Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Operator 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.

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

At least 235 records · Page 13
All sourcesNASA NTRSDOE OSTI
DOE OSTI2025

Automated Resonance Fitting for Nuclear Data Evaluation

Global and national efforts to deliver high-quality nuclear data to users have a wide-ranging impact, affecting applications in national security, reactor operations, basic science, medicine, and more. Cross section evaluation is a major part of this effort, combining theory and experimentation to produce recommended values and uncertainties for reaction probabilities. Resonance region evaluation is a specialized type of nuclear data evaluation that can require significant manual effort and months of time from expert scientists. In this article, non-convex non-linear optimization methods are combined with concepts of inferential statistics to infer a resonance model from experimental data in an automated manner that is not dependent on prior evaluation(s). This methodology aims to enhance the workflow of a resonance evaluator by minimizing time, effort, and the potential for bias from prior assumptions, while enhancing reproducibility and documentation, thereby addressing well-known challenges in the field.

73 NUCLEAR PHYSICS AND RADIATION PHYSICS↗
DOE OSTI2024

Hydra: Computer Vision for Online Data Quality Monitoring

Hydra is a system utilizing computer vision for near real-time data quality monitoring. Currently operational across all of Jefferson Lab’s experimental halls, it reduces the workload of shift takers by autonomously monitoring diagnostic plots during experiments. Hydra uses "off-the-shelf" supervised learning technologies and is supported by a comprehensive MySQL database. To simplify access, web apps have been developed to facilitate both labeling and monitoring of Hydra’s inferences. Hydra can connect with the alarm system and incorporates complete historical tracking, enabling it to identify issues that shift takers could miss. When issues are detected, a natural first question is: "Why does Hydra think there is a problem?" To answer, Hydra employs Gradient-weighted Class Activation Maps (GradCAM) to identify regions of the image that are important for the specific classification. This interpretive layer enhances transparency and trustworthiness, which is essential for integration with experiment workflows and operation. The Hydra system, results, and sociological considerations for deployment will be discussed.

Jeske, Torri↗
DOE OSTI2024

A Dataset of CFD Simulated Industrial Furnace Images for Conditional Automatic Generation with GANs

The steel industry is constantly looking for ways to automate processes and improve efficiency. A standard practice in industry is to simulate how complex systems will operate before they are actually used. Some complex systems, including steel industry processes such as blast furnaces, require complex physics-based simulations utilizing computational fluid dynamics (CFD). These CFD physics-based simulations are very accurate but can take significant time and computational resources to process, resulting in challenges for the implementation of the models in real-world operational environments. In recent years, deep learning (DL) has been considered as a substitute for these CFD models. DL models can be trained on validated CFD simulation data and then used for industrial process inference. Previous DL-based solutions have made great contributions for industrial automation but are currently missing the additional visualization component that CFD simulations also provide. In this paper, we propose a dataset for simple DL generative approaches that can help to address this issue. The dataset and methodology under development to approach this prediction are discussed in this work.

Calix, Ricardo↗
DOE OSTI2024

Poplar

SAND2025-00683O Poplar is a software tool that generates a phylogenetic tree from input gene and genome sequences. It integrates established tools to identify genes within genomes, group sequences, construct gene trees, and infer a species tree. Poplar processes nucleotide sequences, identifies similar sequences using Nucleotide BLAST, groups them with DBSCAN, aligns sequences with MAFFT, constructs gene trees with RAxML-NG, and infers a species tree using ASTRAL-Pro3. This pipeline provides a structured approach to phylogenetic analysis, facilitating the study of evolutionary relationships among species. 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.

Krishnakumar, Raga↗
DOE OSTI2026

Toward an AI-Powered Software Pipeline for Real-Time Tracking and Analysis of Wildfire and Smoke

