Search NASA⌕ Search

SEARCH · Search NASA

Results for “Deep generative model”

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 739 records · Page 41

Understanding neutrinos with accelerator beams and liquid argon time-projection chambers: ICARUS and DUNE

A global program of experiments has worked towards characterizing neutrino oscillation over the past few decades. However, important parameters remain to be measured, and mysteries remain to be elucidated. Current and upcoming experiments are targeting the open questions and probing the consistency of the neutrino oscillation paradigm. Likewise, the liquid argon (LAr) time-projection chamber (TPC) has emerged as a sensitive particle detection technology for neutrino experiments. A current generation of LAr TPC detectors are being used to study neutrinos while also gaining important experience in operating and analyzing with this technology. SBND, MicroBooNE, and ICARUS have collected or are collecting data from beams at Fermilab (near Chicago) to explore the possibility of a sterile neutrino and/or other beyond Standard Model (BSM) physics. SBND and ICARUS will be used to conduct a two-detector analysis as part of the Short Baseline Neutrino (SBN) Program. Additionally, these detectors are enabling important neutrino interaction studies necessary to prepare for the next generation of oscillation experiments. One such oscillation experiment that will come online over the next years is the Deep Underground Neutrino Experiment (DUNE), which will install multiple 10 kiloton LAr TPCs underground in South Dakota (south of Saskatchewan) to conduct oscillation measurements with neutrinos originating in a beamline at Fermilab. A detector complex will be installed at Fermilab as well, to study the beam before the expected flavour oscillations. This “near detector” will also employ a LAr TPC, with a segmented and pixel-based design, as well as other technologies to constrain uncertainties in the oscillation measurement by characterizing the beam and neutrino interactions. This talk will discuss the ICARUS and DUNE experiments, the LAr TPC detector technology, and the efforts to realize and leverage these experiments to better understand the properties of neutrinos.

Howard, Bruce L. [Fermilab]↗

Towards Neutron Transformation Searches

To probe the origins of the baryon asymmetry, baryon number violation, the last unconfirmed Sakharov condition, must be definitively observed experimentally. Similarly, the nature of dark matter is currently unknown, and calls out for new candidates to be investigated. Each of these issues can be considered through the study of neutron transformations.Some rare baryon number violating processes, such as neutron-antineutron transformations, are expected to probe baryogenesis. Here, I show progress on this discovery target through construction of more accurate Monte Carlo models, the design of future detectors, creation of more complete atmospheric neutrino background simulations, and use of automated analysis techniques within the the NNBAR/HIBEAM experimental program at the European Spallation Source (ESS) and the Deep Underground Neutrino Experiment (DUNE). First simulation-based sensitivities for these experiments will be discussed. Modeling of rare neutron-antineutron transformation and subsequent annihilation will be discussed at length for multiple nuclei useful to these and other collaborations. To go along with this work, more comprehensive lepton-scattering nuclear models must be integrated into neutrino event generators for proper atmospheric neutrino background simulations. I discuss the first furnishing of these backgrounds for DUNE, and I highlight a potential path forward for the community in this vein using precisionmore » electron scattering modeling as a facsimile.Aspects of other potentially related neutron – mirror-neutron oscillations pertinent to dark matter and the neutron lifetime anomaly will also be considered for the ESS HIBEAM experiment. Here, I will present the first experimental sensitivity calculations for a broad range of modular experimental setups which will serve as research and design stepping stones toward NNBAR while producing a multitude of physics results over short time scales.« less

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

University of Illinois Campus Deep Direct-Use Feasibility Study - Long-Term Meteorological Data

