Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “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 1,477 records · Page 82
All sourcesNASA NTRSDOE OSTI
DOE OSTI2022

The development and use of decision support framework for informing selection of select agent toxins with modelling studies to inform permissible toxin amounts

Many countries have worked diligently to establish and implement policies and processes to regulate high consequence pathogens and toxins that could have a significant public health impact if misused. In the United States, the Antiterrorism and Effective Death Penalty Act of 1996 (Public Law 104-132, 1996), as amended by the Bioterrorism Preparedness and Response Act of 2002 (Public Law 107-188, 2002) requires that the Department of Health and Human Services (HHS) [through the Centers for Disease Control and Prevention (CDC)] establish a list of bacteria, viruses, and toxins that have the potential to pose a severe threat to public health and safety. Currently, this list is reviewed and updated on a biennial basis using input from subject matter experts (SMEs). We have developed decision support framework (DSF) approaches to facilitate selection of select toxins and, where toxicity data are known, conducted modelling studies to inform selection of toxin amounts that should be excluded from select agent regulations. Exclusion limits allow laboratories to possess toxins under an established limit to support their research or teaching activities without the requirement to register with the Federal Select Agent Program. Fact sheets capturing data from a previously vetted SME workshop convened by CDC, literature review and SME input were developed to assist in evaluating toxins using the DSF approach. The output of the DSF analysis agrees with the current select toxin designations, and no other toxins evaluated in this study were recommended for inclusion on the select agent and toxin list. To inform the selection of exclusion limits, attack scenarios were developed to estimate the amount of toxin needed to impact public health. Scenarios consisted of simulated aerosol releases of a toxin in high-population-density public facilities and the introduction of a toxin into a daily consumable product supply chain. Using published inhalation and ingestion median toxic dose (TD 50 ) and median lethal dose (LD 50 ) values, where available, a range of toxin amounts was examined to estimate the number of people exposed to these amounts in these scenarios. Based on data generated by these models, we proposed toxin exclusion values corresponding to levels below those that would trigger a significant public health response (i.e., amounts estimated to expose up to ten people by inhalation or one hundred people by ingestion to LD 50 or TD 50 levels of toxin in the modeled scenarios).

60 APPLIED LIFE SCIENCES↗
DOE OSTI2022

Arbitrage and Capacity Firming in Coordination with Day-Ahead Bidding of a Hybrid PV Plant

A hybrid PV plant (HPP) combines a photovoltaic (PV) plant with a battery energy storage system (BESS), which is considered a promising step towards the future of renewable power plants by the U.S. Department of Energy. When the renewable penetration reaches a significant level, a hybrid PV plant can bid in as a controllable thermal plant in the future electricity market. In this study, a bidding and BESS scheduling model is proposed for the HPP. The robust optimization (RO) technique has been utilized to identify the worst-case scenario of uncertainties during the bidding process. To address the overly conservative issue of the single-stage RO, we have decoupled the BESS schedule for arbitrage and PV capacity firming by a two-stage RO formulation. By comparing the output of single-stage RO and two-stage RO, the two-stage RO bids and schedules in a more aggressive manner, which increases the income of HPP. Also, the penalty of under-generation is considered in our model so that the day-ahead bidding decision and arbitrage schedules can be adjusted based on the potential UNDER-GENERATION penalty. Because the proposed model is non-convex and contains multi-stages, the Column-and-Constraint Generation (C&CG) algorithm is applied to the model as the solution. The proposed model has shown better economic performance compared to a state-of-art single-stage bidding method in case studies.

BESS scheduling↗
DOE OSTI2022

DarkNews: a Python-based event generator for heavy neutral lepton production in neutrino-nucleus scattering

We introduce DarkNews, a lightweight Python-based Monte-Carlo generator for beyond-the-Standard-Model neutrino-nucleus scattering. The generator handles the production and decay of heavy neutral leptons via additional vector or scalar mediators, as well as through transition magnetic moments. DarkNews samples pre-computed neutrino-nucleus upscattering cross sections and heavy neutrino decay rates to produce dilepton and single-photon events in accelerator neutrino experiments. We present two case studies with differential distributions for models that can explain the MiniBooNE excess. The aim of this code is to aid the neutrino theory and experimental communities in performing searches and sensitivity studies for new particles produced in neutrino upscattering.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2025

Integrating particle flavor into deep learning models for hadronization

Hadronization models used in event generators are physics-inspired functions with many tunable parameters. Since we do not understand hadronization from first principles, there have been multiple proposals to improve the accuracy of hadronization models by utilizing more flexible parametrizations based on neural networks. These recent proposals have focused on the kinematic properties of hadrons, but a full model must also include particle flavor. In this paper, we show how to build a deep learning-based hadronization model that includes both kinematic (continuous) and flavor (discrete) degrees of freedom. Our approach is based on generative adversarial networks and we show the performance within the context of the cluster hadronization model within the erwig event generator.

