Search NASA⌕ Search

SEARCH · Search NASA

Results for “Distributed training”

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 307 records · Page 17

Integrated Design of Ultradurable, Low CO 2 Alternative Binder Systems via Machine Learning

This ARPA-E project developed a machine learning tool to use in formulation design of cementitious binders for concrete having 50% less embodied CO 2 and possessing twice the durability compared to concrete based on ordinary portland cement (OPC) binders. The technical focus was on limestone/calcined clay cement (LC3), the leading replacement for OPC. Here, hierarchical machine learning (HML) was used to model the flowability, set time, strength, and durability of LC3 concrete. This methodology identifies latent variables derived from domain knowledge and empirical models that develop an accurate model for a response surface from small datasets. For the flowability metric, particle packing was a dominant factor, while strength and durability were both strongly determined by the fraction of metakaolin and the water:solids ratio. Under constraints of water:binder ratio, material performance metrics, embodied CO 2 , and cost per tonne of OPC, multi-objective optimization was used to design binders parameterized by the mineral composition replacing OPC, particle size distributions, and water:solids ratio. The trained algorithm was able to predict multiple mixes met these performance criteria, and experimental testing validated the predictions. The model demonstrated here is relevant for North America, where pure kaolin deposits are found broadly. The approach is being taken forward into commercial application by Ansatz AI, a materials informatics company founded by PI Washburn and co-PI Poczos. Through collaborations with the cement and concrete industry, and funding from SBIR programs, a commercial software will be developed in future research.

36 MATERIALS SCIENCE↗

RICIS Symposium 1988

Integrated Environments for Large, Complex Systems is the theme for the RICIS symposium of 1988. Distinguished professionals from industry, government, and academia have been invited to participate and present their views and experiences regarding research, education, and future directions related to this topic. Within RICIS, more than half of the research being conducted is in the area of Computer Systems and Software Engineering. The focus of this research is on the software development life-cycle for large, complex, distributed systems. Within the education and training component of RICIS, the primary emphasis has been to provide education and training for software professionals.

Source record↗

Environmental awareness program development

Work this summer in the Office of Safety, Environment, and Mission Assurance began with a review of current initiatives and environmental projects at the Langley Research Center (LaRC). This involved researching many of the documents on file which detail problems which have occurred as well as various approaches which have been used to address these problems. A large portion of the time was spent interviewing and working with each of the engineers, industrial hygienists and other professionals connected with the Office of Environmental Engineering. A few of the projects I worked on include: Researching environmental compliance, and pollution prevention efforts; touring many of the facilities at LaRC to observe the environmental efforts in the work place; researching equipment needs for the recycling/reclamation center; writing scripts for in-house training videos; working with the video production department to produce a training video; developing e-mail distribution list; developing environmental coordinator's database; and working with others to research logistics of recycling and waste minimization efforts.

Steinhauer, David A.↗

A Global Model for Estimating Atmospheric Phase Scintillation Statistics

Since 2007, the National Aeronautics and Space Administration (NASA) has been collecting atmospheric phase turbulence data from various NASA ground stations throughout the world. The goal of these measurement campaigns has been to generate statistics to characterize the local site turbulence conditions and their impact on widely distributed ground based antenna arrays. This is of critical importance for the situation of uplink arraying, in which a priori knowledge of the fast varying turbulent conditions of water vapor in the troposphere may not be known, and will impact the power combining efficiency of ground based transmitting arrays. Therefore, the design of these type of systems will be dependent on the local climatology of the particular ground station site. Based on the 30+ station years of data collected characterizing atmospheric phase scintillation statistics at various sites, a global model is presented which attempts to predict the average phase statistics of a generic site based on local surface weather data, such as surface pressure, temperature, relative humidity, wind speed, and median wind direction. A model is proposed and based on a standard log power distribution similar to amplitude scintillation models trained on the existing data sets and shows reasonable accuracy against existing data sets.

propagation↗

Four Design Demonstration Elments (DDEs) to be irradiated in the Advanced Test Reactor (ATR) and the Belgian Reactor 2 (BR2)

The U.S. High Performance Research Reactor Conversion fuel qualification team is focused on developing and qualifying plate type uranium-molybdenum (U-Mo) monolithic and uranium silicide (U3Si4) fuel. Several irradiations of mini-plates and full-size plate irradiations will demonstrate the fuel’s behavior. Along with qualifying fuel, larger tests are planned to support licensing fuel elements. These tests are referred to as DDEs. As a result of a scoping study performed in 2018, a decision was made to irradiate two DDEs in ATR at the Idaho National Laboratory (INL) and two other DDEs in BR2 in Belgium. The objective is to demonstrate successful irradiation of each DDE to support the licensing submittal of that specific reactor. Neutronics analysis is being performed to match the power density distribution of the represented elements. Test train hardware design are being done to ensure all the target conditions are being met for the two DDEs to be irradiated.

