XICS). These measurements are complemented by extreme ultra-violet (EUV) spectroscopy that constrains transport closer to the edge. Using new atomic data sets for both XICS and EUV analysis has enabled consideration of line ratios across both spectral ranges and has increased the accuracy of inferred transport coefficients. Inclusion of charge exchange between edge thermal neutrals and impurities is shown to be extremely important in C-Mod pedestals. Atomic D neutral densities from experimental D Lyα measurements at the midplane are compared to SOLPS-ITER simulations, finding good agreement. Bayesian inferences of impurity transport coefficients are presented for L-, EDA H-, and I-mode discharges, making use of the Aurora package for forward modeling and combining our spectroscopic constraints. Experimentally inferred diffusion profiles are found to match turbulent transport models at midradius within uncertainties, using both quasilinear gyro-fluid TGLF SAT-1 and nonlinear ion-scale gyrokinetic CGYRO simulations. Furthermore, significant discrepancies in convection are observed in some cases, suggesting difficulties in predictions of flat or hollow impurity profiles.

neutrals↗

DOE OSTI2024

Edge supercurrent reveals competition between condensates in a Weyl superconductor

In topological materials, the edge states are readily distinguished from the bulk states. The situation where a topological semimetal becomes superconducting so that Cooper pairs occupy both the bulk and the edge states is not well understood. In particular, we do not know if we can force their pairing symmetries to be different. Here we show that, when supercurrent is injected into the superconducting Weyl semimetal MoTe 2 from Nb contacts, the invasive s-wave pairing potential from Nb is incompatible with the intrinsic Cooper pair condensate in MoTe 2 . This incompatibility leads to strong stochasticity in the switching current and an unusual anti-hysteretic behaviour in the current–voltage loops. There is also an asymmetry in the edge oscillations where, as the magnetic field crosses zero, the phase noise switches from one with a noisy spectrum to one that is noise free. Furthermore, using the noise spectrum as a guide, we track the anomalous features to field-induced switching of the device gap function between s-wave symmetry and the unconventional symmetry intrinsic to MoTe 2 . We infer that the behaviour of the gap function along the edges is different from that in the bulk.

Superconducting properties and materials↗

DOE OSTI2024

The trailing edge is everywhere: tree rings reveal the transient risk of extinction hidden inside climate envelope forecasts

Given the importance of climate in shaping species’ geographic distributions, climate change poses an existential threat to biodiversity. Climate envelope modeling, the predominant approach used to quantify this threat, presumes that individuals in populations respond to climate variability and change according to species-level responses inferred from spatial occurrence data—such that individuals at the cool edge of a species’ distribution should benefit from warming (the “leading edge”), whereas individuals at the warm edge should suffer (the “trailing edge”). Using 1,558 tree-ring time series of an aridland pine (Pinus edulis) collected at 977 locations across the species’ distribution, we found that trees everywhere grow less in warmer-than-average and drier-than-average years. Ubiquitous negative temperature sensitivity indicates that individuals across the entire distribution should suffer with warming—the entire distribution is a trailing edge. Species-level responses to spatial climate variation are opposite in sign to individual-scale responses to time-varying climate for approximately half the species’ distribution with respect to temperature and the majority of the species’ distribution with respect to precipitation. These findings, added to evidence from the literature for scale-dependent climate responses in hundreds of species, suggest that correlative, equilibrium-based range forecasts may fail to accurately represent how individuals in populations will be impacted by changing climate. A scale-dependent view of the impact of climate change on biodiversity highlights the transient risk of extinction hidden inside climate envelope forecasts and the importance of evolution in rescuing species from extinction whenever local climate variability and change exceeds individual-scale climate tolerances.

