Search NASA⌕ Search

SEARCH · Search NASA

Results for “deep generative models”

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 1,027 records · Page 57

A THREE-DIMENSIONAL BABCOCK-LEIGHTON SOLAR DYNAMO MODEL

We present a three-dimensional (3D) kinematic solar dynamo model in which poloidal field is generated by the emergence and dispersal of tilted sunspot pairs (more generally bipolar magnetic regions, or BMRs). The axisymmetric component of this model functions similarly to previous 2.5 dimensional (2.5D, axisymmetric) Babcock-Leighton (BL) dynamo models that employ a double-ring prescription for poloidal field generation but we generalize this prescription into a 3D flux emergence algorithm that places BMRs on the surface in response to the dynamo-generated toroidal field. In this way, the model can be regarded as a unification of BL dynamo models (2.5D in radius/latitude) and surface flux transport models (2.5D in latitude/longitude) into a more self-consistent framework that builds on the successes of each while capturing the full 3D structure of the evolving magnetic field. The model reproduces some basic features of the solar cycle including an 11 yr periodicity, equatorward migration of toroidal flux in the deep convection zone, and poleward propagation of poloidal flux at the surface. The poleward-propagating surface flux originates as trailing flux in BMRs, migrates poleward in multiple non-axisymmetric streams (made axisymmetric by differential rotation and turbulent diffusion), and eventually reverses the polar field, thus sustaining the dynamo. In this Letter we briefly describe the model, initial results, and future plans.

79 ASTRONOMY AND ASTROPHYSICS↗

Enhancing Electron Microscopy Image Classification Using Data Augmentation

Manual labeling for machine learning tasks such as image classification is tedious and labor-intensive; as a result, scientific datasets suitable for deep learning applications are scarce and limited. While data augmentation techniques have shown promise for extending image datasets, very little work has been done to understand the impact of combining multiple augmentation methods sequentially or the limits of their effectiveness when combined. Our work addresses this gap by examining how standard and combinatorial data augmentation affects the performance of machine learning models when trained on small datasets for label classification tasks. For our analysis, we generate single, double and quadruple-augmented datasets for a microscopy image classification task using six standard augmentation methods, and compare the resultant improvements observed in binary classification accuracy with three standard image classification models (DenseNet169, MobileNetV2, ResNet101V2). Our experiments show a non-monotonic relationship between the number of simultaneous augmentation methods and classification accuracy, indicating that there is a trade-off between the degree of augmentation and the model performance. These findings suggest that the optimal number of augmentation methods will vary by domain and use case. We also find that the order in which augmentation methods are applied to a limited dataset matters when combining augmentation schemes, with our use case showing performance differences up to 2.6% when the augmentation order is reversed for double-augmented datasets. Our work offers insights to the limits of data augmentation when working on image classification tasks with limited datasets.

Welsman, Jordan A↗

Exascale Co-design for Modeling Materials in Extreme Environments

Computational materials science has provided great insight into the response of materials under extreme conditions that are difficult to probe experimentally. For example, shock-induced plasticity and phase transformation processes in single-crystal and nanocrystalline metals have been widely studied via large-scale molecular dynamics simulations, and many of these predictions are beginning to be tested at advanced 4th generation light sources such as the Advanced Photon Source (APS) and Linac Coherent Light Source (LCLS). I will describe our simulation predictions and their recent verification at LCLS, outstanding challenges in modeling the response of materials to extreme mechanical and radiation environments, and our efforts to tackle these as part of the multi-institutional, multi-disciplinary Exascale Co-design Center for Materials in Extreme Environments (ExMatEx). ExMatEx has initiated an early and deep collaboration between domain (computational materials) scientists, applied mathematicians, computer scientists, and hardware architects, in order to establish the relationships between algorithms, software stacks, and architectures needed to enable exascale-ready materials science application codes within the next decade. We anticipate that we will be able to exploit hierarchical, heterogeneous architectures to achieve more realistic large-scale simulations with adaptive physics refinement, and are using tractable application scale-bridging proxy application testbeds to assess new approaches and requirements. Such current scale-bridging strategies accumulate (or recompute) a distributed response database from fine-scale calculations, in a top-down rather than bottom-up multiscale approach.