11 NUCLEAR FUEL CYCLE AND FUEL MATERIALS↗

Do graph neural networks learn traditional jet substructure?

At the CERN LHC, the task of jet tagging, whose goal is to infer the origin of a jet given a set of final-state particles, is dominated by machine learning methods. Graph neural networks have been used to address this task by treating jets as point clouds with underlying, learnable, edge connections between the particles inside. We explore the decision-making process for one such state-of-the-art network, ParticleNet, by looking for relevant edge connections identified using the layerwise-relevance propagation technique. As the model is trained, we observe changes in the distribution of relevant edges connecting different intermediate clusters of particles, known as subjets. The resulting distribution of subjet connections is different for signal jets originating from top quarks, whose subjets typically correspond to its three decay products, and background jets originating from lighter quarks and gluons. This behavior indicates that the model is using traditional jet substructure observables, such as the number of prongs -- energetic particle clusters -- within a jet, when identifying jets.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

Predicting the required number of training samples

A criterion which measures the quality of the estimate of the covariance matrix of a multivariate normal distribution is developed. Based on this criterion, the necessary number of training samples is predicted. Experimental results which are used as a guide for determining the number of training samples are included.

Kalayeh, H. M.↗

Predicting the required number of training samples

A criterion which measures the quality of the estimate of the covariance matrix of a multivariate normal distribution is developed. Based on this criterion, the necessary number of training samples is predicted. Experimental results which are used as a guide for determining the number of training samples are included. Previously announced in STAR as N82-28109

Kalayeh, H. M.↗

Active operator learning with predictive uncertainty quantification for partial differential equations

With the increased prevalence of neural operators being used to provide rapid solutions to partial differential equations (PDEs), understanding the accuracy of model predictions and the associated error levels is necessary for deploying reliable surrogate models in scientific applications. Existing uncertainty quantification (UQ) frameworks employ ensembles or Bayesian methods, which can incur substantial computational costs during both training and inference. Here, we propose a lightweight predictive UQ method tailored for Deep operator networks (DeepONets) that also generalizes to other operator networks. Numerical experiments on linear and nonlinear PDEs demonstrate that the framework’s uncertainty estimates are unbiased and provide accurate out-of-distribution uncertainty predictions with a sufficiently large training dataset. Our framework provides fast inference and uncertainty estimates that can efficiently drive outer-loop analyses that would be prohibitively expensive with conventional solvers. We demonstrate how predictive uncertainties can be used in the context of Bayesian optimization and active learning problems to yield improvements in accuracy and data-efficiency for outer-loop optimization procedures. In the active learning setup, we extend the framework to Fourier Neural Operators (FNO) and describe a generalized method for other operator networks. To enable real-time deployment, we introduce an inference strategy based on precomputed trunk outputs and a sparse placement matrix, reducing evaluation time by more than a factor of five. Our method provides a practical route to uncertainty-aware operator learning in time-sensitive settings.

97 MATHEMATICS AND COMPUTING↗

An aerosol activation metamodel of v1.2.0 of the pyrcel cloud parcel model: development and offline assessment for use in an aerosol–climate model

We describe an emulator of a detailed cloud parcel model which has been trained to assess droplet nucleation from a complex, multimodal aerosol size distribution simulated by a global aerosol–climate model. The emulator is constructed using a sensitivity analysis approach (polynomial chaos expansion) which reproduces the behavior of the targeted parcel model across the full range of aerosol properties and meteorology simulated by the parent climate model. An iterative technique using aerosol fields sampled from a global model is used to identify the critical aerosol size distribution parameters necessary for accurately predicting activation. Across the large parameter space used to train them, the emulators estimate cloud droplet number concentration (CDNC) with a mean relative error of 9.2% for aerosol populations without giant cloud condensation nuclei (CCN) and 6.9% when including them. Versus a parcel model driven by those same aerosol fields, the best-performing emulator has a mean relative error of 4.6%, which is comparable with two commonly used activation schemes also evaluated here (which have mean relative errors of 2.9 and 6.7%, respectively). We identify the potential for regional biases in modeled CDNC, particularly in oceanic regimes, where our best-performing emulator tends to overpredict by 7%, whereas the reference activation schemes range in mean relative error from -3 to 7%. The emulators which include the effects of giant CCN are more accurate in continental regimes (mean relative error of 0.3%) but strongly overestimate CDNC in oceanic regimes by up to 22%, particularly in the Southern Ocean. Finally, the biases in CDNC resulting from the subjective choice of activation scheme could potentially influence the magnitude of the indirect effect diagnosed from the model incorporating it.

