Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “model 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 1,441 records · Page 80

ATMS Radiometric Noise Characterization

The Advanced Technology Microwave Sounder (ATMS), on SNPP and NOAA-20, provides vertical atmospheric temperature and moisture profiles that are a key input to numerical weather prediction. Full characterization of radiometric noise is critical to error modeling, algorithm development and the potential development of performance requirements and product improvements. This paper presents estimates of white noise and low-frequency 1/f noise as derived from the Allan variance and scan-to-scan autocorrelations of data from the internal hot calibration. This approach allows direct comparison of on-orbit performance of the two units as well as comparison between ground calibration test data and on-orbit performance. The autocorrelation at multiple scan intervals is used as input to a theoretical model of the NET of inferred scene brightness temperature, when using weighted samples of calibration data over multiple scans. This will support selection of optimized calibration weighting functions for each channel, as well as providing further insight into the striping phenomenon. These measured autocorrelations are also compared to the autocorrelations derived from the 1/f spectra obtained both in special ground and on-orbit tests that characterize gain fluctuation. Channel cross-correlations are also presented, which can have a significant impact on effectiveness of direct assimilation performance.

instrument calibration↗

A Real-time View of Orbital Evolution in HM Cancri

HM Cancri is a double-degenerate binary with the shortest orbital period presently known. The 5.36 minute period is seen as a large amplitude, soft X-ray modulation, likely resulting from a hot-spot produced by direct impact accretion. With such a7short orbital period it is expected to have a gravitational wave luminosity comparable8to or larger than that in the X-ray, and its orbital frequency is known to be increasing9at a rate consistent with the expected loss of angular momentum due to gravitational radiation. We use recent Neutron Star Interior Composition Explorer(NICER) observations to extend its long-term X-ray timing baseline to almost 20 yr. Phase coherent timing of these new data combined with existing Chandra data demonstrates conclusively that the rate of orbital frequency increase is slowing, and we measure a non-zero f0=8.95 ± 1.4 x 1027 Hz s2, to our knowledge the first such measurement of its kind for any compact astrophysical binary. With the simultaneous high precision measurement of f0= 3.557 ± 0.005 x 1016 Hz s1, we estimate that the system17will reach its maximum orbital frequency of fmax 3.1172091 mHz in 1,260 ± 200 yr, indicating that the system is close to its epoch of maximum orbital frequency. Assuming mass transfer is conservative, the measurement of f<0 implies that the20accretion rate from the donor is growing, with 5.4 x 1010<M2<4.0 x 1010 M⊙yr2. Further quantitative comparisons with theoretical models should enable more precise inferences regarding its current evolutionary state.

White dwarfs↗

Discounting Water for Optimal Carbon Gain as a Basis of Stomatal Closure

The exchange of carbon dioxide and water vapor between terrestrial ecosystems and the atmosphere is regulated by stomata (small pores in the leaves of plants). Unsurprisingly, environmental factors controlling the opening and closure of stomata has been sought as early as 1800. One approach, popularized in the early 1970s, is a stomatal optimization framework. This framework is based on the hypothesis that plants optimize carbon gain subject to water loss or water availability constraints. This constraint optimization problem was solved in various forms assuming instantaneous adjustments of stomatal aperture to maximize a reward function with no future foresight or legacy effects. Holtzman et al. (2024, https://doi.org/10.1029/2023av001113) offers a novel approach that can diagnose the effective timescale over which the reward function maximization must be time-integrated. The developed method thus optimizes an integrated carbon gain function but adjusted by a discount factor subject to water availability in the root zone. The discount factor considers how the plant values carbon gain to save water and its timescale can be inferred from observations because the model is analytically tractable. The results suggest that the most important climate factor that determines this discount timescale is multi-annual mean of the longest dry period during the growing season. The findings highlight how local climate traits influence the spatial variation in ecosystem-level water use strategies. This sets the stage for expanding such a framework to cases where multiple constraints act in concert while operating at distinct time scales.