Real-time tracking of wildfires and smoke is crucial for effective response, minimizing damage, protecting lives, and efficiently managing resources during fire emergencies. We develop a web-based AI-powered pipeline that detects wildfires in aerial video and estimates deployment-relevant behavior metrics, including cumulative burned area, burned-area growth rate, fire spread direction, and smoke dispersion. The system combines a YOLO-based detector with YCbCr-based fire segmentation, HSV-based smoke segmentation, Farneback optical flow, and centroid-based spatiotemporal tracking. Using ground sampling distance (GSD), pixel-level fire masks are converted to physical burned-area measurements by correlating fire pixel counts with camera altitude and tilt angle. We benchmark YOLO variants and non-YOLO baselines (GoogLeNet, CNN, DBN, Autoencoder, U-Net, and AlexNet) on the IEEE FLAME dataset and a newly created aerial frame dataset, Wildfire-DB. Cross-dataset evaluation uses a strict threshold-transfer protocol: decision thresholds are selected on FLAME validation and transferred unchanged to Wildfire-DB to quantify generalization under domain shift. YOLOv6 achieves the strongest cross-dataset frame-level fire detection on Wildfire-DB (ROC-AUC 0.8200, PR-AUC 0.8044, and transferred-threshold F1 0.7596). For tracking-oriented deployment requiring oriented localization, YOLO11-OBB provides the most reliable cross-dataset behavior among OBB-capable models while remaining computationally feasible. To analyze the feasibility of UAV deployment, we further measure inference efficiency using synchronized GPU and CPU power logs on a fixed workload of 1569 frames. YOLO-family models process the video in 5.73–12.47 seconds with net energy of 1247.28–1775.39 J, substantially lower latency and energy than heavier classification and reconstruction baselines. Overall, model optimality depends on operational objectives: YOLOv6 is best for cross-dataset detection robustness, whereas YOL...

Color segmentation↗
DOE OSTI2024

Isotope effects and Alfvén eigenmode stability in JET H, D, T, DT, and He plasmas

While much about Alfvén eigenmode (AE) stability has been explored in previous and current tokamaks, open questions remain for future burning plasma experiments, especially regarding exact stability threshold conditions and related isotope effects; the latter, of course, requiring good knowledge of the plasma ion composition. In the JET tokamak, eight in-vessel antennas actively excite stable AEs, from which their frequencies, toroidal mode numbers, and net damping rates are assessed. The effective ion mass can also be inferred using measurements of the plasma density and magnetic geometry. Thousands of AE stability measurements have been collected by the Alfvén Eigenmode Active Diagnostic in hundreds of JET plasmas during the recent Hydrogen, Deuterium, Tritium, DT, and Helium-4 campaigns. In this novel AE stability database, spanning all four main ion species, damping is observed to decrease with increasing Hydrogenic mass, but increase for Helium, a trend consistent with radiative damping as the dominant damping mechanism. These data are important for confident predictions of AE stability in both non-nuclear (H/He) and nuclear (D/T) operations in future devices. In particular, if radiative damping plays a significant role in overall stability, some AEs could be more easily destabilized in D/T plasmas than their H/He reference pulses, even before considering fast ion and alpha particle drive. Active MHD spectroscopy is also employed on select HD, HT, and DT plasmas to infer the effective ion mass, thereby closing the loop on isotope analysis and demonstrating a complementary method to typical diagnosis of the isotope ratio.

Alfvén eigenmodes↗
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 OSTI2026

Beyond Point Estimates: Benchmarking Uncertainty Quantification Methods on the AION-1 Astronomical Foundation Model

Foundation models for astronomical surveys offer powerful learned representations that can be transferred to downstream regression tasks such as galaxy property estimation. However, point predictions alone are insufficient for scientific inference; reliable uncertainty quantification (UQ) is essential. We compare seven UQ methods on galaxy property regression using frozen AION-1 foundation-model embeddings, predicting redshift, stellar mass, stellar-population age, gas-phase metallicity, and specific star-formation rate, from Legacy Survey photometry/imaging and DESI spectra, with PROVABGS-derived labels. Distribution-free conformal methods achieve marginal coverage within $\sim$1 pp of the nominal 90% across all properties, while non-conformal baselines (Deep Ensembles, MC~Dropout) fail to calibrate reliably. Among conformal approaches, Conformalized Quantile Regression (CQR) delivers the best coverage in the bin with the poorest model predictions. More importantly, only the Locally Valid and Discriminative (LVD) framework -- particularly when operating on AION-1 embeddings -- also provides finite-sample \emph{local validity}, producing intervals that adapt to each galaxy's local prediction difficulty rather than relying on marginal guarantees alone. These results establish conformal prediction, and LVD in particular, as the preferred UQ framework for uncertainty-aware inference on foundation-model embeddings in astrophysics.

