Search NASA⌕ Search

SEARCH · Search NASA

Results for “Deep Operator Network”

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 415 records · Page 23
All sourcesNASA NTRSDOE OSTI
DOE OSTI2022

A Length Adaptive Algorithm-Hardware Co-design of Transformer on FPGA Through Sparse Attention and Dynamic Pipelining

Transformers are considered one of the most important deep learning models since 2018, in part because it establishes state-of-the-art (SOTA) records and could potentially replace existing Deep Neural Networks (DNNs). Despite the remarkable triumphs, the prolonged turnaround time of Transformer models is a widely recognized roadblock. The variety of sequence lengths imposes additional computing overhead where inputs need to be zero-padded to the maximum sentence length in the batch to accommodate the parallel computing platforms. This paper targets the field-programmable gate array (FPGA) and proposes a coherent sequence length adaptive algorithm–hardware co-design for Transformer acceleration. Particularly, we develop a hardware-friendly sparse attention operator and a length-aware hardware resource scheduling algorithm. The proposed sparse attention operator brings the complexity of attention-based models down to linear complexity and alleviates the off-chip memory traffic. The proposed length-aware resource hardware scheduling algorithm dynamically allocates the hardware resources to fill up the pipeline slots and eliminates bubbles for NLP tasks. Experiments show that our design has very small accuracy loss and has 80.2 × and 2.6 × speedup compared to CPU and GPU implementation, and 4 × higher energy efficiency than state-of-the-art GPU accelerator optimized via CUBLAS GEMM.

Peng, Hongwu↗
DOE OSTI2022

Predicting Solar Energetic Particles Using SDO/HMI Vector Magnetic Data Products and a Bidirectional LSTM Network

Solar energetic particles (SEPs) are an essential source of space radiation, and are hazardous for humans in space, spacecraft, and technology in general. In this paper, we propose a deep-learning method, specifically a bidirectional long short-term memory (biLSTM) network, to predict if an active region (AR) would produce an SEP event given that (i) the AR will produce an M- or X-class flare and a coronal mass ejection (CME) associated with the flare, or (ii) the AR will produce an M- or X-class flare regardless of whether or not the flare is associated with a CME. The data samples used in this study are collected from the Geostationary Operational Environmental Satellite's X-ray flare catalogs provided by the National Centers for Environmental Information. We select M- and X-class flares with identified ARs in the catalogs for the period between 2010 and 2021, and find the associations of flares, CMEs, and SEPs in the Space Weather Database of Notifications, Knowledge, Information during the same period. Each data sample contains physical parameters collected from the Helioseismic and Magnetic Imager on board the Solar Dynamics Observatory. Experimental results based on different performance metrics demonstrate that the proposed biLSTM network is better than related machine-learning algorithms for the two SEP prediction tasks studied here. We also discuss extensions of our approach for probabilistic forecasting and calibration with empirical evaluation

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2025

Identifying environmentally induced calibration changes in cryogenic RF axion detector systems using deep neural networks

The axion is a compelling hypothetical particle that could account for the dark matter in our universe while simultaneously solving the strong CP problem in quantum chromodynamics. The most sensitive axion detection technique demonstrated so far makes use of a high Q cavity immersed in a strong magnetic field, where axions are converted to microwave photons. This is called an axion haloscope and has primarily targeted the 1–10 GHz range. As searches scan up in axion mass, toward the parameter space favored by theoretical predictions, individual cavity sizes decrease in order to achieve higher frequencies. This shrinking cavity volume translates directly to a loss in signal-to-noise, motivating the plan to replace individual cavity detectors with arrays of cavities. When the transition from one to (N) multiple cavities occurs, haloscope searches are anticipated to become much more complicated to operate, requiring N times as many measurements but also the new requirement that N detectors operate in unison, which can be achieved by locking them to a common frequency. To offset this anticipated increase in detector complexity, we aim to develop new tools for diagnosing experiments using neural networks. Current experiments monitor scattering parameters of their receiver for periodically measuring cavity quality factor and coupling. However, off-resonant data remain relatively useless. In this paper, we ask if it is possible that off-resonant information contained in vector network analyzer scans could be used to diagnose equipment failures/anomalies and measure physical conditions (e.g., temperatures and ambient magnetic field). We demonstrate a proof-of-concept that AI techniques can help manage the complexity of an axion haloscope search for operators.