This submission includes meteorological data recorded by National Weather Service at University of Illinois Willard Airport, Savoy IL for period 1972 to 2018. This data is for use in parameterizing the demand and life-cycle assessments associated with the project, and provides information about energy loads for the buildings being included in the DDU applications. This includes how energy demand fluctuates with seasonal changes in climate, which is used to model expected demand for the DDU system. *Note: All times are reported in local standard time. NC: Wind Chill/Heat Index do not meet the required thresholds to be calculated. cli-MATE: MRCC Application Tools Environment Generated at: 2/7/2018 8:52:33 AM CST m = missing data Date = year-month-day Time = 24 hour clock Temp_F = temperature (deg. fahrenheit) RH_pct = relative humidity (percent) Dewpt_F = dew point (deg. fahrenheit) WindSpeed_mph = wind speed (miles/hour) WindDir_deg = wind direction (deg. from north) PeakWindGust_mph = peak wind gust (miles/hour) Visibility_mi = visibility (miles) AtmPress_hPa = atmospheric pressure (hectopascals) Precip_in = precipitation (inches)

15 GEOTHERMAL ENERGY↗

Synthetic galaxy clusters and observations based on Dark Energy Survey Year 3 Data

ABSTRACT We develop a novel data-driven method for generating synthetic optical observations of galaxy clusters. In cluster weak lensing, the interplay between analysis choices and systematic effects related to source galaxy selection, shape measurement, and photometric redshift estimation can be best characterized in end-to-end tests going from mock observations to recovered cluster masses. To create such test scenarios, we measure and model the photometric properties of galaxy clusters and their sky environments from the Dark Energy Survey Year 3 (DES Y3) data in two bins of cluster richness $\lambda \in [30; 45)$, $\lambda \in [45; 60)$ and three bins in cluster redshift ($z\in [0.3; 0.35)$, $z\in [0.45; 0.5)$ and $z\in [0.6; 0.65)$. Using deep-field imaging data, we extrapolate galaxy populations beyond the limiting magnitude of DES Y3 and calculate the properties of cluster member galaxies via statistical background subtraction. We construct mock galaxy clusters as random draws from a distribution function, and render mock clusters and line-of-sight catalogues into synthetic images in the same format as actual survey observations. Synthetic galaxy clusters are generated from real observational data, and thus are independent from the assumptions inherent to cosmological simulations. The recipe can be straightforwardly modified to incorporate extra information, and correct for survey incompleteness. New realizations of synthetic clusters can be created at minimal cost, which will allow future analyses to generate the large number of images needed to characterize systematic uncertainties in cluster mass measurements.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

AI-Driven Crack Detection for Remanufacturing Cylinder Heads Using Deep Learning and Engineering-Informed Data Augmentation

Detecting cracks in cylinder heads traditionally relies on manual inspection, which is time-consuming and susceptible to human error. As an alternative, automated object detection utilizing computer vision and machine learning models has been explored. However, these methods often face challenges due to a lack of sufficiently annotated training data, limited image diversity, and the inherently small size of cracks. Addressing these constraints, this paper introduces a novel automated crack-detection method that enhances data availability through a synthetic data generation technique. Unlike general data augmentation practices, our method involves copying cracks from one location to another, guided by both random and informed engineering decisions about likely crack formations due to cyclic thermomechanical loads. The innovative aspect of our approach lies in the integration of domain-specific engineering knowledge into the synthetic generation process, which substantially improves detection accuracy. We evaluate our method’s effectiveness using two metrics: the F2 score, which emphasizes recall to prioritize detecting all potential cracks, and mean average precision (MAP), a standard measure in object detection. Experimental results demonstrate that, without engineering insights, our method increases the F2 score from 0.40 to 0.65, while maintaining a stable MAP. Incorporating detailed engineering knowledge further enhances the F2 score to 0.70 and improves MAP to 0.57, representing increases of 63% and 43%, respectively. These results confirm that our approach not only mitigates the limitations of traditional data augmentation but also significantly advances the reliability and precision of crack detection in industrial settings.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗

Hybrid geological modeling: Combining machine learning and multiple-point statistics

