Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Distributed computing, machine learning”

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

MO-G-304-02: Knowledge Based DVH Prediction Using a Geometric Dose Transform

Purpose: To demonstrate a novel method for predicting patient dose-volume histograms (DVHs) using a prior database of optimized radiotherapy treatment plans. Such predicted DVHs could be useful for automating treatment planning. Methods: Our initial demonstration utilized a database of 100 prostate intensity-modulated radiotherapy (IMRT) data-sets. Each data-set contained a CT image with contours of the planning target volume (PTV), rectum, and bladder, the parameters of a clinically approved IMRT plan, and a corresponding simulated dose distribution. We applied a novel geometric transformation to remove the influence of the PTV size, shape, and location on the dose distribution. We termed the transformed distribution the geometrically normalized dose distribution (GNDD). This normalization transform was applied to 80 data-sets randomly selected from the database, and a population GNDD was computed as the average. Next, the population GNDD was mapped onto each of the remaining 20 patient datasets using the reverse of the geometric normalization transform, and predicted DVHs were calculated from the reverse transformed dose distributions (GNDD-DVHs). In addition, a state of the art machine learning based method from the literature was tested for comparison. Results: DVH prediction accuracy was quantified by calculating the relative root mean squared error (rRMSE) on predicted DVHs for the 20 test patients using their known DVHs. For bladder, rectum, and PTV average rRMSEs for the GNDD method were 9.7 ± 4.2%, 13.9 ± 6.0%, and 2.3 ± 0.5% respectively. Prediction results using GNDD were roughly equivalent to that from the machine learning method. Conclusion: We developed a new method for predicting DVH curves from a database of prior patient plans. We demonstrated that our simple approach achieves accuracy comparable to a method using a complicated machine learning based approach.

60 APPLIED LIFE SCIENCES↗

Spatiotemporally dynamic implicit large eddy simulation using machine learning classifiers

In this article, we utilize machine learning to dynamically determine if a point on the computational grid requires implicit numerical dissipation for large eddy simulation (LES). The decision making process is learnt through a priori training on quantities derived from direct numerical simulation (DNS) data. In particular, we compute eddy-viscosities obtained through the coarse-graining of DNS quantities and utilize their projection onto a Gaussian distribution to categorize areas that may require dissipation. If our learning determines that closure is necessary, an upwinded scheme is utilized for computing the non-linear Jacobian. In contrast, if it is determined that closure is unnecessary, a symmetric and second-order accurate energy and enstrophy preserving Arakawa scheme is utilized instead. This results in a closure framework that precludes the specification of any model-form for the small scale contributions of turbulence but deploys an appropriate numerical dissipation from explicit closure driven hypotheses. Here, this methodology is deployed for the Kraichnan turbulence test-case and assessed through various statistical quantities such as angle-averaged kinetic energy spectra and vorticity structure functions. Our framework thus establishes a link between the use of explicit LES ideologies for closure and numerical dissipation-based modeling of turbulence leading to improved statistical fidelity of a posteriori simulations.

42 ENGINEERING↗

Convolutional Neural Network–Aided Temperature Field Reconstruction: An Innovative Method for Advanced Reactor Monitoring

In this study, the capabilities of a physics-informed convolutional neural network (CNN) for reconstructing the temperature field from a limited set of measurements taken at the boundaries of internal flows are demonstrated. Such an approach enables the development of less invasive monitoring methods for real-time plant diagnostics. As a test case, a Molten Salt Fast Reactor (MSFR) design was selected. This circulating fuel reactor has received interest from both scientific and industrial communities due to its intrinsic safety and sustainability. Molten salt flows in such reactors, however, can present highly localized temperature peaks that can induce significant thermal stresses onto the vessel walls. At these local maxima, the salt temperature may exceed a thousand kelvins, which makes a direct measurement challenging or even unfeasible. The proposed CNN algorithm allows one to detect indirectly such discontinuities through an accurate, albeit indirect, temperature measurement method during reactor operation. The datasets employed to train and test the machine learning models in the present work were generated with Nek5000, a computational fluid dynamics (CFD) code developed at Argonne National Laboratory. The CNN algorithm is trained with CFD results that span a set of MSFR operational power and flow ranges. Here, to demonstrate the efficacy of the algorithm, predictions are made for test cases contained within the training range but for which the CFD data were not used when training. Results demonstrate that the proposed technique properly characterizes temperature peaks and distributions within the domain for a broad range of scenarios.