36 MATERIALS SCIENCE↗

Assessing the response of methane hydrates to environmental change at the Svalbard continental margin

This project reflects the results of cooperative research efforts between the US Department of Energy and scientists from Norway and Germany, who collaboratively designed the study, collected and analyzed samples from the water column and sediment and arrive at conclusions presented in joint publications. The main goal of the project was to assess the role of gas hydrate deposits in modulating methane discharge revealed through water column data, and assess the changes in environmental parameters, geochemical and microbiological conditions that drive the methane release in this high latitude region. Samples and data were collected from seven expeditions that encompassed extensive water column surveys, gravity coring, remotely-operated towed instrumentation and seafloor drilling campaigns. Geochemical and microbiological results were interpreted in the context of correlative geophysical data and numerical models, to generate a comprehensive and interdisciplinary view of the processes operating along the Svalbard margin. Incubation experiments complement the filed observations and provide additional data on the microbiological response to methane change. Collectively our results show that methane seepage in this margin is a component of a large methane plume, the Svalbard plume, which is not associated with gas hydrate processes. Consistently, numerical models of data from shallow (gravity cores offshore Storfjordrenna, bearing gas hydrate) and deep (MeBo drilling offshore Prins Karls Foreland) sediment samples show that methane and gas hydrate dynamics at sites that lie within the upper edge of gas hydrate stability are not responding to modern changes in bottom water temperature. Rather the data point to a long history of methane release, dominantly controlled by large scale Earth system changes (e.g., geology, oceanography, and glaciology) with gas hydrate as a temporary methane reservoir. Further results document the episodicity of the methane release, the role of microbes in sequestering methane carbon into authigenic carbonate, reaction networks involved in carbon recycling pathways at the sulfate-methane transition, and response of microbial communities to changes in methane flux allowing for a richer understanding of microbial ecology in response to change at methane seep sites.

58 GEOSCIENCES↗

The SAND detector for the DUNE experiment

The Deep Underground Neutrino Experiment (DUNE) is a next-generation project aiming to study several neutrino properties. It will feature two experimental setups: a near detector that will be installed at Fermilab, in proximity of the neutrino-production point, and a far detector at a distance of 1300 km and 1500 m underground, at the SURF laboratory. The DUNE design and configuration will allow the study of neutrino oscillation, astrophysical neutrinos, and beyond standard model physics. The near detector complex foresees three detectors to be installed. Among these, the System for on-Axis Neutrino Detection (SAND) will serve as on-axis beam monitor, reduce the systematic uncertainties for the oscillation analysis, and search for physics beyond the standard model. SAND will be composed of three sub-detectors, surrounded by a 0.6 T superconducting magnet. The outermost detector will be a lead/scintillating-fiber electromagnetic calorimeter while the inner volume will include a 1-ton liquid argon active target placed upstream followed by a target tracker system. The SAND detector and its goals will be shown in this poster.

Alemanno, Francesca [Salento U.; INFN, Lecce]↗

Predicting the Effect of Single and Multiple Mutations on Protein Structural Stability

Predicting how a point mutation alters a protein’s stability can guide pharmaceutical drug design initiatives which aim to counter the effects of serious diseases. Conducting mutagenesis studies in physical proteins can give insights about the effects of amino acid substitutions, but such wet-lab work is prohibitive due to the time as well as financial resources needed to assess the effect of even a single amino acid substitution. Computational methods for predicting the effects of a mutation on a protein structure can complement wet-lab work, and varying approaches are available with promising accuracy rates. In this work we compare and assess the utility of several machine learning methods and their ability to predict the effects of single and double mutations. We in silico generate mutant protein structures, and compute several rigidity metrics for each of them. We use these as features for our Support Vector Regression (SVR), Random Forest (RF), and Deep Neural Network (DNN) methods. We validate the predictions of our in silico mutations against experimental ΔΔG stability data, and attain Pearson Correlation values upwards of 0.71 for single mutations, and 0.81 for double mutations. We perform ablation studies to assess which features contribute most to a model’s success, and also introduce a voting scheme to synthesize a single prediction from the individual predictions of the three models.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