Tame-Narvaez, Karla [Fermilab] (ORCID:000000022249↗
DOE OSTI2024

Information and Statistics in Nuclear Experiment and Theory (ISNET)

As with all empirical sciences, nuclear physics operates in the virtuous cycle of the scientific method: observations inspire theoretical models; models lead to new predictions; predictions are tested in experiments; experiments lead to new observations; and so on. Evaluating what we are inferring, and how certain we are of it, is key to this process. These requirements, and a general interest in applying novel statistical, mathematical, and computational techniques, led to the formation of a dedicated research community entitled “Information and Statistics in Nuclear Experiment and Theory (ISNET)” (https://isnet-series.github.io/), which now includes more than 300 members. While the community’s interests lean toward nuclear theory, the unifying theme for this group is the inference of knowledge from data.

73 NUCLEAR PHYSICS AND RADIATION PHYSICS↗
DOE OSTI2022

Neural network accelerator for quantum control

Efficient quantum control is necessary for practical quantum computing implementations with current technologies. Conventional algorithms for determining optimal control parameters are computationally expensive, largely excluding them from use outside of the simulation. Existing hardware solutions structured as lookup tables are imprecise and costly. By designing a machine learning model to approximate the results of traditional tools, a more efficient method can be produced. Such a model can then be synthesized into a hardware accelerator for use in quantum systems. In this study, we demonstrate a machine learning algorithm for predicting optimal pulse parameters. This algorithm is lightweight enough to fit on a low-resource FPGA and perform inference with a latency of 175 ns and pipeline interval of 5 ns with > 0.99 gate fidelity. In the long term, such an accelerator could be used near quantum computing hardware where traditional computers cannot operate, enabling quantum control at a reasonable cost at low latencies without incurring large data bandwidths outside of the cryogenic environment.

43 PARTICLE ACCELERATORS↗
DOE OSTI2020

Absorber Column CFD model validation against PNNL’s device-scale absorber column on the LCFS unit

Absorber column has been widely used for CO 2 capture in the coal-fired power plants. High-fidelity CFD models play an important role in absorber column design and solvents optimization, which help enhance the CO 2 capture efficiency and reduce the operation cost. This report provides a comprehensive description of the development of CFD absorber models at two different levels, the design and implementation of PNNL’s device-scale absorber column experiment, and the methodology to combine the CFD results, experiment data, and Aspen model for a better understanding of the interface area in packed column. A composite model is firstly proposed in the Discrete Element Method (DEM) packing process, which can model the complex geometry of various packing elements. This generates a realistic packing pattern and accurate packing porosity ε and specific area a p compared to the actual values for absorber column used in LCFS. Two level of CFD absorber models were developed, namely the full-size column model (FCM) to simulate the entire packed column with a focus on the wall/entrance effects, and the representative column model (RCM) to simulate a section of column with a focus on the sensitivity study of interface area. A Design of Experiment (DoE) plan was developed to guide the collection of 100 run CFD data and 12 experiment runs. The 100 CFD runs were carried out in the RCM with Pro-Pak packing and cover a wide operation range and solvent properties. Impact of influential factors on the interface area in packed column were investigated in details. The CFD interface area was then combined with the experimental data and Aspen model to infer some information of the effective contact angle in the column. The accuracy and uncertainties in the interface area and contact angle can be quantified.

01 COAL, LIGNITE, AND PEAT↗
DOE OSTI2022

Deep Learning Based Superconducting Radio-Frequency Cavity Fault Classification at Jefferson Laboratory