21 SPECIFIC NUCLEAR REACTORS AND ASSOCIATED PLANTS↗

Probabilistic predictions and uncertainty estimation for radiological and nuclear effects modeling

Better characterization of meteorological uncertainty is needed to predict the effects of radiological and nuclear releases in the atmosphere. Multi-physics ensembles of atmospheric simulations can estimate uncertainty of physical processes, but they are often limited for computational reasons. Because weather uncertainty is important for emergency response applications, but the conventional way of running multi-physics ensembles is infeasible, we have developed new machine learning-based methods that quickly estimate and identify key sources of meteorological uncertainty. Machine learning accelerates the analysis of weather uncertainty by iteratively learning about model physics options that affect plume predictions. We have demonstrated the power of machine learning by creating a large multi-physics weather and dispersion ensemble dataset containing 1,200 simulations for two hypothetical radiological release scenarios. By training on less than 10% of the ensemble, we can quickly and accurately predict different outcomes, including the mass of radiological material deposited and spatial distribution and extent of contaminated areas.

54 ENVIRONMENTAL SCIENCES↗

Deducing subnanometer cluster size and shape distributions of heterogeneous supported catalysts

Abstract Infrared (IR) spectra of adsorbate vibrational modes are sensitive to adsorbate/metal interactions, accurate, and easily obtainable in-situ or operando. While they are the gold standards for characterizing single-crystals and large nanoparticles, analogous spectra for highly dispersed heterogeneous catalysts consisting of single-atoms and ultra-small clusters are lacking. Here, we combine data-based approaches with physics-driven surrogate models to generate synthetic IR spectra from first-principles. We bypass the vast combinatorial space of clusters by determining viable, low-energy structures using machine-learned Hamiltonians, genetic algorithm optimization, and grand canonical Monte Carlo calculations. We obtain first-principles vibrations on this tractable ensemble and generate single-cluster primary spectra analogous to pure component gas-phase IR spectra. With such spectra as standards, we predict cluster size distributions from computational and experimental data, demonstrated in the case of CO adsorption on Pd/CeO 2 (111) catalysts, and quantify uncertainty using Bayesian Inference. We discuss extensions for characterizing complex materials towards closing the materials gap.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

A practical and efficient approach for Bayesian quantum state estimation

Bayesian inference is a powerful paradigm for quantum state tomography, treating uncertainty in meaningful and informative ways. Yet the numerical challenges associated with sampling from complex probability distributions hampers Bayesian tomography in practical settings. In this article, we introduce an improved, self-contained approach for Bayesian quantum state estimation. Leveraging advances in machine learning and statistics, our formulation relies on highly efficient preconditioned Crank–Nicolson sampling and a pseudo-likelihood. We theoretically analyze the computational cost, and provide explicit examples of inference for both actual and simulated datasets, illustrating improved performance with respect to existing approaches.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

Unsupervised quantum circuit learning in high energy physics

Unsupervised training of generative models is a machine learning task that has many applications in scientific computing. Here, in this work, we evaluate the efficacy of using quantum circuit-based generative models to generate synthetic data of high energy physics processes. We use nonadversarial, gradient-based training of quantum circuit Born machines to generate joint distributions over two and three variables.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

A Nonrelational Data Warehouse for the Analysis of Field and Laboratory Data From Multiple Heterogeneous Photovoltaic Test Sites

