SEARCH · Search NASA

Results for “Ensemble”

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.

SourceResearch connectionFrom yearThrough year

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

At least 217 records · Page 12

All sources NASA NTRS DOE OSTI

DOE OSTI2020

InSituNet: Deep Image Synthesis for Parameter Space Exploration of Ensemble Simulations

We propose InSituNet, a deep learning based surrogate model to support parameter space exploration for ensemble simulations that are visualized in situ. In situ visualization, generating visualizations at simulation time, is becoming prevalent in handling large-scale simulations because of the I/O and storage constraints. However, in situ visualization approaches limit the flexibility of post-hoc exploration because the raw simulation data are no longer available. Although multiple image-based approaches have been proposed to mitigate this limitation, those approaches lack the ability to explore the simulation parameters. Our approach allows flexible exploration of parameter space for large-scale ensemble simulations by taking advantage of the recent advances in deep learning. Specifically, we design InSituNet as a convolutional regression model to learn the mapping from the simulation and visualization parameters to the visualization results. With the trained model, users can generate new images for different simulation parameters under various visualization settings, which enables in-depth analysis of the underlying ensemble simulations. We demonstrate the effectiveness of InSituNet in combustion, cosmology, and ocean simulations through quantitative and qualitative evaluations.

deep learning↗

DOE OSTI2022

Autodifferentiable Ensemble Kalman Filters

Data assimilation is concerned with sequentially estimating a temporally evolving state. This task, which arises in a wide range of scientific and engineering applications, is particularly challenging when the state is high-dimensional and the state-space dynamics are unknown. This paper introduces a machine learning framework for learning dynamical systems in data assimilation. Here, our auto-differentiable ensemble Kalman filters (AD-EnKFs) blend ensemble Kalman filters for state recovery with machine learning tools for learning the dynamics. In doing so, AD-EnKFs leverage the ability of ensemble Kalman filters to scale to high-dimensional states and the power of automatic differentiation to train high-dimensional surrogate models for the dynamics. Numerical results using the Lorenz-96 model show that AD-EnKFs outperform existing methods that use expectation-maximization or particle filters to merge data assimilation and machine learning. In addition, AD-EnKFs are easy to implement and require minimal tuning.

autodifferentiation↗

DOE OSTI2022

Machine learning for postprocessing ensemble streamflow forecasts

Skillful streamflow forecasts can inform decisions in various areas of water policy and management. We integrate numerical weather prediction ensembles, distributed hydrological model, and machine learning to generate ensemble streamflow forecasts at medium-range lead times (1–7 days). We demonstrate the application of machine learning as postprocessor for improving the quality of ensemble streamflow forecasts. Our results show that the machine learning postprocessor can improve streamflow forecasts relative to low-complexity forecasts (e.g., climatological and temporal persistence) as well as standalone hydrometeorological modeling and neural network. The relative gain in forecast skill from postprocessor is generally higher at medium-range timescales compared to shorter lead times; high flows compared to low–moderate flows, and the warm season compared to the cool ones. Overall, our results highlight the benefits of machine learning in many aspects for improving both the skill and reliability of streamflow forecasts.

54 ENVIRONMENTAL SCIENCES↗

DOE OSTI2022

In Silico Prediction of the Toxicity of Nitroaromatic Compounds: Application of Ensemble Learning QSAR Approach

In this work, a dataset of more than 200 nitroaromatic compounds is used to develop Quantitative Structure–Activity Relationship (QSAR) models for the estimation of in vivo toxicity based on 50% lethal dose to rats (LD 50 ). An initial set of 4885 molecular descriptors was generated and applied to build Support Vector Regression (SVR) models. The best two SVR models, SVR_A and SVR_B, were selected to build an Ensemble Model by means of Multiple Linear Regression (MLR). The obtained Ensemble Model showed improved performance over the base SVR models in the training set (R 2 = 0.88), validation set (R 2 = 0.95), and true external test set (R 2 = 0.92). The models were also internally validated by 5-fold cross-validation and Y-scrambling experiments, showing that the models have high levels of goodness-of-fit, robustness and predictivity. The contribution of descriptors to the toxicity in the models was assessed using the Accumulated Local Effect (ALE) technique. The proposed approach provides an important tool to assess toxicity of nitroaromatic compounds, based on the ensemble QSAR model and the structural relationship to toxicity by analyzed contribution of the involved descriptors.

