Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Generative 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 73 records · Page 4

Identification and denoising of radio signals from cosmic-ray air showers using convolutional neural networks

Radio pulses generated by cosmic-ray air showers can be used to reconstruct key properties like the energy and depth of the electromagnetic component of cosmic-ray air showers. Radio detection threshold, influenced by natural and anthropogenic radio background, can be reduced through various techniques. In this work, we demonstrate that convolutional neural networks (CNNs) are an effective way to lower the threshold. We developed two CNNs: a classifier to distinguish radio signal waveforms from background noise and a denoiser to clean contaminated radio signals. Following the training and testing phases, we applied the networks to air-shower data triggered by scintillation detectors of the prototype station for the enhancement of IceTop, IceCube’s surface array at the South Pole. Over a four-month period, we identified 554 cosmic-ray events in coincidence with IceTop, approximately five times more compared to a reference method based on a cut on the signal-to-noise ratio. Comparisons with IceTop measurements of the same air showers confirmed that the CNNs reliably identified cosmic-ray radio pulses and outperformed the reference method. Additionally, we find that CNNs reduce the false-positive rate of air-shower candidates and effectively denoise radio waveforms, thereby improving the accuracy of the power and arrival time reconstruction of radio pulses.

Abbasi, R↗

Adaptive enhanced sampling by force-biasing using neural networks

A machine learning assisted method is presented for molecular simulation of systems with rugged free energy landscapes. The method is general and can be combined with other advanced sampling techniques. In the particular implementation proposed here, it is illustrated in the context of an adaptive biasing force approach where, rather than relying on discrete force estimates, one can resort to a self-regularizing artificial neural network to generate continuous, estimated generalized forces. By doing so, the proposed approach addresses several shortcomings common to adaptive biasing force and other algorithms. Specifically, the neural network enables smooth estimates of generalized forces in sparsely sampled regions, force estimates in previously unexplored regions, and continuous force estimates with which to bias the simulation, as opposed to biases generated at specific points of a discrete grid. The usefulness of the method is illustrated with three different examples, chosen to highlight the wide range of applicability of the underlying concepts. In all three cases, the new method is found to enhance considerably the underlying traditional adaptive biasing force approach. Furthermore, the method is also found to provide improvements over previous implementations of neural network assisted algorithms.

97 MATHEMATICS AND COMPUTING↗

DeepCMB: Lensing reconstruction of the cosmic microwave background with deep neural networks

Next-generation cosmic microwave background (CMB) experiments will have lower noise and therefore increased sensitivity, enabling improved constraints on fundamental physics parameters such as the sum of neutrino masses and the tensor-to-scalar ratio r. Achieving competitive constraints on these parameters requires high signal-to-noise extraction of the projected gravitational potential from the CMB maps. Standard methods for reconstructing the lensing potential employ the quadratic estimator (QE). However, the QE performs suboptimally at the low noise levels expected in upcoming experiments. Other methods, like maximum likelihood estimators (MLE), are under active development. In this work, we demonstrate reconstruction of the CMB lensing potential with deep convolutional neural networks (CNN) - ie, a ResUNet. The network is trained and tested on simulated data, and otherwise has no physical parametrization related to the physical processes of the CMB and gravitational lensing. We show that, over a wide range of angular scales, ResUNets recover the input gravitational potential with a higher signal-to-noise ratio than the QE method, reaching levels comparable to analytic approximations of MLE methods. We demonstrate that the network outputs quantifiably different lensing maps when given input CMB maps generated with different cosmologies. We also show we can use the reconstructed lensing map for cosmological parameter estimation. This application of CNN provides a few innovations at the intersection of cosmology and machine learning. First, while training and regressing on images, we predict a continuous-variable field rather than discrete classes. Second, we are able to establish uncertainty measures for the network output that are analogous to standard methods. We expect this approach to excel in capturing hard-to-model non-Gaussian astrophysical foreground and noise contributions.