DIGS: deep inference of galaxy spectra with neural posterior estimation

Abstract With the advent of billion-galaxy surveys with complex data, the need of the hour is to efficiently model galaxy spectral energy distributions (SEDs) with robust uncertainty quantification. The combination of simulation-based inference (SBI) and amortized neural posterior estimation (NPE) has been successfully used to analyse simulated and real galaxy photometry both precisely and efficiently. In this work, we utilise this combination and build on existing literature to analyse simulated noisy galaxy spectra. Here, we demonstrate a proof-of-concept study of spectra that is (a) an efficient analysis of galaxy SEDs and inference of galaxy parameters with physically interpretable uncertainties; and (b) amortized calculations of posterior distributions of said galaxy parameters at the modest cost of a few galaxy fits with Markov chain Monte Carlo (MCMC) methods. We utilise the SED generator and inference framework Prospector to generate simulated spectra, and train a dataset of 2 × 10 6 spectra (corresponding to a five-parameter SED model) with NPE. We show that SBI—with its combination of fast and amortized posterior estimations—is capable of inferring accurate galaxy stellar masses and metallicities. Our uncertainty constraints are comparable to or moderately weaker than traditional inverse-modelling with Bayesian MCMC methods (e.g. 0.17 and 0.26 dex in stellar mass and metallicity for a given galaxy, respectively). We also find that our inference framework conducts rapid SED inference (0.9–1.2 × 10 5 galaxy spectra via SBI/NPE at the cost of 1 MCMC-based fit). With this work, we set the stage for further work that focuses of SED fitting of galaxy spectra with SBI, in the era of JWST galaxy survey programs and the wide-field Roman Space Telescope spectroscopic surveys.

spectroscopy↗

Making Invisible Visible: Data-Driven Seismic Inversion With Spatio-Temporally Constrained Data Augmentation

Deep learning and data-driven approaches have shown great potential in scientific domains. The promise of data-driven techniques relies on the availability of a large volume of high-quality training datasets. Due to the high cost of obtaining data through expensive physical experiments, instruments, and simulations, data augmentation techniques for scientific applications have emerged as a new direction for obtaining scientific data recently. However, existing data augmentation techniques originating from computer vision yield physically unacceptable data samples that are not helpful for the domain problems that we are interested in. In this article, we develop new data augmentation techniques based on convolutional neural networks. Specifically, our generative models leverage different physics knowledge (such as governing equations, observable perception, and physics phenomena) to improve the quality of the synthetic data. To validate the effectiveness of our data augmentation techniques, we apply them to solve a subsurface seismic full-waveform inversion using simulated CO 2 leakage data. Our interest is to invert for subsurface velocity models associated with very small CO 2 leakage. We validate the performance of our methods using comprehensive numerical tests. Here via comparison and analysis, we show that data-driven seismic imaging can be significantly enhanced by using our data augmentation techniques. Particularly, the imaging quality has been improved by 15% in test scenarios of general-sized leakage and 17% in small-sized leakage when using an augmented training set obtained with our techniques.

58 GEOSCIENCES↗

DeepSZ: identification of Sunyaev–Zel’dovich galaxy clusters using deep learning

Galaxy clusters identified via the Sunyaev–Zel’dovich (SZ) effect are a key ingredient in multiwavelength cluster cosmology. In this paper, we present and compare three methods of cluster identification: the standard matched filter (MF) method in SZ cluster finding, a convolutional neural networks (CNN), and a ‘combined’ identifier. We apply the methods to simulated millimeter maps for several observing frequencies for a survey similar to SPT-3G, the third-generation camera for the South Pole Telescope. The MF requires image pre-processing to remove point sources and a model for the noise, while the CNN requires very little pre-processing of images. Additionally, the CNN requires tuning of hyperparameters in the model and takes cut-out images of the sky as input, identifying the cut-out as cluster-containing or not. We compare differences in purity and completeness. The MF signal-to-noise ratio depends on both mass and redshift. Our CNN, trained for a given mass threshold, captures a different set of clusters than the MF, some with signal-to-noise-ratio below the MF detection threshold. However, the CNN tends to mis-classify cut-out whose clusters are located near the edge of the cut-out, which can be mitigated with staggered cut-out. We leverage the complementarity of the two methods, combining the scores from each method for identification. The purity and completeness are both 0.61 for MF, and 0.59 and 0.61 for CNN. The combined method yields 0.60 and 0.77, a significant increase for completeness with a modest decrease in purity. We advocate for combined methods that increase the confidence of many low signal-to-noise clusters.