54 ENVIRONMENTAL SCIENCES↗

DOE OSTI2024

Uncertainty Visualization Challenges in Decision Systems with Ensemble Data & Surrogate Models: Preprint

Uncertainty visualization is a key component in translating important insights from ensemble data into actionable decision-making by visually conveying various aspects of uncertainty within a system. With the recent advent of fast surrogate models for computationally expensive simulations, users can interact with more aspects of data spaces than ever before. However, the integration of ensemble data with surrogate models in a decision-making tool brings up new challenges for uncertainty visualization, namely how to reconcile and communicate the new and different types of uncertainties brought in by surrogates and how to utilize these new data estimates in actionable ways. In this work, we examine these issues as they relate to high-dimensional data visualization, the integration of discrete datasets and the continuous representations of those datasets, and the unique difficulties associated with systems that allow users to iterate between input and output spaces. We assess the role of uncertainty visualization in facilitating intuitive and actionable interaction with ensemble data and surrogate models, and highlight key challenges in this new frontier of computational simulation.

ensemble visualization↗

DOE OSTI2021

Utilizing ensemble learning for performance and power modeling and improvement of parallel cancer deep learning CANDLE benchmarks

Abstract Machine learning (ML) continues to grow in importance across nearly all domains in modeling to learn from data. Often a tradeoff exists between a model's ability to minimize bias and variance. In this article, we utilize ensemble learning to combine linear, nonlinear, and tree‐/rule‐based ML methods to cope with the bias‐variance tradeoff and result in more accurate models. We use the datasets collected for two parallel cancer deep learning CANDLE benchmarks, NT3 and P1B2, to build performance and power models based on hardware performance counters using single‐object and multiple‐objects ensemble learning to identify the most important counters for improvement on the Cray XC40 Theta at Argonne National Laboratory. Based on the insights from these models, we improve the performance and energy of P1B2 and NT3 by optimizing the deep learning environments TensorFlow, Keras, Horovod, and Python under the huge page size of 8 MB. Experimental results show that ensemble learning not only produces more accurate models but also provides more robust performance counter ranking. We achieve up to 61.15% performance improvement and up to 62.58% energy saving for P1B2 and up to 55.81% performance improvement and up to 52.60% energy saving for NT3 on up to 24,576 cores.

Wu, Xingfu↗

DOE OSTI2020

Ensembles of Networks Produced from Neural Architecture Search

Neural architecture search (NAS) is a popular topic at the intersection of deep learning and high performance computing. NAS focuses on optimizing the architecture of neural networks along with their hyperparameters in order to produce networks with superior performance. Much of the focus has been on how to produce a single best network to solve a machine learning problem, but as NAS methods produce many networks that work very well, this affords the opportunity to ensemble these networks to produce an improved result. Additionally, the diversity of network structures produced by NAS drives a natural bias towards diversity of predictions produced by the individual networks. This results in an improved ensemble over simply creating an ensemble that contains duplicates of the best network architecture retrained to have unique weights.

Herron, Emily↗

DOE OSTI2022

Holevo information and ensemble theory of gravity

Holevo information is an upper bound for the accessible classical information of an ensemble of quantum states. In this work, we use Holevo information to investigate the ensemble theory interpretation of quantum gravity. We study the Holevo information in random tensor network states, where the random parameters are the random tensors at each vertex. Based on the results in random tensor network models, we propose a conjecture on the holographic bulk formula of the Holevo information in the gravity case. As concrete examples of holographic systems, we compute the Holevo information in the ensemble of thermal states and thermo-field double states in the Sachdev-Ye-Kitaev model. The results are consistent with our conjecture.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

DOE OSTI2020

Matrix ensembles with global symmetries and ’t Hooft anomalies from 2d gauge theory

