Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Training Time”

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 1,657 records · Page 92
All sourcesNASA NTRSDOE OSTI
NASA NTRS2000

The Strategy for Polar Exploration: Planes, Trains, and Automobiles

The polar regions are both interesting and challenging to explore. The record of climate history and the behavior of Martian volatiles over time are thought to be contained in the polar terrains. Furthermore, the polar regions are probably the best environment to search for evidence of living organisms on Mars because they have both the presence of water ice and summertime temperatures at the surface that exceed the freezing point of water. In addition, melting at the base of the polar caps is predicted to occur which could result in a deep aquifer beneath the polar caps. Such an aquifer is potentially another habitat for life. Clearly, assessing the question of volaties, climate, and life in the polar regions would benefit from landed missions that can sample and interact with the surface. Mobility on the surface is also important for polar exploration due to the apparent wide diversity of terrains that occur on both local and regional scales. Additional information is contained in the original extended abstract.

Stoker, C.↗
NASA NTRS2016

The Trick Simulation Toolkit: A NASA/Open source Framework for Running Time Based Physics Models

This paper describes the design and use at of the Trick Simulation Toolkit, a simulation development environment for creating high fidelity training and engineering simulations at the NASA Johnson Space Center and many other NASA facilities. It describes Trick's design goals and how the development environment attempts to achieve those goals. It describes how Trick is used in some of the many training and engineering simulations at NASA. Finally it describes the Trick NASA/Open source project on Github.

Penn, John M.↗
NASA NTRSDate not supplied

Psychophysiological Methods to Assess Pilot Productive Safety Behaviors

The NASA System-Wide Safety (SWS) Project is focused on developing new technologies and operational concepts for the aviation industry to meet the increasing global demand while maintaining the current ultra-safe system safety levels. To achieve this, the SWS Project is developing research priorities, including In-time System-wide Safety Assurance (ISSA) and In-time Aviation Safety Management System (IASMS; Ellis et al., 2019). A critical component of the IASMS is the human as pilot and in other roles in aviation operations as demonstrated by SWS human factors research on rare occurrences of human error and the far more prevalent human safety producing behaviors (e.g., Hollnagel, 2016). The talk presented by Chad Stephens of NASA Langley Research Center and NASA SWS Project will describe the history of human factors research involving psychophysiological and biocybernetics methods supporting aviation safety conducted at NASA. Specific examples of recent NASA crew state monitoring research focused on a psychophysiological assessment method and system to enable Training for Attention Management will be demonstrated. Current SWS research including the SWS Operations and Technologies for Enabling Resilient In-Time Assurance (SOTERIA) flight simulation study and a data testbed created to enable study of Human Contributions to Safety (HC2S) will be presented. Ongoing collaborative research efforts with Boeing researchers will be highlighted and opportunities for further collaboration will be discussed.

psychophysiology↗
DOE OSTI2024

MedNAS: Multiscale Training-Free Neural Architecture Search for Medical Image Analysis

Deep neural networks have demonstrated impressive results in medical image analysis, but designing suitable architectures for each specific task is expertise dependent and time consuming. Neural architecture search (NAS) offers an effective means of discovering architectures. It has been highly successful in numerous applications, particularly in natural image classification. Yet, medical images possess unique characteristics, such as small regions and a wide variety of lesion sizes, that differentiate them from natural images. Furthermore, most current NAS methods struggle with high computational costs, especially when dealing with high-resolution image datasets. In this article, we present a novel evolutionary NAS method called multiscale training-free neural architecture search (MSTF-NAS) to address these challenges. Specifically, to accommodate the broad range of lesion region sizes in disease diagnosis, we develop a new reduction cell search space that enables the search algorithm to explicitly identify the optimal scale combination for multiscale feature extraction. Further, to overcome the issue of high computational costs, we utilize training-free indicators as performance measures for candidate architectures, which allows us to search for the optimal architecture more efficiently. More specifically, by considering the capability and simplicity of various networks, we formulate a multiobjective optimization problem that involves two training-free indicators and model complexity for candidate architectures. Extensive experiments on a large medical image benchmark and a publicly available breast cancer detection dataset are conducted. The empirical results demonstrate that our MSTF-NAS outperforms both human-designed architectures and current state-of-the-art NAS algorithms on both datasets, indicating the effectiveness of our proposed method.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2020

