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 487 records · Page 27
All sourcesNASA NTRSDOE OSTI
DOE OSTI2018

The Semireduced Mechanism for Nitric Oxide Reduction by Non-Heme Diiron Complexes: Modeling Flavodiiron Nitric Oxide Reductases

Flavodiiron nitric oxide reductases (FNORs) are a subclass of Favodiiron proteins (FDPs) capable of preferential binding and subsequent reduction of NO to N 2 O. FNORs are found in certain pathogenic bacteria, equipping them with resistance to nitrosative stress, generated as a part of the immune defense in humans, and allowing them to proliferate. Here, we report the spectroscopic characterization and detailed reactivity studies of the diiron dinitrosyl model complex [Fe 2 (BPMP)(OPr)(NO)2](OTf) 2 for the FNOR active site that is capable of reducing NO to N 2 O [Zheng et al., J. Am. Chem. Soc. 2013, 135, 4902-4905]. Using UV-vis spectroscopy, cyclic voltammetry, and spectro-electrochemis- try, we show that one reductive equivalent is in fact sufficient for the quantitative generation of N 2 O, following a semi-reduced reaction mechanism. This reaction is very efficient and produces N 2 O with a first-order rate constant k > 10 2 s -1 . Further isotope labeling studies confirm an intramolecular N-N coupling mechanism, consistent with the rapid time scale of the reduction and a very low barrier for N-N bond formation. Accordingly, the reaction proceeds at -80 °C, allowing for the direct observation of the mixed-valent product of the reaction. At higher temperatures, the initial reaction product is unstable and decays, ultimately generating the diferrous complex [Fe 2 (BPMP)(OPr) 2 ](OTf) and an unidentified ferric product. Finally, these results combined offer deep insight into the mechanism of NO reduction by the relevant model complex [Fe 2 (BPMP)(OPr)(NO) 2 ] 2+ and provide direct evidence that the semireduced mechanism would constitute a highly efficient pathway to accomplish NO reduction to N 2 O in FNORs and in synthetic catalysts.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2025

DeepAndes: A Self-Supervised Vision Foundation Model for Multispectral Remote Sensing Imagery of the Andes

By mapping sites at large scales usingremotely sensed data, archaeologists can generate unique insights into long-term demographic trends, interregional social networks, and human adaptations in the past. Remote sensing surveys complement field-based approaches, and their reach can be especially great when combined with deep learning and computer vision techniques. However, conventional supervised deep learning methods face challenges in annotating fine-grained archaeological features at scale. In addition, while recent vision foundation models have shown remarkable success in learning large-scale remote sensing data with minimal annotations, most off-the-shelf solutions are designed for RGB images rather than multispectral satellite imagery, such as the eight-band data used in our study. In this article, we introduce DeepAndes, a transformer-based vision foundation model trained on three million multispectral satellite images, specifically tailored for Andean archaeology. DeepAndes incorporates a customized DINOv2 self-supervised learning algorithm optimized for eight-band multispectral imagery, marking the first foundation model designed explicitly for the Andes region. We evaluate its image understanding performance through imbalanced image classification, image instance retrieval, and pixel-level semantic segmentation tasks. Our experiments show that DeepAndes achieves superior F1 scores, mean average precision, and Dice scores in few-shot learning scenarios, significantly outperforming models trained from scratch or pretrained on smaller datasets. This underscores the effectiveness of large-scale self-supervised pretraining in archaeological remote sensing.

Guo, Junlin [Vanderbilt Univ., Nashville, TN (Unit↗
DOE OSTI2014

Performance Assessment Modeling and Sensitivity Analyses of Generic Disposal System Concepts

The Used Fuel Disposition Campaign (UFDC) of the U.S. Department of Energy (DOE) Office of Nuclear Energy (NE) is conducting research and development (R&D) on generic deep geologic disposal systems (i.e., repositories) for high-activity nuclear wastes (i.e., used nuclear fuel (UNF) and high-level radioactive waste (HLW)) that exist today or that could be generated in future fuel cycles. This report describes specific activities in FY2014 toward the development of an enhanced generic disposal system modeling and analysis capability that utilizes high performance computing (HPC) environments to simulate important multi-physics phenomena and couplings associated with the potential behavior of a geologic repository for UNF and HLW.