The Hilbert space of a quantum system with internal global symmetry $\textit{G}$ decomposes into sectors labelled by irreducible representations of $\textit{G}$. If the system is chaotic, the energies in each sector should separately resemble ordinary random matrix theory. We show that such “sector-wise” random matrix ensembles arise as the boundary dual of two- dimensional gravity with a $\textit{G}$ gauge field in the bulk. Within each sector, the eigenvalue density is enhanced by a nontrivial factor of the dimension of the representation, and the ground state energy is determined by the quadratic Casimir. We study the consequences of ’t Hooft anomalies in the matrix ensembles, which are incorporated by adding specific topological terms to the gauge theory action. The effect is to introduce projective representations into the decomposition of the Hilbert space. Finally, we consider ensembles with $\textit{G}$ symmetry and time reversal symmetry, and analyze a simple case of a mixed anomaly between time reversal and an internal $\mathbb{Z}$ 2 symmetry.

2D Gravity↗

DOE OSTI2024

The lion, the witch, and the wormhole: ensemble averaging the symmetric product orbifold

Abstract We consider the ensemble average of two dimensional symmetric product orbifold CFTs Sym N (𝕋 D ) over the Narain moduli space. We argue for a bulk dual given byNcopies of an abelian Chern-Simons theory coupled to topological gravity, endowed with a discrete gauge symmetry exchanging theNcopies. As a check of this proposal, we calculate the ensemble average of various partition and correlation functions of the symmetric product orbifold theory and compare the resulting expressions to gauge theory quantities in the bulk. We comment on the ensemble average of the tensionless string partition function on AdS 3 × S 3 × 𝕋 4 by considering the specific case ofD= 4 with the addition of supersymmetry.

Physics↗

DOE OSTI2020

Assessing mean climate change signals in the global CORDEX-CORE ensemble

The new Coordinated Output for Regional Evaluations (CORDEX-CORE) ensemble provides high-resolution, consistent regional climate change projections for the major inhabited areas of the world. It serves as a solid scientific basis for further research related to vulnerability, impact, adaptation and climate services in addition to existing CORDEX simulations. The aim of this study is to investigate and document the climate change information provided by the CORDEX-CORE simulation ensemble, as a part of the World Climate Research Programme (WCRP) CORDEX community. An overview of the annual and monthly mean climate change information in selected regions in different CORDEX domains is presented for temperature and precipitation, providing the foundation for detailed follow-up studies and applications. Initially, two regional climate models (RCMs), REMO and RegCM were used to downscale global climate model output. The driving simulations by AR5 global climate models (AR5-GCMs) were selected to cover the spread of high, medium, and low equilibrium climate sensitivity at a global scale. The CORDEX-CORE ensemble has doubled the spatial resolution compared to the previously existing CORDEX simulations in most of the regions (25 $\,\mathrm {km}$ (0.22 $^{\circ }$ /jats:inline-formula>) versus 50 $\,\mathrm {km}$ (0.44 $^{\circ }$ )) leading to a potentially improved representation of, e.g., physical processes in the RCMs. The analysis focuses on changes in the IPCC physical climate reference regions. The results show a general reasonable representation of the spread of the temperature and precipitation climate change signals of the AR5-GCMs by the CORDEX-CORE simulations in the investigated regions in all CORDEX domains by mostly covering the AR5 interquartile range of climate change signals. The simulated CORDEX-CORE monthly climate change signals mostly follow the AR5-GCMs, although for specific regions they show a different change in the course of the year compared to the AR5-GCMs, especially for RCP8.5, which needs to be investigated further in region specific process studies.

54 ENVIRONMENTAL SCIENCES↗

DOE OSTI2023

Discussion on “Saving Storage in Climate Ensembles: A Model-Based Stochastic Approach”

Abstract We thank the authors for this interesting paper that highlights important ideas and concepts for the future of climate model ensembles and their storage, as well as future uses of stochastic emulators. Stochastic emulators are particularly relevant because of the statistical nature of climate model ensembles, as discussed in previous work of the authors (Castruccio et al. in J Clim 32:8511–8522, 2019; Hu and Castruccio in J Clim 34:8409–8418, 2021). We thank the authors for sharing of some of their data with us in order to illustrate this discussion. In the following, in Sect. 1 we discuss alternative techniques currently used and studied, namely lossy compression and ideas emerging from the climate modeling community, that could feed the discussion on ensemble and storage. In that section, we also present numerical results of compression performed on the data shared by the authors. In Sect. 2, we discuss the current statistical model proposed by the authors and its context. We discuss other potential uses of stochastic emulators in climate and Earth modeling.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2024

