SEARCH · Engineering Papers

Results for “Neural Network Potentials”

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 217 records · Page 12

All sources NASA NTRS DOE OSTI

DOE OSTI2024

Integrated photonic encoder for low power and high-speed image processing

Abstract Modern lens designs are capable of resolving greater than 10 gigapixels, while advances in camera frame-rate and hyperspectral imaging have made data acquisition rates of Terapixel/second a real possibility. The main bottlenecks preventing such high data-rate systems are power consumption and data storage. In this work, we show that analog photonic encoders could address this challenge, enabling high-speed image compression using orders-of-magnitude lower power than digital electronics. Our approach relies on a silicon-photonics front-end to compress raw image data, foregoing energy-intensive image conditioning and reducing data storage requirements. The compression scheme uses a passive disordered photonic structure to perform kernel-type random projections of the raw image data with minimal power consumption and low latency. A back-end neural network can then reconstruct the original images with structural similarity exceeding 90%. This scheme has the potential to process data streams exceeding Terapixel/second using less than 100 fJ/pixel, providing a path to ultra-high-resolution data and image acquisition systems.

47 OTHER INSTRUMENTATION↗

DOE OSTI2024

Sparsified time-dependent Fourier neural operators for fusion simulations

This paper presents a sparsified Fourier neural operator for coupled time-dependent partial differential equations (ST-FNO) as an efficient machine learning surrogate for fluid and particle-based fusion codes such as NIMROD (Non-Ideal Magnetohydrodynamics with Rotation - Open Discussion) and GTC (Gyrokinetic Toroidal Code). ST-FNO leverages the structures in the governing equations and utilizes neural operators to represent Green's function-like numerical operators in the corresponding numerical solvers. Once trained, ST-FNO can rapidly and accurately predict dynamics in fusion devices compared with first-principle numerical algorithms. In general, ST-FNO represents an efficient and accurate machine learning surrogate for numerical simulators for multi-variable nonlinear time-dependent partial differential equations, with the proposed architectures and loss functions. The efficacy of ST-FNO has been demonstrated using quiescent H-mode simulation data from NIMROD and kink-mode simulation data from GTC. The ST-FNO H-mode results show orders of magnitude reduction in memory and central processing unit usage in comparison with the numerical solvers in NIMROD when computing fields over a selected poloidal plane. The ST-FNO kink-mode results achieve a factor of 2 reduction in the number of parameters compared to baseline FNO models without accuracy loss.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗

NASA NTRSDate not supplied

SWIPE: Spectral Water Inversion Processor and Emulator

Degradation of Earth’s inland water resources due to anthropogenic perturbations and climate anomalies at both local and global scales continues to place human health at substantial risk. There is now a growing necessity to develop pragmatic approaches that allow timely and effective extrapolation of local processes, to spatially resolved global products, and to promote operational and sustainable resource policy management. This presentation will be discussing the progress made developing SWIPE: Spectral Water Inversion Processor and Emulator. SWIPE is a platform for advanced modeling of coastal and inland aquatic habitats. The goal is create a comprehensive and cohesive system to leverage recent advancements in computation and machine learning to develop a synthetic training ground for sensitivity studies and algorithm development. The four principal facets of SWIPE include: 1. Advanced two-layer coated sphere bio-optical modeling and GPU radiative transfer modeling, 2. Big Data involving massive synthetic spectral libraries of optical properties of various global aquatic particles, surface reflectance, and top-of-atmosphere reflectance, all at hyperspectral resolution leveraging high-end computing systems at NASA Ames Research Center, 3. Deep Learning for algorithm development for water quality inversion of concentrations of common biogeophysical variables as well as optics, full uncertainty characterization by water type, and forward emulation, and lastly, 4. Image Processing for application of developed retrieval algorithms for both hyperspectral and multispectral sensors with experimental corrections for global adjacency, noise, sunglint, and benthic reflectance. This presentation will demonstrate the Equivalent Algal Populations (EAP) two-layer coated sphere scattering model which has been used develop spectral libraries of hyperspectral inherent optical properties of roughly 80 species of phytoplankton, covering 15 different classes and nine taxonomic functional types. The EAP model was also used to derive spectral properties of 10 different non-algal particle functional types. Examples of how the SMART-G (Speed-up Monte-carlo Advanced Radiative Transfer using GPU) radiative transfer code is used to model optically complex aquatic signals will be presented and discussed in the context of creating a massive synthetic database which can leverage the full power of next generation machine learning techniques and high end computing for water quality inversion. We will discuss our active investigation in things like appropriate model architectures, dimensionality reduction techniques such as PCA and autoencoders, uncertainty quantification and abstaining, and which variables actually benefit most from hyperspectral information versus multispectral resolution. We are also curious about questions relating to cost/benefit analysis in terms of computation resources, neural network complexity, and data volumes. Answers to these questions will hopefully elaborate on cost efficiency for potential future sensor design considerations.

