Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Latent space”

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 253 records · Page 14
All sourcesNASA NTRSDOE OSTI
DOE OSTI2024

Graph learning for particle accelerator operations

Particle accelerators play a crucial role in scientific research, enabling the study of fundamental physics and materials science, as well as having important medical applications. This study proposes a novel graph learning approach to classify operational beamline configurations as good or bad. By considering the relationships among beamline elements, we transform data from components into a heterogeneous graph. We propose to learn from historical, unlabeled data via our self-supervised training strategy along with fine-tuning on a smaller, labeled dataset. Additionally, we extract a low-dimensional representation from each configuration that can be visualized in two dimensions. Leveraging our ability for classification, we map out regions of the low-dimensional latent space characterized by good and bad configurations, which in turn can provide valuable feedback to operators. This research demonstrates a paradigm shift in how complex, many-dimensional data from beamlines can be analyzed and leveraged for accelerator operations.

43 PARTICLE ACCELERATORS↗
DOE OSTI2025

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

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

47 OTHER INSTRUMENTATION↗
DOE OSTI2024

Contrastive Machine Learning with Gamma Spectroscopy Data Augmentations for Detecting Shielded Radiological Material Transfers

Data analysis techniques can be powerful tools for rapidly analyzing data and extracting information that can be used in a latent space for categorizing observations between classes of data. Machine learning models that exploit learned data relationships can address a variety of nuclear nonproliferation challenges like the detection and tracking of shielded radiological material transfers. The high resource cost of manually labeling radiation spectra is a hindrance to the rapid analysis of data collected from persistent monitoring and to the adoption of supervised machine learning methods that require large volumes of curated training data. Instead, contrastive self-supervised learning on unlabeled spectra can enhance models that are built on limited labeled radiation datasets. This work demonstrates that contrastive machine learning is an effective technique for leveraging unlabeled data in detecting and characterizing nuclear material transfers demonstrated on radiation measurements collected at an Oak Ridge National Laboratory testbed, where sodium iodide detectors measure gamma radiation emitted by material transfers between the High Flux Isotope Reactor and the Radiochemical Engineering Development Center. Label-invariant data augmentations tailored for gamma radiation detection physics are used on unlabeled spectra to contrastively train an encoder, learning a complex, embedded state space with self-supervision. A linear classifier is then trained on a limited set of labeled data to distinguish transfer spectra between byproducts and tracked nuclear material using representations from the contrastively trained encoder. The optimized hyperparameter model achieves a balanced accuracy score of 80.30%. Any given model—that is, a trained encoder and classifier—shows preferential treatment for specific subclasses of transfer types. Regardless of the classifier complexity, a supervised classifier using contrastively trained representations achieves higher accuracy than using spectra when trained and tested on limited labeled data.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
DOE OSTI2022

A Probabilistic Autoencoder for Type Ia Supernova Spectral Time Series

We construct a physically parameterized probabilistic autoencoder (PAE) to learn the intrinsic diversity of Type Ia supernovae (SNe Ia) from a sparse set of spectral time series. The PAE is a two-stage generative model, composed of an autoencoder that is interpreted probabilistically after training using a normalizing flow. We demonstrate that the PAE learns a low-dimensional latent space that captures the nonlinear range of features that exists within the population and can accurately model the spectral evolution of SNe Ia across the full range of wavelength and observation times directly from the data. By introducing a correlation penalty term and multistage training setup alongside our physically parameterized network, we show that intrinsic and extrinsic modes of variability can be separated during training, removing the need for the additional models to perform magnitude standardization. We then use our PAE in a number of downstream tasks on SNe Ia for increasingly precise cosmological analyses, including the automatic detection of SN outliers, the generation of samples consistent with the data distribution, and solving the inverse problem in the presence of noisy and incomplete data to constrain cosmological distance measurements. We find that the optimal number of intrinsic model parameters appears to be three, in line with previous studies, and show that we can standardize our test sample of SNe Ia with an rms of 0.091 ± 0.010 mag, which corresponds to 0.074 ± 0.010 mag if peculiar velocity contributions are removed.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2022

A Machine Learning Framework to Predict Images of Edge-on Protoplanetary Disks

The physical structure and properties of protoplanetary disks are typically derived from spatially resolved disk images. Edge-on disks in particular provide an important view point on the vertical structure and degree of settling of disks. Such analyses rely on radiative transfer (RT) calculations that are generally computationally intensive due to the high optical depth of disks. Here we present a machine learning framework that has the potential to dramatically speed up the forward modeling process by approximating the results of RT calculations. This framework, trained on an initial set of RT calculations, utilizes an autoencoder neural network to enable the generation of synthetic scattered light images of edge-on disks directly from a set of physical parameters. We demonstrate that this framework generates synthetic images 2–3 orders of magnitude faster than using RT calculations. These machine learning-generated images appear to approximate the RT images well, in particular preserving their size and shape. We also find a strong correlation between the latent space representations of the generated disk images and several of their associated physical parameters. Finally, we discuss potential changes to the framework, such as methods to further improve the image quality, extending the framework to multiple wavelengths, and inverting the process to infer physical parameters from observed images. Overall, these new tools have the potential to enable a more efficient and uniform analysis of edge-on disk properties and the initial conditions of planet formation.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2022