Stochastic symplectic reduced-order modeling for model-form uncertainty quantification in molecular dynamics simulations in various statistical ensembles

Here, this work focuses on the representation of model-form uncertainties in molecular dynamics simulations in various statistical ensembles. In prior contributions, the modeling of such uncertainties was formalized and applied to quantify the impact of, and the error generated by, pair-potential selection in the microcanonical ensemble (NVE). In this work, we extend this formulation and present a linear-subspace reduced-order model for the canonical (NVT) and isobaric (NPT) ensembles. The symplectic reduced-order basis is randomized on the tangent space of the Stiefel manifold to provide topological relationships and capture model-form uncertainty. Using the Large-scale Atomic/Molecular Massively Parallel Simulator (LAMMPS), we assess the relevance of these stochastic reduced-order atomistic models on canonical problems involving a Lennard-Jones fluid and an argon crystal melt.

42 ENGINEERING↗

DOE OSTI2022

Generalizability analysis of tool condition monitoring ensemble machine learning models

Tool condition monitoring (TCM) is an essential research area for the optimization and automation of metal machining processes, and could help manufacturers reduce costs, production time, machine downtime, energy use, and part scrappage. However, TCM systems developed in prior studies have struggled to reach the high level of generalizability which is necessary for industrial applications. This study addresses TCM system generalizability to new machining conditions, how variations in machining and environmental conditions may be used to improve model generalizability, and ensemble machine learning techniques for TCM. Further, milling tool life experiments were conducted using various machining conditions, and the processes' sound, spindle power, and axial load signals were collected. Different machine learning models were evaluated for the prediction of tool wear levels, including four individual models and five ensemble models. Changes in cutting speed were found to display a large effect on model performance, while the chip load showed some effect, and the feed rate had little effect. A simulated noise data augmentation technique for model improvement is applied within TCM for the first time, and resulted in increased model generalizability and reduced overfitting. Across several performance metrics the extremely randomized trees ensemble machine learning model generally performed the best for this application, achieving a leave-one-group-out cross validation accuracy score of 92.4 %, a 10-fold cross validation score of 98.9 %, and an averaged accuracy across 11 generalizability tests of 87.3 %.

42 ENGINEERING↗

DOE OSTI2020

Persistent Protein Motions in a Rugged Energy Landscape Revealed by Normal Mode Ensemble Analysis

Proteins are allosteric machines that couple motions at distinct, often distant, sites to control biological function. Low-frequency structural vibrations are a mechanism of this long-distance connection and are often used computationally to predict correlations, but experimentally identifying the vibrations associated with specific motions has proved challenging. Spectroscopy is an ideal tool to explore these excitations, but measurements have been largely unable to identify important frequency bands. The result is at odds with some previous calculations and raises the question what methods could successfully characterize protein structural vibrations. Here we show the lack of spectral structure arises in part from the variations in protein structure as the protein samples the energy landscape. However, by averaging over the energy landscape as sampled using an aggregate 18.5 μs of all-atom molecular dynamics simulation of hen egg white lysozyme and normal-mode analyses, we find vibrations with large overlap with functional displacements are surprisingly concentrated in narrow frequency bands. These bands are not apparent in either the ensemble averaged vibrational density of states or isotropic absorption. However, in the case of the ensemble averaged anisotropic absorption, there is persistent spectral structure and overlap between this structure and the functional displacement frequency bands. We systematically lay out heuristics for calculating the spectra robustly, including the need for statistical sampling of the protein and inclusion of adequate water in the spectral calculation. The results show the congested spectrum of these complex molecules obscures important frequency bands associated with function and reveal a method to overcome this congestion by combining structurally sensitive spectroscopy with robust normal mode ensemble analysis.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

DOE OSTI2022

Characterization of Heparin’s Conformational Ensemble by Molecular Dynamics Simulations and Nuclear Magnetic Resonance Spectroscopy