Sevougian, S. David↗
DOE OSTI2019

Understanding the vertical structure of potential vorticity in tropical depressions

Here, potential vorticity (PV) has been used to understand the intensification and motion of a variety of tropical vortices. In this work, atmospheric reanalyses and idealized models are used to understand how the vertical structures of moist convective heating and adiabatic advection jointly shape the vertical structures of PV in tropical depressions. Observationally based estimates reveal a top-heavy PV structure in tropical depressions, contrasting with bottom-heavy structures of absolute vorticity and diabatic PV generation. These distinct vertical structures are reproduced in an axisymmetric model which employs the weak temperature gradient approximation for conceptual simplicity and is forced by stratiform and deep convective heating. When provided in isolation, the stratiform and deep convective heatings produce PV maxima at 500 hPa and near the surface, respectively. When these two heatings are applied simultaneously, interactions between the stratiform and deep convective modes enhance the adiabatic advective tendencies produced by the transverse circulation, making the PV distribution more top-heavy. In the lower and middle troposphere, radial advection also greatly reduces the radius of the PV structure relative to that of the imposed heating, consistent with structures in observed tropical depressions; the implications of these differences in radial structures for using the flux form of the relevant conservation equations (e.g. for PV substance or absolute vorticity) are discussed.

54 ENVIRONMENTAL SCIENCES↗
NASA NTRS1998

A Quantitative Investigation of Entrainment and Detrainment in Numerically Simulated Convective Clouds: Simulations of Cumulonimbus Clouds - Pt. 2

Deep cumulonimbus clouds are simulated using a model that makes accurate diagnoses of entrainment and detrainment rates and of the properties of entrained and detrained air. Clouds generated by a variety of initial thermodynamic soundings are compared. In the simulations, updraft entrainment rates are large near and above cloud base, through the entire depth of the conditionally unstable layer. Stronger updrafts in a more unstable environment are better able to entrain relatively undisturbed environmental air, while weaker updrafts can entrain only air that has been modified by the clouds. When the maximum buoyancy is large, the updraft includes parcels with a wide range of buoyancies, while weaker clouds are more horizontally uniform. Strong downdrafts originate from levels at which updrafts detrain, and their mass flux depends on the mass flux of the updraft. The magnitude of mixing between cloud and environment, not the entrainment rate, varies inversely with the cloud radius. How much of the mixed air is entrained depends on the buoyancy.

Cohen, Charles↗
DOE OSTI2024

Understanding the High Energy Higgs Sector with the CMS Experiment and Artificial Intelligence

This dissertation describes efforts towards understanding the Higgs boson at the highest energies humanly accessible, using the CMS experiment at the Large Hadron Collider and advances in artificial intelligence (AI) and machine learning (ML). We present searches for resonant and nonresonant Higgs-boson (H) pair production in the all-hadronic two beauty-quark and two vector boson (V) final state, using a novel strategy to measure the quartic HHVV coupling and search for new Higgs-like bosons. By targeting highly Lorentz-boosted Higgs pairs, we probe effects of potential new physics in the high energy Higgs sector, which could hold answers to fundamental mysteries of nature such as baryon asymmetry. To enable these and future searches, we introduce as well significant developments in AI/ML, including in the identification of boosted H$\rightarrow$VV decays with deep transformer networks and advances in AI-accelerated fast simulations of the CMS detector. The latter notably includes the development of the first, highly performant generative models for point-cloud data in high energy physics, which have the potential to improve CMS' computational efficiency by up to three orders of magnitude. We also highlight novel solutions to the important and challenging problems of calibrating and validating these ML techniques. Finally, we present new approaches to search for new physics in a model-agnostic manner, using physics-informed ML methods equivariant to Lorentz transformations. The quartic HHVV coupling is observed (expected) to be constrained to $[-0.04, 2.05]$ ($[0.05, 1.98]$) at the 95% confidence level relative to the standard model prediction, representing the second-most sensitive measurement of this coupling by CMS to date. Exclusion limits on the production cross section of new heavy resonances decaying to two Higgs-like bosons are expected to be as low as 0.3 fb for high resonance masses.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2019