Engel, Andrew W. [Pacific Northwest National Labor↗
DOE OSTI2026

A non-intrusive framework using acoustic signals and deep learning for boiling diagnostics in visual-limited environments

Accurate monitoring of boiling heat transfer is critical for safeguarding high-power systems operating in environments where conventional optical diagnostics are hindered by radiation fields or restricted visual accessibility. This study presents a non-intrusive framework that integrates hydroacoustic sensing with deep learning to infer near-wall boiling characteristics and enable predictive thermal assessment without visual access. In a prototypical subcooled flow-boiling facility representative of the Isotope Production Facility (IPF) at Los Alamos, hydrophones capture boiling-induced acoustic emissions that are transformed into background-removed Short-Time Fourier Transform (STFT) spectrograms. A convolutional neural network (CNN) then regresses heat flux, wall superheat, and key bubble parameters directly from these spectrograms. The CNN achieved predictive accuracy under nominal conditions and demonstrated robustness and generalization under acoustic noise for Signal-to-Noise Ratios (SNRs) down to approximately 0 dB. When integrated into an ANSYS CFX wall-boiling model, the acoustically inferred parameters reproduced boiling curve and critical heat flux (CHF) values consistent with image-based benchmarks. Furthermore, the model retained reliable performance under moderate variations in bulk temperature, flow rate, and hydrophone placement, confirming its generalizability across practical boundary conditions. These results demonstrate the feasibility of hydroacoustic-based deep learning as a viable path toward real-time, radiation-tolerant boiling diagnostics and predictive thermal safety assessment in inaccessible systems such as the IPF.

42 ENGINEERING↗
DOE OSTI2022

Device-Centric Ransomware Detection using Machine Learning-Based Memory Forensics for Smart Inverters

Ransomware attacks are the fastest-growing form of cyberattacks worldwide. Recently, ransomware attacks have targeted industrial control systems (ICSs), including power grids. Lessons learned from recent incidents in ICSs show that ransomware groups can deliver ransomware into not only the organization’s control servers, but also the operational technology (OT) devices such as smart inverters and smart grid devices. This paper proposes a machine learning (ML)- based memory forensics method enabling the detection of ransomware binaries stored in the memory of a commercial smart inverter. Device firmware binary files are extracted from a Serial Peripheral Interface (SPI) flash memory, and samples of both benign and ransomware binaries are generated by a binary manipulation method and a real-world ransomware encryption, separately. A deep transfer learning (DTL) method is used to retrain a convolutional neural network (CNN)-based ransomware detection algorithm using the generated samples. The experimental result validates that the proposed ML-based memory forensics method can accurately detect ransomware files.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2022

A Wireless Underground Sensor Network Field Pilot for Agriculture and Ecology: Soil Moisture Mapping Using Signal Attenuation

Wireless Underground Sensor Networks (WUSNs) that collect geospatial in situ sensor data are a backbone of internet-of-things (IoT) applications for agriculture and terrestrial ecology. In this paper, we first show how WUSNs can operate reliably under field conditions year-round and at the same time be used for determining and mapping soil conditions from the buried sensor nodes. We demonstrate the design and deployment of a 23-node WUSN installed at an agricultural field site that covers an area with a 530 m radius. The WUSN has continuously operated since September 2019, enabling real-time monitoring of soil volumetric water content (VWC), soil temperature (ST), and soil electrical conductivity. Secondly, we present data collected over a nine-month period across three seasons. We evaluate the performance of a deep learning algorithm in predicting soil VWC using various combinations of the received signal strength (RSSI) from each buried wireless node, above-ground pathloss, the distance between wireless node and receive antenna (D), ST, air temperature (AT), relative humidity (RH), and precipitation as input parameters to the model. The AT, RH, and precipitation were obtained from a nearby weather station. We find that a model with RSSI, D, AT, ST, and RH as inputs was able to predict soil VWC with an R 2 of 0.82 for test datasets, with a Root Mean Square Error of ±0.012 (m 3 /m 3 ). Hence, a combination of deep learning and other easily available soil and climatic parameters can be a viable candidate for replacing expensive soil VWC sensors in WUSNs.