HYPHY: Deep Generative Conditional Posterior Mapping of Hydrodynamical Physics

Generating large-volume hydrodynamical simulations for cosmological observables is a computationally demanding task necessary for next-generation observations. In this work, we construct a novel fully convolutional variational autoencoder (VAE) to synthesize hydrodynamic fields conditioned on dark matter fields from N -body simulations. After training the model on a single hydrodynamical simulation, we are able to probabilistically map new dark-matter-only simulations to corresponding full hydrodynamical outputs. By sampling over the latent space of our VAE, we can generate posterior samples and study the variance of the mapping. We find that our reconstructed field provides an accurate representation of the target hydrodynamical fields as well as reasonable variance estimates. This approach has promise for the rapid generation of mocks as well as for implementation in a full inverse model of observed data.

79 ASTRONOMY AND ASTROPHYSICS↗
NASA NTRS2020

A Path Towards Quantum Advantage in Training Deep Generative Models with Quantum Annealing

A class of quantum-classical hybrid machine-learning algorithms can be obtained by integrating classical deep generative models with quantum probability distributions as 'priors' over their latent variables. We introduce a hybrid implementation of variational autoencoders (QVAE) and also present a technique to hybridize flow-based invertible generative models. We demonstrate the use of D-Wave quantum annealers as physical simulators of quantum Boltzmann machines (QBM) to perform quantum-assisted training of QVAE. Latent-space QBM develop slowly mixing modes, opening a path to obtain quantum advantage in generative modeling with available quantum devices.

Vinci, Walter↗
NASA NTRSDate not supplied

High dimensional similarity search with quantum assisted variational autoencoder

Recent progress in quantum algorithms and hardware is indicator of the potential importance of quantum computing in the next future. However, finding suitable application areas remains an active area of research. Quantum machine learning [1] is touted as a potential approach to demonstrate quantum advantage within both the gate-model [2,3] and the adiabatic [4,5] schemes. For instance, the Quantum-assisted Variational Autoencoder (QVAE) [6] has been proposed as a quantum enhancement to the discrete VAE [7]. We extend on previous work and study the real-world applicability of a QVAE, specifically, for similarity search in large-scale high dimensional datasets. While similarity search algorithms are available for low dimensional datasets, scaling to billion-scale datasets with thousands of dimensions is non-trivial. We show how the latent-space representation of a QVAE can be used to construct a space-efficient search index. We back up our claims by experimental results which show a correlation between the Hamming distance in the embedded space and the Euclidean distance in the original space on the Moderate Resolution Imaging Spectroradiometer (MODIS) dataset. Further, we show real-world speedups compared to linear search and demonstrate memory efficient scaling to large-scale datasets.

Nicholas D Gao↗
NASA NTRS2021

Loss of Control Detection for Commercial Transports Using Conditional Variational Autoencoders

This work describes a detector for the loss of control of a commercial transport in flight. The detector has a belief state defined by the latent variable stochastic modeling of a conditional variational autoencoder (CVAE) constructed with bidirectional recurrent layers. In 2000, the Boeing Company and the NASA Langley Research Center jointly developed a quantitative set of metrics for defining loss-of-control (LOC) for a commercial transport. We use the thresholds for these quantitative metrics to define a condition vector for training the CVAE. We demonstrate through experimentation that reconstruction probability is an accurate indicator that the vehicle has shifted to an LOC state. Second, we introduce a technique for inferring that the vehicle is experiencing a flight state change is approaching by measuring a shift in the sampling Gaussian distributions of the latent space. We provide an analysis of its applicability to flight data from a NASA generic commercial transport-type aircraft.

