Search NASA⌕ Search

SEARCH · Search NASA

Results for “Model 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 91 records · Page 5
All sourcesNASA NTRSDOE OSTI
DOE OSTI2022

Predicting resistive wall mode stability in NSTX through balanced random forests and counterfactual explanations

Abstract Recent progress in the disruption event characterization and forecasting framework has shown that machine learning guided by physics theory can be easily implemented as a supporting tool for fast computations of ideal stability properties of spherical tokamak plasmas. In order to extend that idea, a customized random forest (RF) classifier that takes into account imbalances in the training data is hereby employed to predict resistive wall mode (RWM) stability for a set of high beta discharges from the NSTX spherical tokamak. More specifically, with this approach each tree in the forest is trained on samples that are balanced via a user-defined over/under-sampler. The proposed approach outperforms classical cost-sensitive methods for the problem at hand, in particular when used in conjunction with a random under-sampler, while also resulting in a threefold reduction in the training time. In order to further understand the model’s decisions, a diverse set of counterfactual explanations based on determinantal point processes (DPP) is generated and evaluated. Via the use of DPP, the underlying RF model infers that the presence of hypothetical magnetohydrodynamic activity would have prevented the RWM from concurrently going unstable, which is a counterfactual that is indeed expected by prior physics knowledge. Given that this result emerges from the data-driven RF classifier and the use of counterfactuals without hand-crafted embedding of prior physics intuition, it motivates the usage of counterfactuals to simulate real-time control by generating the β N levels that would have kept the RWM stable for a set of unstable discharges.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
DOE OSTI2026

wavess 1.2: presenting an HLA-aware within-host virus sequence simulation framework

Motivation Understanding how virus sequences are shaped by selection can inform vaccine design and transmission inference. Modeling within-host evolution to interrogate these questions requires a detailed mechanistic framework that accurately captures sequence diversification. The CD8 + cytotoxic T-lymphocyte (CTL) response plays an important role in immune-mediated selection and can leave strong signatures in virus sequences; however, existing sequence-based within-host virus modeling frameworks do not explicitly include a human leukocyte antigen (HLA)-aware CTL response. Results We extended our previously published within-host sequence evolution simulator, wavess, to include an explicit CTL response, and share a method for identifying HLA-specific CTL epitopes given a founder virus sequence. We also updated the model to permit a variable recombination rate, which allows for modeling non-adjacent genes, segmented genomes, and recombination hotspots. These extensions to wavess allow for more accurate simulation of viruses and virus genes, particularly in regions of the genome where the immune response is dominated by CTLs (rather than antibodies). It also provides the foundation for investigations of how these newly-added biological mechanisms influence within-host evolution. Availability and implementation The core of wavess is written in Python 3, with helper functions written in R. It is available at https://github.com/MolEvolEpid/wavess.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2024

Graph neural network for neutrino physics event reconstruction

Liquid argon time projection chamber (LArTPC) detector technology offers a wealth of high-resolution information on particle interactions, and leveraging that information to its full potential requires sophisticated automated reconstruction techniques. Here, this article describes NUGRAPH 2, a graph neural network for low-level reconstruction of simulated neutrino interactions in a LArTPC detector. Simulated neutrino interactions in the MicroBooNE detector geometry are described as heterogeneous graphs, with energy depositions on each detector plane forming nodes on planar subgraphs. The network utilizes a multihead attention message-passing mechanism to perform background filtering and semantic labeling on these graph nodes, identifying those associated with the primary physics interaction with 98.0% efficiency and labeling them according to particle type with 94.9% efficiency. The network operates directly on detector observables across multiple two-dimensional representations but utilizes a three-dimensional-context-aware mechanism to encourage consistency between these representations. Model inference takes 0.12 s / event on a CPU and 0.005 s / event batched on a GPU. This architecture is designed to be a general-purpose solution for particle reconstruction in neutrino physics, with the potential for deployment across a broad range of detector technologies, and offers a core convolution engine that can be leveraged for a variety of tasks beyond the two described in this paper.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2021

BraggNN : fast X-ray Bragg peak analysis using deep learning

X-ray diffraction based microscopy techniques such as high-energy diffraction microscopy (HEDM) rely on knowledge of the position of diffraction peaks with high precision. These positions are typically computed by fitting the observed intensities in detector data to a theoretical peak shape such as pseudo-Voigt. As experiments become more complex and detector technologies evolve, the computational cost of such peak-shape fitting becomes the biggest hurdle to the rapid analysis required for real-time feedback in experiments. To this end, we propose BraggNN, a deep-learning based method that can determine peak positions much more rapidly than conventional pseudo-Voigt peak fitting. When applied to a test dataset, peak center-of-mass positions obtained from BraggNN deviate less than 0.29 and 0.57 pixels for 75 and 95% of the peaks, respectively, from positions obtained using conventional pseudo-Voigt fitting (Euclidean distance). When applied to a real experimental dataset and using grain positions from near-field HEDM reconstruction as ground-truth, grain positions using BraggNN result in 15% smaller errors compared with those calculated using pseudo-Voigt. Recent advances in deep-learning method implementations and special-purpose model inference accelerators allow BraggNN to deliver enormous performance improvements relative to the conventional method, running, for example, more than 200 times faster on a consumer-class GPU card with out-of-the-box software.