SWIPE↗

NASA NTRSDate not supplied

Machine Learning Approaches for Rare-Earth Silicate Environmental Barrier Coating Thermochemical and Thermomechanical Property Predictions

Environmental barrier coatings (EBCs) are a necessary enabling technology for the transition from superalloys to silicon carbide (SiC) ceramic matrix composites (CMCs) in gas turbine engines for increased efficiency and decreased fuel costs. SiC-based CMCs are prone to oxidation-based degradation in the engine hot section, and rare-earth (RE) silicates are promising candidates for EBCs due to their close thermal expansion match to the composite substrate and oxidation resistance. However, the design of EBCs is hindered by the large chemical space of candidate materials and the difficulty in obtaining material properties for engineering optimization. This is especially difficult as research continues into mixed-cation or “high-entropy” RE silicates. First-principles computational methods such as density functional theory (DFT) are highly effective at calculating material properties to guide coating design but are limited by their computational cost. Atomistic simulations have the potential to both accelerate property calculations and expand the properties able to be calculated due to their lower computational compared to DFT. However, they require interatomic potentials (IAPs) specific to the material system of interest, and, to our knowledge, there are no suitable IAPs for RE silicates. Machine learning (ML) is a promising technique to accelerate material property predictions indirectly by generating IAPs for atomistic simulations or via direct prediction. In this work, we present two ML approaches to accelerate the calculation of RE silicate properties relevant to EBC design: 1) a ML-derived interatomic potential (IAP) for atomistic simulations of yttrium disilicate (Y2Si2O7) from DFT training data, and 2) a neural network (NN) model to directly predict thermochemical properties of RE silicates and oxides directly from easily obtainable unit cell parameters. Classical MD simulations using the IAP yield lattice properties and bond lengths in good agreement with both DFT and experimental results from x-ray diffraction. Thermodynamic properties calculated using the finite-displacement phonon method and quasi-harmonic approximation were orders of magnitude faster than DFT with good agreement to the DFT results. The IAP was also used to calculate properties such as coefficient of thermal expansion (CTE) that require large simulation supercells and are therefore difficult with DFT. The IAP correctly predicted the anisotropic nature of the CTE in three different phases of Y2Si2O7. The NN model predicts constant pressure heat capacity, Cp, orders of magnitude faster than DFT calculations, which can enable its use as a surrogate model for multiscale simulations. The two methods presented in this work demonstrate the utility of ML for accelerating the prediction of RE silicate properties, which can in turn accelerate EBC design and optimization.

machine learning↗

NASA NTRS2023

Plant Disease Detection: Exploring Applications in Hyperspectral Imaging and Machine Learning for Agriculture

The threat of crop disease on food security and agriculture is projected to escalate, leading to reduced crop yields, global economic loss, and endangered food availability to vulnerable populations. Early identification of plant disease is crucial to combatting the crisis but traditional manual methods for disease detection are laborious and may miss early signs of infection. The proposed solution suggests equipping a drone with a hyperspectral camera to collect images and analyzing the data with neural networks trained to flag and classify infected plants. This approach offers a faster, more accurate, and potentially more cost-effective alternative to current practices. While the expensive and complex nature of hyperspectral imaging (HSI) may be an obstacle to the adoption of the drone, rapidly advancing technologies compounded with rental-based usage may make these tools simpler, cheaper, and more accessible to a wider audience. The research further discusses the potential for automated flight paths and the expansion of disease detection to a broader range of crops.