This work investigates the efficacy of deep learning (DL) for classifying C100 superconducting radio-frequency (SRF) cavity faults in the Continuous Electron Beam Accelerator Facility (CEBAF) at Jefferson Lab. CEBAF is a large, high-power continuous wave recirculating linac that utilizes 418 SRF cavities to accelerate electrons up to 12 GeV. Recent upgrades to CEBAF include installation of 11 new cryomodules (88 cavities) equipped with a low-level RF system that records RF time-series data from each cavity at the onset of an RF failure. Typically, subject matter experts (SME) analyze this data to determine the fault type and identify the cavity of origin. This information is subsequently utilized to identify failure trends and to implement corrective measures on the offending cavity. Manual inspection of large-scale, time-series data, generated by frequent system failures is tedious and time consuming, and thereby motivates the use of machine learning (ML) to automate the task. This study extends work on a previously developed system based on traditional ML methods (Tennant and Carpenter and Powers and Shabalina Solopova and Vidyaratne and Iftekharuddin, Phys. Rev. Accel. Beams, 2020, 23, 114601), and investigates the effectiveness of deep learning approaches. The transition to a DL model is driven by the goal of developing a system with sufficiently fast inference that it could be used to predict a fault event and take actionable information before the onset (on the order of a few hundred milliseconds). Because features are learned, rather than explicitly computed, DL offers a potential advantage over traditional ML. Specifically, two seminal DL architecture types are explored: deep recurrent neural networks (RNN) and deep convolutional neural networks (CNN). We provide a detailed analysis on the performance of individual models using an RF waveform dataset built from past operational runs of CEBAF. In particular, the performance of RNN models incorporating long short-term memory (LSTM) are analyzed along with the CNN performance. Furthermore, comparing these DL models with a state-of-the-art fault ML model shows that DL architectures obtain similar performance for cavity identification, do not perform quite as well for fault classification, but provide an advantage in inference speed.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2021

Artificial Reasoning System for Symptom-Based Conditional Failure Probability Estimation Using Bayesian Network

Advances in nuclear power technologies require enhanced capabilities for operator advice and autonomous control. One of the first tasks in the development of such capabilities is the formulation of symptom-based conditional failure probabilities for structures, systems, and components (SSCs) of interest, for which the primary goal is to aid plant personnel in deducing the probabilistic performance status of the monitored SSCs and in detecting impending faults/failure. The task of conditional failure probability estimation is a bidirectional inference problem and shall be logically tackled by the Bayesian network (BN) approach. As a knowledge-based artificial intelligence tool and a probabilistic graphical model, BN offers the capability of reasoning under uncertainty and graphical representation emulating the physical behavior of the target SSC. This paper provides a systematic overview of the BN technique and the software tools for handling implementation of BN models, along with the associated knowledge representation and reasoning paradigm. Both operational data and expert judgement can be readily incorporated into the knowledge base of a BN model. The challenges with data availability are highlighted, and the general approach to target SSC identification is presented. Our focus is upon failure-prone and risk-important balance of plant assets, especially cases having strong operator involvement. An exemplary case study on the failure of a motor-driven centrifugal pump is also conducted to demonstrate the usefulness and technical feasibility of the proposed artificial reasoning system using an expert system shell.

Zhao, Xingang↗
DOE OSTI2022

Differentially Private Synthesis and Sharing of Network Data Via Bayesian Exponential Random Graph Models

Abstract Network data often contain sensitive relational information. One approach to protecting sensitive information while offering flexibility for network analysis is to share synthesized networks based on the information in originally observed networks. We employ differential privacy (DP) and exponential random graph models (ERGMs) and propose the DP-ERGM method to synthesize network data. We apply DP-ERGM to two real-world networks. We then compare the utility of synthesized networks generated by DP-ERGM, the DyadWise Randomized Response (DWRR) approach, and the Synthesis through Conditional distribution of Edge given nodal Attribute (SCEA) approach. In general, the results suggest that DP-ERGM preserves the original information significantly better than two other approaches in network structural statistics and inference for ERGMs and latent space models. Furthermore, DP-ERGM satisfies node DP through modeling the global network structure with ERGM, a stronger notion of privacy than the edge DP under which DWRR and SCEA operate.

graph synthesis↗
DOE OSTI2023

FPGA Architectures for Distributed ML Systems for Real-time Beam Loss De-blending

The Accelerator Real-time Edge AI for Distributed Systems (READS) project’s goal is to create a Artificial Intelligence (AI) system for real-time beam loss de-blending within the accelerator enclosure, which houses two accelerators: the Main Injector (MI) and the Recycler Ring (RR). In periods of joint operation, when both machines contain high intensity beam, radioactive beam losses from MI and RR overlap on the enclosure’s beam loss monitoring Beam Loss Monitor (BLM) system, making it difficult to attribute those losses to a single machine. Incorrect diagnoses result in unnecessary downtime that incurs both financialand experimental cost. The ML system will automatically disentangle each machine’s contributions to those measured losses, while not disrupting the existing operations-critical functions of the BLM system. This paper will focus on the evolution of the architectures, which provided the high-frequency, low-latency collection of synchronized data streams to make real-time inferences. The ML models, used for learning both local and global machine signatures and producing high quality inferences based on raw BLM loss measurements, will only be discussed at a high-level.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2022