Accurately modeling and constructing a geologically realistic subsurface model remains an outstanding problem as the morphology controls the flow behaviors. Particularly, one of the pattern-based methods, namely cross-correlation based simulation, has been proved to be an effective way to reconstruct a realistic model, at both small and large scales. However, conditioning to point data in the large-scale problems is still a crucial issue in these algorithms, since there is always a trade-off between the quality of the realizations and the degree of point data reproduction. Specifically, it is not practical to build a training image (TI) which includes all the possibilities and variabilities. Therefore, finding a pattern that can represent the point data and, at the same time, preserving the connectivities is difficult. This leads to producing highly-connected realizations with a significant mismatch or poor models with a reasonable degree of point data reproduction. To accurately reproduce the densely distributed hard data, pixel-based methods can also produce some unrealistic artifacts around the hard data. In this paper, to overcome this challenge, however, we use pattern-based methods as they often produce more disconnected geobodies when dealing with dense hard data, and proposed a hybrid algorithm using the pattern-based methods and convolutional neural network (CNN). The trained CNN model is utilized to improve the quality of conditioning to point data for the original realizations generated by the pattern-based algorithm. As such, the mismatch locations are identified, and the same regions are used in the training of CNN to mimic the procedure through which a missing region can be filled. To evaluate the performance of the proposed hybrid algorithm, it is tested on cases with different dimensions and different numbers of facies. Then, the newly improved realizations are compared with the initial realizations generated by the pattern-based algorithm. The comparison is also conducted by the flow simulation test. And it indicates that the proposed hybrid algorithm can better reproduce the point data, while the connectivities are better preserved.

58 GEOSCIENCES↗

Deep Learning for Multigroup Cross-Section Representation in Two-Step Core Calculations

Here we investigate using deep learning, a type of machine-learning algorithm employing multiple layers of artificial neurons, for the mathematical representation of multigroup cross sections for use in the Griffin reactor multiphysics code for two-step deterministic neutronics calculations. A three-dimensional fuel element typical of a high-temperature gas reactor as well as a two-dimensional sodium-cooled fast reactor lattice are modeled using the Serpent Monte Carlo code, and multigroup macroscopic cross sections are generated for various state parameters to produce a training data set and a separate validation data set. A fully connected, feedforward neural network is trained using the open-source PyTorch machine-learning framework, and its accuracy is compared against the standard piecewise linear interpolation model. Additionally, we provide in this work a generic technique for propagating the cross-section model errors up to the k eff using sensitivity coefficients with the first-order uncertainty propagation rule. Quantifying the eigenvalue error due to the cross-section regression errors is especially practical for appropriately selecting the mathematical representation of the cross sections. We demonstrate that the artificial neural network model produces lower errors and therefore enables better accuracy relative to the piecewise linear model when the cross sections exhibit nonlinear dependencies; especially when a coarse grid is employed, where the errors can be halved by the artificial neural network. However, for linearly dependent multigroup cross sections as found for the sodium-cooled fast reactor case, a simpler linear regression outperforms deeper networks.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗

Calibrating Bayesian generative machine learning for Bayesiamplification

Recently, combinations of generative and Bayesian deep learning have been introduced in particle physics for both fast detector simulation and inference tasks. These neural networks aim to quantify the uncertainty on the generated distribution originating from limited training statistics. The interpretation of a distribution-wide uncertainty however remains ill-defined. We show a clear scheme for quantifying the calibration of Bayesian generative machine learning models. For a Continuous Normalizing Flow applied to a low-dimensional toy example, we evaluate the calibration of Bayesian uncertainties from either a mean-field Gaussian weight posterior, or Monte Carlo sampling network weights, to gauge their behaviour on unsteady distribution edges. Well calibrated uncertainties can then be used to roughly estimate the number of uncorrelated truth samples that are equivalent to the generated sample and clearly indicate data amplification for smooth features of the distribution.

