Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “distributed inference”

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 847 records · Page 47
All sourcesNASA NTRSDOE OSTI
DOE OSTI2025

WHOLESCALE - Water & Hole Observations Leverage Effective Stress Calculations And Lessen Expenses (Final Technical Report 2020 - 2024)

The WHOLESCALE acronym stands for Water & Hole Observations Leverage Effective Stress Calculations and Lessen Expenses. The goal of the WHOLESCALE project is to simulate the spatial distribution and temporal evolution of stress in the geothermal system at San Emidio in Nevada, United States. To reach this goal, the WHOLESCALE team has developed a methodology to incorporate and interpret data from four methods of measurement into a multi-physics model that couples thermal, hydrological, and mechanical (T H-M) processes. The WHOLESCALE team has applied this methodology at the San Emidio geothermal field, located ~100 km north of Reno, Nevada in the northwestern Basin and Range province. The WHOLESCALE team includes 30 individuals working at two universities, two national laboratories, and one industry partner. Two master-degree students and five post-doctoral researchers have gained professional experience and earned partial financial support via the WHOLESCALE project. The WHOLESCALE team has taken advantage of the perturbations created by changes in pumping operations during planned shutdowns in 2016, 2021, and 2022 to infer temporal changes in the state of stress in the geothermal system at San Emidio, Nevada, U.S. The WHOLESCALE results support the working hypothesis that increasing pore-fluid pressure reduces the effective normal stress acting across fault zones. During normal operations, pumping in deep production wells decreases fluid pressures and thus increases the effective normal stresses on faults, reducing microseismicity. During planned shutdowns, the cessation of production increases pore-fluid pressure and reduces effective normal stress. The WHOLESCALE products generated during the 4-year period between 2020 and 2024 include: three articles published in the open-access, peer-reviewed scientific literature, two master’s theses, 20 presentations or papers at scientific conferences, and 17 data sets available on public repositories. The WHOLESCALE project has been completed in two phases that included three performance periods separated by two Go/No-go Stage Gate Reviews. Tasks were classified by data type (i.e., Geologic Structure, Borehole, Geodesy, Hydrology, Seismology, and Modeling). The first phase of the project started July 31, 2020 and included ongoing project coordination (Task 1), a project kickoff (Task 2), analysis of existing data (Task 3), development of the initial stress model & deployment design (Task 4), and Go/No-go Decision Point #1 (Task 5). Phase II began with implementing the 2022 deployment (Task 6), followed by Go/No-go Decision Point #2 (Task 7) The remainder of Phase II consisted of analyzing data collected during deployment (Task 8), calibration of the stress model on all observations (Task 9), and the Final Review (August 23, 2024) & Reporting (Task 10).

15 GEOTHERMAL ENERGY↗
DOE OSTI2021

In Situ Inference for Earth System Predictability

Focal Area: Focal Area 3: Insight gleaned from complex simulated data using AI, big data analytics, and other advanced methods, including explainable AI and physics- or knowledge-guided AI. Science Challenge: An understanding of future evolution in precipitation extremes is critical to numerous DOE mission questions. Extreme events are by nature short time-scale events that are difficult to diagnose in available model data. Accurate modeling of extreme events necessarily requires high spatial resolution at the storm scale locally. However, the environment in which storms grow is dependent on global, remote, processes. These complex spatiotemporal relationships are impossible to diagnose at resolutions required to accurately model storms responsible for extreme precipitation. At exascale, climate simulations will produce results at fine enough resolution to investigate these relationships. However, the resulting data from these simulations will be far too large to save for post-simulation analysis. We advocate for fitting statistical models inside the simulations as they run, a context known as in situ, which will facilitate scientific investigations using the full fine-scale data stream. Figure 1 shows an example of the type of model we could consider, a Bayesian hierarchical spatial regression model. Precipitation extremes at each grid cell are modeled using extreme value distributions. Since extremes are rare, fitting models to individual grid cells can result in high variance and poor estimates. Instead, the model can be made more robust by smoothing the parameters of the extreme value model across space. Additionally, the parameters themselves can be functionally linked to other variables elsewhere in the simulation. Thus, we can use the fine-scale data to build more robust models for extremes that link extreme behavior to other climate patterns.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2021

Unabsorbed light beamlets for diagnosing coronal density profiles and absorption nonuniformity in direct-drive implosions on OMEGA