79 ASTRONOMY AND ASTROPHYSICS↗

DeepCMB: Lensing Reconstruction of the CMB with Deep Neural Networks

Next-generation cosmic microwave background (CMB) experiments will have lower noise and therefore increased sensitivity, enabling improved constraints on fundamental physics parameters such as the sum of neutrino masses and the tensor-to-scalar ratio r. Achieving competitive constraints on these parameters requires high signal-to-noise extraction of the projected gravitational potential from the CMB maps. Standard methods for reconstructing the lensing potential employ the quadratic estimator (QE). However, the QE performs suboptimally at the low noise levels expected in upcoming experiments. Other methods, like maximum likelihood estimators (MLE), are under active development. In this work, we demonstrate reconstruction of the CMB lensing potential with deep convolutional neural networks (CNN) - ie, a ResUNet. The network is trained and tested on simulated data, and otherwise has no physical parametrization related to the physical processes of the CMB and gravitati onal lensing. We show that, over a wide range of angular scales, ResUNets recover the input gravitational potential with a higher signal-to-noise ratio than the QE method, reaching levels comparable to analytic approximations of MLE methods. We demonstrate that the network outputs quantifiably different lensing maps when given input CMB maps generated with different cosmologies. We also show we can use the reconstructed lensing map for cosmological parameter estimation. This application of CNN provides a few innovations at the intersection of cosmology and machine learning. First, while training and regressing on images, we predict a continuous-variable field rather than discrete classes. Second, we are able to establish uncertainty measures for the network output that are analogous to standard methods. We expect this approach to excel in capturing hard-to-model non-Gaussian astrophysical foreground and noise contributions.

79 ASTRONOMY AND ASTROPHYSICS↗

PAVE: An In Situ Framework for Scientific Visualization and Machine Learning Coupling

Machine learning (ML) has emerged as a tool for understanding data at scale. However, this new methodology comes at a cost because ML requires the use of even more HPC resources to generate ML algorithms. In addition to the compute resources required to develop ML algorithms, ML does not sidestep one of the biggest challenges on leading-edge HPC systems: the increasing gap between compute performance and I/O bandwidth. This has led to a strong push towards in situ, processing the data as it is generated, strategies to mitigate the I/O bottleneck. Unfortunately, there are no in situ frameworks dedicated to coupling scientific visualization and ML at scale to develop ML algorithms for scientific visualization. To address the ML and in situ visualization gap, we introduce PAVE. PAVE is an in situ framework which addresses the data management needs between visualisation and machine learning tasks. We demonstrate our framework with a case study that accelerates physically-based light rendering, path-tracing, through the use of a conditional Generative Adversarial neural Network (cGAN). PAVE couples the training over path-traced images resulting in a generative model able to produce scene renderings with accurate light transport and global illumination of a quality comparable to offline approaches in a more efficient manner.

Kim, Mark B.↗

Data reduction through optimized scalar quantization for more compact neural networks

Raw data generation for several existing and planned large physics experiments now exceeds TB/s rates, generating untenable data sets in very little time. Those data often demonstrate high dimensionality while containing limited information. Meanwhile, Machine Learning algorithms are now becoming an essential part of data processing and data analysis. Those algorithms can be used offline for post processing and post data analysis, or they can be used online for real time processing providing ultra low latency experiment monitoring. Both use cases would benefit from data throughput reduction while preserving relevant information: one by reducing the offline storage requirements by several orders of magnitude and the other by allowing ultra fast online inferencing with low complexity Machine Learning models. Moreover, reducing the data source throughput also reduces material cost, power and data management requirements. In this work we demonstrate optimized nonuniform scalar quantization for data source reduction. This data reduction allows lower dimensional representations while preserving the relevant information of the data, thus enabling high accuracy Tiny Machine Learning classifier models for online fast inferences. We demonstrate this approach with an initial proof of concept targeting the CookieBox, an array of electron spectrometers used for angular streaking, that was developed for LCLS-II as an online beam diagnostic tool. We used the Lloyd-Max algorithm with the CookieBox dataset to design an optimized nonuniform scalar quantizer. Optimized quantization lets us reduce input data volume by 69% with no significant impact on inference accuracy. When we tolerate a 2% loss on inference accuracy, we achieved 81% of input data reduction. Finally, the change from a 7-bit to a 3-bit input data quantization reduces our neural network size by 38%.