Heparin is a highly charged, polysulfated polysaccharide and serves as an anticoagulant. Heparin binds to multiple proteins throughout the body, suggesting a large range of potential therapeutic applications. Although its function has been characterized in multiple physiological contexts, heparin’s solution conformational dynamics and structure–function relationships are not fully understood. Molecular dynamics (MD) simulations facilitate the analysis of a molecule’s underlying conformational ensemble, which then provides important information necessary for understanding structure–function relationships. However, for MD simulations to afford meaningful results, they must both provide adequate sampling and accurately represent the energy properties of a molecule. The aim of this study is to compare heparin’s conformational ensemble using two well-developed force fields for carbohydrates, known as GLYCAM06 and CHARMM36, using replica exchange molecular dynamics (REMD) simulations, and to validate these results with NMR experiments. In this work, the anticoagulant sequence, an ultra-low-molecular-weight heparin, known as Arixtra (fondaparinux, sodium), was simulated with both parameter sets. The results suggest that GLYCAM06 matches experimental nuclear magnetic resonance three-bond J-coupling values measured for Arixtra better than CHARMM36. In addition, NOESY and ROESY experiments suggest that Arixtra is very flexible in the sub-millisecond time scale and does not adopt a unique structure at 25 C. Moreover, GLYCAM06 affords a much more dynamic conformational ensemble for Arixtra than CHARMM36.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

DOE OSTI2025

Using Machine Learning to Generate a GISS ModelE Calibrated Physics Ensemble (CPE)

A neural network (NN) surrogate of the NASA GISS ModelE atmosphere (version E3) is trained on a perturbed parameter ensemble (PPE) spanning 45 physics parameters and 36 outputs. The NN is leveraged in a Markov Chain Monte Carlo (MCMC) Bayesian parameter inference framework to generate a second posterior constrained ensemble coined a “calibrated physics ensemble,” or CPE. The CPE members are characterized by diverse parameter combinations and are, by definition, close to top-of-atmosphere radiative balance, and must broadly agree with numerous hydrologic, energy cycle and radiative forcing metrics simultaneously. Global observations of numerous cloud, environment, and radiation properties (provided by global satellite products) are crucial for CPE generation. The inference framework explicitly accounts for discrepancies (or biases) in satellite products during CPE generation. We demonstrate that product discrepancies strongly impact calibration of important model parameter settings (e.g., convective plume entrainment rates; fall speed for cloud ice). Structural improvements new to E3 are retained across CPE members (e.g., stratocumulus simulation). Notably, the framework improved the simulation of shallow cumulus and Amazon rainfall while not degrading radiation fields, an upgrade that neither default parameters nor Latin Hypercube parameter searching achieved. Analyses of the initial PPE suggested several parameters were unimportant for output variation. However, many “unimportant” parameters were needed for CPE generation, a result that brings to the forefront how parameter importance should be determined in PPEs. From the CPE, two diverse 45-dimensional parameter configurations are retained to generate radiatively-balanced, auto-tuned atmospheres that were used in two E3 submissions to CMIP6.

54 ENVIRONMENTAL SCIENCES↗

DOE OSTI2025

“Which Projections Do I Use?” Strategies for Climate Model Ensemble Subset Selection Based on Regional Stakeholder Needs

Climate model (or earth system model) projections are increasingly used for climate adaptation planning and impact assessments. As part of this process, many end‐users evaluate a subset of downscaled climate projections without being aware of the implications of downscaling methodology for statistics or event outcomes. Approaches for determining a subset of global climate models to use often focus on values from the raw models, rather than from their downscaled counterparts, in other words assuming that the statistical distribution of the multi‐model ensemble does not change post downscaling. This study demonstrates that a downscaled ensemble will typically retain the change distribution as a raw ensemble, but individual models can differ dramatically post‐downscaling. We recommend that subset‐selection methods account for this possibility and that decision‐relevant downscaled climate projections provide proper descriptions of fitness‐for‐purpose and essential caveats, so that non‐specialists can interpret the results with an appropriate level of confidence.

54 ENVIRONMENTAL SCIENCES↗