Laser light scattered from a target is the most-direct measurement for diagnosing laser absorption in a direct-drive implosion. The 3ωGOI (gated optical imager) beamlets diagnostic images unabsorbed light from all 60 OMEGA beams as distinct “beamlet” spots for each beam. The implosion can be diagnosed using the position and intensity of these beamlets. The position of each beamlet in the image is determined by refraction and can be used to fit the coronal plasma density profile of the implosion. The inferred plasma density profiles are comparable to profiles predicted by the 1-D hydrodynamics code LILAC but suggest the predictions underestimate the density farther out in the corona. The intensity of light in each spot depends on the cumulative effects of absorption and cross-beam energy transfer along the beamlet’s path through the corona. Furthermore, the measured variation in intensity and polarization between similar spots indicates that absorption during OMEGA implosions is less uniform than previously known.

47 OTHER INSTRUMENTATION↗
DOE OSTI2023

The impact of halo concentration on the Sunyaev Zel’dovich effect signal from massive galaxy clusters

ABSTRACT The Sunyaev Zel’dovich (SZ) effect is sensitive to the pressure of ionized gas inside galaxy clusters, which is in turn controlled largely by the gravitational potential of the cluster. Changing the concentration parameter describing the cluster mass distribution impacts the gravitational potential and thus the cluster SZ signal, with implications for cosmological and other analyses of SZ-selected clusters. We investigate the concentration–SZ relation in theory and simulations. We find that the impact of concentration on the inner SZ profile (R ≲ 0.75R200c) can be captured with standard polytropic gas models. However, we find that such models do a poor job of reproducing the outer SZ profiles (R ≳ 0.75R200c) and the relation between the integrated SZ signal, Y, and concentration. This disagreement results from a sharp truncation of the gas pressure profile near the splashback radius, likely caused by virial shocks. We develop a simple description of the truncation that leads to a good match with the simulated SZ profiles out to several R200c for clusters of varying mass and concentration, and that also accurately predicts the concentration–Y relationship. Finally, we determine how inference of the linear bias parameter and splashback radius for SZ-selected clusters can be biased by ignoring the concentration dependence of the SZ signal, finding that bias to the former is essentially negligible, while bias to the latter can be as much as 2 per cent.

Astronomy & Astrophysics↗
DOE OSTI2023

FPGA Architectures for Distributed ML Systems for Real-time Beam Loss De-blending

The Accelerator Real-time Edge AI for Distributed Systems (READS) project’s goal is to create a Artificial Intelligence (AI) system for real-time beam loss de-blending within the accelerator enclosure, which houses two accelerators: the Main Injector (MI) and the Recycler Ring (RR). In periods of joint operation, when both machines contain high intensity beam, radioactive beam losses from MI and RR overlap on the enclosure’s beam loss monitoring Beam Loss Monitor (BLM) system, making it difficult to attribute those losses to a single machine. Incorrect diagnoses result in unnecessary downtime that incurs both financialand experimental cost. The ML system will automatically disentangle each machine’s contributions to those measured losses, while not disrupting the existing operations-critical functions of the BLM system. This paper will focus on the evolution of the architectures, which provided the high-frequency, low-latency collection of synchronized data streams to make real-time inferences. The ML models, used for learning both local and global machine signatures and producing high quality inferences based on raw BLM loss measurements, will only be discussed at a high-level.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
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 OSTI2026

Correlation between microstructure and residual stress formation in friction stir welded armor steels characterized by neutron diffraction