54 ENVIRONMENTAL SCIENCES↗

Exploiting Multi-Domain Features for Detection of Unclassified Electromagnetic Signals

Deep Learning based classification techniques have shown excellent performance in static environments, where the training and testing samples are drawn from the same distribution. However, real world scenarios often present samples that do not belong to the known set of classes chosen during training. This is quite common for electromagnetic signals, where it is impractical to assume that all possible waveforms are known a-priori, specially in scenarios like warfare. To address this problem, we propose a deep learning based adversarial model where the generator learns to generate waveform features that can deceive the discriminator model as true samples. We introduce domain knowledge of wireless signals by decomposing the signal into a lower dimensional unique feature set, which is used for classifying known versus unknown signals. We further introduce multiple domain representations of the signal to extract features and combine them together to accurately classify new waveforms as an unknown class. Our results show that combined features from multiple domains outperform any single domain representation, especially at low SNR regimes with fewer number of samples to classify.

99 - GENERAL AND MISCELLANEOUS↗

Exploiting Multi-Domain Features for Detection of Unclassified Electromagnetic Signals (Presentation)

Deep Learning based classification techniques have shown excellent performance in static environments, where the training and testing samples are drawn from the same distribution. However, real world scenarios often present samples that do not belong to the known set of classes chosen during training. This is quite common for electromagnetic signals, where it is impractical to assume that all possible waveforms are known a-priori, specially in scenarios like warfare. To address this problem, we propose a deep learning based adversarial model where the generator learns to generate waveform features that can deceive the discriminator model as true samples. We introduce domain knowledge of wireless signals by decomposing the signal into a lower dimensional unique feature set, which is used for classifying known versus unknown signals. We further introduce multiple domain representations of the signal to extract features and combine them together to accurately classify new waveforms as an unknown class. Our results show that combined features from multiple domains outperform any single domain representation, especially at low SNR regimes with fewer number of samples to classify.

99 - GENERAL AND MISCELLANEOUS↗

Selecting XFEL single-particle snapshots by geometric machine learning

A promising new route for structural biology is single-particle imaging with an X-ray Free-Electron Laser (XFEL). This method has the advantage that the samples do not require crystallization and can be examined at room temperature. However, high-resolution structures can only be obtained from a sufficiently large number of diffraction patterns of individual molecules, so-called single particles. Here, we present a method that allows for efficient identification of single particles in very large XFEL datasets, operates at low signal levels, and is tolerant to background. This method uses supervised Geometric Machine Learning (GML) to extract low-dimensional feature vectors from a training dataset, fuse test datasets into the feature space of training datasets, and separate the data into binary distributions of “single particles” and “non-single particles.” As a proof of principle, we tested simulated and experimental datasets of the Coliphage PR772 virus. We created a training dataset and classified three types of test datasets: First, a noise-free simulated test dataset, which gave near perfect separation. Second, simulated test datasets that were modified to reflect different levels of photon counts and background noise. These modified datasets were used to quantify the predictive limits of our approach. Third, an experimental dataset collected at the Stanford Linear Accelerator Center. The single-particle identification for this experimental dataset was compared with previously published results and it was found that GML covers a wide photon-count range, outperforming other single-particle identification methods. Moreover, a major advantage of GML is its ability to retrieve single particles in the presence of structural variability.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