54 ENVIRONMENTAL SCIENCES↗

DOE OSTI2026

Two-Stage Wildlife Event Classification for Edge Deployment

Camera-based wildlife monitoring is often overwhelmed by non-target triggers and slowed by manual review or cloud-dependent inference, which can prevent timely intervention for high stakes human–wildlife conflicts. Our key contribution is a deployable, fully offline edge vision sensor that achieves near-real-time, highly accurate wildlife event classification by combining detector-based empty-image suppression with a lightweight classifier trained with a staged transfer-learning curriculum. Specifically, Stage 1 uses a pretrained You Only Look Once (YOLO)-family detector for permissive animal localization and empty-trigger suppression, and Stage 2 uses a lightweight EfficientNet-based binary classifier to confirm puma on detector crops and gate downstream actions. Our design is robust to low-quality nighttime monochrome imagery (motion blur, low contrast, illumination artifacts, and partial-body captures) and operates using commercially available components in connectivity-limited settings. In field deployments running since May 2025, end-to-end latency from camera trigger to action command is approximately 4 s. Ablation studies using a dataset of labeled wildlife images (pumas, not pumas) show that the two-stage approach substantially reduces false alarms in identifying pumas relative to a full-image classifier while maintaining high recall. On the held-out test set (N = 1434 events), the proposed two-stage cascade achieves precision 0.983, recall 0.975, F1 0.979, accuracy 0.986, and balanced accuracy 0.983, with only 8 false positives and 12 false negatives. The system can be easily adapted for other species, as demonstrated by rapid retraining of the second stage to classify ringtails. Downstream responses (e.g., notifications and optional audio/light outputs) provide flexible actuation capabilities that can be configured to support intervention.

58 GEOSCIENCES↗

DOE OSTI2022

CrossSim Inference Manual v2.0

Neural networks are largely based on matrix computations. During forward inference, the most heavily used compute kernel is the matrix-vector multiplication (MVM): $W \vec{x} $. Inference is a first frontier for the deployment of next-generation hardware for neural network applications, as it is more readily deployed in edge devices, such as mobile devices or embedded processors with size, weight, and power constraints. Inference is also easier to implement in analog systems than training, which has more stringent device requirements. The main processing kernel used during inference is the MVM.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2024

An ontology-based knowledge graph for representing interactions involving RNA molecules

The "RNA world" represents a novel frontier for the study of fundamental biological processes and human diseases and is paving the way for the development of new drugs tailored to each patient's biomolecular characteristics. Although scientific data about coding and non-coding RNA molecules are constantly produced and available from public repositories, they are scattered across different databases and a centralized, uniform, and semantically consistent representation of the "RNA world" is still lacking. We propose RNA-KG, a knowledge graph (KG) encompassing biological knowledge about RNAs gathered from more than 60 public databases, integrating functional relationships with genes, proteins, and chemicals and ontologically grounded biomedical concepts. To develop RNA-KG, we first identified, pre-processed, and characterized each data source; next, we built a meta-graph that provides an ontological description of the KG by representing all the bio-molecular entities and medical concepts of interest in this domain, as well as the types of interactions connecting them. Finally, we leveraged an instance-based semantically abstracted knowledge model to specify the ontological alignment according to which RNA-KG was generated. RNA-KG can be downloaded in different formats and also queried by a SPARQL endpoint. A thorough topological analysis of the resulting heterogeneous graph provides further insights into the characteristics of the "RNA world". RNA-KG can be both directly explored and visualized, and/or analyzed by applying computational methods to infer bio-medical knowledge from its heterogeneous nodes and edges. The resource can be easily updated with new experimental data, and specific views of the overall KG can be extracted according to the bio-medical problem to be studied.

59 BASIC BIOLOGICAL SCIENCES↗

DOE OSTI2025

Physics consistent machine learning framework for inverse modeling with applications to ICF capsule implosions

In high energy density physics (HEDP) and inertial confinement fusion (ICF), predictive modeling is complicated by uncertainty in parameters that characterize various aspects of the modeled system, such as those characterizing material properties, equation of state (EOS), opacities, and initial conditions. Typically, however, these parameters are not directly observable. What is observed instead is a time sequence of radiographic projections using X-rays. In this work, we define a set of sparse hydrodynamic features derived from the outgoing shock profile and outer material edge, which can be obtained from radiographic measurements, to directly infer such parameters. Our machine learning (ML)-based methodology involves a pipeline of two architectures, a radiograph-to-features network (R2FNet) and a features-to-parameters network (F2PNet), that are trained independently and later combined to approximate a posterior distribution for the parameters from radiographs. We show that the machine learning architectures are able to accurately infer initial conditions and EOS parameters, and that the estimated parameters can be used in a hydrodynamics code to obtain density fields, shocks, and material interfaces that satisfy thermodynamic and hydrodynamic consistency. Finally, we demonstrate that features resulting from an unknown EOS model can be successfully mapped onto parameters of a chosen analytical EOS model, implying that network predictions are learning physics, with a degree of invariance to the underlying choice of EOS model. To the best of our knowledge, our framework is the first demonstration of recovering both thermodynamic and hydrodynamic consistent density fields from noisy radiographs.

97 MATHEMATICS AND COMPUTING↗