Friction stir welding (FSW) is a solid-state joining process that minimizes the heat-affected zone (HAZ) compared with fusion-based arc welding, making it well suited for joining martensitic armor steels where hardness and ballistic resistance are critical. This study investigates residual stress formation in three defect-free FSW butt-joint configurations relevant to armored-vehicle fabrication: similar rolled homogeneous armor (RHA–RHA, Case 1), similar high-hardness armor (HHA–HHA, Case 2), and dissimilar HHA–RHA (Case 3) joints produced under temperature-controlled conditions (770 °C). Neutron diffraction was employed to quantify the magnitude and spatial distribution of residual stresses in the longitudinal, transverse, and normal directions and to correlate them with weld microstructure and hardness. Tensile residual stresses were concentrated in the softened HAZ, reaching approximately 300 MPa for Case 2 and 400 MPa for Case 1 (≈50–70 % of the base-metal yield strength; ∼581 MPa for RHA and ∼566 MPa for HHA), while compressive residual stresses dominated the stir zone. The spatial extent of tensile stresses scaled with the width of the softened HAZ, which was largest in the dissimilar HHA–RHA joint and smallest in the HHA–HHA joint. Full-width-at-half-maximum (FWHM) analysis revealed low microstrain in overtempered HAZ regions and high microstrain in the stir zone associated with severe plastic deformation and fresh martensite formation. This work demonstrates that residual stress evolution in FSW of martensitic armor steels is governed not primarily by peak temperature or thermal contraction, as inferred from fusion-welding analogies, but by the competition between transformation-induced volumetric expansion and tempering-induced stress relaxation. The relative dominance of these mechanisms is shown to depend on alloy hardenability and local thermal history, leading to more extensive HAZ softening and broader tensile stress regions in the lower-hardenability RHA steel. These findings establish a transferable mechanistic framework for optimizing solid-state joining strategies in high-strength steels and other transformation-hardening alloys beyond armor applications.

Friction stir welding↗
DOE OSTI2022

Atikokan Digital Twin: Machine learning in a biomass energy system

The Atikokan Generating Station, operated by Ontario Power Generation, has a 200 MW, biomass-fired tower boiler that operates on a dispatch schedule with a five-minute cycle. The boiler is generally operated in the range of 40–100 MW using two of five burner levels. In order to optimize boiler performance, we propose the implementation of a unique digital twin. Our digital twin abstraction couples Bayesian inference from science-based models and from observations (machine learning) with decision theory to predict operating-variable set points that optimize the physical asset (the boiler) in the presence of uncertainty (artificial intelligence). We focus this paper on the continuous Bayesian machine learning part of the Atikokan Digital Twin; we discuss decision theory in a companion paper. We identify and learn about 12 operational, model, and measured-output parameters and their uncertainties from high-fidelity, science-based simulations of the Atikokan boiler and from the observed measurements at the power plant. Since the goal of the Atikokan Digital Twin is to implement it online in real time, we require fast function evaluations for the quantities of interest extracted from the simulations in the Bayesian analysis. We use Gaussian process regression/interpolation to create accurate, robust surrogate models. We define the Bayesian priors and likelihood function and solve for the posterior distributions of the 12 parameters. Here we then propagate these distributions (i.e., parameters with uncertainty) into the predicted distributions of 790 quantities of interest to learn about the relative importance of various sources of error including experimental, model, and operating-parameter errors.

09 BIOMASS FUELS↗
DOE OSTI2026

Multiscale modeling of packed-bed microwave reactors and estimation of intrinsic materials' permittivity

Modeling of packed-bed microwave reactors relies on an accurate representation of particle size, shape, and distribution within the bed, as well as the particles' dielectric properties. The measured permittivity of microwave susceptors (powders or structured materials) depends on the geometric features of the particles and the porosity of the bed, as well as the specific form factor of a structured material. These are effective properties and cannot be used to analyze other reactor configurations unless the geometric effects are removed. Therefore, we introduce a methodology for extracting the intrinsic particle permittivity from experimentally measured effective permittivity by combining cavity-based measurements with multiscale simulations and machine learning. Further, we develop the first multiscale model of packed-bed microwave reactors that incorporate particle effects (geometric features, random packing, and particle contact). This approach bridges macroscopic observables with mesoscopic physics, enabling analysis of local hotspots, arcing, and contact effects that control reactor performance. Using polymer-based spherical activated carbon (PBSAC) and silicon carbide (SiC) as examples, we demonstrate that the inferred particle permittivity is consistent with independent experimental heating profiles we collect from microwave reactors without adjustable parameters. Finally, this methodology establishes a foundation for predictive, multiscale design of microwave packed-bed reactors that explicitly accounts for particle-scale effects, enabling the estimation of intrinsic permittivity for the first time.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2023

Neural networks for parameter estimation in intractable models

The goal is to use deep learning models to estimate parameters in statistical models when standard likelihood estimation methods are computationally infeasible. For instance, inference for max-stable processes is exceptionally challenging even with small datasets, but simulation is straightforward. Data from model simulations are used to train deep neural networks and learn statistical parameters from max-stable models. The proposed neural network-based method provides a competitive alternative to current approaches, as demonstrated by considerable accuracy and computational time improvements. Finally, it serves as a proof of concept for deep learning in statistical parameter estimation and can be extended to other estimation problems.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2026