Nonequilibrium statistical mechanics and optimal prediction of partially-observed complex systems

Abstract Only a subset of degrees of freedom are typically accessible or measurable in real-world systems. As a consequence, the proper setting for empirical modeling is that of partially-observed systems. Notably, data-driven models consistently outperform physics-based models for systems with few observable degrees of freedom; e.g. hydrological systems. Here, we provide an operator-theoretic explanation for this empirical success. To predict a partially-observed system’s future behavior with physics-based models, the missing degrees of freedom must be explicitly accounted for using data assimilation and model parametrization. Data-driven models, in contrast, employ delay-coordinate embeddings and their evolution under the Koopman operator to implicitly model the effects of the missing degrees of freedom. We describe in detail the statistical physics of partial observations underlying data-driven models using novel maximum entropy and maximum caliber measures. The resulting nonequilibrium Wiener projections applied to the Mori–Zwanzig formalism reveal how data-driven models may converge to the true dynamics of the observable degrees of freedom. Additionally, this framework shows how data-driven models infer the effects of unobserved degrees of freedom implicitly, in much the same way that physics models infer the effects explicitly. This provides a unified implicit-explicit modeling framework for predicting partially-observed systems, with hybrid physics-informed machine learning methods combining both implicit and explicit aspects.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2024

Deployment of inference as a service at the US CMS Tier-2 data centers

Coprocessors, especially GPUs, will be a vital ingredient of data production workflows at the HL-LHC. At CMS, the GPU-as-a-service approach for production workflows is implemented by the SONIC project (Services for Optimized Network Inference on Coprocessors). SONIC provides a mechanism for outsourcing computationally demanding algorithms, such as neural network inference, to remote servers, where requests from multiple clients are intelligently distributed across multiple GPUs by a load-balancing service. This talk highlights the recent progress in deploying SONIC at selected U.S. CMS Tier-2 data centers. Using realistic CMS Run3 data processing workflows, such as those containing transformer-based algorithms, we demonstrate how SONIC is integrated into the production-like environment to enable accelerated inference offloading. We will present developments from both the client and server sides, including production job and data center configurations for NVIDIA and AMD GPUs. We will also present performance scaling benchmarks and discuss the challenges of operating SONIC in CMS production, such as server discovery, GPU saturation, fallback server logic, etc.

Holzman, Burt↗
DOE OSTI2024

Soil Carbon Dynamics Following Land Use Changes and Conversion to Oil Palm Plantations in Tropical Lowlands Inferred From Radiocarbon

We measured the 14C and 13C isotopic values of soil organic carbon in mineral soil from lowland tropical forests to provide insight into how quickly carbon is turning over in the soil following conversion of primary forests to oil palm plantations. In addition to areas converted to oil palm plantations in Peru, Indonesia, and Cameroon, we examine pastures and secondary forests in Peru as a comparison to the carbon cycling processes operating in the oil palm plantations.This dataset includes radiocarbon (Δ14C) and stable carbon (δ13C) isotopes of soil organic carbon in mineral soils from natural lowland forests and oil palm plantations in Peru, Indonesia, and Cameroon. We additionally examine plots of secondary forests following agricultural use and pastures on cleared natural forest in Peru. In addition to isotopic data, this dataset includes soil carbon and nitrogen concentrations and stock, soil texture (percent sand, silt, and clay), pH, ECEC (effective cation exchange capacity), base saturation, and bulk density. Soils were sampled in 4 depth increments to 100 cm depth.This dataset supports the publication Finstad et al., 2020. Finstad, K., van Straaten, O., Veldkamp, E., & McFarlane, K. (2020). Soil carbon dynamics following land use changes and conversion to oil palm plantations in tropical lowlands inferred from radiocarbon. Global Biogeochemical Cycles, 34, e2019GB006461. https://doi.org/10.1029/2019GB006461

54 ENVIRONMENTAL SCIENCES↗