Chan, Jay↗
DOE OSTI2025

Holistic Microstructure Control Strategies in Photopolymerization‐Induced Phase Separation of Acrylate Systems

Open porous materials, known for their large surface area and interconnected structures, are essential in various applications, including batteries, ion exchange, catalysis, filtration, and electronic waste recycling. A critical aspect of the functionality of porous membranes is the precise control of pore size and morphology. Photopolymerization-induced phase separation (photo-PIPS) offers a convenient and versatile methods for creating porous structures. However, controlling the porous morphology remains challenging due to the complex interplay between thermodynamics, polymerization kinetics, and monomer structures, which makes it difficult to establish the relationship between processing conditions and resulting morphology in photo-PIPS. Herein, a physics-based phase-field model capable of generating and characterizing the microstructures of porous materials based on both average and localized features is developed. Using the phase-field simulations as test bed, the effects of polarity, light intensity, and curing temperature, as well as the previously unexplored roles of chain transfer agents and substrates, on the morphology of the resulting porous microstructure are investigated. Experiments are performed to verify the results predicted by the simulations. This work lays out a comprehensive guide for designing PIPS-derived porous microstructures and offers practical engineering strategies for tailoring microstructure-level topology and size of pores for application-specific needs.

36 MATERIALS SCIENCE↗
DOE OSTI2021

Thermodynamics of order and randomness in dopant distributions inferred from atomically resolved imaging

Abstract Exploration of structure-property relationships as a function of dopant concentration is commonly based on mean field theories for solid solutions. However, such theories that work well for semiconductors tend to fail in materials with strong correlations, either in electronic behavior or chemical segregation. In these cases, the details of atomic arrangements are generally not explored and analyzed. The knowledge of the generative physics and chemistry of the material can obviate this problem, since defect configuration libraries as stochastic representation of atomic level structures can be generated, or parameters of mesoscopic thermodynamic models can be derived. To obtain such information for improved predictions, we use data from atomically resolved microscopic images that visualize complex structural correlations within the system and translate them into statistical mechanical models of structure formation. Given the significant uncertainties about the microscopic aspects of the material’s processing history along with the limited number of available images, we combine model optimization techniques with the principles of statistical hypothesis testing. We demonstrate the approach on data from a series of atomically-resolved scanning transmission electron microscopy images of Mo x Re 1- x S 2 at varying ratios of Mo/Re stoichiometries, for which we propose an effective interaction model that is then used to generate atomic configurations and make testable predictions at a range of concentrations and formation temperatures.

25 ENERGY STORAGE↗
DOE OSTI2025

GenAI4UQ: A software for forward and inverse uncertainty quantification using conditional generative AI

We introduce GenAI4UQ, a software package for forward and inverse uncertainty quantification in model calibration, parameter estimation, and ensemble forecasting. GenAI4UQ leverages a generative AI-based conditional modeling framework to address limitations of traditional inverse modeling techniques, such as Markov Chain Monte Carlo (MCMC) methods. By replacing computationally intensive iterative processes with a direct, learned mapping, GenAI4UQ enables efficient calibration of input parameters and generation of predictions directly from observations. The software supports rapid ensemble forecasting with robust uncertainty quantification while maintaining computational and storage efficiency. Built-in auto-tuning of hyperparameters simplifies model training, ensuring accessibility for users with varying expertise. Its versatile conditional generative framework is applicable across diverse scientific domains. While GenAI4UQ offers significant advantages in flexibility and efficiency, users should interpret its uncertainty estimates with caution in data-sparse scenarios, as the model may overestimate uncertainty—an effect common to all surrogate-based approaches including MCMC with surrogate models. Despite this, GenAI4UQ transforms inverse modeling by providing a fast, reliable, and user-friendly solution. It empowers researchers and practitioners to quickly estimate parameter distributions and generate model predictions for new observations, facilitating efficient decision-making and advancing the state of uncertainty quantification in computational modeling.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2025