Enabling probabilistic learning on manifolds through double diffusion maps

Here, we present a generative learning framework for probabilistic sampling that extends Probabilistic Learning on Manifolds (PLoM), which is designed to generate statistically consistent realizations of a random vector in a finite-dimensional Euclidean space, informed by a (representative) set of observations. In its original form, PLoM constructs a reduced-order probabilistic model by combining three main components: (a) kernel density estimation to approximate the underlying probability measure, (b) Diffusion Maps to characterize the manifold of the data, and (c) a reduced-order Itô Stochastic Differential Equation (ISDE) to sample from the learned distribution. However, its sampling dynamics are posed in the ambient space and the retained number of reduced coordinates is chosen by projection-reconstruction error. In practice, this often (i) requires more coordinates than the data’s intrinsic dimension to achieve stable sampling and (ii) lacks a smooth, basis-independent lifting back to the data domain; moreover, standard Diffusion Maps emphasize harmonic eigenfunctions and can miss non-harmonic latent structure. We address these limitations by decoupling geometry learning from sampling: a first Diffusion Maps pass identifies non-harmonic coordinates on which we formulate a full-order ISDE directly in the latent space, while Double Diffusion Maps captures multiscale geometric features and Geometric Harmonics (GH) learns a smooth lifting map to the ambient variables that is independent of the particular diffusion basis. This hybrid design preserves the system’s dynamical richness with a compact geometric representation and enables principled out-of-sample inference. The effectiveness and robustness of the proposed method are illustrated through two numerical studies: one based on data generated from two-dimensional Hermite polynomial functions and another based on high-fidelity simulations of a detonation wave in a reactive flow.

Double diffusion maps↗
DOE OSTI2022

Comprehensive compartmental model and calibration algorithm for the study of clinical implications of the population-level spread of COVID-19: a study protocol

The complex dynamics of the coronavirus disease 2019 (COVID-19) pandemic has made obtaining reliable long-term forecasts of the disease progression difficult. Simple mechanistic models with deterministic parameters are useful for short-term predictions but have ultimately been unsuccessful in extrapolating the trajectory of the pandemic because of unmodelled dynamics and the unrealistic level of certainty that is assumed in the predictions. We propose a 22-compartment epidemiological model that includes compartments not previously considered concurrently, to account for the effects of vaccination, asymptomatic individuals, inadequate access to hospital care, post-acute COVID-19 and recovery with long-term health complications. Additionally, new connections between compartments introduce new dynamics to the system and provide a framework to study the sensitivity of model outputs to several concurrent effects, including temporary immunity, vaccination rate and vaccine effectiveness. Subject to data availability for a given region, we discuss a means by which population demographics (age, comorbidity, socioeconomic status, sex and geographical location) and clinically relevant information (different variants, different vaccines) can be incorporated within the 22-compartment framework. Considering a probabilistic interpretation of the parameters allows the model's predictions to reflect the current state of uncertainty about the model parameters and model states. We propose the use of a sparse Bayesian learning algorithm for parameter calibration and model selection. This methodology considers a combination of prescribed parameter prior distributions for parameters that are known to be essential to the modelled dynamics and automatic relevance determination priors for parameters whose relevance is questionable. This is useful as it helps prevent overfitting the available epidemiological data when calibrating the parameters of the proposed model. Population-level administrative health data will serve as partial observations of the model states.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2022

Functional Data Analysis for Extracting the Intrinsic Dimensionality of Spectra: Application to Chemical Homogeneity in the Open Cluster M67

High-resolution spectroscopic surveys of the Milky Way have entered the Big Data regime and have opened avenues for solving outstanding questions in Galactic archeology. However, exploiting their full potential is limited by complex systematics, whose characterization has not received much attention in modern spectroscopic analyses. In this work, we present a novel method to disentangle the component of spectral data space intrinsic to the stars from that due to systematics. Using functional principal component analysis on a sample of 18,933 giant spectra from APOGEE, we find that the intrinsic structure above the level of observational uncertainties requires ≈10 functional principal components (FPCs). Our FPCs can reduce the dimensionality of spectra, remove systematics, and impute masked wavelengths, thereby enabling accurate studies of stellar populations. To demonstrate the applicability of our FPCs, we use them to infer stellar parameters and abundances of 28 giants in the open cluster M67. We employ Sequential Neural Likelihood, a simulation-based Bayesian inference method that learns likelihood functions using neural density estimators, to incorporate non-Gaussian effects in spectral likelihoods. By hierarchically combining the inferred abundances, we limit the spread of the following elements in M67: Fe ≲ 0.02 dex; C ≲ 0.03 dex; O, Mg, Si, Ni ≲ 0.04 dex; Ca ≲ 0.05 dex; N, Al ≲ 0.07 dex (at 68% confidence). Our constraints suggest a lack of self-pollution by core-collapse supernovae in M67, which has promising implications for the future of chemical tagging to understand the star formation history and dynamical evolution of the Milky Way.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2021