47 OTHER INSTRUMENTATION↗
DOE OSTI2023

Learning diffractive optical communication around arbitrary opaque occlusions

Abstract Free-space optical communication becomes challenging when an occlusion blocks the light path. Here, we demonstrate a direct communication scheme, passing optical information around a fully opaque, arbitrarily shaped occlusion that partially or entirely occludes the transmitter’s field-of-view. In this scheme, an electronic neural network encoder and a passive, all-optical diffractive network-based decoder are jointly trained using deep learning to transfer the optical information of interest around the opaque occlusion of an arbitrary shape. Following its training, the encoder-decoder pair can communicate any arbitrary optical information around opaque occlusions, where the information decoding occurs at the speed of light propagation through passive light-matter interactions, with resilience against various unknown changes in the occlusion shape and size. We also validate this framework experimentally in the terahertz spectrum using a 3D-printed diffractive decoder. Scalable for operation in any wavelength regime, this scheme could be particularly useful in emerging high data-rate free-space communication systems.

36 MATERIALS SCIENCE↗
DOE OSTI2024

Low latency optical-based mode tracking with machine learning deployed on FPGAs on a tokamak

Active feedback control in magnetic confinement fusion devices is desirable to mitigate plasma instabilities and enable robust operation. Optical high-speed cameras provide a powerful, non-invasive diagnostic and can be suitable for these applications. Here, in this study, we process high-speed camera data, at rates exceeding 100 kfps, on in situ field-programmable gate array (FPGA) hardware to track magnetohydrodynamic (MHD) mode evolution and generate control signals in real time. Our system utilizes a convolutional neural network (CNN) model, which predicts the n = 1 MHD mode amplitude and phase using camera images with better accuracy than other tested non-deep-learning-based methods. By implementing this model directly within the standard FPGA readout hardware of the high-speed camera diagnostic, our mode tracking system achieves a total trigger-to-output latency of 17.6 μs and a throughput of up to 120 kfps. This study at the High Beta Tokamak-Extended Pulse (HBT-EP) experiment demonstrates an FPGA-based high-speed camera data acquisition and processing system, enabling application in real-time machine-learning-based tokamak diagnostic and control as well as potential applications in other scientific domains.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
DOE OSTI2021

Smart Methane Emission Detection System Development Final Report

Working with the Department of Energy's National Energy Technology Laboratory, Southwest Research Institute® (SwRI®) developed a system to identify methane leaks reliably, accurately, and autonomously at critical midstream sections of the natural gas distribution network in real- time for the purpose of mitigating methane emissions using Optical Gas Imaging (OGI) cameras. SwRI's Smart Leak Detection – Methane (SLED/M) adds a high degree of automation to the process of methane leak detection to minimize sources of human error, minimize response time to a leak event, and maximize midstream visibility. Furthermore, SwRI has been working towards integrating Quantitative OGI (QOGI) capabilities into this existing technology. By leveraging Deep Learning, SwRI now has the capability to estimate fugitive emission leak rates quickly and reliably, which allows operators to detect emissions, quantify leak rate, prioritize repairs, and validate the repairs in a single instrument. The next generation QOGI technology leverages the same cameras used in Leak Detection and Repair (LDAR) programs, with improvements in safety and speed for traditional quantification-based repairs, ultimately leading to less overhead cost for the operators.