Quantum magic and multipartite entanglement in the structure of nuclei

Motivated by the Gottesman-Knill theorem, we present a detailed study of the quantum complexity of p -shell and s d -shell nuclei. Valence-space nuclear shell-model wave functions generated by the code are mapped to qubit registers using the Jordan-Wigner mapping (12 qubits for the p shell and 24 qubits for the s d shell), from which measures of the many-body entanglement ( n -tangles) and magic (nonstabilizerness) are determined. While exact evaluations of these measures are possible for nuclei with a modest number of active nucleons, Monte Carlo simulations are required for the more complex nuclei. The broadly applicable Pauli-string I ̂ Z ̂ exact (PSIZe) Markov chain Monte Carlo (MCMC) technique is introduced to accelerate the evaluation of measures of magic in deformed nuclei (with hierarchical wave functions), by factors of ≈ 8 for some nuclei. Significant multinucleon entanglement is found in the s d shell, dominated by proton-neutron configurations, along with significant measures of magic. This is evident not only for the deformed states, but also for nuclei on the path to instability via regions of shape coexistence and level inversion. These results indicate that quantum-computing resources will accelerate precision simulations of such nuclei and beyond. Published by the American Physical Society 2025

73 NUCLEAR PHYSICS AND RADIATION PHYSICS↗
DOE OSTI2025

Influence of Control and Limiter Schemes on Sequence-Domain Fault Models of Grid-Forming Inverter-Interfaced Distributed Generators

Unlike synchronous generators, the fault response of grid-forming (GFM) inverter-interfaced distributed generators (IIDGs) is notably governed by the selection of control and current limiting strategies rather than inherent physical traits. While recent research has focused on the sequence domain fault model of GFM IIDGs, a research gap exists in elucidating the influence of control and current limiting schemes on this model's characteristics. This article aims to fill this void by examining how different control and current limiting schemes influence the positive and negative sequence impedances in the phasor-domain fault model of GFM IIDGs. This investigation encompasses droop-based, virtual synchronous machine-based, and virtual oscillator-based reference generation controls alongside rotating and stationary reference-frame-based voltage controls. Furthermore, saturation-based, latching-based, circular and virtual impedance-based current limiting schemes are analyzed. To achieve this goal, a thorough numerical simulation study is conducted. Findings indicate that outer reference generation controls exhibit minimal impact. Conversely, the choice of voltage control and various current limiting schemes emerge as the predominant factors shaping the sequence models of GFM IIDGs. These analyses and results are instrumental in devising reliable protection strategies within inverter-based grids, as a comprehensive understanding of electrical elements in the sequence domain is imperative for effective protective measures.

current limiters↗
DOE OSTI2024

Preventive Power Outage Estimation Based on a Novel Scenario Clustering Strategy

The increasing occurrence of extreme weather events is challenging power grid operation. For extreme weather events, the system operator is responsible for estimating the power outages and scheduling the restoration resources. This paper proposes an outage evaluation framework to identify the possible unserved load profiles, vulnerable areas, and mobile energy adequacy. The outputs of an outage prediction model tool are used to generate numerous faulted line scenarios. Next, each scenario's nodal unserved load profile is obtained by solving a three-phase restoration model that considers repair crews and mobile energy resources (MERs). Then, a novel scenario clustering strategy is developed to cluster the unserved load profiles into multiple representative profiles which the system operator can focus on. Finally, case studies on a distribution system evaluate the damage caused by an extreme weather event and verify the effectiveness of the proposed scenario clustering strategy.

MATHEMATICS AND COMPUTING,POWER TRANSMISSION AND D↗
DOE OSTI2024

Protonation Stimulates the Layered to Rock Salt Phase Transition of Ni‐Rich Sodium Cathodes

Abstract Protonation of oxide cathodes triggers surface transition metal dissolution and accelerates the performance degradation of Li‐ion batteries. While strategies are developed to improve cathode material surface stability, little is known about the effects of protonation on bulk phase transitions in these cathode materials or their sodium‐ion battery counterparts. Here, using NaNiO 2 in electrolytes with different proton‐generating levels as model systems, a holistic picture of the effect of incorporated protons is presented. Protonation of lattice oxygens stimulate transition metal migration to the alkaline layer and accelerates layered‐rock‐salt phase transition, which leads to bulk structure disintegration and anisotropic surface reconstruction layers formation. A cathode that undergoes severe protonation reactions attains a porous architecture corresponding to its multifold performance fade. This work reveals that interactions between electrolyte and cathode that result in protonation can dominate the structural reversibility/stability of bulk cathodes, and the insight sheds light for the development of future batteries.