Data-Driven Day-Ahead PV Estimation Using Hybrid Deep Learning

Ongoing smart grid activities and associated automation resulted in rich set of data. Here, these data can be utilized for monitoring and estimation of real time photovoltaic (PV) generation. Inherent variability in PV and related impact on power systems is a challenging problem. Improving the accuracy of PV generation estimation is beneficial for both the PV owners and the grid operators. Recently, deep learning algorithms possible by the availability of data have shown its advantages for time series estimation; however, its application on PV generation estimation is still in the early stage. In this paper, a hybrid estimation model with a combination of long-short-term-memory network (LSTM) and persistence model (PM) is developed to provide day-ahead PV estimation at 15-minute time interval with high accuracy and robustness. Simulation results show the superior performance of the proposed method over existing methods for most of the test cases.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2024

On CCN Effects upon Convective Cold Pool Timing and Features

Abstract Cold pools produced by deep convection can initiate new convection, and their representation in larger-scale weather and climate models could improve prediction of the extent and timing of upscale growth. Cold pools originate from latent cooling from precipitation changing phase, but little attention has been paid to microphysical influences on cold pool characteristics, particularly CCN effects. Datasets obtained from the CACTI and RELAMPAGO field campaigns, along with idealized numerical modeling, are utilized to investigate the hypothesis that convective storms forming in higher-CCN environments generate their first surface rainfall later, delaying cold pool initiation. Aircraft observations of CCN and shallow convection on 9 days do suggest a CCN effect. Those ingesting more CCN contained fewer drizzle drops, although a decreased cloud depth with increasing CCN was also likely a limiting factor. In three of those cases that later developed into deep convection, the timing of cold pool onset was not ubiquitously delayed in environments with more CCN. Idealized numerical simulations suggest that an ordinary thunderstorm can experience small delays in cold pool onset with increasing CCN due to changes in graupel production, but CCN effects on the cold pool from a supercell thunderstorm can be easily overpowered by its unique dynamics. A strong inverse relationship between cold pool strength, expansion rate, and depth with increasing CCN is suggested by the results of the ordinary thunderstorm simulation. Further consideration of CCN appears warranted for future cold pool parameterization development, but other environmental factors affecting storm morphology and precipitation cannot be ignored.

Meteorology & Atmospheric Sciences↗
DOE OSTI2025

Global tuning of hadronic interaction models with accelerator-based and astroparticle data

In high-energy and astroparticle physics, event generators play an essential role, even in the simplest data analyses. As analysis techniques become more sophisticated, e.g. based on deep neural networks, their correct description of the observed event characteristics becomes even more important. Physical processes occurring in hadronic collisions are simulated within a Monte Carlo framework. A major challenge is the modeling of hadron dynamics at low momentum transfer, which includes the initial and final phases of every hadronic collision. QCD-inspired phenomenological models used for these phases cannot guarantee completeness or correctness over the full phase space. These models usually include parameters which must be tuned to suitable experimental data. Until now, event generators have been developed and tuned mainly on the basis of data from high-energy physics experiments at accelerators. The wealth of data available from the latest generation of astroparticle experiments has not yet been fully exploited, and in many cases is not satisfactorily described. Both kinds of data sets are complementary as astroparticle experiments provide sensitivity especially to hadrons produced nearly parallel to the collision axis and cover center-of-mass energies up to several hundred TeV, well beyond those reached at colliders so far. In this report, we provide an overview of state-of-the-art event generators and their tuning, including the most relevant inputs from high-energy accelerator and astroparticle experiments. We present a road map that shows, for the first time, how the unified tuning of event generators with accelerator-based and astroparticle data can be performed.

Albrecht, J. [Ruhr U., Bochum, RAPP Ctr.; Ruhr U.,↗
DOE OSTI2026

LAF-Net: A Deep Residual and Cross-Attention Framework for Day-Ahead Load Forecasting: Preprint

Accurate day-ahead load forecasting is essential for reliable power system operations and market efficiency. System operators such as the Midcontinent Independent System Operator (MISO) rely on forecasts from multiple vendors, yet combining them effectively remains a persistent challenge due to vendor-specific biases. This paper presents a novel LSTM-Attention Fusion Network with Error Representation (LAF-Net) that enhances day-ahead hourly load forecasting through deep residual learning and multi-modal cross-attention. The proposed model builds a historical error memory from past vendor performance and dynamically queries it with future hour context to generate adaptive, hour-specific trust weights for each vendor. A bounded residual correction further refines forecasts by mitigating systematic and temporally localized errors. Tested on real MISO LBA data with multi-vendor forecasts, LAF-Net consistently outperforms the best vendor baseline across all 38 LBAs, achieving more than a 40% reduction in system-level mean absolute error (MAE) during peak load hours relative to the best vendor baseline.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2021