97 MATHEMATICS AND COMPUTING↗

Improved Madden–Julian Oscillations with Improved Physics: The Impact of Modified Convection Parameterizations

Two modifications are made to the deep convection parameterization in the NCAR Community Climate System Model, version 3 (CCSM3): a dilute plume approximation and an implementation of the convective momentum transport (CMT). These changes lead to significant improvement in the simulated Madden–Julian oscillations (MJOs). With the dilute plume approximation, temperature and convective heating perturbations become more positively correlated. Consequently, more available potential energy is generated and the intraseasonal variability (ISV) becomes stronger. The organization of ISV is also improved, which is manifest in coherent structures between different MJO phases and an improved simulation of the eastward propagation of MJOs with a reasonable eastward speed. The improved propagation can be attributed to a better simulation of the low-level zonal winds due to the inclusion of CMT. The authors posit that the large-scale zonal winds are akin to a selective conveyor belt that facilitates the organization of ISVs into highly coherent structures, which are important features of observed MJOs. The conclusions are supported by two supplementary experiments, which include the dilute plume approximation and CMT separately.

54 ENVIRONMENTAL SCIENCES↗

Unsupervised Deep Learning Can Identify Physical Parameters

Parametrizing a problem is one of the biggest obstacles toward the application of physical methods to novel systems. In this research, we show that deep learning methods can be used to accelerate this parametrization process. We use an unsupervised learning algorithm, a variational autoencoder, to extract meaningful physical parameters from unlabeled time-series generated from classical physical systems. For example, given time series data of projectile motion and the instruction to represent the data in a small number of unspecified parameters, the model can discover, without further direction, the concepts of velocity and gravity. Using this method, one can uncover information about the physics of a system, even when the relevant physical parameters are unknown to the experimenter. This has obvious applications to novel systems in which parameters are not known a priori. Moreover, errors in the reconstruction of the parameters can be used to reveal meaningful info rmation about state transitions, which can be conceptualized as a generalization of similar unsupervised learning methods used to detect phase transitions in the thermodynamics of particle systems to systems that evolve in the time domain. While our proof-of-concept applications are modest, this method shows potential for making progress in a wide array of problems both in physics and outside of the field.

Veillette, John↗

An Evaluation of the Large-Scale Implementation of Ocean Thermal Energy Conversion (OTEC) Using an Ocean General Circulation Model with Low-Complexity Atmospheric Feedback Effects

Previous investigations of the large-scale deployment of Ocean Thermal Energy Conversions (OTEC) systems are extended by allowing some atmospheric feedback in an ocean general circulation model. A modified ocean-atmosphere thermal boundary condition is used where relaxation corresponds to atmospheric longwave radiation to space, and an additional term expresses horizontal atmospheric transport. This produces lower steady-state OTEC power maxima (8 to 10.2 TW instead of 14.1 TW for global OTEC scenarios, and 7.2 to 9.3 TW instead of 11.9 TW for OTEC implementation within 100 km of coastlines). When power production peaks, power intensity remains practically unchanged, at 0.2 TW per Sverdrup of OTEC deep cold seawater, suggesting a similar degradation of the OTEC thermal resource. Large-scale environmental effects include surface cooling in low latitudes and warming elsewhere, with a net heat intake within the water column. These changes develop rapidly from the propagation of Kelvin and Rossby waves, and ocean current advection. Two deep circulation cells are generated in the Atlantic and Indo-Pacific basins. The Atlantic Meridional Overturning Circulation (AMOC) is reinforced while an AMOC-like feature appears in the North Pacific, with deep convective winter events at high latitudes. Transport between the Indo-Pacific and the Southern Ocean is strengthened, with impacts on the Atlantic via the Antarctic Circumpolar Current (ACC).