stomata↗

Continuous Time Group Discovery in Dynamic Graphs

With the rise in availability and importance of graphs and networks, it has become increasingly important to have good models to describe their behavior. While much work has focused on modeling static graphs, we focus on group discovery in dynamic graphs. We adapt a dynamic extension of Latent Dirichlet Allocation to this task and demonstrate good performance on two datasets. Modeling relational data has become increasingly important in recent years. Much work has focused on static graphs - that is fixed graphs at a single point in time. Here we focus on the problem of modeling dynamic (i.e. time-evolving) graphs. We propose a scalable Bayesian approach for community discovery in dynamic graphs. Our approach is based on extensions of Latent Dirichlet Allocation (LDA). LDA is a latent variable model for topic modeling in text corpora. It was extended to deal with topic changes in discrete time and later in continuous time. These models were referred to as the discrete Dynamic Topic Model (dDTM) and the continuous Dynamic Topic Model (cDTM), respectively. When adapting these models to graphs, we take our inspiration from LDA-G and SSN-LDA, applications of LDA to static graphs that have been shown to effectively factor out community structure to explain link patterns in graphs. In this paper, we demonstrate how to adapt and apply the cDTM to the task of finding communities in dynamic networks. We use link prediction to measure the quality of the discovered community structure and apply it to two different relational datasets - DBLP author-keyword and CAIDA autonomous systems relationships. We also discuss a parallel implementation of this approach using Hadoop. In Section 2, we review LDA and LDA-G. In Section 3, we review the cDTM and introduce cDTMG, its adaptation to modeling dynamic graphs. We discuss inference for the cDTM-G and details of our parallel implementation in Section 4 and present its performance on two datasets in Section 5 before concluding in Section 6.

97 MATHEMATICS AND COMPUTING↗

Tensor-Dictionary Learning with Deep Kruskal-Factor Analysis

We introduce new dictionary learning methods for tensor-variate data of any order. We represent each data item as a sum of Kruskal decomposed dictionary atoms within the framework of beta-process factor analysis (BPFA). Our model is nonparametric and can infer the tensor-rank of each dictionary atom. This Kruskal-Factor Analysis (KFA) is a natural generalization of BPFA. We also extend KFA to a deep convolutional setting and develop online learning methods. We test our approach on image processing and classification tasks achieving state of the art results for 2D & 3D inpainting and Caltech 101. The experiments also show that atom-rank impacts both overcompleteness and sparsity.

Stevens, Andrew J.↗

Bayesian inference for plasmonic nanometrology

Here, we introduce a Bayesian method for the characterization of plasmonic nanoparticles, which is applicable to both near- and far-field problems. Designed to combine data generated from any photon-plasmon interaction experiment with physically motivated theoretical models, our approach leverages state-of-the-art Markov chain Monte Carlo sampling techniques and returns parameter estimates on nanometric scales. Simulated spectral data sets, describing resonant scattering of photons from ellipsoidal and toroidal nanoparticles, are explored as concrete examples of our approach, with the resulting Bayesian estimates showing excellent agreement with the ground truth, even under conditions of high statistical noise. By incorporating Bayes factors into the method as well, we reveal how model selection can determine which one of competing geometric shapes better explains the observed data. Our comprehensive nanometrology procedure can be tailored to a variety of light-particle interaction models, and its reliance on Bayesian inference furnishes automatic uncertainty quantification. In addition to applicability to a host of plasmonic configurations such as nanoparticle dimers, trimers, and array studies, it is proposed that the presented analysis can be extended to the quantum regime, where nonclassical photon statistics may provide additional insight for inference of scatterer properties.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

Thermal evolution of earth and moon growing by planetesimal impacts

Improved estimates of impact energy partitioning are combined with models of planetesimal size distribution and planetary growth to infer the early thermal evolutions of the earth and moon. Binary accretion models of the moon which allow for enhancement of velocities by proximity of the earth do not get hot enough for appreciable melting unless a planetesimal mass distribution starting at a rather high value (earth mass/20 or more) is assumed. This melting occurs deeper than is inferred from petrological and thermotectonic data; hence the results favor formation of the moon as a consequence of a great impact (or great impacts) into the earth.

Kaula, W. M.↗

A Variational Inference Approach to Inverse Problems with Gamma Hyperpriors

Hierarchical models with gamma hyperpriors provide a flexible, sparse-promoting framework to bridge L 1 and L 2 regularizations in Bayesian formulations to inverse problems. Despite the Bayesian motivation for these models, existing methodologies are limited to maximum a posteriori estimation. The potential to perform uncertainty quantification has not yet been realized. This paper introduces a variational iterative alternating scheme for hierarchical inverse problems with gamma hyperpriors. The proposed variational inference approach yields accurate reconstruction, provides meaningful uncertainty quantification, and is easy to implement. In addition, it lends itself naturally to conduct model selection for the choice of hyperparameters. Here, we illustrate the performance of our methodology in several computed examples, including a deconvolution problem and sparse identification of dynamical systems from time series data.