Deep learning for NLTE spectral opacities

Computer simulations of high energy density science experiments are computationally challenging, consisting of multiple physics calculations including radiation transport, hydrodynamics, atomic physics, nuclear reactions, laser–plasma interactions, and more. To simulate inertial confinement fusion (ICF) experiments at high fidelity, each of these physics calculations should be as detailed as possible. However, this quickly becomes too computationally expensive even for modern supercomputers, and thus many simplifying assumptions are made to reduce the required computational time. Much of the research has focused on acceleration techniques for the various packages in multiphysics codes. In this work, we explore a novel method for accelerating physics packages via machine learning. The non-local thermodynamic equilibrium (NLTE) package is one of the most expensive calculations in the simulations of indirect drive inertial confinement fusion, taking several tens of percent of the total wall clock time. We explore the use of machine learning to accelerate this package, by essentially replacing the physics calculation with a deep neural network that has been trained to emulate the physics code. Overall, we demonstrate the feasibility of this approach on a simple problem and perform a side-by-side comparison of the physics calculation and the neural network inline in an ICF Hohlraum simulation. We show that the neural network achieves a 10× speed up in NLTE computational time while achieving good agreement with the physics code for several quantities of interest.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
NASA NTRS2003

Development of Methodologies for IV and V of Neural Networks

Non-deterministic systems often rely upon neural network (NN) technology to "lean" to manage flight systems under controlled conditions using carefully chosen training sets. How can these adaptive systems be certified to ensure that they will become increasingly efficient and behave appropriately in real-time situations? The bulk of Independent Verification and Validation (IV&V) research of non-deterministic software control systems such as Adaptive Flight Controllers (AFC's) addresses NNs in well-behaved and constrained environments such as simulations and strict process control. However, neither substantive research, nor effective IV&V techniques have been found to address AFC's learning in real-time and adapting to live flight conditions. Adaptive flight control systems offer good extensibility into commercial aviation as well as military aviation and transportation. Consequently, this area of IV&V represents an area of growing interest and urgency. ISR proposes to further the current body of knowledge to meet two objectives: Research the current IV&V methods and assess where these methods may be applied toward a methodology for the V&V of Neural Network; and identify effective methods for IV&V of NNs that learn in real-time, including developing a prototype test bed for IV&V of AFC's. Currently. no practical method exists. lSR will meet these objectives through the tasks identified and described below. First, ISR will conduct a literature review of current IV&V technology. TO do this, ISR will collect the existing body of research on IV&V of non-deterministic systems and neural network. ISR will also develop the framework for disseminating this information through specialized training. This effort will focus on developing NASA's capability to conduct IV&V of neural network systems and to provide training to meet the increasing need for IV&V expertise in such systems.

Taylor, Brian↗
NASA NTRS2008

A Multi-Season Study of the Effects of MODIS Sea-Surface Temperatures on Operational WRF Forecasts at NWS Miami, FL