16 TIDAL AND WAVE POWER↗

Predicting Thermal Conductivity Evolution of Polycrystalline Materials Under Irradiation Using Multiscale Approach

A multiscale methodology was developed to predict the evolution of thermal conductivity of polycrystalline fuel under irradiation. In the mesoscale level, phase field model was used to predict the evolution of gas bubble microstructure. Generation of gas atoms and vacancies were taken into consideration. In the macroscopic scale, a statistical continuum mechanics model was applied to predict the anisotropic thermal conductivity evolution during irradiation. Microstructure predicted by phase field model was fed into statistical continuum mechanics model to predict properties and behavior. Influence of irradiation intensity, exposition time and morphology were investigated. This approach provides a deep understanding on microstructure evolution and property prediction from a basic scientific viewpoint.

36 MATERIALS SCIENCE↗

A non-cooperative meta-modeling game for automated third-party calibrating, validating and falsifying constitutive laws with parallelized adversarial attacks

The evaluation of constitutive models, especially for high-risk and high-regret engineering applications, requires efficient and rigorous third-party calibration, validation and falsification. While there are numerous efforts to develop paradigms and standard procedures to validate models, difficulties may arise due to the sequential, manual, and often biased nature of the commonly adopted calibration and validation processes, thus slowing down data collections, hampering the progress towards discovering new physics, increasing expenses and possibly leading to misinterpretations of the credibility and application ranges of proposed models. This work attempts to introduce concepts from game theory and machine learning techniques to overcome many of these existing difficulties. Here, we introduce an automated meta-modeling game where two competing AI agents systematically generate experimental data to calibrate a given constitutive model and to explore its weakness such that the experiment design and model robustness can be improved through competitions. The two agents automatically search for the Nash equilibrium of the meta-modeling game in an adversarial reinforcement learning framework without human intervention. In particular, a protagonist agent seeks to find the more effective ways to generate data for model calibrations, while an adversary agent tries to find the most devastating test scenarios that expose the weaknesses of the constitutive model calibrated by the protagonist. By capturing all possible design options of the laboratory experiments into a single decision tree, we recast the design of experiments as a game of combinatorial moves that can be resolved through deep reinforcement learning by the two competing players. Our adversarial framework emulates idealized scientific collaborations and competitions among researchers to achieve a better understanding of the application range of the learned material laws and prevent misinterpretations caused by conventional AI-based third-party validation. Numerical examples are given to demonstrate the wide applicability of the proposed meta-modeling game with adversarial attacks on both human-crafted constitutive models and machine learning models.

97 MATHEMATICS AND COMPUTING↗

GLAD-M35: a joint P and S global tomographic model with uncertainty quantification

We present our third and final generation joint P and S global adjoint tomography (GLAD) model, GLAD-M35, and quantify its uncertainty based on a low-rank approximation of the inverse Hessian. Starting from our second-generation model, GLAD-M25, we added 680 new earthquakes to the database for a total of 2160 events. New P-wave categories are included to compensate for the imbalance between P- and S-wave measurements, and we enhanced the window selection algorithm to include more major-arc phases, providing better constraints on the structure of the deep mantle and more than doubling the number of measurement windows to 40 million. Two stages of a Broyden–Fletcher–Goldfarb–Shanno (BFGS) quasi-Newton inversion were performed, each comprising five iterations. With this BFGS update history, we determine the model’s standard deviation and resolution length through randomized singular value decomposition.

58 GEOSCIENCES↗

Dataset for Top Model Decision Tree: Selecting Segmentation Models for Reliable Quantitative Analysis in Low- and Ultralow-Dose CryoEM

Motivation Multiple deep learning model architectures can be used to segment bacterial membranes in cryoEM images. However, an AI-based tool advancement is often presented with only a single segmentation model for broad use, and this single model may show inconsistent results across datasets from different users. Here, we present the Top Model Decision Tree, a model screening framework to screen for the best model to generate bacterial inner and outer membrane masks based on user priorities. We use pre-trained segmentation models from YOLOv11, YOLO26, U-Net, Detectron2 and SAM3 fine-tuned on bacterial inner and outer membranes imaged with cryoEM. Run the Framework This notebook must be opened in Google Colab. Mount Google Drive and run with a GPU-based runtime. Open the notebook and follow steps to git clone in folders and files within this repository. There will be a repeating top_model_decision_tree.ipynb (notebook clone) that will not be used. Save your .png binary mask files and .csv table outputs within your Google Drive or download before closing the notebook. The models and all analysis/training scripts are available at [GitHub: https://github.com/Lynnicia/CryoEM_membranes_top_model_decision_tree and https://github.com/Sireesiru/Semantic-Segmentation-of-bacterial-cell-envelope-using-U-Nets.