Newton H Campbell↗
NASA NTRSDate not supplied

Use of Design of Experiments in Determining Neural Network Architectures for Loss of Control Detection

We describe empirical methods for selecting a neural network architecture to implement belief state inference on generic commercial transport aircraft. We highlight a case study on the planning, execution, and analysis of a set of experiments to determine the configurations of a conditional variational autoencoder (CVAE). Our main contribution is the application of a structured method that can be used for machine learning in many aerospace applications. This method optimizes the structure and training parameters of a neural network for belief state inference, using Design of Experiments (DOE) statistical methodologies. The motivation for this specific DOE analysis was to identify the appropriate hyperparameters for measuring the CVAE reconstruction probability and latent space, such that the measurements can be used to infer qualitative state changes for the aircraft. We demonstrate that this process yields information about a trained neural network’s utility for this specific application, along with a quantifiable range of certainty. We execute 84 experiments using loss-of-control flight maneuver data from the NASA T-2 aircraft, demonstrating that this empirical process allows us to construct cheap and simple models with specific attributes amenable to belief state inference in aerospace applications.

Loss of Control↗
NASA NTRSDate not supplied

Use of Design of Experiments in Determining Neural Network Architectures for Loss of Control Detection

We describe empirical methods for selecting a neural network architecture to implement belief state inference on generic commercial transport aircraft. We highlight a case study on the planning, execution, and analysis of a set of experiments to determine the configurations of a conditional variational autoencoder (CVAE). Our main contribution is the application of a structured method that can be used for machine learning in many aerospace applications. This method optimizes the structure and training parameters of a neural network for belief state inference, using Design of Experiments (DOE) statistical methodologies. The motivation for this specific DOE analysis was to identify the appropriate hyperparameters for measuring the CVAE reconstruction probability and latent space, such that the measurements can be used to infer qualitative state changes for the aircraft. We demonstrate that this process yields information about a trained neural network’s utility for this specific application, along with a quantifiable range of certainty. We execute 84 experiments using loss-of-control flight maneuver data from the NASA T 2 aircraft, demonstrating that this empirical process allows us to construct cheap and simple models with specific attributes amenable to belief state inference in aerospace applications.

Loss of Control↗
NASA NTRSDate not supplied

Use of Design of Experiments in Determining Neural Network Architectures for Loss of Control Detection

Abstract—We describe empirical methods for selecting a neural network architecture to implement belief state inference on generic commercial transport aircraft. We highlight a case study on the planning, execution, and analysis of a set of experiments to determine the configurations of a conditional variational autoencoder (CVAE). Our main contribution is the application of a structured method that can be used for machine learning in many aerospace applications. This method optimizes the structure and training parameters of a neural network for belief state inference, using Design of Experiments (DOE) statistical methodologies. The motivation for this specific DOE analysis was to identify the appropriate hyperparameters for measuring the CVAE reconstruction probability and latent space, such that the measurements can be used to infer qualitative state changes for the aircraft. We demonstrate that this process yields information about a trained neural network’s utility for this specific application, along with a quantifiable range of certainty. We execute 84 experiments using loss-of-control flight maneuver data from the NASA T-2 aircraft, demonstrating that this empirical process allows us to construct cheap and simple models with specific attributes amenable to belief state inference in aerospace applications.

neural networks↗
NASA NTRS2024

Transfer-AE: A novel autoencoder-based impact detection model for structural digital twin

Accurately detecting the location and intensity of impacts is crucial for ensuring structural safety. Currently, AI-based structural impact detection methods are widely used for their excellent detection accuracy. However, their generalization capability is limited by the scenarios present in the training data. Many complex and dangerous impact scenarios are difficult to conduct real-world experiments on to collect sufficient samples. To capture all impact scenarios and fully leverage the advantages of AI-based detection technologies, advanced methods involve combining real-world structural monitoring data with corresponding numerical models to construct digital twins. These methods continuously refine the created numerical models with limited real-world data and provide diverse impact scenarios through numerical model simulations. However, there are inevitable differences between digital models and physical models that are challenging to correct through mechanical means. This discrepancy in data distribution between the two models significantly hinders the application of digital twin technology in impact/event identification tasks. To address this challenge, this study proposes a novel model based on autoencoders, named Transfer-AE. Transfer-AE encodes the common features of digital twins in the latent space to bridge the uncertainty gap at a macro scale between numerical models and physical models and synchronously fits the magnitude and location of the impact load in the decoder. This enables consistent detection results for the same impact event, whether the sample comes from the numerical model or the physical model. Transfer-AE includes two operating modes: Mode 1 has a fixed computational complexity with stable inference speed, but the training cost and difficulty increase with data distribution. Mode 2's computational complexity increases with data distribution, but it has a fixed training cost and speed. In both cases involving the geodesic dome structure simulating a deep space habitat and the IASC-ASCE benchmark structure, Transfer-AE demonstrated the best performance in impact localization and quantification tasks compared to mainstream domain-adaptive transfer models.