A nonrelational, distributed computing, data warehouse, and analytics environment (Energy-CRADLE) was developed for the analysis of field and laboratory data from multiple heterogeneous photovoltaic (PV) test sites. This data informatics and analytics infrastructure was designed to process diverse formats of PV performance data and climatic telemetry time-series data collected from a PV outdoor test network, i.e., the Solar Durability and Lifetime Extension global SunFarm network, as well as point-in-time laboratory spectral and image measurements of PV material samples. Using Hadoop/HBase for the distributed data warehouse, Energy-CRADLE does not have a predefined data table schema, which enables ingestion of data in diverse and changing formats. For easy data ingestion and data retrieval, Energy-CRADLE utilizes Hadoop streaming to enable Python MapReduce and provides a graphical user interface, i.e., py-CRADLE. By developing the Hadoop distributed computing platform and the HBase NoSQL database schema for solar energy, Energy-CRADLE exemplifies an integrated, scalable, secure, and user-friendly data informatics and analytics system for PV researchers. Furthermore, an example of Energy-CRADLE enabled scalable, data-driven, analytics is presented, where machine learning is used for anomaly detection across 2.2 million real-world current-voltage (I–V) curves of PV modules in three distinct Koppen–Geiger climatic zones.

14 SOLAR ENERGY↗

Data augmentation for disruption prediction via robust surrogate models

The goal of this work is to generate large statistically representative data sets to train machine learning models for disruption prediction provided by data from few existing discharges. Such a comprehensive training database is important to achieve satisfying and reliable prediction results in artificial neural network classifiers. Here, we aim for a robust augmentation of the training database for multivariate time series data using Student t process regression. We apply Student t process regression in a state space formulation via Bayesian filtering to tackle challenges imposed by outliers and noise in the training data set and to reduce the computational complexity. Thus, the method can also be used if the time resolution is high. We use an uncorrelated model for each dimension and impose correlations afterwards via colouring transformations. We demonstrate the efficacy of our approach on plasma diagnostics data of three different disruption classes from the DIII-D tokamak. To evaluate if the distribution of the generated data is similar to the training data, we additionally perform statistical analyses using methods from time series analysis, descriptive statistics and classic machine learning clustering algorithms.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗

Quantum Machine-Learning for Eigenstate Filtration in Two-Dimensional Materials

Quantum machine-learning algorithms have emerged to be a promising alternative to their classical counterparts as they leverage the power of quantum computers. Such algorithms have been developed to solve problems like electronic structure calculations of molecular systems and spin models in magnetic systems. However, the discussion in all these recipes focuses specifically on targeting the ground state. Herein we demonstrate a quantum algorithm that can filter any energy eigenstate of the system based on either symmetry properties or a predefined choice of the user. The workhorse of our technique is a shallow neural network encoding the desired state of the system with the amplitude computed by sampling the Gibbs–Boltzmann distribution using a quantum circuit and the phase information obtained classically from the nonlinear activation of a separate set of neurons. We show that the resource requirements of our algorithm are strictly quadratic. To demonstrate its efficacy, we use state filtration in monolayer transition metal dichalcogenides which are hitherto unexplored in any flavor of quantum simulations. We implement our algorithm not only on quantum simulators but also on actual IBM-Q quantum devices and show good agreement with the results procured from conventional electronic structure calculations. We thus expect our protocol to provide a new alternative in exploring the band structures of exquisite materials to usual electronic structure methods or machine-learning techniques that are implementable solely on a classical computer.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

SDN-NGenIA, a Software Defined Next Generation Integrated Architecture for HEP and Data Intensive Science