Studies at the Short-term Prediction Research and Transition (SPORT) Center have suggested that the use of Moderate Resolution Imaging Spectroradiometer (MODIS) sea-surface temperature (SST) composites in regional weather forecast models can have a significant positive impact on short-term numerical weather prediction in coastal regions. Recent work by LaCasse et al (2007, Monthly Weather Review) highlights lower atmospheric differences in regional numerical simulations over the Florida offshore waters using 2-km SST composites derived from the MODIS instrument aboard the polar-orbiting Aqua and Terra Earth Observing System satellites. To help quantify the value of this impact on NWS Weather Forecast Offices (WFOs), the SPORT Center and the NWS WFO at Miami, FL (MIA) are collaborating on a project to investigate the impact of using the high-resolution MODIS SST fields within the Weather Research and Forecasting (WRF) prediction system. The project's goal is to determine whether more accurate specification of the lower-boundary forcing within WRF will result in improved land/sea fluxes and hence, more accurate evolution of coastal mesoscale circulations and the associated sensible weather elements. The NWS MIA is currently running WRF in real-time to support daily forecast operations, using the National Centers for Environmental Prediction Nonhydrostatic Mesoscale Model dynamical core within the NWS Science and Training Resource Center's Environmental Modeling System (EMS) software. Twenty-seven hour forecasts are run dally initialized at 0300, 0900, 1500, and 2100 UTC on a domain with 4-km grid spacing covering the southern half of Florida and adjacent waters of the Gulf of Mexico and Atlantic Ocean. Each model run is initialized using the Local Analysis and Prediction System (LAPS) analyses available in AWIPS. The SSTs are initialized with the NCEP Real-Time Global (RTG) analyses at 1/12deg resolution (approx.9 km); however, the RTG product does not exhibit fine-scale details consistent with its grid resolution. SPORT is conducting parallel WRF EMS runs identical to the operational runs at NWS MIA except for the use of MODIS SST composites in place of the RTG product as the initial and boundary conditions over water, The MODIS SST composites for initializing the SPORT WRF runs are generated on a 2-km grid four times daily at 0400, 0700, 1600, and 1900 UTC, based on the times of the overhead passes of the Aqua and Terra satellites. The incorporation of the MODIS SST data into the SPORT WRF runs is staggered such that SSTs are updated with a new composite every six hours in each of the WRF runs. From mid-February to July 2007, over 500 parallel WRF simulations have been collected for analysis and verification. This paper will present verification results comparing the NWS MIA operational WRF runs to the SPORT experimental runs, and highlight any substantial differences noted in the predicted mesoscale phenomena for specific cases.

Case, Jonathan L.↗
DOE OSTI2025

TorchBraid: High-Performance Layer-Parallel Training of Deep Neural Networks with MPI and GPU Acceleration

TorchBraid is a high-performance implementation of layer-parallel training for deep neural networks (DNNs) supporting MPI-based parallelism and GPU acceleration. Layer-parallel training has been developed to overcome the serialization inherent in forward and backward propagation of DNNs that limits utilization of computational resources in the strong scaling limit. To achieve this, TorchBraid integrates the PyTorch neural network framework with the state-of-the-art XBraid time-parallel library. Furthermore, this article presents the use and performance of TorchBraid, in addition to solutions for overcoming the algorithmic challenges inherent in combining automatic differentiation with layer-parallel. Results are presented with and without GPU acceleration for the Tiny ImageNet and MNIST image classification data sets, as well as recurrent neural networks. Overall, TorchBraid enables fast training of DNNs, both in a strong and weak scaling context. In addition to the TorchBraid software, several new advances in applying layer-parallel algorithms are detailed. Integration of layer-parallel with data-parallel algorithms is presented for the first time, showing the computational advantages of the combination. Standard deep learning techniques, like batch-normalization, are developed for layer-parallel training. Finally, a new approach combining layer-parallel with spatial coarsening in order to accelerate training for 3D image classification shows roughly a 10× speedup over serial execution.