59 BASIC BIOLOGICAL SCIENCES↗

Snowmass 2021 cross frontier report: Dark matter complementarity

The fundamental nature of Dark Matter is a central theme of the Snowmass 2021 process, extending across all frontiers. In the last decade, advances in detector technology, analysis techniques and theoretical modeling have enabled a new generation of experiments and searches while broadening the types of candidates we can pursue. Over the next decade, there is great potential for discoveries that would transform our understanding of dark matter. In the following, we outline a road map for discovery developed in collaboration among the frontiers. A strong portfolio of experiments that delves deep, searches wide, and harnesses the complementarity between techniques is key to tackling this complicated problem, requiring expertise, results, and planning from all Frontiers of the Snowmass 2021 process.

Boveia, Antonio [The Ohio State Univ., Columbus, O↗

Dark Matter Complementarity (Snowmass 2021 Cross Frontier Report: Extended Version)

The fundamental nature of Dark Matter is a central theme of the Snowmass 2021 process, extending across all frontiers. In the last decade, advances in detector technology, analysis techniques and theoretical modeling have enabled a new generation of experiments and searches while broadening the types of candidates we can pursue. Over the next decade, there is great potential for discoveries that would transform our understanding of dark matter. In the following, we outline a road map for discovery developed in collaboration among the frontiers. A strong portfolio of experiments that delves deep, searches wide, and harnesses the complementarity between techniques is key to tackling this complicated problem, requiring expertise, results, and planning from all Frontiers of the Snowmass 2021 process.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

Task 1.5 Genomic Shift and Drift Trends of Emerging Pathogens

The Lawrence Livermore National Laboratory (LLNL) Bioinformatics group has recently taken on a role in DTRA's Transformation Medical Technologies Initiative (TMTI). The high-level goal of TMTI is to accelerate the development of broad-spectrum countermeasures. To achieve those goals, TMTI has a near term need to conduct analyses of genomic shift and drift trends of emerging pathogens, with a focused eye on select agent pathogens, as well as antibiotic and virulence markers. Most emerging human pathogens are zoonotic viruses with a genome composed of RNA. The high mutation rate of the replication enzymes of RNA viruses contributes to sequence drift and provides one mechanism for these viruses to adapt to diverse hosts (interspecies transmission events) and cause new human and zoonotic diseases. Additionally, new viral pathogens frequently emerge due to genetic shift (recombination and segment reassortment) which allows for dramatic genotypic and phenotypic changes to occur rapidly. Bacterial pathogens also evolve via genetic drift and shift, although sequence drift generally occurs at a much slower rate for bacteria as compared to RNA viruses. However, genetic shift such as lateral gene transfer and inter- and intragenomic recombination enables bacteria to rapidly acquire new mechanisms of survival and antibiotic resistance. New technologies such as rapid whole genome sequencing of bacterial genomes, ultra-deep sequencing of RNA virus populations, metagenomic studies of environments rich in antibiotic resistance genes, and the use of microarrays for the detection and characterization of emerging pathogens provide mechanisms to address the challenges posed by the rapid emergence of pathogens. Bioinformatic algorithms that enable efficient analysis of the massive amounts of data generated by these technologies as well computational modeling of protein structures and evolutionary processes need to be developed to allow the technology to fulfill its potential.

59 BASIC BIOLOGICAL SCIENCES↗