Bayesian shrinkage↗

Parameter Estimation for Compact Binary Coalescence Signals with the First Generation Gravitational-Wave Detector Network

Compact binary systems with neutron stars or black holes are one of the most promising sources for ground-based gravitational-wave detectors. Gravitational radiation encodes rich information about source physics; thus parameter estimation and model selection are crucial analysis steps for any detection candidate events. Detailed models of the anticipated waveforms enable inference on several parameters, such as component masses, spins, sky location and distance, that are essential for new astrophysical studies of these sources. However, accurate measurements of these parameters and discrimination of models describing the underlying physics are complicated by artifacts in the data, uncertainties in the waveform models and in the calibration of the detectors. Here we report such measurements on a selection of simulated signals added either in hardware or software to the data collected by the two LIGO instruments and the Virgo detector during their most recent joint science run, including a blind injection where the signal was not initially revealed to the collaboration. We exemplify the ability to extract information about the source physics on signals that cover the neutron-star and black-hole binary parameter space over the component mass range 1M25M and the full range of spin parameters. The cases reported in this study provide a snapshot of the status of parameter estimation in preparation for the operation of advanced detectors.

Aasi, J.↗

Graphical models for optimal power flow

Optimal power flow (OPF) is the central optimization problem in electric power grids. Although solved routinely in the course of power grid operations, it is known to be strongly NP-hard in general, and weakly NP-hard over tree networks. In this paper, we formulate the optimal power flow problem over tree networks as an inference problem over a tree-structured graphical model where the nodal variables are low-dimensional vectors. We adapt the standard dynamic programming algorithm for inference over a tree-structured graphical model to the OPF problem. Combining this with an interval discretization of the nodal variables, we develop an approximation algorithm for the OPF problem. Further, we use techniques from constraint programming (CP) to perform interval computations and adaptive bound propagation to obtain practically efficient algorithms. Compared to previous algorithms that solve OPF with optimality guarantees using convex relaxations, our approach is able to work for arbitrary tree-structured distribution networks and handle mixed-integer optimization problems. Further, it can be implemented in a distributed message-passing fashion that is scalable and is suitable for “smart grid” applications like control of distributed energy resources. In conclusion, numerical evaluations on several benchmark networks show that practical OPF problems can be solved effectively using this approach.

24 POWER TRANSMISSION AND DISTRIBUTION↗

wa-hls4ml and lui-gnn: A benchmark and GNN-based surrogate model for hls4ml resource and latency estimation

As machine learning (ML) increasingly serves as a tool for addressing real-time challenges in scientific applications, the development of advanced tooling has significantly reduced the time required to iterate on various designs. These advancements have solved major obstacles, but also exposed new challenges. For example, processes that were not previously considered bottlenecks, such as model synthesis, are now becoming limiting factors in the rapid iteration of designs. To reduce these emerging constraints, multiple efforts are being launched toward designing an ML-based surrogate model that estimates resource usage of synthesized accelerator architectures. This model would reduce the design iteration time, especially when designing within a set of given hardware constraints. This approach shows considerable potential, but as it stands, the effort is early and would benefit from coordination and standardization to assist future work as it emerges. We introduce wa-hls4ml, a benchmark for ML accelerator resource and latency estimation, and its corresponding initial dataset of more than 100,000 fully connected neural networks, all synthesized using hls4ml and targeting Xilinx FPGAs. In addition to the resource utilization and latency data provided, the dataset includes generated artifacts and log files for many of the synthesized neural networks, in order to support future research in ML-based code generation. The benchmark evaluates the performance of resource and latency predictors against several common ML model architectures, primarily originating from scientific domains, as exemplar models, as well as the average performance across a subset of the dataset. We measure the performance of a given predictor model through multiple metrics, including $R^2$ score and SMAPE on regression tasks, as well as inference time to further characterize the estimator under test. Additionally, we introduce the latency/utilization inference graph neural network (lui-gnn), a surrogate model that uses a graph neural network to represent input architectures in the form of a directed graph. This graph representation allows for a diverse set of model architectures to all be effectively handled by a surrogate model. We present the architecture and performance of the model, as evaluated by the new proposed benchmark, including SMAPE, $R^2$ score, and inference times, and find that lui-gnn generally predicts latency and utilization for the 75\% quantile within several percent of the synthesized resources on the synthetic test dataset, indicating that this approach of estimating resource and latency via a surrogate models has promise and warrants further research.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