Layer-parallel↗
NASA NTRSDate not supplied

The Application of Remote Sensing and Machine Learning to Improve Early Warning Systems for Harmful Algal Events in the Highland Lake Chain, TX

Beginning in 2019, harmful algal events have caused canine deaths in both Lady Bird Lake and Lake Travis located near Austin, Texas. These two reservoirs are part of the larger Highland Lakes chain, managed by the City of Austin Department of Watershed Protection (COA DWP) and the Lower Colorado River Authority (LCRA), which fulfill municipal, commercial, and agricultural water demands. Given the recent increase in favorable environmental conditions for algal events in central Texas, NASA DEVELOP partnered with LCRA and COA DWP to improve monitoring and early detection of algal events, utilizing satellite remote sensing and machine learning. Spatially and temporally varied chlorophyll a concentrations, cyanobacteria detections, turbidity, and water surface temperature products are used as environmental proxies. Landsat 8 Operational Land Imager (OLI) and the Sentinel-2 MultiSpectral Instrument (MSI) data were used to provide a combined revisit time of up to ~3 days and < 30 m per pixel products. Chlorophyll a concentrations were estimated using a pre-trained Mixture Density Network, and cyanobacteria detection was accomplished using the Broad Wavelength Algae Index, which can differentiate algal blooms from algal proliferations (mats). In situ data were used to validate remotely sensed measurements and quantify uncertainties. Preliminary results show a good fit between the modeled output and in situ observations, suggesting that remote sensing data can be used to retrieve biogeochemical properties and/or inherent optical properties (IOPs) of water columns in these inland human-made lakes. Uncertainties were introduced from the sensitivity to atmospheric correction, inherent mismatch between satellite and sampling data, and a relatively lower signal-to-noise ratio over water. The resulting products enable near real-time monitoring of environmental proxies relevant to algal event presence in the Highland Lakes chain, and will ultimately support water management, decision making, and risk communication.

Shuyu Chang↗
DOE OSTI2023

Model-parallel Fourier neural operators as learned surrogates for large-scale parametric PDEs

Fourier neural operators (FNOs) are a recently introduced neural network architecture for learning solution operators of partial differential equations (PDEs), which have been shown to perform significantly better than comparable deep learning approaches. Once trained, FNOs can achieve speed-ups of multiple orders of magnitude over conventional numerical PDE solvers. However, due to the high dimensionality of their input data and network weights, FNOs have so far only been applied to two-dimensional or small three-dimensional problems. To remove this limited problem-size barrier, we propose a model-parallel version of FNOs based on domain-decomposition of both the input data and network weights. Here, we demonstrate that our model-parallel FNO is able to predict time-varying PDE solutions of over 2.6 billion variables on Perlmutter using up to 512 A100 GPUs and show an example of training a distributed FNO on the Azure cloud for simulating multiphase CO 2 dynamics in the Earth’s subsurface.

58 GEOSCIENCES↗
DOE OSTI2024

A machine learning decision criterion for reducing scan time for hyperspectral neutron computed tomography systems

We present the first machine learning-based autonomous hyperspectral neutron computed tomography experiment performed at the Spallation Neutron Source. Hyperspectral neutron computed tomography allows the characterization of samples by enabling the reconstruction of crystallographic information and elemental/isotopic composition of objects relevant to materials science. High quality reconstructions using traditional algorithms such as the filtered back projection require a high signal-to-noise ratio across a wide wavelength range combined with a large number of projections. This results in scan times of several days to acquire hundreds of hyperspectral projections, during which end users have minimal feedback. To address these challenges, a golden ratio scanning protocol combined with model-based image reconstruction algorithms have been proposed. This novel approach enables high quality real-time reconstructions from streaming experimental data, thus providing feedback to users, while requiring fewer yet a fixed number of projections compared to the filtered back projection method. In this paper, we propose a novel machine learning criterion that can terminate a streaming neutron tomography scan once sufficient information is obtained based on the current set of measurements. Our decision criterion uses a quality score which combines a reference-free image quality metric computed using a pre-trained deep neural network with a metric that measures differences between consecutive reconstructions. The results show that our method can reduce the measurement time by approximately a factor of five compared to a baseline method based on filtered back projection for the samples we studied while automatically terminating the scans.