36 MATERIALS SCIENCE↗
DOE OSTI2023

A 3D Implementation of Convolutional Neural Network for Fast Inference

Low latency inference has many applications in edge machine learning. In this paper, we present a run-time configurable convolutional neural network (CNN) inference ASIC design for low-latency edge machine learning. By implementing a 5-stage pipelined CNN inference model in a 3D ASIC technology, we demonstrate that the model distributed on two dies utilizing face-to-face (F2F) 3D integration achieves superior performance. Our experimental results show that the design based on 3D integration achieves 43% better energy-delay product when compared to the traditional 2D technology.

Miniskar, Narasinga Rao↗
DOE OSTI2024

Increasing Rubisco as a simple means to enhance photosynthesis and productivity now without lowering nitrogen use efficiency

Summary Global demand for food may rise by 60% mid‐century. A central challenge is to meet this need using less land in a changing climate. Nearly all crop carbon is assimilated through Rubisco, which is catalytically slow, reactive with oxygen, and a major component of leaf nitrogen. Developing more efficient forms of Rubisco, or engineering CO 2 concentrating mechanisms into C 3 crops to competitively repress oxygenation, are major endeavors, which could hugely increase photosynthetic productivity (≥ 60%). New technologies are bringing this closer, but improvements remain in the discovery phase and have not been reduced to practice. A simpler shorter‐term strategy that could fill this time gap, but with smaller productivity increases (c. 10%) is to increase leaf Rubisco content. This has been demonstrated in initial field trials, improving the productivity of C 3 and C 4 crops. Combining three‐dimensional leaf canopies with metabolic models infers that a 20% increase in Rubisco increases canopy photosynthesis by 14% in sugarcane (C 4 ) and 9% in soybean (C 3 ). This is consistent with observed productivity increases in rice, maize, sorghum and sugarcane. Upregulation of Rubisco is calculated not to require more nitrogen per unit yield and although achieved transgenically to date, might be achieved using gene editing to produce transgene‐free gain of function mutations or using breeding.

Plant Sciences↗
DOE OSTI2023

Software for Heliospheric Science

This software is being developed to support data analysis, modeling, and simulation for the growing field of heliosphere physics. In particular, this software will implement data analysis, modeling, inference, and simulation of physical mechanisms describing how energetic neutral atoms behave within the Earth’s heliosphere and in the interstellar medium beyond.

VanDervort, Lauren↗
DOE OSTI2019

CosmoGAN: creating high-fidelity weak lensing convergence maps using Generative Adversarial Networks

Abstract Inferring model parameters from experimental data is a grand challenge in many sciences, including cosmology. This often relies critically on high fidelity numerical simulations, which are prohibitively computationally expensive. The application of deep learning techniques to generative modeling is renewing interest in using high dimensional density estimators as computationally inexpensive emulators of fully-fledged simulations. These generative models have the potential to make a dramatic shift in the field of scientific simulations, but for that shift to happen we need to study the performance of such generators in the precision regime needed for science applications. To this end, in this work we apply Generative Adversarial Networks to the problem of generating weak lensing convergence maps. We show that our generator network produces maps that are described by, with high statistical confidence, the same summary statistics as the fully simulated maps.

Mustafa, Mustafa (ORCID:0000000291770283)↗
DOE OSTI2023

Disentangling Beam Losses in The Fermilab Main Injector Enclosure Using Real-Time Edge AI

The Fermilab Main Injector enclosure houses two accelerators, the Main Injector and Recycler Ring. During normal operation, high intensity proton beams exist simultaneously in both. The two accelerators share the same beam loss monitors (BLM) and monitoring system. Deciphering the origin of any of the 260 BLM readings is often difficult. The (Accelerator) Real-time Edge AI for Distributed Systems project, or READS, has developed an AI/ML model, and implemented it on fast FPGA hardware, that disentangles mixed beam losses and attributes probabilities to each BLM as to which machine(s) the loss originated from in real-time. The model inferences are then streamed to the Fermilab accelerator controls network (ACNET) where they are available for operators and experts alike to aid in tuning the machines.