Lifetime Prediction for Degradation of Solar Mirrors using Step-Stress Accelerated Testing (Presentation)

This research is to illustrate the use of statistical inference techniques in order to quantify the uncertainty surrounding reliability estimates in a step-stress accelerated degradation testing (SSADT) scenario. SSADT can be used when a researcher is faced with a resource-constrained environment, e.g., limits on chamber time or on the number of units to test. We apply the SSADT methodology to adegradation experiment involving concentrated solar power (CSP) mirrors and compare the results to a more traditional multiple accelerated testing paradigm. Specifically, our work includes: (1) designing a durability testing plan for solar mirrors (3M's new improved silvered acrylic 'Solar Reflector Film (SFM) 1100') through the ultra-accelerated weathering system (UAWS), (2) definingdegradation paths of optical performance based on the SSADT model which is accelerated by high UV-radiant exposure, and (3) developing service lifetime prediction models for solar mirrors using advanced statistical inference. We use the method of least squares to estimate the model parameters and this serves as the basis for the statistical inference in SSADT. Several quantities of interest canbe estimated from this procedure, e.g., mean-time-to-failure (MTTF) and warranty time. The methods allow for the estimation of quantities that may be of interest to the domain scientists.

14 SOLAR ENERGY↗

Electron Precipitation Parameters and Ionospheric Conductances Inferred from Auroral Images Acquired by the Visible Imaging Systems (VIS) on the Polar Spacecraft

The Visible Imaging System (VIS) on the polar spacecraft provided time sequences of auroral images at multiple wavelengths that yield information of auroral dynamics on a global scale with a spatial resolution of - 20 km and temporal resolution of approx. 1 minute. Time sequences of VIS images in which the aurora was highly dynamic are used to infer global maps for the electron precipitation parameters, energy flux and characteristic energies, and ionospheric conductances. The maps are inferred from the corresponding VIS images using an auroral model (Lumerzheim et al., 1987). The temporal and spatial resolution of the VIS inferred patterns are unprecedented. The inferred patterns are highly structured and vary significantly on a time scale of less than 5 minutes. These patterns can be very beneficial for global physics-based numerical models for the high-latitude ionosphere which previously had to rely on statistical models for the electron precipitation and ionospheric conductance.

Sigwarth, John B.↗

Radiation Source Localization Using Surrogate Models Constructed from 3-D Monte Carlo Transport Physics Simulations

Recent research has focused on the development of surrogate models for radiation source localization in a simulated urban domain. We employ the Monte Carlo N-Particle (MCNP) code to provide high- delity simulations of radiation transport within an urban domain. The model is constructed to employ a source location (x, y, z) as input and return the estimated count rate for a set of speci ed detector locations. Because MCNP simulations are computationally expensive, we develop e cient and accurate surrogate models of the detector responses. We construct surrogate models using Gaussian processes (GP) and neural networks (NN) that we train and verify using the MCNP simulations. The trained surrogate models provide an e cient framework for Bayesian inference and experimental design. We employ Delayed Rejection Adaptive Metropolis (DRAM), a Markov Chain Monte Carlo (MCMC) algorithm, to infer the location and intensity of an unknown source. The DRAM results yield a posterior probability distribution for the source's location conditioned on the observed detector count rates. The posterior distribution exhibits regions of high and low probability within the simulated environment identifying potential source locations. In this manner, we can quantify the source location to within at least one of these regions of high probability in the considered cases. Employing these methods, we are able to reduce the space of potential source locations by at least 60%.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗

EVOLUTION OF SOLAR PARAMETERS SINCE 1750 BASED ON A TRUNCATED DYNAMO MODEL

We use a truncated dynamo model and observations of the sunspot number to infer cycle-to-cycle variations of several dynamo parameters. A correlation study between model parameters and solar cycle observables (period, amplitude, and rising time) is done, and our results are compared with the results of other authors. Using the strongest correlations found, we determined a series of relationships that can be used for prediction purposes. This technique indicates that solar cycle 24 will have a sunspot maximum of approximately 84 around June of 2013. In the context of the used model, most of the variability found in the solar cycle can be attributed to changes in the strength of the meridional circulation. The results also point to a common origin for the source of variation of the meridional flow and differential rotation and/or the {alpha}-effect.