plant disease detection↗

NASA NTRSDate not supplied

Predictive Workload Model for Air Traffic Controllers during UAM Operations

The effect of airspace factors on air traffic controller (ATC) workload has been an active area of study for almost three decades due to the importance of safety considerations necessary to design and maintain operations. Existing literature has examined several traffic-related (e.g., number of aircraft under control, loss of separation) contributors to ATC workload and proposed mathematical functions to best describe controller response. However, future air traffic continues to increase in complexity with the introduction of urban air mobility (UAM) – or the transportation of humans and cargo using electric vertical takeoff and landing (eVTOL) aircraft. UAM aims to alleviate congestion for existing ground transportation systems and improve mobility within urban centers and other high-demand locations. This shift in the traditional airspace paradigm necessitates an evolved understanding of model use and development for ATC workload prediction. This study aimed to develop an ATC workload forecasting model based on human-in-the-loop (HITL) simulation data for UAM operations at large airports. Data collected from the HITL simulation served as the training and testing data for a Long Short-Term Memory recurrent neural network and enabled time-series forecasting of ATC workload from traffic characteristics. Results demonstrated the potential of LSTM models for forecasting ATC workload 40 minutes into the future and highlighted important considerations for future development.

predictive model↗

NASA NTRSDate not supplied

Predictive Workload Model for Air Traffic Controllers during UAM Operations

predictive model↗

DOE OSTI2024

Predicting Drug Effects from High-dimensional Asymmetric Drug Data Sets using Graph Neural Networks: A Comprehensive Analysis of Multi-target Drug Effect Prediction

Graph neural networks (GNNs) have emerged as one of the most effective Machine learning (ML) techniques for drug effect prediction from drug molecular graphs. Despite having immense potential, GNN models lack performance when using data sets that contain high dimensional asymmetrically co-occurrent drug effects as targets with complex correlations between them. Training individual learning models for each drug effect and incorporating every prediction result for a wide spectrum of drug effects is beyond practicality. Such an implication provides a testbed to address this challenge as multi-target prediction problems, aiming to predict all drug effects at a time. We develop standard and hybrid graph neural networks (GNNs)to perform two separate tasks that are multi-regression for continuous values and multi-label classification for categorical values contained in our data sets. Since this step makes the target data even more sparse and introduces asymmetric label co-occurrence, the learning of multi-label classification models becomes difficult and heavily impacts the GNN's performance. To address these challenges, we propose a new data oversampling technique to improve multi-label classification performances on all the given imbalanced molecular graph data sets. Using the technique, we improve the data imbalance ratio of the drug effects better than before while protecting the data set's integrity. Finally, we evaluate multi-label classification performance using the best-performant hybrid GNN model on all the oversampled data sets obtained from the proposed oversampling technique. These results outperform those of other ML models including GNN models when they are trained on the original data sets or oversampled data sets using MLSMOTE (a well-known oversampling technique) in all evaluation metrics precision, recall, and F1 score by a significant margin.

Bose, Avishek [ORNL]↗

NASA NTRS1994

Neural network application to comprehensive engine diagnostics

We have previously reported on the use of neural networks for detection and identification of faults in complex microprocessor controlled powertrain systems. The data analyzed in those studies consisted of the full spectrum of signals passing between the engine and the real-time microprocessor controller. The specific task of the classification system was to classify system operation as nominal or abnormal and to identify the fault present. The primary concern in earlier work was the identification of faults, in sensors or actuators in the powertrain system as it was exercised over its full operating range. The use of data from a variety of sources, each contributing some potentially useful information to the classification task, is commonly referred to as sensor fusion and typifies the type of problems successfully addressed using neural networks. In this work we explore the application of neural networks to a different diagnostic problem, the diagnosis of faults in newly manufactured engines and the utility of neural networks for process control.

Marko, Kenneth A.↗

NASA NTRS1995

Searching for patterns in remote sensing image databases using neural networks

We have investigated a method, based on a successful neural network multispectral image classification system, of searching for single patterns in remote sensing databases. While defining the pattern to search for and the feature to be used for that search (spectral, spatial, temporal, etc.) is challenging, a more difficult task is selecting competing patterns to train against the desired pattern. Schemes for competing pattern selection, including random selection and human interpreted selection, are discussed in the context of an example detection of dense urban areas in Landsat Thematic Mapper imagery. When applying the search to multiple images, a simple normalization method can alleviate the problem of inconsistent image calibration. Another potential problem, that of highly compressed data, was found to have a minimal effect on the ability to detect the desired pattern. The neural network algorithm has been implemented using the PVM (Parallel Virtual Machine) library and nearly-optimal speedups have been obtained that help alleviate the long process of searching through imagery.