97 MATHEMATICS AND COMPUTING↗
NASA NTRS1993

Radial basis function network learns ceramic processing and predicts related strength and density

Radial basis function (RBF) neural networks were trained using the data from 273 Si3N4 modulus of rupture (MOR) bars which were tested at room temperature and 135 MOR bars which were tested at 1370 C. Milling time, sintering time, and sintering gas pressure were the processing parameters used as the input features. Flexural strength and density were the outputs by which the RBF networks were assessed. The 'nodes-at-data-points' method was used to set the hidden layer centers and output layer training used the gradient descent method. The RBF network predicted strength with an average error of less than 12 percent and density with an average error of less than 2 percent. Further, the RBF network demonstrated a potential for optimizing and accelerating the development and processing of ceramic materials.

Cios, Krzysztof J.↗
DOE OSTI2023

Physics constrained unsupervised deep learning for rapid, high resolution scanning coherent diffraction reconstruction

By circumventing the resolution limitations of optics, coherent diffractive imaging (CDI) and ptychography are making their way into scientific fields ranging from X-ray imaging to astronomy. Yet, the need for time consuming iterative phase recovery hampers real-time imaging. While supervised deep learning strategies have increased reconstruction speed, they sacrifice image quality. Furthermore, these methods’ demand for extensive labeled training data is experimentally burdensome. Here, we propose an unsupervised physics-informed neural network reconstruction method, PtychoPINN, that retains the factor of 100-to-1000 speedup of deep learning-based reconstruction while improving reconstruction quality by combining the diffraction forward map with real-space constraints from overlapping measurements. In particular, PtychoPINN gains a factor of 4 in linear resolution and an 8 dB improvement in PSNR while also accruing improvements in generalizability and robustness. This blend of performance and computational efficiency offers exciting prospects for high-resolution real-time imaging in high-throughput environments such as X-ray free electron lasers (XFELs) and diffraction-limited light sources.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2022

Seismic Waveform Inversion Capability on Resource-Constrained Edge Devices

Seismic full wave inversion (FWI) is a widely used non-linear seismic imaging method used to reconstruct subsurface velocity images, however it is time consuming, has high computational cost and depend heavily on human interaction. Recently, deep learning has accelerated it’s use in several data-driven techniques, however most deep learning techniques suffer from overfitting and stability issues. In this work, we propose an edge computing-based data-driven inversion technique based on supervised deep convolutional neural network to accurately reconstruct the subsurface velocities. Deep learning based data-driven technique depends mostly on bulk data training. In this work, we train our deep convolutional neural network (DCN) (UNet and InversionNet) on the raw seismic data and their corresponding velocity models during the training phase to learn the non-linear mapping between the seismic data and velocity models. The trained network is then used to estimate the velocity models from new input seismic data during the prediction phase. The prediction phase is performed on a resource-constrained edge device such as Raspberry Pi. Raspberry Pi provides real-time and on-device computational power to execute the inference process. In addition, we demonstrate robustness of our models to perform inversion in the presence on noise by performing both noise-aware and no-noise training and feeding the resulting trained models with noise at different signal-to-noise (SNR) ratio values. We make great efforts to achieve very feasible inference times on the Raspberry Pi for both models. Specifically, the inference times per prediction for UNet and InversionNet models on Raspberry Pi were 22 and 4 s respectively whilst inference times for both models on the GPU were 2 and 18 s which are very comparable. Finally, we have designed a user-friendly interactive graphical user interface (GUI) to automate the model execution and inversion process on the Raspberry Pi.

Manu, Daniel (ORCID:0000000154982677)↗
DOE OSTI2024

Deep learning-based temporal deconvolution for photon time-of-flight distribution retrieval

The acquisition of the time of flight (ToF) of photons has found numerous applications in the biomedical field. Over the last decades, a few strategies have been proposed to deconvolve the temporal instrument response function (IRF) that distorts the experimental time-resolved data. However, these methods require burdensome computational strategies and regularization terms to mitigate noise contributions. Herein, we propose a deep learning model specifically to perform the deconvolution task in fluorescence lifetime imaging (FLI). The model is trained and validated with representative simulated FLI data with the goal of retrieving the true photon ToF distribution. Its performance and robustness are validated with well-controlled in vitro experiments using three time-resolved imaging modalities with markedly different temporal IRFs. The model aptitude is further established with in vivo preclinical investigation. Overall, these in vitro and in vivo validations demonstrate the flexibility and accuracy of deep learning model-based deconvolution in time-resolved FLI and diffuse optical imaging.