Transfer Learning using Denoising Auto-Encoders for Cellular-Level Annotation of Tumor in Pathology Slides

Adversarial examples can produce altered classifications using only seemingly innocuous, imperceptible perturbations to the original image. The imperceptibility of adversarial perturbations suggests that the corresponding classifiers use decision criteria different than those of a human. In a medical setting, inexplicable decision criteria confound a pathologist’s willingness to trust machine-generated annotations. Here, we analyze denoising tumor detection models to see if they are robust to imperceptible adversarial perturbations. Moreover, to be more fully trusted by pathologists, we require tumor detectors that generate interpretable annotations which segment pathology slides into tumorous and normal regions at the cellular level. We therefore compare transfer learning based on two different autoencoder architectures, one derived from a deep denoising bottleneck autoencoder and one from an over-complete sparse autoencoder. Both autoencoders were first trained in an unsupervised manner on a set of pathology slides drawn from the Camelyon16 dataset. The latent representations produced by each autoencoder were then passed to separate neural networks that were trained in a supervised manner on binary tumor-normal masks generated by pathologists at cellular resolution. Both tumor detectors supported better than 90% AUC PR as measured by the area under the precision/recall curve on a held-out pathology slide. To assess the underlying decision criteria used by both tumor detectors, we constructed imperceptible adversarial examples which reduced the AUC PR of both models to less than 70%. Random noise of the same amplitude had almost no effect on the AUC PR of either model. Additionally, each tumor detector was resistant to adversarial “transfer” attacks targeting the other. The adversarial perturbations showed strong characteristic differences: the deep denoising models perturbations were a very diffuse, seemingly unrecognizable pattern while the sparse coding models perturbations showed traces of tissue cells.

47 OTHER INSTRUMENTATION↗
DOE OSTI2022

A finite-volume scheme for modeling compressible magnetohydrodynamic flows at low Mach numbers in stellar interiors

Fully compressible magnetohydrodynamic (MHD) simulations are a fundamental tool for investigating the role of dynamo amplification in the generation of magnetic fields in deep convective layers of stars. The flows that arise in such environments are characterized by low (sonic) Mach numbers ($\mathscr{M}$ son ≲ 10 –2 ). In these regimes, conventional MHD codes typically show excessive dissipation and tend to be inefficient as the Courant–Friedrichs–Lewy (CFL) constraint on the time step becomes too strict. In this work we present a new method for efficiently simulating MHD flows at low Mach numbers in a space-dependent gravitational potential while still retaining all effects of compressibility. The proposed scheme is implemented in the finite-volume SEVEN-LEAGUE HYDRO (SLH) code, and it makes use of a low-Mach version of the five-wave Harten–Lax–van Leer discontinuities (HLLD) solver to reduce numerical dissipation, an implicit–explicit time discretization technique based on Strang splitting to overcome the overly strict CFL constraint, and a well-balancing method that dramatically reduces the magnitude of spatial discretization errors in strongly stratified setups. The solenoidal constraint on the magnetic field is enforced by using a constrained transport method on a staggered grid. We carry out five verification tests, including the simulation of a small-scale dynamo in a star-like environment at $\mathscr{M}$ son ~ 10 –3 . We demonstrate that the proposed scheme can be used to accurately simulate compressible MHD flows in regimes of low Mach numbers and strongly stratified setups even with moderately coarse grids.

79 ASTRONOMY AND ASTROPHYSICS↗
NASA NTRS1981

Observations and models of inertial waves in the deep ocean

A study of the structure of the inertial peak in deep ocean kinetic energy is presented, based on records taken from Polymode arrays deployed in the western North Atlantic Ocean. Results are interpreted in terms of both local sources and turning point effects on internal waves generated at lower latitudes, and it is found that three classes of environment and their corresponding spectra emerge from peak height variations: (1) the 1500-m level near the Mid-Atlantic Ridge, with the greatest peak height of 18 dB; (2) the upper and deep ocean over rough topography and the deep ocean underneath the Gulf Stream, with the intermediate peak height of 11.5 dB; and (3) the deep ocean over smooth topography, with the lowest peak height of 7.5 dB. Using the globally valid wave functions obtained by Munk and Phillips (1968), frequency spectra near f are calculated numerically. The model is latitudinally dependent, with the frequency shift and bandwidth of the inertial peak decreasing with latitude.