Paola, Justin D.↗

DOE OSTI2024

Missing Wedge Completion via Unsupervised Learning with Coordinate Networks

Cryogenic electron tomography (cryoET) is a powerful tool in structural biology, enabling detailed 3D imaging of biological specimens at a resolution of nanometers. Despite its potential, cryoET faces challenges such as the missing wedge problem, which limits reconstruction quality due to incomplete data collection angles. Recently, supervised deep learning methods leveraging convolutional neural networks (CNNs) have considerably addressed this issue; however, their pretraining requirements render them susceptible to inaccuracies and artifacts, particularly when representative training data is scarce. To overcome these limitations, we introduce a proof-of-concept unsupervised learning approach using coordinate networks (CNs) that optimizes network weights directly against input projections. This eliminates the need for pretraining, reducing reconstruction runtime by 3–20× compared to supervised methods. Our in silico results show improved shape completion and reduction of missing wedge artifacts, assessed through several voxel-based image quality metrics in real space and a novel directional Fourier Shell Correlation (FSC) metric. Our study illuminates benefits and considerations of both supervised and unsupervised approaches, guiding the development of improved reconstruction strategies.

42 ENGINEERING↗

DOE OSTI2026

Peak2Patch: High-Fidelity Functional Group Identification through Attention-Based Fusion of Infrared and Mass Spectra

Identifying molecular structure based on spectroscopic readings is a key task in a variety of chemical and biological applications. Common spectroscopy techniques, such as Infrared (IR) Spectroscopy and Mass Spectrometry (MS), provide detailed information on the structure of molecular compounds but nonetheless require expert-level knowledge to decode. Machine learning has emerged as a potential solution for automating structure prediction from chemical spectra; however, current approaches generally focus on single sensor modalities, neglecting to leverage the complementary information contained within differing spectra. In this paper, we introduce Peak2Patch, a novel approach to fusion-enhanced prediction of functional groups from IR and mass spectra. First, we perform a detailed comparison of backbone networks for encoding both sparse mass spectra and dense IR spectra and demonstrate the superior performance of transformer neural networks over current state-of-the-art convolutional neural networks. Second, we evaluate three broad categories of fusion: early (raw feature), middle (deep feature), and late (decision) fusion, demonstrating the potential of a deep feature fusion-based approach. Lastly, we present Peak2Patch, our attention-based fusion scheme, which leverages cross-attention to mix features between encoded tokens of the two modalities. We validate our approach on a publicly available multimodal spectroscopic data set of 790k simulated molecules, demonstrating a large improvement in functional group prediction over both the previous state-of-the-art and our own strong single-modal baselines.

Jacobson, Philip [Sandia National Laboratories (SN↗

NASA NTRS1994

A Feasibility Study for Perioperative Ventricular Tachycardia Prognosis and Detection and Noise Detection Using a Neural Network and Predictive Linear Operators

To locate the accessory pathway(s) in preexicitation syndromes, epicardial and endocardial ventricular mapping is performed during anterograde ventricular activation via accessory pathway(s) from data originally received in signal form. As the number of channels increases, it is pertinent that more automated detection of coherent/incoherent signals is achieved as well as the prediction and prognosis of ventricular tachywardia (VT). Today's computers and computer program algorithms are not good in simple perceptual tasks such as recognizing a pattern or identifying a sound. This discrepancy, among other things, has been a major motivating factor in developing brain-based, massively parallel computing architectures. Neural net paradigms have proven to be effective at pattern recognition tasks. In signal processing, the picking of coherent/incoherent signals represents a pattern recognition task for computer systems. The picking of signals representing the onset ot VT also represents such a computer task. We attacked this problem by defining four signal attributes for each potential first maximal arrival peak and one signal attribute over the entire signal as input to a back propagation neural network. One attribute was the predicted amplitude value after the maximum amplitude over a data window. Then, by using a set of known (user selected) coherent/incoherent signals, and signals representing the onset of VT, we trained the back propagation network to recognize coherent/incoherent signals, and signals indicating the onset of VT. Since our output scheme involves a true or false decision, and since the output unit computes values between 0 and 1, we used a Fuzzy Arithmetic approach to classify data as coherent/incoherent signals. Furthermore, a Mean-Square Error Analysis was used to determine system stability. The neural net based picking coherent/incoherent signal system achieved high accuracy on picking coherent/incoherent signals on different patients. The system also achieved a high accuracy of picking signals which represent the onset of VT, that is, VT immediately followed these signals. A special binary representation of the input and output data allowed the neural network to train very rapidly as compared to another standard decimal or normalized representations of the data.