43 PARTICLE ACCELERATORS↗
DOE OSTI2024

Simulating the CMS High Granularity Calorimeter with ML

Detector simulation is a key component of physics analysis and related activities in CMS. In the upcoming High Luminosity LHC era, simulation will be required to use a smaller fraction of computing in order to satisfy resource constraints. At the same time, CMS will be upgraded with the new High Granularity Calorimeter (HGCal), which requires significantly more resources to simulate than the existing CMS calorimeters. This computing challenge motivates the use of generative machine learning models as surrogates to replace full physics-based simulation. We study the application of state-of-the-art diffusion models to simulate particle showers in the CMS HGCal. We will discuss methods to overcome the challenges posed by the high-dimensional, irregular geometry of the HGCal. The quality of the showers produced by the diffusion model will be assessed by comparison to the full GEANT4-based simulation. The increase in simulation throughput will be quantified and methods to accelerate the diffusion model inference will also be discussed.

Amram, Oz↗
DOE OSTI2025

Optimal Transport as a Tool for Scientific Discovery in Radiation Biology

This report summarizes findings from research conducted for the “Exploration of the Poten tial for Artificial Intelligence and Machine Learning to Advance Low-Dose Radiation Biology Re search” (RadBio-AI) program, supported by the U.S. Department of Energy, Office of Science, Office of Biological and Environmental Research, under Awards KP1601011/FWP CC121 and KP1601017/FWP CC121. The research reported here was undertaken in an effort to assess the potential of optimal measure transport methods as components within the larger scope of a com putational framework envisioned to support research in the radiation biology domain. Within this effort, our interest centered on enabling a unified generic framework where probabilistic modeling, inference, and statistical learning can be carried out for a wide range of data distributions. As described next in Section 1 (and in more detail in our original publication), optimal measure transport offers the possibility of such unified approach.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2026

Computer vision-based rock bolt detection in orthomosaic imagery obtained in the Waste Isolation Pilot Plant underground facility

Assessing structural integrity of large underground tunnel facilities is often a time consuming and human-labor intensive task. Thus, research using various modes of sensing and automated detection of key structural components in mines is posed to aid in safety assessments and establishing overall structural health. We propose an approach utilizing off-the-shelf camera and lidar technology fixed to a custom sensing platform, image stitching techniques, fine-tuned object detection models, and specialized model-inference methods to automatically detect, count, and map roof bolts for assessment of structural safety in man-made underground tunnels. Results show a novel workflow for effective object counting in orthomosaic tunnel ceiling images generated from collections in GPS-denied mining environments. Additionally, we demonstrate effective fine-tuning of EfficientDet object detectors utilizing state-of-the-art image augmentation techniques known as the mosaic and mixup transformations. Our work is demonstrated on sensed data and imagery collected from the Department of Energy (DOE) Waste Isolation Pilot Plant (WIPP) where miles of tunnel ceiling must be assessed for structural integrity.

42 ENGINEERING↗
DOE OSTI2025

Masked Symbol Modeling for Demodulation of Oversampled Baseband Communication Signals in Impulsive Noise-Dominated Channels

Recent breakthroughs in natural language processing show that attention mech- anism in Transformer networks, trained via masked-token prediction, enables models to capture the semantic context of the tokens and internalize the grammar of language. While the application of Transformers to communication systems is a burgeoning field, the notion of context within physical waveforms remains under-explored. This paper addresses that gap by re-examining inter-symbol con- tribution (ISC) caused by pulse-shaping overlap. Rather than treating ISC as a nuisance, we view it as a deterministic source of contextual information embedded in oversampled complex baseband signals. We propose Masked Symbol Model- ing (MSM), a framework for the physical (PHY) layer inspired by Bidirectional Encoder Representations from Transformers methodology. In MSM, a subset of symbol-aligned samples is randomly masked, and a Transformer predicts the missing symbol identifiers using the surrounding “in-between” samples. Through this objective, the model learns the latent syntax of complex baseband waveforms. We illustrate MSM’s potential by applying it to the task of demodulating sig- nals corrupted by impulsive noise, where the model infers corrupted segments by leveraging the learned context. Our results suggest a path toward receivers that interpret, rather than merely detect communication signals, opening new avenues for context-aware PHY layer design.

Bedir, Oguz↗
DOE OSTI2023

Multiwavelength Observations of a New Redback Millisecond Pulsar 4FGL J1910.7-5320