Fu, L.-L.↗
DOE OSTI2021

An experimental program with high duty-cycle polarized and unpolarized positron beams at Jefferson Lab

Positron beams, both polarized and unpolarized, are identified as important ingredients for the experimental programs at the next generation of lepton accelerators. In the context of the hadronic physics program at Jefferson Lab (JLab), positron beams are complementary, even essential, tools for a precise understanding of the electromagnetic structure of nucleons and nuclei, in both the elastic and deep-inelastic regimes. For instance, elastic scattering of polarized and unpolarized electrons and positrons from the nucleon enables a model independent determination of its electromagnetic form factors. Also, the deeply-virtual scattering of polarized and unpolarized electrons and positrons allows unambiguous separation of the different contributions to the cross section of the lepto-production of photons and of lepton-pairs, enabling an accurate determination of the nucleons and nuclei generalized parton distributions, and providing an access to the gravitational form factors of the energy-momentum tensor. Furthermore, positron beams offer the possibility of alternative tests of the Standard Model of particle physics through the search of a dark photon, the precise measurement of electroweak couplings, and the investigation of charged lepton flavor violation. This document discusses the perspectives of an experimental program with high duty-cycle positron beams at JLab.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2015

The Physics of Gain Mechanisms in a Self-Amplified Spontaneous Emission Free-Electron Laser

This is the final report for the DoE BES contract DE-FG02-07ER46272. This grant began under a title that gives its history in a few words: The Physics of Gain Mechanisms in a Self-Amplified Spontaneous Emission Free-Electron Laser. At the time of adopting this name, the UCLA Particle Beam Physics Laboratory (PBPL) was at the forefront of the first demonstrations of SASE FEL, giving the experimental basis for the 4th generation X-ray light source now exemplified by the LCLS, a remarkable generation of machines that have revolutionize nanoscale and ultrafast science. The grant title indicates that physical aspects of the FEL are of interest, and implies that progress requires comprehensive investigations. These aspects include: the physics and technology of high brightness electron beam generation, phase space manipulations, advanced beam diagnostics, state-of-the-art undulators, studies of FEL mode characteristics, as well as the introduction of new theoretical models and start-to-end simulations, all yielding a deep understanding of the SASE FEL. The latest period (2010-13) of BES grant support has been the most productive yet for the UCLA PBPL, and the extensive list of accomplishments is illustrative of our central contributions to advanced FEL research. We give a concise overview here and review our research results in further detail below. In FEL and ultrafast beam physics, we have experimentally investigated: production of helical beams and FEL modes with orbital angular momentum; chirp-taper single-spike FEL gain; new FROG techniques optimized for FEL, introduced coherent imaging of beam profiles using transition radiation; and demonstrated a next generation cryoundulator. We have performed deep theoretical studies of these phenomena and other advanced FEL physics concepts, such as the space-charge amplifier. In high brightness beams, we have: introduced a new class of hybrid photoinjector for <100 fs beam production; developed new approaches to self-shaped ellipsoidal beams; used nonlinear plasma oscillations to create beam pulse trains; tested new plasmonic, high quantum efficiency cathodes, and developed new methods of beam measurement with um spatial/sub-fs temporal resolution. In ultrafast imaging, we have: developed advanced electro-optic timing systems, performed the 1st pump-probe study using single shot UED, demonstrated continuously time-resolved UED with RF deflection; made initial use of inverse Compton scattering (ICS) X-ray sources in application through single-shot inline phase contrast imaging, established single-shot X-ray diffraction, and observed ICS high harmonic generation and redshifting due to nonlinear effects. In 5th generation light source research, we have developed the techniques of narrowband, very high power coherent Cerenkov radiation sources based on dielectric wakefield devices. This work is represented by numerous publications in leading journals: e.g. Nature Physics, Physical Review Letters, Applied Physics Letters. The PBPL program’s influence on the field also extends to organization of the electron beam applications community; we have organized the first international UED workshops and the initial two meetings dedicated to 5th generation light source.

