Search NASA⌕ Search

SEARCH · Search NASA

Results for “Recurrent Neural Networks”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

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

At least 235 records · Page 13

Biologically inspired approaches for biosurveillance anomaly detection and data fusion

This study developed and tested biologically inspired computational methods to detect anomalous signals in data streams that could indicate a pending outbreak or bio-weapon attack. Current large-scale biosurveillance systems are plagued by two principal deficiencies: (1) timely detection of disease-indicating signals in noisy data and (2) anomaly detection across multiple channels. Anomaly detectors and data fusion components modeled after human immune system processes were tested against a variety of natural and synthetic surveillance datasets. A pilot scale immune-system-based biosurveillance system performed at least as well as traditional statistical anomaly detection data fusion approaches. Machine learning approaches leveraging Deep Learning recurrent neural networks were developed and applied to challenging unstructured and multimodal health surveillance data. Within the limits imposed of data availability, both immune systems and deep learning methods were found to improve anomaly detection and data fusion performance for particularly challenging data subsets.

59 BASIC BIOLOGICAL SCIENCES↗

Identifying Neutrino Final States and Energies in MicroBooNE with New Deep-Learning Based LArTPC Reconstruction Frameworks

MicroBooNE, a Liquid Argon Time Projection Chamber (LArTPC) located in the $\nu_{\mu}$-dominated Booster Neutrino Beam at Fermilab, has been studying $\nu_{e}$ charged-current (CC) interaction rates to shed light on the MiniBooNE low energy excess. The LArTPC technology employed by MicroBooNE provides the capability to image neutrino interactions with mm-scale precision. Computer vision and other machine learning techniques are promising tools for image processing that could boost efficiencies for selecting $\nu_{e}$-CC and other rare signals, reduce cosmic and beam-induced backgrounds, and improve the reconstruction of neutrino energies. The MicroBooNE experiment has been at the forefront of developing and testing such techniques for use in physics analyses. In this poster we overview deep-learning based reconstruction methods. We will showcase the use of a recurrent neural network to estimate neutrino energies and present a new reconstruction framework that uses convolutional neural networks to locate neutrino interaction vertices, tag pixels with track and shower labels, and perform particle identification on reconstructed clusters. We will present studies characterizing the performance of these new tools and demonstrate their effectiveness through their use in an inclusive $\nu_{e}$-CC event selection.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

Low Power, Radiation Resilient Synchronous Edge Processing for Remote Monitoring

Next-generation space remote sensing systems may be equipped with imaging arrays that sense data at a rate that outstrips the processing capability of any computing hardware that can operate within a satellite’s power budget. This project developed novel convolutional and recurrent neural networks to detect and estimate point-like events amid clutter, and investigated their efficient and accurate implementation on analog in-memory computing systems that are 10-1000× more energy-efficient than digital processors. This project leveraged two memory devices at different levels of technological maturity: a large-scale analog computing prototype using commercial SONOS charge-trap memory, and electrochemical memory (ECRAM) with intrinsic radiation hardness. We experimentally demonstrated end-to-end analog processing of our neural networks on SONOS and characterized the radiation response of both SONOS and ECRAM. We advanced the state-of-the-art in ECRAM precision and reliability, and developed co-design methods to enable accurate long-term operation of SONOS analog accelerators in space radiation environments.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗

Steady Spills, Stronger Signals: Machine Learning for Slow Spill Analysis

Particle accelerator experiments rely on stable, consistent proton beams to maximize scientific discovery. This presentation introduces beam spills, duty factor, and beam stability using a meteor shower analogy before exploring how feedback control and machine learning, including recurrent neural networks (RNNs), can analyze spill data, identify patterns, and predict beam behavior. Together, these approaches support beam optimization and improve our understanding of accelerator performance for experiments such as Mu2e.

Prescott, Matthew J. [Fermilab]↗

Incorporating polar field data for improved solar flare prediction

In this paper, we consider incorporating data associated with the sun’s north and south polar field strengths to improve solar flare prediction performance using machine learning models. When used to supplement local data from active regions on the photospheric magnetic field of the sun, the polar field data provides global information to the predictor. While such global features have been previously proposed for predicting the next solar cycle’s intensity, in this paper we propose using them to help classify individual solar flares. We conduct experiments using HMI data employing four different machine learning algorithms that can exploit polar field information. Additionally, we propose a novel probabilistic mixture of experts model that can simply and effectively incorporate polar field data and provide on-par prediction performance with state-of-the-art solar flare prediction algorithms such as the Recurrent Neural Network (RNN). Our experimental results indicate the usefulness of the polar field data for solar flare prediction, which can improve Heidke Skill Score (HSS2) by as much as 10.1%.