We present the study of multiwavelength observations of an unidentified Fermi Large Area Telescope (LAT) source, 4FGL J1910.7-5320, a new candidate redback millisecond pulsar binary. In the 4FGL 95% error region of 4FGL J1910.7-5320, we find a possible binary with a 8.36 hr orbital period from the Catalina Real-Time Transient Survey, confirmed by optical spectroscopy using the SOAR telescope. This optical source was recently independently discovered as a redback pulsar by the TRAPUM project, confirming our prediction. We fit the optical spectral energy distributions of 4FGL J1910.7-5320 with a blackbody model, inferring a maximum distance of 4.1 kpc by assuming that the companion fills its Roche lobe with a radius of R = 0.7 R ⊙ . Using a 12.6 ks Chandra X-ray observation, we identified an X-ray counterpart for 4FGL J1910.7-5320, with a spectrum that can be described by an absorbed power law with a photon index of 1.0 ± 0.4. The spectrally hard X-ray emission shows tentative evidence for orbital variability. Using more than 12 yr of Fermi-LAT data, we refined the position of the γ-ray source, and the optical candidate still lies within the 68% positional error circle. In addition to 4FGL J1910.7-5320, we find a variable optical source with a periodic signal of 4.28 hr inside the 4FGL catalog 95% error region of another unidentified Fermi source, 4FGL J2029.5-4237. However, the γ-ray source does not have a significant X-ray counterpart in an 11.7 ks Chandra observation, with a 3σ flux upper limit of 2.4 × 10 -14 erg cm -2 s -1 (0.3–7 keV). Moreover, the optical source is outside our updated Fermi-LAT 95% error circle. These observational facts all suggest that this new redback millisecond pulsar powers the gamma-ray source 4FGL J1910.7-5320 while 4FGL J2029.5-4237 is unlikely the γ-ray counterpart to the 4.28 hr variable.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2025

Development of Surveillance Test Articles for Materials Degradation Management in MSR Environments

Materials in molten salt reactors (MSR) undergo accelerated degradation from corrosion, irradiation, and cyclic loads at elevated temperatures. Establishing a materials surveillance program to enable the assessment of material deterioration is critical to assure structural integrity of MSRs components. This presentation summarizes recent efforts towards the development of surveillance test articles for collecting various damages for monitoring materials degradation. Surveillance test articles with reduced dimensions were designed to capture creep-fatigue damage from cyclic loading at elevated temperatures. The strain evolution of test articles during thermal cycling was analyzed both numerically and experimentally. Out-of-reactor thermal cycling demonstrated successful capture of strain range for materials assessment. Moreover, test articles were subject to both mechanical loads and molten salt exposure, and the damage due to stress and corrosion was investigated. Additionally, damage inference models were developed to predict the remaining life of materials based on the accumulated damage in surveillance test articles.

36 - MATERIALS SCIENCE↗
DOE OSTI2026

Component-Level Inverse Design of Transmon Qubits Using Neural Networks

Designing a superconducting qubit to realize specific Hamiltonian parameters typically requires iterating through a time and compute-intensive forward loop in which the designer chooses a layout geometry, simulates it, extracts circuit parameters such as capacitances, and refines the geometry. We study the inverse version of this task using a neural-network workflow that maps target Hamiltonian parameters directly to component-level layout parameters, which we subsequently demonstrate on a planar transmon layout. During training, we pair the inverse model with a frozen forward surrogate model and evaluate the loss in Hamiltonian space rather than in layout-parameter space. In validation against a conventional EM solver, 97% of generated designs produce usable geometries, and the inverse-plus-surrogate pipeline reaches mean percent errors of 0.73% for qubit frequency and 1.58% for anharmonicity, comparable to or below the fabrication and simulation-to-measurement uncertainty expected for academic-process transmon devices of this type. A single pipeline query takes ~60 ms on CPU, versus ~2 min for a conventional EM capacitance extraction on the same hardware, a speedup of approximately 2,000x. Batching minimizes the AI model inference overhead, reducing the runtime to 3.1 microseconds per sample on CPU and 2.6 microseconds per sample on GPU at a batch size of 2048, resulting in speedups of 3.9 x 10^7 and 4.6 x 10^7, respectively, relative to a single conventional CPU EM extraction. Our results indicate that component-level inverse design usefully extends and complements conventional EM simulation, including for small datasets on the order of 1,000 samples.

Seidel, Olivia [Fermilab; Texas U., Arlington]↗
DOE OSTI2025

Data-driven high-dimensional statistical inference with generative models

Crucial to many measurements at the LHC is the use of correlated multi-dimensional information to distinguish rare processes from large backgrounds, which is complicated by the poor modeling of many of the crucial backgrounds in Monte Carlo simulations. In this work, we introduce HI-SIGMA, a method to perform unbinned high-dimensional statistical inference with data-driven background distributions. In contradistinction to many applications of Simulation Based Inference in High Energy Physics, HI-SIGMA relies on generative ML models, rather than classifiers, to learn the signal and background distributions in the high-dimensional space. These ML models allow for interpretable inference while also incorporating model errors and other sources of systematic uncertainties. We showcase this methodology on a simplified version of a di-Higgs measurement in the bbγγ final state, where the di-photon resonance allows for background interpolation from sidebands into the signal region. We demonstrate that HI-SIGMA provides improved sensitivity as compared to standard classifier-based methods, and that systematic uncertainties can be straightforwardly incorporated by extending methods which have been used for histogram based analyses.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