03 NATURAL GAS↗
DOE OSTI2024

D2NO: Efficient handling of heterogeneous input function spaces with distributed deep neural operators

Neural operators have been applied in various scientific fields, such as solving parametric partial differential equations, dynamical systems with control, and inverse problems. However, challenges arise when dealing with input functions that exhibit heterogeneous properties, requiring multiple sensors to handle functions with minimal regularity. To address this issue, discretization-invariant neural operators have been used, allowing the sampling of diverse input functions with different sensor locations. However, existing frameworks still require an equal number of sensors for all functions. We propose a novel distributed approach to further relax the discretization requirements and solve the heterogeneous dataset challenges. Our method involves partitioning the input function space and processing individual input functions using independent and separate neural networks. A centralized neural network is used to handle shared information across all output functions. This distributed methodology reduces the number of gradient descent back-propagation steps, improving efficiency while maintaining accuracy. Here, we demonstrate that the corresponding neural network is a universal approximator of continuous nonlinear operators and present three numerical examples to validate its performance.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2022

Wavelet and Deep-Learning-Based Approach for Generation System Problematic Parameters Identification and Calibration

Accurate models of generation systems are critical for maintaining reliable and secure grid operations. In this paper, a novel and systematic approach is proposed to identify and calibrate the generation system problematic parameters using continuous wavelet transform (CWT) and advanced deep-learning technology. The phasor measurement unit (PMU) data are used through “event playback” to check whether the parameter calibration is required, and if yes, a group of suspicious parameters will be identified as the primary problematic parameter candidates (PPCs). These primary PPCs are randomly perturbed to generate the event playback simulation data, which are used by the CWT and convolutional neural networks (CNNs) to further narrow down the primary PPCs into a smaller set of candidates. Then, the identified candidates are perturbed again to generate massive event playback simulation data for training a parameter calibration neural network. Here, we designed a multi-output neural network structure to find the mappings between the perturbed parameters and the simulation data using both CNN and long short-term memory (LSTM) models. Finally, the well-trained and tested CNN-LSTM model is used to estimate the accurate value of the suspicious parameters with actual PMU measurements. The proposed CNN-LSTM network can accurately and reliably estimate the generation-system problematic parameters, and has better performance when compared to other machine-learning methods, such as the multilayer perceptron network and the conditional variational autoencoder method. The accuracy and effectiveness of the proposed approach have been validated through simulation and real-world data.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2022

DNN-based policies for stochastic AC OPF

We report a prominent challenge to the safe and optimal operation of the modern power grid arises due to growing uncertainties in loads and renewables. Stochastic optimal power flow (SOPF) formulations provide a mechanism to handle these uncertainties by computing dispatch decisions and control policies that maintain feasibility under uncertainty. Most SOPF formulations consider simple control policies such as affine policies that are mathematically simple and resemble many policies used in current practice. Motivated by the efficacy of machine learning (ML) algorithms and the potential benefits of general control policies for cost and constraint enforcement, we put forth a deep neural network (DNN)-based policy that predicts the generator dispatch decisions in real time in response to uncertainty. The weights of the DNN are learnt using stochastic primal–dual updates that solve the SOPF without the need for prior generation of training labels and can explicitly account for the feasibility constraints in the SOPF. The advantages of the DNN policy over simpler policies and their efficacy in enforcing safety limits and producing near optimal solutions are demonstrated in the context of a chance constrained formulation on a number of test cases.

29 ENERGY PLANNING, POLICY, AND ECONOMY↗
DOE OSTI2018

Automated Labeling of Electron Microscopy Images Using Deep Learning

© 2018 IEEE. Searching for scientific data requires metadata providing a relevant context. Today, generating metadata is a time and labor intensive manual process that is often neglected, and important datasets are not accessible through search. We investigate the use of machine learning to generalize metadata from a subset of labeled data, thus increasing the availability of meaningful metadata for search. Specifically, we consider electron microscopy images collected at the National Center for Electron Microscopy (NCEM) at the Lawrence Berkeley National Laboratory (LBNL) and use deep learning to discern characteristics from a small subset of labeled images and transfer labels to the entire image corpus. Relatively small training set sizes and a minimum resolution of 512\times 512 pixels required by the application domain pose unique challenges. We overcome these challenges by using a simple yet powerful convolutional network architecture that limits the number of free parameters to lower the required amount of computational power and reduce the risk of overfitting. We achieve a classification accuracy of approximately 80% in discerning between images recorded in two operating modes of the electron microscope-transmission electron microscopy (TEM) and scanning transmission electron microscopy (STEM). We use transfer learning-i.e., re-using the pre-trained convolution layers from the TEM vs. STEM classification problem-to generalize labels and achieve an accuracy of approximately 70 % despite current experiments being limited to small training data sets. We present these predictions as suggestions to domain scientists through a web-based tool to accelerate the labeling process with the goal of further validating our approach and improving the accuracy of automatically created labels.