97 MATHEMATICS AND COMPUTING↗

A Biophysical Neural Model To Describe Spatial Visual Attention

Visual scenes have enormous spatial and temporal information that are transduced into neural spike trains. Psychophysical experiments indicate that only a small portion of a spatial image is consciously accessible. Electrophysiological experiments in behaving monkeys have revealed a number of modulations of the neural activity in special visual area known as V4, when the animal is paying attention directly towards a particular stimulus location. The nature of the attentional input to V4, however, remains unknown as well as to the mechanisms responsible for these modulations. We use a biophysical neural network model of V4 to address these issues. We first constrain our model to reproduce the experimental results obtained for different external stimulus configurations and without paying attention. To reproduce the known neuronal response variability, we found that the neurons should receive about equal, or balanced, levels of excitatory and inhibitory inputs and whose levels are high as they are in in vivo conditions. Next we consider attentional inputs that can induce and reproduce the observed spiking modulations. We also elucidate the role played by the neural network to generate these modulations.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

Recovering the phase and amplitude of X-ray FEL pulses using neural networks and differentiable models

Dynamics experiments are an important use-case for X-ray free-electron lasers (XFELs), but time-domain measurements of the X-ray pulses themselves remain a challenge. Shot-by-shot X-ray diagnostics could enable a new class of simpler and potentially higher-resolution pump-probe experiments. Here, we report training neural networks to combine low-resolution measurements in both the time and frequency domains to recover X-ray pulses at high-resolution. Critically, we also recover the phase, opening the door to coherent-control experiments with XFELs. The model-based generative neural-network architecture can be trained directly on unlabeled experimental data and is fast enough for real-time analysis on the new generation of MHz XFELs.

42 ENGINEERING↗

Effects of bursting dynamic features on the generation of multi-clustered structure of neural network with symmetric spike-timing-dependent plasticity learning rule

In this paper, the generation of multi-clustered structure of self-organized neural network with different neuronal firing patterns, i.e., bursting or spiking, has been investigated. The initially all-to-all-connected spiking neural network or bursting neural network can be self-organized into clustered structure through the symmetric spike-timing-dependent plasticity learning for both bursting and spiking neurons. However, the time consumption of this clustering procedure of the burst-based self-organized neural network (BSON) is much shorter than the spike-based self-organized neural network (SSON). Our results show that the BSON network has more obvious small-world properties, i.e., higher clustering coefficient and smaller shortest path length than the SSON network. Also, the results of larger structure entropy and activity entropy of the BSON network demonstrate that this network has higher topological complexity and dynamical diversity, which benefits for enhancing information transmission of neural circuits. Hence, we conclude that the burst firing can significantly enhance the efficiency of clustering procedure and the emergent clustered structure renders the whole network more synchronous and therefore more sensitive to weak input. This result is further confirmed from its improved performance on stochastic resonance. Therefore, we believe that the multi-clustered neural network which self-organized from the bursting dynamics has high efficiency in information processing.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

Kilonova light-curve interpolation with neural networks

Kilonovae are the electromagnetic transients created by the radioactive decay of freshly synthesized elements in the environment surrounding a neutron star merger. To study the fundamental physics in these complex environments, kilonova modeling requires, in part, the use of radiative transfer simulations. The microphysics involved in these simulations results in high computational cost, prompting the use of emulators for parameter inference applications. Utilizing a training set of 22 248 high-fidelity simulations (composed of 412 unique ejecta parameter combinations evaluated at 54 viewing angles), we use a neural network to efficiently train on existing radiative transfer simulations and predict light curves for new parameters in a fast and computationally efficient manner. Our neural network can generate millions of new light curves in under a minute. We discuss our emulator's degree of off-sample reliability and parameter inference of the AT2017gfo observational data. Finally, we discuss tension introduced by multiband inference in the parameter inference results, particularly with regard to the neural network's recovery of viewing angle. Published by the American Physical Society 2024