25 ENERGY STORAGE↗
DOE OSTI2024

Measurement of the primary Lund jet plane density in proton-proton collisions at $ \sqrt{\textrm{s}} $ = 13 TeV

A measurement is presented of the primary Lund jet plane (LJP) density in inclusive jet production in proton-proton collisions. The analysis uses 138 fb$^{−1}$ of data collected by the CMS experiment at $ \sqrt{s} $ = 13 TeV. The LJP, a representation of the phase space of emissions inside jets, is constructed using iterative jet declustering. The transverse momentum k$_{T}$ and the splitting angle ∆R of an emission relative to its emitter are measured at each step of the jet declustering process. The average density of emissions as function of ln(k$_{T}$/GeV) and ln(R/∆R) is measured for jets with distance parameters R = 0.4 or 0.8, transverse momentum p$_{T}$> 700 GeV, and rapidity |y| < 1.7. The jet substructure is measured using the charged-particle tracks of the jet. The measured distributions, unfolded to the level of stable charged particles, are compared with theoretical predictions from simulations and with perturbative quantum chromodynamics calculations. Due to the ability of the LJP to factorize physical effects, these measurements can be used to improve different aspects of the physics modeling in event generators.[graphic not available: see fulltext]

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2020

A global analysis strategy to resolve neutrino NSI degeneracies with scattering and oscillation data

Neutrino non-standard interactions (NSI) with the first generation of standard model fermions can span a parameter space of large dimension and exhibit degeneracies that cannot be broken by a single class of experiment. Oscillation experiments, together with neutrino scattering experiments, can merge their observations into a highly informational dataset to combat this problem. We consider combining neutrino-electron and neutrino-nucleus scattering data from the Borexino and COHERENT experiments, including a projection for the upcoming coherent neutrino scattering measurement at the CENNS-10 liquid argon detector. We extend the reach of these data sets over the NSI parameter space with projections for neutrino scattering at a future multi-ton scale dark matter detector and future oscillation measurements from atmospheric neutrinos at the Deep Underground Neutrino Experiment (DUNE). In order to perform this global anal- ysis, we adopt a novel approach using the copula method, utilized to combine posterior information from different experiments with a large, generalized set of NSI parameters. We find that the contributions from DUNE and a dark matter detector to the Borexino and COHERENT fits can improve constraints on the electron and quark NSI parameters by up to a factor of 2 to 3, even when relatively many NSI parameters are left free to vary in the analysis.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2021

Resolving the ($\mathscr{g}$-2)$_μ$ discrepancy with $\mathcal{F}$–SU(5) intersecting D-branes

A discrepancy between the measured anomalous magnetic moment of the muon (g - 2) μ and computed Standard Model value now stands at a combined 4.2σ following experiments at Brookhaven National Lab (BNL) and the Fermi National Accelerator Laboratory (FNAL). A solution to the disagreement is uncovered in flipped SU(5) with additional TeV-Scale vector-like 10 +$\bar{10}$ multiplets and charged singlet derived from local F-Theory, collectively referred to as $\mathcal {F}$-SU(5). Here we engage general No-Scale supersymmetry (SUSY) breaking in $\mathcal {F}$-SU(5) D-brane model building to alleviate the (g-2)μ. tension between the Standard Model and observations. A robust Δa μ (SUSY) is realized via mixing of M 5 and M 1X at the secondary SU(5) x U(1) X unification scale in $\mathcal {F}$-SU(5) emanating from SU(5) breaking and U(1) X flux effects. Calculations unveil Δa μ (SUSY) = 19.0-22.3 x 10 -10 for gluino masses of M($\tilde{g}$ = 2.25-2.56 TeV nd higgsino dark matter, aptly residing within the BNL+FNAL 1σ mean. This (g – 2)μ favorable region of the model space also generates the correct light Higgs boson mass and branching ratios of companion rare decay processes, and is further consistent with all LHC Run 2 constraints. Finally, we also examine the heavy SUSY Higgs boson in light of recent LHC searches for an extended Higgs sector.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗
DOE OSTI2021