This project aims to enable the LHC and other leading programs in high energy physics and other global science domains funded by the DOE to operate with a new level of efficiency and control, through the development of a Next Generation Integrated Architecture (NGenIA) based on intelligent software defined network (SDN)-driven network systems coupled to high throughput applications. While the initial focus is on the challenging LHC use case, the systems and products being developed are general, and apply to many fields of data intensive science ranging from astrophysical sky surveys to bioinformatics and earth observation, as well as other organizations facing the challenges of extracting knowledge from distributed multi-petabyte data stores. A central concept in this development program is a new paradigm ‘consistent network operations’ among widely distributed computing and storage facilities, where stable high throughput flows, at set rates, cross load-balanced network paths, up to flexible high water marks that are adjusted in real time to accommodate other network traffic. The large smooth flows are launched and managed by SDN services that act in concert with the experiments’ site-resident data distribution and management systems, to meet the expanding needs of the science programs. The technical goals include the construction of autonomous, intelligent site-resident services that interact dynamically with network-resident services, and with the science programs’ principal data distribution and management tools, to request or command network resources in support of high throughput petascale to exascale workflow Specific work items include: 1. Developing compact Data Transfer Nodes (DTNs) with auto-tuning functions that support data transfer rates in the 100 Gbps to the 1 Tbps range when used with high throughput data transfer applications 2. Deep site orchestration among virtualized clusters, storage subsystems and subnets to successfully coschedule CPU, storage and network resources 3. Science-program designed site architectures, operational modes, and policy and resource usage priorities, adjudicated across multiple network domains and virtual organizations, using the orchestration functions and methods 4. Seamlessly extending end-to-end operation across both extra-site and intra-site boundaries through the use of Open vSwitch (OVS), FireQoS + next generation Science DMZs 5. Novel methods of system integration that enable granular control of extreme scale long distance transfers through flow matching of scattered source-destination address pairs to multi-domain dynamic circuits 6. Funneling massive sets of streams to DTNs at the site edge hosting petascale buffer pools configured for flows of 100 Gbps and up, exploiting state of the art data transfers 7. Adaptive scheduling based on pervasive end-to-end monitoring, including DTN or compute-node resident agents providing comprehensive end-system profiling 8. Developing unsupervised and supervised machine learning and modeling methods to optimize the workflow involving terabyte to multi-petabyte datasets.

47 OTHER INSTRUMENTATION↗

HEPCloud Operations at Fermilab—The First Five Years

The HEPCloud Facility at Fermilab has now been in production operation for five years. This facility is a unified provisioning gateway to US high performance computing centers, including NERSC, OLCF, and ALCF, other large supercomputers run by the NSF, and commercial clouds. HEPCloud delivers hundreds of millions of core-hours yearly for CMS. HEPCloud also serves other Fermilab experiments including DUNE, Mu2e, Muon g-2, and NOvA. In this paper we present the practical considerations of operating a distributed facility such as HEPCloud. We also mention some of the interesting research and development that HEPCloud has been used for including GPU-based machine learning inference servers, and tests of Quantum Computing.

Timm, Steven [Fermilab]↗

Probing effective field theory operators in the associated production of top quarks with a Z boson in multilepton final states at $\sqrt{s}$ = 13 TeV

A search for new top quark interactions is performed within the framework of an effective field theory using the associated production of either one or two top quarks with a Z boson in multilepton final states. The data sample corresponds to an integrated luminosity of 138 fb -1 of proton-proton collisions at √s = 13 TeV collected by the CMS experiment at the LHC. Five dimension-six operators modifying the electroweak interactions of the top quark are considered. Novel machine-learning techniques are used to enhance the sensitivity to effects arising from these operators. Distributions used for the signal extraction are parameterized in terms of Wilson coefficients describing the interaction strengths of the operators. All five Wilson coefficients are simultaneously fit to data and 95% confidence level intervals are computed. All results are consistent with the SM expectations.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

A performance model for GPUs with caches

To exploit the abundant computational power of the world's fastest supercomputers, an even workload distribution to the typically heterogeneous compute devices is necessary. While relatively accurate performance models exist for conventional CPUs, accurate performance estimation models for modern GPUs do not exist. This paper presents two accurate models for modern GPUs: a sampling-based linear model, and a model based on machine-learning (ML) techniques which improves the accuracy of the linear model and is applicable to modern GPUs with and without caches. We first construct the sampling-based linear model to predict the runtime of an arbitrary OpenCL kernel. Based on an analysis of NVIDIA GPUs' scheduling policies we determine the earliest sampling points that allow an accurate estimation. The linear model cannot capture well the significant effects that memory coalescing or caching as implemented in modern GPUs have on performance. We therefore propose a model based on ML techniques that takes several compiler-generated statistics about the kernel as well as the GPU's hardware performance counters as additional inputs to obtain a more accurate runtime performance estimation for modern GPUs. We demonstrate the effectiveness and broad applicability of the model by applying it to three different NVIDIA GPU architectures and one AMD GPU architecture. On an extensive set of OpenCL benchmarks, on average, the proposed model estimates the runtime performance with less than 7 percent error for a second-generation GTX 280 with no on-chip caches and less than 5 percent for the Fermi-based GTX 580 with hardware caches. On the Kepler-based GTX 680, the linear model has an error of less than 10 percent. On an AMD GPU architecture, Radeon HD 6970, the model estimates with 8 percent of error rates. As a result, the proposed technique outperforms existing models by a factor of 5 to 6 in terms of accuracy.