79 ASTRONOMY AND ASTROPHYSICS↗

Earthquake Nowcasting with Deep Learning

We review previous approaches to nowcasting earthquakes and introduce new approaches based on deep learning using three distinct models based on recurrent neural networks and transformers. We discuss different choices for observables and measures presenting promising initial results for a region of Southern California from 1950–2020. Earthquake activity is predicted as a function of 0.1-degree spatial bins for time periods varying from two weeks to four years. The overall quality is measured by the Nash Sutcliffe efficiency comparing the deviation of nowcast and observation with the variance over time in each spatial region. The software is available as open source together with the preprocessed data from the USGS.

Fox, Geoffrey Charles (ORCID:0000000310171391)↗

Tracing and Forecasting Metabolic Indices of Cancer Patients Using Patient-Specific Deep Learning Models

We develop a patient-specific dynamical system model from the time series data of the cancer patient’s metabolic panel taken during the period of cancer treatment and recovery. The model consists of a pair of stacked long short-term memory (LSTM) recurrent neural networks and a fully connected neural network in each unit. It is intended to be used by physicians to trace back and look forward at the patient’s metabolic indices, to identify potential adverse events, and to make short-term predictions. When the model is used in making short-term predictions, the relative error in every index is less than 10% in the L ∞ norm and less than 6.3% in the L 1 norm in the validation process. Once a master model is built, the patient-specific model can be calibrated through transfer learning. As an example, we obtain patient-specific models for four more cancer patients through transfer learning, which all exhibit reduced training time and a comparable level of accuracy. This study demonstrates that this modeling approach is reliable and can deliver clinically acceptable physiological models for tracking and forecasting patients’ metabolic indices.

60 APPLIED LIFE SCIENCES↗

An Evolve-Then-Correct Reduced Order Model for Hidden Fluid Dynamics

In this paper, we put forth an evolve-then-correct reduced order modeling approach that combines intrusive and nonintrusive models to take hidden physical processes into account. Specifically, we split the underlying dynamics into known and unknown components. In the known part, we first utilize an intrusive Galerkin method projected on a set of basis functions obtained by proper orthogonal decomposition. We then present two variants of correction formula based on the assumption that the observed data are a manifestation of all relevant processes. The first method uses a standard least-squares regression with a quadratic approximation and requires solving a rank-deficient linear system, while the second approach employs a recurrent neural network emulator to account for the correction term. We further enhance our approach by using an orthonormality conforming basis interpolation approach on a Grassmannian manifold to address off-design conditions. The proposed framework is illustrated here with the application of two-dimensional co-rotating vortex simulations under modeling uncertainty. The results demonstrate highly accurate predictions underlining the effectiveness of the evolve-then-correct approach toward real-time simulations, where the full process model is not known a priori.

long short-term memory↗

Data Quality Monitoring for the Hadron Calorimeters Using Transfer Learning for Anomaly Detection

The proliferation of sensors brings an immense volume of spatio-temporal (ST) data in many domains, including monitoring, diagnostics, and prognostics applications. Data curation is a time-consuming process for a large volume of data, making it challenging and expensive to deploy data analytics platforms in new environments. Transfer learning (TL) mechanisms promise to mitigate data sparsity and model complexity by utilizing pre-trained models for a new task. Despite the triumph of TL in fields like computer vision and natural language processing, efforts on complex ST models for anomaly detection (AD) applications are limited. In this study, we present the potential of TL within the context of high-dimensional ST AD with a hybrid autoencoder architecture, incorporating convolutional, graph, and recurrent neural networks. Motivated by the need for improved model accuracy and robustness, particularly in scenarios with limited training data on systems with thousands of sensors, this research investigates the transferability of models trained on different sections of the Hadron Calorimeter of the Compact Muon Solenoid experiment at CERN. The key contributions of the study include exploring TL’s potential and limitations within the context of encoder and decoder networks, revealing insights into model initialization and training configurations that enhance performance while substantially reducing trainable parameters and mitigating data contamination effects.

47 OTHER INSTRUMENTATION↗

Novel deep learning methods for track reconstruction

For the past year, the HEP.TrkX project has been investigating machine learning solutions to LHC particle track reconstruction problems. A variety of models were studied that drew inspiration from computer vision applications and operated on an image-like representation of tracking detector data. While these approaches have shown some promise, image-based methods face challenges in scaling up to realistic HL-LHC data due to high dimensionality and sparsity. In contrast, models that can operate on the spacepoint representation of track measurements ("hits") can exploit the structure of the data to solve tasks efficiently. In this paper we will show two sets of new deep learning models for reconstructing tracks using space-point data arranged as sequences or connected graphs. In the first set of models, Recurrent Neural Networks (RNNs) are used to extrapolate, build, and evaluate track candidates akin to Kalman Filter algorithms. Such models can express their own uncertainty when trained with an appropriate likelihood loss function. The second set of models use Graph Neural Networks (GNNs) for the tasks of hit classification and segment classification. These models read a graph of connected hits and compute features on the nodes and edges. They adaptively learn which hit connections are important and which are spurious. The models are scaleable with simple architecture and relatively few parameters. Results for all models will be presented on ACTS generic detector simulated data.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