Experimental Constraints on Solid Nitride Phases in Rocky Mantles of Reduced Planets and Implications for Observable Atmosphere Compositions

Abstract Astronomical surveys have discovered thousands of transiting exoplanets, revealing that rocky planets are common in the galaxy. A planet's interior chemistry is frequently inferred by average density, described by mass‐radius (M‐R) relationships. However, M‐R relationships give rise to non‐unique interpretations of a planet's interior composition, an issue that limits our ability to characterize far‐away worlds. We present experimental and density functional theoretical results addressing the influence of an ultra‐reducing (oxygen‐poor) interior chemistry on rocky mantle phases and discuss the possible implications for atmospheric observables. We show that silicon carbide (SiC) and molecular nitrogen (N 2 ) react to form solid silicon nitride (γ‐Si 3 N 4 ) at high pressures and high temperatures in a laser‐heated diamond‐anvil cell, consistent with ab initio computations. Si 3 N 4 remains stable under extreme conditions and when quenched to ambient conditions. As SiC is a common compound found under very reducing conditions, these results indicate that nitrogen may form solid phases in an oxygen‐poor rocky planet. If, by sequestering nitrogen in a planet's mantle, the distribution of nitrogen between a planet's interior and atmosphere is altered (i.e., a nitrogen‐rich mantle and nitrogen‐poor atmosphere), these results indicate that there may be atmospheric observables connected to the mantle‐redox state of a rocky planet besides the oxygen‐containing phases ubiquitous in exoplanet literature.

Daviau, Kierstin↗
DOE OSTI2025

A new constraint on galaxy–halo connections of [O ii ] emitters via HOD modelling with angular clustering and luminosity functions from the Subaru HSC survey

ABSTRACT Establishing a robust connection model between emission-line galaxies (ELGs) and their host dark haloes is of paramount importance in anticipation of upcoming redshift surveys. We propose a novel halo occupation distribution (HOD) framework that incorporates galaxy luminosity, a key observable reflecting ELG star-formation activity, into the galaxy occupation model. This innovation enables prediction of galaxy luminosity functions (LFs) and facilitates joint analyses using both angular correlation functions (ACFs) and LFs. Using physical information from luminosity, our model provides more robust constraints on the ELG–halo connection compared to methods relying solely on ACF and number density constraints. Our model was applied to $\rm [O\, {\small II}]$-emitting galaxies observed at two redshift slices at $z=1.193$ and 1.471 from the Subaru Hyper Suprime-Cam PDR2. Our model effectively reproduces observed ACFs and LFs observed in both redshift slices. Compared to the established Geach et al. HOD model, our approach offers a more nuanced depiction of ELG occupation across halo mass ranges, suggesting a more realistic representation of ELG environments. Our findings suggest that ELGs at $z\sim 1.4$ may evolve into Milky-Way-like galaxies, as their inferred halo masses evolve accordingly based on the extended Press–Schechter formalism, highlighting their role as potential building blocks in galaxy formation scenarios. By incorporating the LF as a constraint linking galaxy luminosity to halo properties, our HOD model provides a more precise understanding of ELG-host halo relationships. Furthermore, this approach facilitates the generation of high-quality ELG mock catalogues for future surveys. As the LF is a fundamental observable, our framework is potentially applicable to diverse galaxy populations, offering a versatile tool for analysing data from next-generation galaxy surveys.