Street context of various demographic groups in their daily mobility

Abstract We present an urban science framework to characterize phone users’ exposure to different street context types based on network science, geographical information systems (GIS), daily individual trajectories, and street imagery. We consider street context as the inferred usage of the street, based on its buildings and construction, categorized in nine possible labels. The labels define whether the street is residential, commercial or downtown, throughway or not, and other special categories. We apply the analysis to the City of Boston, considering daily trajectories synthetically generated with a model based on call detail records (CDR) and images from Google Street View. Images are categorized both manually and using artificial intelligence (AI). We focus on the city’s four main racial/ethnic demographic groups (White, Black, Hispanic and Asian), aiming to characterize the differences in what these groups of people see during their daily activities. Based on daily trajectories, we reconstruct most common paths over the street network. We use street demand (number of times a street is included in a trajectory) to detect each group’s most relevant streets and regions. Based on their street demand, we measure the street context distribution for each group. The inclusion of images allows us to quantitatively measure the prevalence of each context and points to qualitative differences on where that context takes place. Other AI methodologies can further exploit these differences. This approach presents the building blocks to further studies that relate mobile devices’ dynamic records with the differences in urban exposure by demographic groups. The addition of AI-based image analysis to street demand can power up the capabilities of urban planning methodologies, compare multiple cities under a unified framework, and reduce the crudeness of GIS-only mobility analysis. Shortening the gap between big data-driven analysis and traditional human classification analysis can help build smarter and more equal cities while reducing the efforts necessary to study a city’s characteristics.

Salgado, Ariel (ORCID:0000000177015372)↗
DOE OSTI2023

Direct observation of C 3 S particle dissolution using fast nano X-ray computed tomography

Tricalcium silicate (C 3 S) occupies 50 % to 70 % of ordinary portland cement (OPC) by mass and it is an important component affecting the hydration of OPC [1], [2], [3], [4], [5], [6], [7]. Generally, the hydration of C 3 S is described by two processes: the dissolution of C 3 S particles and the precipitation of hydration products. While it is understood that the dissolution rates of C 3 S vary with time, more precise measurements are needed to understand this process. Many mechanisms have been proposed to explain the time-evolving dissolution rates of C 3 S [2]. The metastable barrier hypothesis suggests that a thin metastable layer of hydrates forms around the C 3 S particle surface and prohibits the access of grains to the aqueous solution [8], [9], [10], [11], [12]. The slow dissolution step hypothesis suggests that the increased ion concentration from the initial reaction delays the C 3 S dissolution [2], [13], [14], [15], [16], [17]. More recent publications suggest that C 3 S may react differently depending on the existence of crystallographic defects [18], [19], [20]. Etch pits are thought to open on the particle surface during the initial reaction and this contributes to the C 3 S dissolution [21], [22]. As hydrates precipitate and cover these highly reactive surfaces, hydration slows down and the induction period starts [18], [23], [24], [25], [26]. Many experiments have been conducted to test the aforementioned mechanisms. Some hydration studies utilize bulk measurements, such as isothermal calorimetry [27], [28], [29], pore solution analysis [30], quasi-elastic neutron scattering [31], and nuclear magnetic resonance spectroscopy [32], [33]. One limitation of these measurements is that they do not provide direct and detailed information on the individual C 3 S particles. Some other studies utilize imaging techniques, such as scanning electron microscopy (SEM) [34], [35], [36] and transmission electron microscopy (TEM) [37]. However, SEM/TEM cannot track the evolution of individual particles throughout hydration [34], [35], [38], [39], [40] and they do not give insights into the microstructure of materials before hydration [34], [35], [39]. This makes it challenging to draw strong conclusions from only SEM or TEM observations. Synchrotron X-ray tomography techniques have been used more broadly in recent years to study cement hydration. They are not only non-destructive but also able to image a sample in full 3D with resolutions that can reach from micron to nanoscale. Nano computed tomography (nCT) is one technique that has been applied to study cement hydration at the nanoscale [26], [41]. A typical nCT can reach a pixel size from 15 to 65 nm, providing enough detail for observing features <1 μm. However, nCT often takes >0.5 h to finish one scan. This makes the application of this technique on continuous scans for in-situ observations challenging. Fast X-ray computerized tomography (fCT) is another technique that has shown success in studying the time-evolving cement microstructures [20], [42], [43], [44], [45], [46], [47], [48], [49]. Due to the high flux of the X-ray beam from the synchrotron ring, fCT allows a scan to be captured within 1 min at a pixel size of 1 μm. This allows a paste sample to be continuously scanned during the hydration process. However, the micron-sized resolutions limit does not provide detailed insights for particles <5 μm [20], [49]. Fortunately, the combination of nCT and fCT has allowed the development of fast nano X-ray computed tomography (fnCT). fnCT can capture a 3D data set in <2 min at a pixel size of 50 nm. This makes this procedure an exciting method to evaluate hydrating pastes. fnCT collects multiple X-ray radiographs at various rotation angles and generates a 3D model of the scanned sample, which is also referred to as a 3D tomography [50], [51]. In one tomography, the X-ray absorptions of different components (e.g., C 3 S and hydrates) differ as functions of density and chemistry [52], [53]. These X-ray absorption contrasts can be used to extract detailed information about the 3D microstructure [26], [54], [55]. In this paper, fnCT is used to collect time-lapse tomographs of hydrating C 3 S paste from 18 min after mixing to 7 h of hydration. The bulk measurements of anhydrous C 3 S, as well as the microstructural changes of individual C 3 S particles, are directly observed, quantified, and discussed. The dissolution behavior of C 3 S particles at various size scales is systematically analyzed and compared. This work aims to find the relationship between the size of C 3 S particle sizes and their dissolution rates. This provides significant insights into the early-age hydration of C 3 S on length and time scales not previously possible. Because of the magnitude of the data and the substantial amount of observations, this work will solely focus on the change in the anhydrous particles. Changes in the hydration products will be reported in future work.