PHOTOMETRIC REDSHIFT PROBABILITY DISTRIBUTIONS FOR GALAXIES IN THE SDSS DR8

We present redshift probability distributions for galaxies in the Sloan Digital Sky Survey (SDSS) Data Release 8 imaging data. We used the nearest-neighbor weighting algorithm to derive the ensemble redshift distribution N(z), and individual redshift probability distributions P(z) for galaxies with r < 21.8 and u < 29.0. As part of this technique, we calculated weights for a set of training galaxies with known redshifts such that their density distribution in five-dimensional color-magnitude space was proportional to that of the photometry-only sample, producing a nearly fair sample in that space. We estimated the ensemble N(z) of the photometric sample by constructing a weighted histogram of the training-set redshifts. We derived P(z)'s for individual objects by using training-set objects from the local color-magnitude space around each photometric object. Using the P(z) for each galaxy can reduce the statistical error in measurements that depend on the redshifts of individual galaxies. The spectroscopic training sample is substantially larger than that used for the DR7 release. The newly added PRIMUS catalog is now the most important training set used in this analysis by a wide margin. We expect the primary sources of error in the N(z) reconstruction to be sample variance and spectroscopic failures: The training sets are drawn from relatively small volumes of space, and some samples have large incompleteness. Using simulations we estimated the uncertainty in N(z) due to sample variance at a given redshift to be {approx}10%-15%. The uncertainty on calculations incorporating N(z) or P(z) depends on how they are used; we discuss the case of weak lensing measurements. The P(z) catalog is publicly available from the SDSS Web site.

79 ASTRONOMY AND ASTROPHYSICS↗

Plug & play directed evolution of proteins with gradient-based discrete MCMC

Abstract A long-standing goal of machine-learning-based protein engineering is to accelerate the discovery of novel mutations that improve the function of a known protein. We introduce a sampling framework for evolving proteins in silico that supports mixing and matching a variety of unsupervised models, such as protein language models, and supervised models that predict protein function from sequence. By composing these models, we aim to improve our ability to evaluate unseen mutations and constrain search to regions of sequence space likely to contain functional proteins. Our framework achieves this without any model fine-tuning or re-training by constructing a product of experts distribution directly in discrete protein space. Instead of resorting to brute force search or random sampling, which is typical of classic directed evolution, we introduce a fast Markov chain Monte Carlo sampler that uses gradients to propose promising mutations. We conduct in silico directed evolution experiments on wide fitness landscapes and across a range of different pre-trained unsupervised models, including a 650 M parameter protein language model. Our results demonstrate an ability to efficiently discover variants with high evolutionary likelihood as well as estimated activity multiple mutations away from a wild type protein, suggesting our sampler provides a practical and effective new paradigm for machine-learning-based protein engineering.

59 BASIC BIOLOGICAL SCIENCES↗

Bayesian model updating with finite element vs surrogate models: Application to a miter gate structural system

Bayesian finite element (FE) model updating using direct model evaluations of large-scale high-fidelity FE models is extremely computationally expensive. Surrogate models can be used as fast emulators of FE models to accelerate the model calibration process. The physics/mechanics-based FE models are still the underpinning behind the surrogate models. Here, this paper evaluates the loss in accuracy and the gain in computational time while performing Bayesian model updating by using surrogate model evaluations compared to using direct FE model evaluations. This evaluation is crucial before entirely relying on surrogate models in model updating for structural health monitoring (SHM) and damage prognosis (DP) purposes. This paper also demonstrates Bayesian updating and surrogate model construction of large-scale high-fidelity FE models of infrastructure systems. In this regard, the miter gate structural system is considered as the testbed structure. Three predominant damage modes (loss of contact between gate and wall, loss of thickness due to corrosion, and loss of tension in the diagonal rods) are considered for model updating purposes. Bayesian model updating is performed using direct FE evaluations by leveraging parallel computing. Two types of surrogates, namely polynomial chaos expansion (PCE) and Gaussian process regression (GPR), are developed for the miter gate. Model updating is performed again using the trained surrogate models, and the updating results are compared with their counterparts obtained using the direct FE evaluation results. The posterior distribution of the FE model parameters obtained using the trained surrogates are sufficiently accurate with respect to the posterior obtained utilizing the direct FE evaluations. In addition, an approximate 4-fold decrease in the computational time was observed when using surrogate model evaluations instead of direct FE evaluations for model updating.

42 ENGINEERING↗

The Application of Dedicated Controllers to Parallel/Serial Exhauster Trains

Twenty new dedicated controllers were interfaced to the Distributed Control System (DCS) at NASA Lewis Research Center. Better surge avoidance, improved energy savings, interface intricacies, and plant complexities are the subjects of this paper. Problems with the existing Programmable Logic Controller (PLC) control logic are described as well as the solutions implemented with the new controllers. The complexity of the new communication network between the dedicated controllers, Multipurpose Micro-Processor (MMPs), and the operator workstations are illustrated. The complicated nature of the plant and methods of controlling the associated processes are also discussed.

Sadhukhan, Debashis↗