Moebes, T. A.↗

DOE OSTI2024

A Neural Network-Based Power Mismatch Elimination Strategy for Integrated Solar and ESS AC/DC Systems (MARS)

The multiport autonomous reconfigurable solar power plant (MARS) is a promising concept for the integration of photovoltaic (PV) and energy storage system (ESS) to the transmission ac grid and a high-voltage direct current (HVdc) link. The presence of PV and ESS in each arm of the MARS results in uneven distribution of active power among different submodules (SMs), thereby leading to unbalanced SM capacitor voltages and potentially compromising the system stability. Moreover, in the case of partial shadings, shaded PV SMs will suffer from decreased power injections causing power mismatch in the MARS system. To address this issue, a neural-network-based power mismatch elimination (NNPME) strategy is proposed in this article. The proposed NNPME strategy optimizes ESS usage and leverages both dc and ac circulating currents to facilitate power transfer among the SMs, arms, and phases of the MARS system. Simulation and control hardware-in-the-loop (cHIL) experiments demonstrate the effectiveness of the proposed NNPME strategy. Compared with the traditional approaches, the proposed NNPME strategy can significantly enhance system efficiency and ensure stable and continuous operation, even in the presence of uneven power distribution within the MARS system.

14 SOLAR ENERGY↗

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

Machine Learning for DUNE Supernova Trigger

One of the major scientific goals of the Deep Underground Neutrino Experiment (DUNE) is to detect and measure the neutrino flux originating from galactic core-collapse supernovae. These neutrinos provide an opportunity to study the end of life evolution of massive stars, and reveal information about the structure of core-collapse that is not visible in observations of the electromagnetic spectrum. Because of the rarity of these events, it is crucial that DUNE is able to detect supernova neutrino interactions when they occur. However, this will require sifting through a large quantity of data, motivating the development of a trigger algorithm to identify significant events and discard irrelevant data. Machine learning provides a potential approach to building this trigger. This project generates ADC and ground truth images of simulated neutrino interactions in a LArTPC detector to be used for machine learning, and uses them to train a sparse Convolutional Neural Network (C NN). The performance of this model when applied to the task of pixel classification based on interaction type is examined. This project found that the sparse CNN approach has the potential to have high accuracy in pixel classification, meaning it may be highly relevant to the development of a supernova neutrino trigger for the DUNE far detector.

Damish, S.↗

DOE OSTI2026

Anomaly Detection in the SBND Experiment Based on Graph Neural Networks

Traditional anomaly detection in SBND experiments require data reconstruction and manual supervision, and thus has the drawbacks of long detection time, being labour intensive and incapable of predicting potential future anomalies. Machine learning models, especially autoencoders, have been widely applied in anomaly detection, and developing an autoencoder for anomaly detection in SBND experiment is going to tremendously improve the efficiency and accuracy of the experiment. The autoencoder has the advantage of automation, efficiency, and can be used to predict future anomalies in the SBND experiment.

Fu, Jiayu [U. Chicago (main)]↗

DOE OSTI2024

Zero-Power Analog Optical Processing

The motivation behind this research is the growing challenge of handling the massive amounts of data generated by modern imaging systems. Conventional digital image processing techniques are struggling to keep pace with the demands of high-resolution and high-speed imaging systems for remote sensing due to their high-power consumption and data storage requirements. We present a novel approach based on analog photonics to address this challenge. The proposed system utilizes a silicon-photonics-based image encoder positioned after image formation and initial optical-to-electrical conversion. The photonic encoder compresses image data using a passive disordered photonic structure to perform kernel-type random projections of the raw data. The compressed data is then processed by a back-end neural network, which reconstructs the original image with high fidelity (structural similarity exceeding 90%). Our proposed approach has the potential to compress images with ~ 1000X lower power consumption compared to digital approaches with data rates exceeding 1 terapixel/second.

97 MATHEMATICS AND COMPUTING↗