Weber, Gunther H↗
DOE OSTI2024

TwinMe4AD: WGAN-based Digital Twins for Anomaly Detection

SAND2024-08373O TwinMe4AD is a Python-based software tool designed for anomaly detection using digital twins that closely mimic real, wearable healthcare datasets. The tool is invaluable for scenarios where collecting data is either expensive or impractical, serving as a privacy-preserving solution. Sensitive information is protected by training deep learning models on synthetic data derived from real datasets. One of TwinMe4AD's key features is its anomaly detection capability, which is based on fourth-order moments of parameters. This versatile approach can be applied across a range of datasets, from univariate to multivariate, making it compatible with various types of data. It also generates synthetic twins using Wasserstein Generative Adversarial Networks (WGANs), allowing users to create a small cohort of a population similar to that of a village population. 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.

Poorey, Kunal↗
DOE OSTI2025

Towards automated and real-time multi-object detection of anguilliform fishes from sonar data using YOLOv8 deep learning algorithm

Eels (Anguilla spp.), including American eels (Anguilla rostrata), European eels (Anguilla anguilla), and Japanese eels (Anguilla japonica), are species of critical management and regulatory concern due to their vulnerability to various stressors during downstream migrations. Accurate and efficient detection of migrating eels can improve our understanding of fish behaviors and fish-hydraulic structure interactions, thereby facilitating the design, operation, and optimization of more effective downstream passage facilities from both biological and economic perspectives. However, a real-time, automated framework for detecting migrating eels in real-world applications is currently lacking. Leveraging imaging sonar as a reliable technology for fish passage monitoring, field data are acquired using imaging sonar and then converted to single sonar frames/images for subsequent analysis. In this study, a framework based on the You Only Look Once Version 8 (YOLOv8)-based convolutional neural network is proposed for multi-object detection of eels and non-eel fish using the sonar images after image subtraction and additional wavelet denoising. The results from both training and testing phases demonstrate that the framework's ability can successfully detect both eels and non-eel fish in preprocessed sonar images, achieving F1-scores and mAP@0.50 exceeding 0.84. Additionally, the incorporation of wavelet denoising during preprocessing slightly improve detection performance. Furthermore, the transferability of this framework from eel to lamprey detection is demonstrated to be feasible given the similar morphological characteristics of these two species. Overall, the proposed framework achieves accurate and efficient detection of migrating eels, providing reliable and real-time information that can help conserve vulnerable eel and eel-like populations.

Deep learning↗
DOE OSTI2025

Even Higher-Level Synthesis: An Exploration of AI Hardware Accelerators using HLS4ML