Detecting Anomalous Computation with RNNs on GPU-Accelerated HPC Machines

This paper presents a workload classification framework that discriminates illicit computation from authorized workloads on GPU-accelerated HPC systems. As such systems become more and more powerful, they are exploited by attackers to run malicious and for-profit programs that typically require extremely high computing ability to be successful. Our classification framework leverages the distinctive signatures between illicit and authorized workloads, and explore machine learning methods to learn the workloads and classify them. The framework uses lightweight, non-intrusive workload profiling to collect model input data, and explores multiple machine learning methods, particularly recurrent neural network (RNN) that is suitable for online anomalous workload detection. Evaluation results on three generations of GPU machines demonstrate that the workload classification framework can tell apart the illicit authorized workloads with a high accuracy of over 95%.

Pengfei, Zou↗

CSB-RNN: A Faster-Than-Realtime RNN Acceleration Framework with Compressed Structured Blocks

Recurrent Neural Networks (RNN) is widely applied to temporal sequence analysis, where real-time performance is usually in demand. However, RNN suffers a heavy computational workload as the model comes with a large weight matrix. To alleviate the pain, model compression (pruning) schemes have been proposed for RNN that pruning the redundant (near-zero) weight-values. On the one hand, the non-structured pruning methods achieve a considerable pruning rate while bringing the computational irregularity, which is un-friendly to parallel-hardware. On the other hand, the existing structured pruning methods consider the hardware parallelism; However, they suffer a poor pruning rate due to the restrict constraints on pruning structure. This paper presents CSB-RNN, an optimized full-stack RNN framework with the novel compressed structured block (CSB) technique. The CSB-pruned RNN model comes with both fine-granularity that benefits the pruning rate and regular structure that facilitates the hardware-parallelism. Further, we propose a novel hardware architecture for inferencing the CSB-pruned model. Different from conventional parallel hardware, this architecture solves the block-workload imbalance issue and achieves an over 95% hardware utilization. With the experiments on 10 RNN models in 5 application domains, the CSB-RNN realizes 7×-20× lossless compression and up to 50× acceptable lossy-compression, which is 2×-7× to the prior art. With the addition of the novel hardware, the compressed-RNN inference reaches a super real-time latency of 10-400µs with FPGA implementation.

Shi, Runbin↗

Core-collapse contamination in photometric samples of Type Ia Supernovae

This is an exciting time for cosmology with type Ia supernovae (SNe Ia). The recentlyconcluded Dark Energy Survey SN programme (DES-SN) has obtained the largest anddeepest high-redshift cosmological SN Ia sample, and the Vera Rubin Observatory isexpected to observe at least one order of magnitude more SNe Ia in the next decade.In both these experiments, only a limited fraction (.10 per cent) of the SNe can bespectroscopically classified. This leaves us with large ‘photometric’ SN samples, withthe potential for significant contamination by core-collapse SNe that may bias SN Iacosmological measurements. This thesis demonstrates how this contamination can bemodelled and accounted for in current and future cosmological analyses.First, I present state-of-the-art simulations of the SN universe. These are designedto accurately model the population of SNe Ia, peculiar SNe Ia and core-collapse SNe, aswell as their host galaxies. To improve the diversity and quality of the simulated corecollapseSNe, I build a new library of core-collapse SN templates using spectroscopicand photometric (optical and near-ultraviolet) data of 67 core-collapse SNe from theliterature. I account for our incomplete knowledge of core-collapse SN properties bygenerating a set of SN simulations (rather than a single one), each exploring differentmodelling choices and template libraries. I then characterise selection effects in theDES-SN survey and incorporate them in the simulations, thus obtaining a series ofDES-like simulated SN samples that can be compared to the observed DES-SN data.The agreement between the simulations and data is excellent across many observed SNproperties, including Hubble residuals. These simulations are the first to reproduce theobserved photometric SN and host galaxy properties in high-redshift surveys with no fine-tuning of the input parameters.I use my simulation framework to train and test the performance of SuperNNova,a photometric SN classifier based on recurrent neural networks. I explore differenttraining and validation strategies and show that, across all the DES-SN simulationstested, SuperNNova reduces core-collapse SN contamination to 0.8–3.5 per cent. Ithen show that biases due to contamination on the equation-of-state of dark energy,w, are < 0:008 when using our reference SuperNNova model. This compares to anexpected statistical uncertainty on w from the DES-SN sample of 0:039, thus showing that contamination is not a limiting systematic for the cosmological analysis of theDES-SN sample.The results presented in this thesis are the foundation of the DES SN Ia cosmologicalanalysis; they also provide important implications for the future of SN cosmology,as they demonstrate that contamination is not expected to significantly degrade thecosmological figure of merit of the Rubin SN Ia analysis.