Chengjia Han↗
DOE OSTI2020

Poster Abstract: Investigating Occupancy Profiles Using Convolutional Neural Networks: Preprint

In this paper, we implement a convolutional neural networks based autoencoder to investigate occupancy profiles. We use the American time use survey data, which contains 191,558 schedules with binary occupancy information. Our results suggest that the trained filters provide an important insight of occupancy profiles (i.e., dominant and distinct patterns), and the latent space compresses the profiles with representative information.

14 SOLAR ENERGY↗
DOE OSTI2021

Autoencoders on FPGAs for real-time, unsupervised new physics detection at 40 MHz at the Large Hadron Collider

In this paper, we show how to adapt and deploy anomaly detection algorithms based on deep autoencoders, for the unsupervised detection of new physics signatures in the extremely challenging environment of a real-time event selection system at the Large Hadron Collider (LHC). We demonstrate that new physics signatures can be enhanced by three orders of magnitude, while staying within the strict latency and resource constraints of a typical LHC event filtering system. This would allow for collecting datasets potentially enriched with high-purity contributions from new physics processes. Through per-layer, highly parallel implementations of network layers, support for autoencoder-specific losses on FPGAs and latent space based inference, we demonstrate that anomaly detection can be performed in as little as $80\,$ns using less than 3% of the logic resources in the Xilinx Virtex VU9P FPGA. Opening the way to real-life applications of this idea during the next data-taking campaign of the LHC.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
DOE OSTI2021

Mapping Post-Climate Change Biogeographical Regions with Deep Latent Variable Models

Forecasting future changes to biodiversity due to shifts in climate is challenging due to nonlinear interactions between species as recorded in their presence/absence data. This work proposes using variational autoencoders with environmental covariates to identify low-dimensional structure in species’ joint co-occurrence patterns and leveraging this simplified representation to provide multivariate predictions of their habitat extent under future climate scenarios. We pursue a latent space clustering approach to map biogeographical regions of frequently co-occurring species and apply this methodology to a dataset from northern Belgium, generating predictive maps illustrating how these regions may expand or contract with changing temperature under a future climate scenario.

Krapu, Chris↗
DOE OSTI2023

Domain Adaptive Graph Neural Networks for Constraining Cosmological Parameters Across Multiple Data Sets

Deep learning models have been shown to outperform methods that rely on summary statistics, like the power spectrum, in extracting information from complex cosmological data sets. However, due to differences in the subgrid physics implementation and numerical approximations across different simulation suites, models trained on data from one cosmological simulation show a drop in performance when tested on another. Similarly, models trained on any of the simulations would also likely experience a drop in performance when applied to observational data. Training on data from two different suites of the CAMELS hydrodynamic cosmological simulations, we examine the generalization capabilities of Domain Adaptive Graph Neural Networks (DA-GNNs). By utilizing GNNs, we capitalize on their capacity to capture structured scale-free cosmological information from galaxy distributions. Moreover, by including unsupervised domain adaptation via Maximum Mean Discrepancy (MMD), we enable our models to extract domain-invariant features. We demonstrate that DA-GNN achieves higher accuracy and robustness on cross-dataset tasks (up to $28\%$ better relative error and up to almost an order of magnitude better $\chi^2$). Using data visualizations, we show the effects of domain adaptation on proper latent space data alignment. This shows that DA-GNNs are a promising method for extracting domain-independent cosmological information, a vital step toward robust deep learning for real cosmic survey data.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2021

Self-Supervised Anomaly Detection via Neural Autoregressive Flows with Active Learning

Many self-supervised methods have been proposed with the target of image anomaly detection. These methods often rely on the paradigm of data augmentation with predefined transformations such as flipping, cropping, and rotations. However, it is not straightforward to apply these techniques for non-image data, such as time series or tabular data, while the performance of the existing deep approaches has been under our expectation on tasks beyond images. In this work, we propose a novel active learning (AL) scheme that relied on neural autoregressive flows (NAF) for self-supervised anomaly detection, specifically on small-scale data. Unlike other generative models such as GANs or VAEs, flow-based models allow to explicitly learn the probability density and thus can assign accurate likelihoods to normal data which makes it usable to detect anomalies. The proposed NAF-AL method is achieved by efficiently generating random samples from latent space and transforming them into feature space along with likelihoods via invertible mapping. The samples with lower likelihoods are selected and further checked by outlier detection using Mahalanobis distance. The augmented samples incorporating with normal samples are used for training a better detector so as to approach decision boundaries. Compared with random transformations, NAF-AL can be interpreted as a likelihood-oriented data augmentation that is more efficient and robust. Extensive experiments show that our approach outperforms existing baselines on multiple time series and tabular datasets, and a real-world application in advanced manufacturing, with significant improvement on anomaly detection accuracy and robustness over the state-of-the-art.

Zhang, Jiaxin↗