Ishikawa, Shogo (ORCID:0000000221184211)↗
DOE OSTI2024

Bridging New Observational Capabilities and Process-Level Simulation: Insights into Aerosol Roles in the Earth System

The spatial distribution of ambient aerosol particles significantly impacts aerosol–radiation–cloud interactions, which contribute to the largest uncertainty in global anthropogenic radiative forcing estimations. However, the atmospheric boundary layer and lower free troposphere have not been adequately sampled in terms of spatiotemporal resolution, hindering a comprehensive characterization of various atmospheric processes and impeding our understanding of the Earth system. To address this research data gap, we have leveraged the development of uncrewed aerial systems (UAS) and advanced measurement techniques to obtain mesoscale spatial data on aerosol microphysical and optical properties around the U.S. Southern Great Plains (SGP) atmospheric observatory. Our study also benefits from state-of-the-art laboratory facilities that include three-dimensional molecular imaging techniques enabled by secondary ion mass spectrometry and nanogram-level chemical composition analysis via micronebulization aerosol mass spectrometry. Through our study, we have developed a framework for observation–modeling integration, enabling an examination of how various assumptions about the organic–inorganic components mixing state, inferred from chemical analysis, affect clouds and radiation in observation-constrained model simulations. By integrating observational constraints (derived from offline chemical analysis of the aerosol surface using collected samples) with in situ UAS observations, we have identified a prominent role of organic-enriched nanometer layers located at the surface of aerosol particles in determining profiles of aerosol optical and hygroscopic properties over the SGP observatory. Furthermore, we have improved the agreement between predicted clouds and ground-based cloud lidar measurements. This UAS–model–laboratory integration exemplifies how these new advanced capabilities can significantly enhance our understanding of aerosol–radiation–cloud interactions.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2025

Improving Trustworthiness of Data-Driven Power Grid Contingency Analysis With Bayesian Residual Graph Neural Networks

The evolving energy landscape requires novel tools to efficiently perform contingency analysis and reliability assessment of power grids, potentially in real-time. The high computational cost of traditional power flow solvers limits their applicability in practice. Machine learning (ML) surrogates such as deep neural networks (NNs) accelerate power flow solvers computations, enabling high-order contingency analysis and real-time decision-making by learning highly nonlinear functions and integrating grid topology via graph architectures. However, (graph) NNs lack predictive power away from training data and do not provide predictive confidence estimates. Here, we present a Bayesian residual graph NN that integrates knowledge from low-fidelity data via residual training and embeds granular quantification of uncertainties, improving trustworthiness critical for high-consequence decision-making. Applying Bayesian concepts to NNs is challenging due to the high-dimensionality of both the parameter space, complicating derivation of a meaningful prior, and the output space in large grid systems, requiring enhanced techniques to assess the predicted high-dimensional uncertainties. Our contributions include: (1) Deriving a prior for fully connected and graph NNs that leverages low-fidelity data to guide mean predictions and appropriately control prior predictive uncertainty. (2) Integrating this prior within an ensembling with anchoring scheme for efficient approximate posterior inference. (3) Deriving enhanced metrics to assess accuracy of both the mean and uncertainty predictions in high dimensions, appropriately accounting for correlations propagated through graph layers. The resulting Bayesian residual graph NN is tested on a contingency analysis task for 14-bus and 118-bus grids.

24 - POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2023

Size distribution of polycyclic aromatic hydrocarbons in space: an old new light on the 11.2/3.3 μm intensity ratio

The intensity ratio of the 11.2/3.3 μm emission bands is considered to be a reliable tracer of the size distribution of polycyclic aromatic hydrocarbons (PAHs) in the interstellar medium (ISM). This paper describes the validation of the calculated intrinsic infrared (IR) spectra of PAHs that underlie the interpretation of the observed ratio. The comparison of harmonic calculations from the NASA Ames PAH IR spectroscopic database to gas-phase experimental absorption IR spectra reveals a consistent underestimation of the 11.2/3.3 μm intensity ratio by 34%. IR spectra based on higher level anharmonic calculations, on the other hand, are in very good agreement with the experiments. While there are indications that the 11.2/3.3 μm ratio increases systematically for PAHs in the relevant size range when using a larger basis set, it is unfortunately not yet possible to reliably calculate anharmonic spectra for large PAHs. Based on these considerations, we have adjusted the intrinsic ratio of these modes and incorporated this in an interstellar PAH emission model. This corrected model implies that typical PAH sizes in reflection nebulae such as NGC 7023 – previously inferred to be in the range of 50 to 70 carbon atoms per PAH are actually in the range of 40 to 55 carbon atoms. The higher limit of this range is close to the size of the C 60 fullerene (also detected in reflection nebulae), which would be in line with the hypothesis that, under appropriate conditions, large PAHs are converted into the more stable fullerenes in the ISM.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