With the rise of artificial intelligence, the popularization of deep learning, and a constantly evolving industry, the demand for flexible and efficient tools has never been greater. As algorithms grow more complex, their runtime and energy consumption increase exponentially. Customized hardware accelerators, long used for specific mathematical operations, remain essential for managing modern applications' computational and power demands. Hardware accelerators can speed up complex computations by orders of magnitude, but their manual design and verification processes are often challenging and time-consuming. High-Level Synthesis (HLS) provides a solution by transforming high-level algorithm descriptions, typically written in C++ or SystemC, into synthesizable RTL suitable for hardware implementation. This approach reduces development time for RTL engineers while offering flexibility beyond what traditional handwritten RTL can provide. We extended this capability to the machine-learning domain with the open-source framework hls4ml, which allows neural networks trained in Python frameworks like Tensorflow or PyTorch to be synthesized into efficient hardware representations for the traditional FPGA and ASIC flows. This breakthrough addresses the growing need for reduced design turnaround and easy verification of ML hardware accelerators with low latency and power efficiency constraints. During this tutorial, we will demonstrate how Python complements HLS by simplifying the ML design process, bridging the gap between software and hardware development. Attendees will explore how we translate neural networks modeled in Python into fixed-point C++ models suitable for HLS workflows. We will dive into strategies like Value-Range Analysis and Quantization-Aware Training, which optimize these designs for deployment and evaluate their accuracy, power consumption, and energy efficiency. To exemplify these concepts, experts from Fermilab will share their experiences applying this technology to high-energy physics experiments, where real-time, low-latency processing is critical. Over the years, Fermilab engineers have demonstrated how deep neural networks, optimized for hardware using hls4ml, can meet the stringent requirements of trigger systems at the CERN Large Hadron Collider. These systems rely on rapid decision-making to process immense data volumes while retaining only the most relevant events for further analysis. The application of hls4ml has also been extended to innovative technologies like smart pixel arrays. These smart pixels integrate ML inference capabilities directly into sensor devices, enabling localized data processing at the pixel level. This approach drastically reduces the need to transmit raw data to external processing units, significantly decreasing power consumption and latency. By embedding neural networks within the pixel architecture, the smart pixels can identify and prioritize relevant data in real time, providing a highly efficient solution for edge computing in scenarios such as particle detectors and imaging systems. Fermilab's work highlights the potential of hardware-accelerated ML in scenarios where both speed and power efficiency are mission-critical. Through this tutorial, attendees will gain valuable insights into the challenges and solutions of deploying ML in hardware. Understanding how HLS and hls4ml streamline the development of neural network-based hardware accelerators is fundamental for the industry's future. Participants will learn how these technologies are shaping the future of AI and scientific computing.

Di Guglielmo, Giuseppe [Fermilab]↗
DOE OSTI2024

Deep Multitask Learning Models for Radiation Estimation at High Energy Accelerator Facility

Controlling the dose of radiation exposure in potential radioactive facilities is critical for ensuring the safety of staff and the public. Here, in this paper, we developed machine learning models to estimate radiation exposure efficiently at the Thomas Jefferson National Accelerator Facility (JLab), aiming to enhance safety in both accelerator facilities and public areas. Multiple sensors were deployed around the three experimental halls at JLab. Data on single-beam currents, energy levels, and radiation values at the sensor locations were collected during accelerator operation. We proposed a multi-task learning model for radiation estimation, utilizing either one-dimensional convolutional neural networks (1-D CNNs) or long short-term memory networks (LSTMs) as the backbone. The proposed model was trained to simultaneously estimate radiation levels at the sensor locations. Experimental results demonstrated that the proposed model with LSTM backbone achieved the best estimation performance, with an average R 2 score of 0.7557 for estimation within the same year and 0.7157 for estimation across different years. These results significantly surpassed those of competing models.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
DOE OSTI2020

Machine learning for nonintrusive model order reduction of the parametric inviscid transonic flow past an airfoil

Fluid flow in the transonic regime finds relevance in aerospace engineering, particularly in the design of commercial air transportation vehicles. Computational fluid dynamics models of transonic flow for aerospace applications are computationally expensive to solve because of the high degrees of freedom as well as the coupled nature of the conservation laws. While these issues pose a bottleneck for the use of such models in aerospace design, computational costs can be significantly minimized by constructing special, structure-preserving surrogate models called reduced-order models. In this work, we propose a machine learning method to construct reduced-order models via deep neural networks and we demonstrate its ability to preserve accuracy with a significantly lower computational cost. In addition, our machine learning methodology is physics-informed and constrained through the utilization of an interpretable encoding by way of proper orthogonal decomposition. Application to the inviscid transonic flow past the RAE2822 airfoil under varying freestream Mach numbers and angles of attack, as well as airfoil shape parameters with a deforming mesh, shows that the proposed approach adapts to high-dimensional parameter variation well. Notably, the proposed framework precludes the knowledge of numerical operators utilized in the data generation phase, thereby demonstrating its potential utility in the fast exploration of design space for diverse engineering applications. Comparison against a projection-based nonintrusive model order reduction method demonstrates that the proposed approach produces comparable accuracy and yet is orders of magnitude computationally cheap to evaluate, despite being agnostic to the physics of the problem.

97 MATHEMATICS AND COMPUTING↗