97 MATHEMATICS AND COMPUTING↗

Collective I/O Tuning Using Analytical and Machine-Learning Models

The ever larger demand of scientific applications for computation and data is currently driving a continuous increase in scale of parallel computers. The inherent complexity of scaling up a computing systems in terms of both hardware and software stack exposes an increasing number of factors impacting the performance and complicating the process of optimization. In particular, the optimization of parallel I/O has become increasingly challenging due to increasing storage hierarchy and well known performance variability of shared storage systems. This paper focuses on model-based autotuning of the two-phase collective I/O algorithm from a popular MPI distribution on the Blue Gene/Q architecture. We propose a novel hybrid model, constructed as a composition of analytical models for communication and storage operations and black-box models for the performance of the individual operations. We perform an in-depth study of the complexity involved in performance modeling including architecture, software stack and noise. In particular we address this challenges of modeling the performance of shared storage systems by building a benchmark that helps synthesizing factors such as topology, file caching, and noise. The experimental results show that the hybrid approach produces significantly better results than state-of-the-art machine learning approaches and shows a higher robustness to noise, at the cost of a higher modeling complexity

I/O performance modeling↗

Modeling phase transformations in Mn-rich disordered rocksalt cathodes with machine-learning interatomic potentials

Mn-rich disordered rocksalt (DRX) cathode materials exhibit a phase transformation from a disordered to a partially disordered spinel-like structure (δ-phase) during electrochemical cycling. Here, in this computational study, we use charge-informed molecular dynamics with a fine-tuned CHGNet foundation potential to investigate the phase transformation in LixMn 0.8 Ti 0.1 O 1.9 F 0.1 . Our results indicate that transition metal migration occurs and reorders to form the spinel-like ordering in an FCC anion framework. The transformed structure contains a higher concentration of nontransition metal (0-TM) face-sharing channels, which are known to improve Li transport kinetics. Analysis of the Mn valence distribution suggests that the appearance of tetrahedral Mn 2+ is a consequence of spinel-like ordering, rather than the trigger for cation migration as previously suggested. Calculated equilibrium intercalation voltage profiles demonstrate that the δ-phase, unlike the ordered spinel, exhibits solid-solution signatures at low voltage. A higher Li capacity is obtained than in the DRX phase. This study provides atomic insights into solid-state phase transformation and its relation to experimental electrochemistry, highlighting the potential of machine-learning interatomic potentials for understanding complex oxide materials.

Zhong, Peichen [University of California, Berkeley↗

Simulated sulfur K-edge X-ray absorption spectroscopy database of lithium thiophosphate solid electrolytes

X-ray absorption spectroscopy (XAS) is a premier technique for materials characterization, providing key information about the local chemical environment of the absorber atom. In this work, we develop a database of sulfur K-edge XAS spectra of crystalline and amorphous lithium thiophosphate materials based on the atomic structures reported in Chem. Mater., 34, 6702 (2022). The XAS database is based on simulations using the excited electron and core-hole pseudopotential approach implemented in the Vienna Ab initio Simulation Package. Our database contains 2681 S K-edge XAS spectra for 66 crystalline and glassy structure models, making it the largest collection of first-principles computational XAS spectra for glass/ceramic lithium thiophosphates to date. This database can be used to correlate S spectral features with distinct S species based on their local coordination and short-range ordering in sulfide-based solid electrolytes. The data is openly distributed via the Materials Cloud, allowing researchers to access it for free and use it for further analysis, such as spectral fingerprinting, matching with experiments, and developing machine learning models.

36 MATERIALS SCIENCE↗