79 ASTRONOMY AND ASTROPHYSICS↗

Scalable Risk Assessment of Rare Events in Power Systems With Uncertain Wind Generation and Loads

Risk assessment of rare events has become increasingly important in power system planning and operation with the increasing integration of renewable energy and the presence of system uncertainties. However, quantifying the risk posed by rare events via the traditional method, i.e., Monte Carlo sampling (MCS), incurs substantial computational expense stemming from the vast ensemble of power flow simulations. To accelerate the assessment, this paper proposes a Deep Neural Network (DNN)-kernelized vector-valued Gaussian Process (VVGP) approach with excellent computational efficiency while maintaining high accuracy. Consequently, serving as a surrogate model for the power flow solver, the DNN-kernelized VVGP enables significantly faster but accurate risk assessment compared to the power flow solver. The developed surrogate model evaluates low-order N - k events that contain more than 90% instances by adeptly capturing the topological features while the high-order N - k events are assessed via a power flow solver, thereby striking a balance between computational efficiency and uncertainty quantification accuracy. Moreover, the model incorporates a Support Vector Machine (SVM) classifier to resample concerning low-probability tail events to counteract the biases potentially introduced during the DNN-kernelized VVGP evaluations. Simulations conducted on the modified IEEE 24-bus, 118-bus, and European 1354-bus systems demonstrate that the proposed method maintains the accuracy benchmark set by MCS while significantly reducing computational demands in large-scale power systems as compared to other state-of-the-art methods.

17 WIND ENERGY↗

Geometry-complete diffusion for 3D molecule generation and optimization

Abstract Generative deep learning methods have recently been proposed for generating 3D molecules using equivariant graph neural networks (GNNs) within a denoising diffusion framework. However, such methods are unable to learn important geometric properties of 3D molecules, as they adopt molecule-agnostic and non-geometric GNNs as their 3D graph denoising networks, which notably hinders their ability to generate valid large 3D molecules. In this work, we address these gaps by introducing the Geometry-Complete Diffusion Model (GCDM) for 3D molecule generation, which outperforms existing 3D molecular diffusion models by significant margins across conditional and unconditional settings for the QM9 dataset and the larger GEOM-Drugs dataset, respectively. Importantly, we demonstrate that GCDM’s generative denoising process enables the model to generate a significant proportion of valid and energetically-stable large molecules at the scale of GEOM-Drugs, whereas previous methods fail to do so with the features they learn. Additionally, we show that extensions of GCDM can not only effectively design 3D molecules for specific protein pockets but can be repurposed to consistently optimize the geometry and chemical composition of existing 3D molecules for molecular stability and property specificity, demonstrating new versatility of molecular diffusion models. Code and data are freely available on GitHub .

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

The effective field theory of K-mouflage

We describe K-mouflage models of modified gravity using the effective field theory of dark energy. We show how the Lagrangian density K defining the K-mouflage models appears in the effective field theory framework, at both the exact fully nonlinear level and at the quadratic order of the effective action. We find that K-mouflage scenarios only generate the operator (δg{sup 00}{sub (u)}){sup n} at each order n. We also reverse engineer K-mouflage models by reconstructing the whole effective field theory, and the full cosmological behaviour, from two functions of the Jordan-frame scale factor in a tomographic manner. This parameterisation is directly related to the implementation of the K-mouflage screening mechanism: screening occurs when K' is large in a dense environment such as the deep matter and radiation eras. In this way, K-mouflage can be easily implemented as a calculable subclass of models described by the effective field theory of dark energy which could be probed by future surveys.

79 ASTRONOMY AND ASTROPHYSICS↗

CryoTEN: efficiently enhancing cryo-EM density maps using transformers

Abstract Motivation Cryogenic electron microscopy (cryo-EM) is a core experimental technique used to determine the structure of macromolecules such as proteins. However, the effectiveness of cryo-EM is often hindered by the noise and missing density values in cryo-EM density maps caused by experimental conditions such as low contrast and conformational heterogeneity. Although various global and local map-sharpening techniques are widely employed to improve cryo-EM density maps, it is still challenging to efficiently improve their quality for building better protein structures from them. Results In this study, we introduce CryoTEN—a 3D UNETR++ style transformer to improve cryo-EM maps effectively. CryoTEN is trained using a diverse set of 1295 cryo-EM maps as inputs and their corresponding simulated maps generated from known protein structures as targets. An independent test set containing 150 maps is used to evaluate CryoTEN, and the results demonstrate that it can robustly enhance the quality of cryo-EM density maps. In addition, automatic de novo protein structure modeling shows that protein structures built from the density maps processed by CryoTEN have substantially better quality than those built from the original maps. Compared to the existing state-of-the-art deep learning methods for enhancing cryo-EM density maps, CryoTEN ranks second in improving the quality of density maps, while running >10 times faster and requiring much less GPU memory than them. Availability and implementation The source code and data are freely available at https://github.com/jianlin-cheng/cryoten.