43 PARTICLE ACCELERATORS↗
DOE OSTI2021

Quantitative modeling of carcinogenesis induced by single beams or mixtures of space radiations using targeted and non-targeted effects

Abstract Ionizing radiations encountered by astronauts on deep space missions produce biological damage by two main mechanisms: (1) Targeted effects (TE) due to direct traversals of cells by ionizing tracks. (2) Non-targeted effects (NTE) caused by release of signals from directly hit cells. The combination of these mechanisms generates non-linear dose response shapes, which need to be modeled quantitatively to predict health risks from space exploration. Here we used a TE + NTE model to analyze data on APC (1638N/+) mouse tumorigenesis induced by space-relevant doses of protons, 4 He, 12 C, 16 O, 28 Si or 56 Fe ions, or γ rays. A customized weighted Negative Binomial distribution was used to describe the radiation type- and dose-dependent data variability. This approach allowed detailed quantification of dose–response shapes, NTE- and TE-related model parameters, and radiation quality metrics (relative biological effectiveness, RBE, and radiation effects ratio, RER, relative to γ rays) for each radiation type. Based on the modeled responses for each radiation type, we predicted the tumor yield for a Mars-mission-relevant mixture of these radiations, using the recently-developed incremental effect additivity (IEA) synergy theory. The proposed modeling approach can enhance current knowledge about quantification of space radiation quality effects, dose response shapes, and ultimately the health risks for astronauts.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2011

THERMAL EVOLUTION AND STRUCTURE MODELS OF THE TRANSITING SUPER-EARTH GJ 1214b

The planet GJ 1214b is the second known super-Earth with a measured mass and radius. Orbiting a quiet M star, it receives considerably less mass-loss driving X-ray and UV radiation than CoRoT-7b, so that the interior may be quite dissimilar in composition, including the possibility of a large fraction of water. We model the interior of GJ 1214b assuming a two-layer (envelope+rock core) structure where the envelope material is either H/He, pure water, or a mixture of H/He and H{sub 2}O. Within this framework, we perform models of the thermal evolution and contraction of the planet. We discuss possible compositions that are consistent with M{sub p} = 6.55 M{sub +}, R{sub p} = 2.678 R{sub +}, an age {tau} = 3-10 Gyr, and the irradiation level of the atmosphere. These conditions require that if water exists in the interior, it must remain in a fluid state, with important consequences for magnetic field generation. These conditions also require the atmosphere to have a deep isothermal region extending down to 80-800 bar, depending on composition. Our results bolster the suggestion of a metal-enriched H/He atmosphere for the planet, as we find water-world models that lack an H/He atmosphere to require an implausibly large water-to-rock ratio of more than 6:1. We instead favor an H/He/H{sub 2}O envelope with high water mass fraction ({approx}0.5-0.85), similar to recent models of the deep envelope of Uranus and Neptune. Even with these high water mass fractions in the H/He envelope, generally the bulk composition of the planet can have subsolar water:rock ratios. Dry, water-enriched, and pure water envelope models differ to an observationally significant level in their tidal Love numbers k{sub 2} of, respectively, {approx}0.018, {approx}0.15, and {approx}0.7.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2020

Neural-based time series forecasting of loss of coolant accidents in nuclear power plants

During the last few years, deep learning in neural networks has demonstrated impressive successes in the areas of computer vision, speech and image recognition, text generation, and many others. However, sensitive engineering areas such as nuclear engineering benefited less from these efficient techniques. In this work, deep learning expert systems are utilized to model and predict time series progression of a design-basis nuclear accident, featuring a loss of coolant accident. Two major findings are accomplished in this work. First, the ability to train expert systems with high accuracy, which could help nuclear power plant operators to figure out plant responses during the accident. Second, building fast, efficient, and accurate deep models to simulate nuclear phenomena, which could be valuable to nuclear computational science. In this work, large amount of time series data is obtained from simulation tools by simulating different conditions of the base-case/nominal accident scenario. Four critical outputs/responses are monitored during the accident (e.g. temperature, pressure, break flow rate, water level). Two approaches are adopted in this work. The first approach is to use feedforward deep neural networks (DNN) to fit all time steps and outputs in a single model. The second approach is to use long short-term memory (LSTM) to fit all time steps together for each reactor response separately. Both DNN and LSTM demonstrate very good performance in predicting the test and base-case scenarios, with accuracy as low as 92% and as high as 99%, where these test scenarios are unknown to the expert systems and are not included in the model training. In addition, both approaches demonstrate a significant reduction in computational costs, as the deep expert system is able to accurately predict the accident 100,000 times faster than the original simulation tool. Given sufficient data, the methodology adopted in this study demonstrates that DNN/LSTM expert systems can be used as a decision support system to model advanced time series phenomena within nuclear power plants with high accuracy and negligible computational costs.

42 ENGINEERING↗