79 ASTRONOMY AND ASTROPHYSICS↗

A generative artificial intelligence framework for long-time plasma turbulence simulations

Generative deep learning techniques are employed in a novel framework for the construction of surrogate models capturing the spatiotemporal dynamics of 2D plasma turbulence. The proposed Generative Artificial Intelligence Turbulence (GAIT) framework enables the acceleration of turbulence simulations for long-time transport studies. GAIT leverages a convolutional variational auto-encoder and a recurrent neural network to generate new turbulence data from existing simulations, extending the time horizon of transport studies with minimal computational cost. The application of the GAIT framework to plasma turbulence using the Hasegawa–Wakatani (HW) model is presented, evaluating its performance via various analyses. Very good agreement is found between the GAIT and the HW models in the spatiotemporal Fourier and Proper Orthogonal Decomposition spectra, the flow topology characterized by the Okubo–Weiss parameter, and the time autocorrelation function of turbulent fluctuations. Excellent agreement has also been obtained in the probability distribution function of particle displacements and the effective turbulent diffusivity. In-depth analyses of the latent space of turbulent states, choice of hyperparameters and alternative deep learning models for the time prediction are presented. Our results highlight the potential of Artificial Intelligence-based surrogate models to overcome the computational challenges in turbulence simulation, which can be extended to other situations such as geophysical fluid dynamics.

Artificial intelligence↗

System and Method for Modeling the Flow Performance Features of an Object

The method and apparatus includes a neural network for generating a model of an object in a wind tunnel from performance data on the object. The network is trained from test input signals (e.g., leading edge flap position, trailing edge flap position, angle of attack, and other geometric configurations, and power settings) and test output signals (e.g., lift, drag, pitching moment, or other performance features). In one embodiment, the neural network training method employs a modified Levenberg-Marquardt optimization technique. The model can be generated 'real time' as wind tunnel testing proceeds. Once trained, the model is used to estimate performance features associated with the aircraft given geometric configuration and/or power setting input. The invention can also be applied in other similar static flow modeling applications in aerodynamics, hydrodynamics, fluid dynamics, and other such disciplines. For example, the static testing of cars, sails, and foils, propellers, keels, rudders, turbines, fins, and the like, in a wind tunnel, water trough, or other flowing medium.

Jorgensen, Charles↗

Uncertainty-aware photovoltaic generation estimation through fusion of physics with harmonics information using Bayesian neural networks

We develop an aggregate photovoltaic generation estimation methodology that uses diverse inputs and can reason on its current input-dependent predictive uncertainty. Named PVPHEst, for PhotoVoltaic Physics- & Harmonics-driven Estimator, the resulting tool is intelligently weighing and fusing information carried by the output of physics models, harmonics, and line sensors, using Bayesian neural networks and related techniques aimed at solving machine learning problems with intrinsic uncertainty quantification. As each of the three input classes carries heterogeneous information that only sheds light on one facet of the estimation problem but its value can diminish in the face of diverse grid phenomena, PV-PHEst with its estimation and uncertainty reasoning capabilities perform a nontrivial and potentially mission-critical task of value to grid operators.

24 POWER TRANSMISSION AND DISTRIBUTION↗

Augmented Reality Data Generation for Training Deep Learning Neural Network

One of the major challenges in deep learning is retrieving sufficiently large labeled training datasets, which can become expensive and time consuming to collect. A unique approach to training segmentation is to use Deep Neural Network (DNN) models with a minimal amount of initial labeled training samples. The procedure involves creating synthetic data and using image registration to calculate affine transformations to apply to the synthetic data. The method takes a small dataset and generates a highquality augmented reality synthetic dataset with strong variance while maintaining consistency with real cases. Results illustrate segmentation improvements in various target features and increased average target confidence.