79 ASTRONOMY AND ASTROPHYSICS↗

Identifying Neutrino Final States and Energies in MicroBooNE with New Deep-Learning Based LArTPC Reconstruction Frameworks

MicroBooNE, a Liquid Argon Time Projection Chamber (LArTPC) located in the $\nu_{\mu}$-dominated Booster Neutrino Beam at Fermilab, has been studying $\nu_{e}$ charged-current (CC) interaction rates to shed light on the MiniBooNE low energy excess. The LArTPC technology employed by MicroBooNE provides the capability to image neutrino interactions with mm-scale precision. Computer vision and other machine learning techniques are promising tools for image processing that could boost efficiencies for selecting $\nu_{e}$-CC and other rare signals, reduce cosmic and beam-induced backgrounds, and improve the reconstruction of neutrino energies. The MicroBooNE experiment has been at the forefront of developing and testing such techniques for use in physics analyses. In this poster we overview deep-learning based reconstruction methods. We will showcase the use of a recurrent neural network to estimate neutrino energies and present a new reconstruction framework that uses convolutional neural networks to locate neutrino interaction vertices, tag pixels with track and shower labels, and perform particle identification on reconstructed clusters. We will present studies characterizing the performance of these new tools and demonstrate their effectiveness through their use in an inclusive $\nu_{e}$-CC event selection.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

MSU IETC LSTM Ethernet Decode (AN EDGE)

This research explores the ability of machine learning to perform signal separation of an Ethernet style encoded, full-duplex communication. Typical signal separation currently requires an active tap of the communication line, followed by a recombination and retransmission of the data. The purpose of this research is to study a passive approach to data acquisition from a full-duplex signal. The machine learning model used in this research is a long-short-term memory recurrent neural network (LSTM-RNN). The results show that the LSTM was largely successful in recreating the transmission signal from the measured data points, though the separated signals have not yet been tested using a decoding method.

Full Duplex Signals↗

Recurrent Convolutional Deep Neural Networks for Modeling Time-Resolved Wildfire Spread Behavior

The increasing incidence and severity of wildfires underscores the necessity of accurately predicting their behavior. While high-fidelity models derived from first principles offer physical accuracy, they are too computationally expensive for use in real-time fire response. Low-fidelity models sacrifice some physical accuracy and generalizability via the integration of empirical measurements, but enable real-time simulations for operational use in fire response. Machine learning techniques have demonstrated the ability to bridge these objectives by learning first-principles physics while achieving computational speedups. While deep learning approaches have demonstrated the ability to predict wildfire propagation over large time periods, time-resolved fire-spread predictions are needed for active fire management. Here, in this work, we evaluate the ability of deep learning approaches in accurately modeling the time-resolved dynamics of wildfires. We use an autoregressive process in which a convolutional recurrent deep learning model makes predictions that propagate a wildfire over 15 min increments. We apply the model to four simulated datasets of increasing complexity, containing both field fires with homogeneous fuel distribution as well as real-world topologies sampled from the California region of the United States. We show that even after 100 autoregressive predictions representing more than 24 h of simulated fire spread, the resulting models generate stable and realistic propagation dynamics, achieving a Jaccard score between 0.89 and 0.94 when predicting the resulting fire scar. The inference time of the deep learning models are examined and compared, and directions for future work are discussed.

54 ENVIRONMENTAL SCIENCES↗

Recurrent and convolutional neural networks for sequential multispectral optoacoustic tomography ( MSOT ) imaging

Abstract Multispectral optoacoustic tomography (MSOT) is a beneficial technique for diagnosing and analyzing biological samples since it provides meticulous details in anatomy and physiology. However, acquiring high through‐plane resolution volumetric MSOT is time‐consuming. Here, we propose a deep learning model based on hybrid recurrent and convolutional neural networks to generate sequential cross‐sectional images for an MSOT system. This system provides three modalities (MSOT, ultrasound, and optoacoustic imaging of a specific exogenous contrast agent) in a single scan. This study used ICG‐conjugated nanoworms particles (NWs‐ICG) as the contrast agent. Instead of acquiring seven images with a step size of 0.1 mm, we can receive two images with a step size of 0.6 mm as input for the proposed deep learning model. The deep learning model can generate five other images with a step size of 0.1 mm between these two input images meaning we can reduce acquisition time by approximately 71%.

Juhong, Aniwat↗