Pandey, Vikas (ORCID:0000000154771095)↗
DOE OSTI2020

Preliminary results in using Deep Learning to emulate BLOB, a nuclear interaction model

Purpose: A reliable model to simulate nuclear interactions is fundamental for Ion-therapy. We already showed how BLOB (“Boltzmann-Langevin One Body”), a model developed to simulate heavy ion interactions up to few hundreds of MeV/u, could simulate also 12 C reactions in the same energy domain. However, its computation time is too long for any medical application. For this reason we present the possibility of emulating it with a Deep Learning algorithm. Methods: The BLOB final state is a Probability Density Function (PDF) of finding a nucleon in a position of the phase space. We discretised this PDF and trained a Variational Auto-Encoder (VAE) to reproduce such a discrete PDF. As a proof of concept, we developed and trained a VAE to emulate BLOB in simulating the interactions of 12 C with 12 C at 62 MeV/u. To have more control on the generation, we forced the VAE latent space to be organised with respect to the impact parameter (b) training a classifier of b jointly with the VAE. Results: In this work, the distributions obtained from the VAE are similar to the input ones and the computation time needed to use the VAE as a generator is negligible. Conclusions: We show that it is possible to use a Deep Learning approach to emulate a model developed to simulate nuclear reactions in the energy range of interest for Ion-therapy. We foresee the implementation of the generation part in C++ and to interface it with the most used Monte Carlo toolkit: Geant4.

73 NUCLEAR PHYSICS AND RADIATION PHYSICS↗
DOE OSTI2022

Continuous-time probabilistic models for longitudinal electronic health records

Analysis of longitudinal Electronic Health Record (EHR) data is an important goal for precision medicine. Difficulty in applying Machine Learning (ML) methods, either predictive or unsupervised, stems in part from the heterogeneity and irregular sampling of EHR data. Here, we present an unsupervised probabilistic model that captures nonlinear relationships between variables over continuous-time. This method works with arbitrary sampling patterns and captures the joint probability distribution between variable measurements and the time intervals between them. Inference algorithms are derived that can be used to evaluate the likelihood of future using under a trained model. As an example, we consider data from the United States Veterans Health Administration (VHA) in the areas of diabetes and depression. Likelihood ratio maps are produced showing the likelihood of risk for moderate-severe vs minimal depression as measured by the Patient Health Questionnaire-9 (PHQ-9).

59 BASIC BIOLOGICAL SCIENCES↗
NASA NTRS2005

Sunspot Pattern Classification using PCA and Neural Networks (Poster)

The sunspot classification scheme presented in this paper is considered as a 2-D classification problem on archived datasets, and is not a real-time system. As a first step, it mirrors the Zuerich/McIntosh historical classification system and reproduces classification of sunspot patterns based on preprocessing and neural net training datasets. Ultimately, the project intends to move from more rudimentary schemes, to develop spatial-temporal-spectral classes derived by correlating spatial and temporal variations in various wavelengths to the brightness fluctuation spectrum of the sun in those wavelengths. Once the approach is generalized, then the focus will naturally move from a 2-D to an n-D classification, where "n" includes time and frequency. Here, the 2-D perspective refers both to the actual SOH0 Michelson Doppler Imager (MDI) images that are processed, but also refers to the fact that a 2-D matrix is created from each image during preprocessing. The 2-D matrix is the result of running Principal Component Analysis (PCA) over the selected dataset images, and the resulting matrices and their eigenvalues are the objects that are stored in a database, classified, and compared. These matrices are indexed according to the standard McIntosh classification scheme.

Rajkumar, T.↗