Torres, Gil↗

Comparison of Prediction Modeling Methodologies for Aeroacoustic Characterization of Hovering sUAS Rotors

This work compared artificial neural network and multivariate orthogonal function modeling methodologies for the prediction and characterization of isolated hovering sUAS rotor aerodynamics and aeroacoustics. Design of Experiments was used to create input feature spaces over 9 input features: the number of rotor blades, rotor size, rotor speed, the amount of blade twist, blade taper ratio, tip chord length, collective pitch, airfoil camber, and airfoil thickness. CAMRAD~II and AARON were executed at the points defined by the input feature space to predict aerodynamic and aeroacoustic quantities. These predicted aerodynamic and aeroacoustic data were then used to generate artificial neural networks and polynomial response surface models. The two prediction model methodologies were evaluated over test data previously unseen by the models, which showed good prediction capabilities for both model types, with slightly lower prediction error for the artificial neural networks. A characterization study was performed, which showed that input features correspondent to the spanwise sectional blade lift and drag were the most significant factors to the aerodynamic thrust and power, respectively. It was also shown that the aeroacoustic quantities were highly dependent on variations in rotor speed and size, which affect the Doppler factor for tonal noise and the spanwise Reynolds number for broadband noise.

Christopher S Thurman↗

Neural Network and Regression Approximations Used in Aircraft Design

NASA Lewis Research Center's CometBoards Test Bed was used to create regression and neural network models for a High-Speed Civil Transport (HSCT) aircraft. Both approximation models that replaced the actual analysis tool predicted the aircraft response in a trivial computational effort. The models allow engineers to quickly study the effects of design variables on constraint and objective values for a given aircraft configuration. For example, an engineer can change the engine size by 1000 pounds of thrust and quickly see how this change affects all the output values without rerunning the entire simulation. In addition, an engineer can change a constraint and use the approximation models to quickly reoptimize the configuration. Generating the neural network and the regression models is a time-consuming process, but this exercise has to be carried out only once. Furthermore, an automated process can reduce calculations substantially.

Patnaik, Surya N.↗

ForSE: A GAN-based Algorithm for Extending CMB Foreground Models to Subdegree Angular Scales

We present ForSE (Foreground Scale Extender), a novel Python package that aims to overcome the current limitations in the simulation of diffuse Galactic radiation, in the context of cosmic microwave background (CMB) experiments. ForSE exploits the ability of generative adversarial neural networks (GANs) to learn and reproduce complex features present in a set of images, with the goal of simulating realistic and non-Gaussian foreground radiation at subdegree angular scales. This is of great importance in order to estimate the foreground contamination to lensing reconstruction, delensing, and primordial B-modes for future CMB experiments. We applied this algorithm to Galactic thermal dust emission in both total intensity and polarization. Our results show how ForSE is able to generate small-scale features (at 12') having as input the large-scale ones (80'). The injected structures have statistical properties, evaluated by means of the Minkowski functionals, in good agreement with those of the real sky and which show the correct amplitude scaling as a function of the angular dimension. Furthermore, the obtained thermal dust Stokes Q and U full-sky maps as well as the ForSE package are publicly available for download.

79 ASTRONOMY AND ASTROPHYSICS↗

Deep Learning and Uncertainty Quantification for Climate Resilience

Modeling and monitoring of earth’s processes through physical models and satellite observations at high resolutions is crucial for ensuring society’s ability to adapt to climate change. Deep learning (DL) has been shown to be a valuable tool for generating high resolution data, emulating physical models, and detecting weather patterns which can then be used to inform stakeholders and decision makers. However, both the data and model parameters contain substantial uncertainties that may alter users’ decisions. In this work we present two DL applications on high-resolution climate and satellite datasets using Bayesian neural networks to generate well calibrated uncertainty estimates.

Vandal, Thomas↗