Biochemistry & Molecular Biology↗

Measurements of sound radiation from cavities at subsonic speeds

To better understand the physical mechanisms responsible for noise generated by flow over cavities with a range of dimensions common to commercial aircraft, a series of measurements of farfield sound pressure level, fluctuating surface pressure, and drag coefficient was made. An examination of the resultant data shows that two theoretical models are needed for this range of dimensions. The shallow cavity (width-to-depth ratio larger than 1.0) can be approximated by a dipole located near the downstream edge of the cavity and the deep cavity (ratio less than 1.0) can be approximated by a dipole located near the downstream edge with the superimposed effects of the upstream edge of the cavity.

Yu, Y. H.↗

Passive seismic experiment - A summary of current status

The data set obtained from the four-station Apollo seismic network including signals from approximately 11,800 events, is surveyed. Some refinement of the lunar model will result, but its gross features remain the same. Attention is given to the question of a small, molten lunar core, the answer to which remains dependent on analysis of signals from a far side impact. Seventy three sources of repeating, deep moonquakes have been identified, thirty nine of which have been accurately located. Concentrated at depths from 800 to 1000 km, the periodicities of these events have led to the hypothesis that they are generated by tidal stresses. Lunar seismic data has also indicated that the meteoroid population is ten times lower than originally determined from earth based observations. Lunar seismic activity is much lower and mountainous masses show no sign of sinking, in contrast to earth, as a result of the lunar crust being four times thicker. While much work remains to be done, significant correlation between terrestrial and lunar observations can be seen.

Latham, G. V.↗

Application of Dimensionality Reduction in Machine Learning Modeling of CO2 Storage

In this study, we developed deep learning models that are capable of predicting spatio-temporal outputs of CO2 saturation, pressure, and brine production in a 3D saline storage reservoir over 30 years of continuous CO2 injection and a 50-year post-injection timeframe. To improve computational efficiency and maintain performance accuracy, the model framework involves ensembling multi-layer autoencoder networks that provide dimensionality reduction of geologic inputs with fully connected long short-term memory (LSTM) neural networks that generate time-series prediction. This study was presented as poster at the 2022 Carbon Management Project Review Meeting held in Pittsburgh, PA (August 15 – 19, 2022).

Bello, Kolawole↗

Catalyzing deep decarbonization with federated battery diagnosis and prognosis for better data management in energy storage systems

Industrial data analytics methods play a central role in improving energy storage performance and efficiency, impacting the future of electrified transportation and renewable electricity generation. However, significant challenges hinder the large-scale deployment of batteries. Conventional methods rely on centralized collection and processing of fleet-level data, leading to database size issues and privacy concerns due to potential data breaches. To enable scalable deployment of battery management systems, this article proposes a federated battery diagnosis and prognosis model, which distributes the processing of battery standard current-voltage-time-usage data in a privacy-preserving manner. Instead of transferring the raw data, this approach communicates only the locally processed parameters, thus reducing communication load and preserving data confidentiality. The federated model offers a paradigm shift in battery health management through privacy-preserving distributed methods for battery data processing and lifetime prediction, ensuring the reliable and sustainable deployment of lithium-ion batteries in a rapidly evolving world.

asset health management↗

Identifying Robust Decarbonization Pathways for the Western U.S. Electric Power System Under Deep Climate Uncertainty

Climate change threatens the resource adequacy of future power systems. Existing research and practice lack frameworks for identifying decarbonization pathways that are robust to climate-related uncertainty. We create such an analytical framework, then use it to assess the robustness of alternative pathways to achieving 60% emissions reductions from 2022 levels by 2040 for the Western U.S. power system. Our framework integrates power system planning and resource adequacy models with 100 climate realizations from a large climate ensemble. Climate realizations drive electricity demand; thermal plant availability; and wind, solar, and hydropower generation. Among five initial decarbonization pathways, all exhibit modest to significant resource adequacy failures under climate realizations in 2040, but certain pathways experience significantly less resource adequacy failures at little additional cost relative to other pathways. By identifying and planning for an extreme climate realization that drives the largest resource adequacy failures across our pathways, we produce a new decarbonization pathway that has no resource adequacy failures under any climate realizations. This new pathway is roughly 5% more expensive than other pathways due to greater capacity investment, and shifts investment from wind to solar and natural gas generators. Our analysis suggests modest increases in investment costs can add significant robustness against climate change in decarbonizing power systems. Our framework can help power system planners adapt to climate change by stress testing future plans to potential climate realizations, and offers a unique bridge between energy system and climate modeling.

29 ENERGY PLANNING, POLICY, AND ECONOMY↗