42 ENGINEERING↗
DOE OSTI2022

Spark plasma sintered, MoNbTi-based multi-principal element alloys with Cr, V, and Zr

MoNbTi, MoNbTiZr, CrMoNbTiZr, and MoNbTiVZr multi-principal element alloys (MPEAs) were fabricated via spark plasma sintering (SPS) and investigated for use in high-strength applications. The fabrication method by SPS and powder metallurgy differs from those presented in the prior literature, where most MPEAs are fabricated using arc melting (AM) methods. Here cryogenic milling was used to maximize potential defect sinks (grain boundaries) for radiation resistance and to increase ultimate tensile strength through the Hall-Petch effect. SPS was chosen for consolidation in order to maintain a fine-grained structure during densification. Each alloy was characterized using x-ray diffraction and scanning electron microscopy for phase identification and compositional homogeneity. The base ternary alloy MoNbTi presented a predominantly single BCC system with minor cubic phases. The introduction of additional alloying elements—Zr, V, and Cr—heightened the phase complexity and increased the fractions of a secondary BCC phase and an HCP phase from Zr. The addition of Cr induced a larger fraction of the Laves phase to form. The addition of V caused the precipitation of small Mo inclusions. Thermodynamic analysis was performed to understand the separation of phases in each alloy. Discrepancies among the phase predictions generated by thermodynamic models, phases previously presented in the literature, and the characterization results suggest that MPEA fabrication methods, especially solid-state methods, require significant investigation to ensure that alloys can remain stable throughout their anticipated service lifetimes.

36 MATERIALS SCIENCE↗
DOE OSTI2025

Bayesian Entropy Neural Networks for physics-aware prediction

This article addresses the need for deep learning models to integrate well-defined constraints into their outputs, driven by their application in surrogate models, learning with limited data and partial information, and scenarios requiring flexible model behavior to incorporate non-data sample information. We introduce Bayesian Entropy Neural Networks (BENN), a framework grounded in Maximum Entropy (MaxEnt) principles, designed to impose constraints on Bayesian Neural Network (BNN) predictions. BENN is capable of constraining not only the predicted values but also their derivatives and variances, ensuring a more robust and reliable model output. To achieve simultaneous uncertainty quantification and constraint satisfaction, we employ the method of multipliers approach. This allows for the concurrent estimation of neural network parameters and the Lagrangian multipliers associated with the constraints. Our experiments, spanning diverse applications such as beam deflection modeling and microstructure generation, demonstrate the effectiveness of BENN. The results highlight significant improvements over traditional BNNs and showcase competitive performance relative to contemporary constrained deep learning methods.

14 SOLAR ENERGY↗