79 ASTRONOMY AND ASTROPHYSICS↗

Measuring the giant radio galaxy length distribution with the LoTSS

Many massive galaxies launch jets from the accretion disk of their central black hole, but only ~10 3 instances are known in which the associated outflows form giant radio galaxies (GRGs, or giants): luminous structures of megaparsec extent that consist of atomic nuclei, relativistic electrons, and magnetic fields. Large samples are imperative to understanding the enigmatic growth of giants, and recent systematic searches in homogeneous surveys constitute a promising development. For the first time, it is possible to perform meaningful precision statistics with GRG lengths, but a framework to do so is missing. We measured the intrinsic GRG length distribution by combining a novel statistical framework with a LOFAR Two-metre Sky Survey (LoTSS) sample of freshly discovered giants. In turn, this allowed us to answer an array of questions on giants. For example, we can now assess how rare a 5 Mpc giant is compared with one of 1 Mpc, and how much larger – given a projected length – the corresponding intrinsic length is expected to be. Notably, we can now also infer the GRG number density in the Local Universe. We assumed the intrinsic GRG length distribution to be Paretian (i.e. of power-law form) with tail index ξ, and predicted the observed distribution by modelling projection and selection effects. To infer ξ, we also systematically searched the LoTSS for hitherto unknown giants and compiled the largest catalogue of giants to date. We show that if intrinsic GRG lengths are Pareto distributed with index ξ, then projected GRG lengths are also Pareto distributed with index ξ. Selection effects induce curvature in the observed projected GRG length distribution: angular length selection flattens it towards the lower end, while surface brightness selection steepens it towards the higher end. We explicitly derived a GRG’s posterior over intrinsic lengths given its projected length, laying bare the ξ dependence. We also discovered 2060 giants within LoTSS DR2 pipeline products; our sample more than doubles the known population. Spectacular discoveries include the largest, second-largest, and fourth-largest GRG known (l p = 5.1 Mpc, l p = 5.0 Mpc, and l p = 4.8 Mpc), the largest GRG known hosted by a spiral galaxy (l p = 2.5 Mpc), and the largest secure GRG known beyond redshift 1 (l p = 3.9 Mpc). We increase the number of known giants whose angular length exceeds that of the Moon from 10 to 23; among the discoveries is the angularly largest known radio galaxy in the Northern Sky, which is also the angularly largest known GRG ($\phi$ = 2°). Combining theory and data, we determined that intrinsic GRG lengths are well described by a Pareto distribution, and measured the index ξ = –3.5 ± 0.5. This implies that, given its projected length, a GRG’s intrinsic length is expected to be just 15% larger. Finally, we determined the comoving number density of giants in the Local Universe to be n GRG = 5 ± 2(100 Mpc) –3 . We developed a practical mathematical framework that elucidates the statistics of giant radio galaxy lengths. Through a LoTSS search, we also discovered 2060 new giants. By combining both advances, we determined that intrinsic GRG lengths are well described by a Pareto distribution with index ξ = –3.5 ± 0.5, and that giants are truly rare in a cosmological sense: most clusters and filaments of the Cosmic Web are not currently home to a giant. Thus, our work yields new observational constraints for analytical models and simulations featuring radio galaxy growth.

79 ASTRONOMY AND ASTROPHYSICS↗

A Bayesian Approach to the Eagar–Tsai Model for Melt Pool Geometry Prediction with Implications in Additive Manufacturing of Metals

Here, this paper focuses on improving the melt pool geometry predictions and quantifying uncertainties using an adapted version of the Eagar–Tsai (E–T) model that incorporates temperature-dependent properties of the material as well as powder conditions. Additionally, Bayesian inference is employed to predict distributions for the E–T model input parameters of laser absorptivity and powder bed porosity by incorporating experimental results into the analysis. Monte Carlo uncertainty propagation is then used with these parameter distributions to estimate the melt pool depth and associated uncertainty. Our results for the 316L stainless steel suggest that both the absorptivity and powder bed porosity are strongly influenced by the laser power. In contrast, the scanning speed has only a marginal effect on both the absorptivity and powder bed porosity. We constructed a printability map using the Bayesian E–T model based on power-dependent input parameter values to demonstrate the merit of the approach. The Bayesian approach improved the accuracy in predicting the keyhole regions in the laser power-scan speed parameter space for the 316L stainless steel. Although applied to a specific adaptation of the E–T model, the method put forth can be extended to quantify uncertainties in other numerical models as well as in the estimation of unknown parameters.

316L Stainless Steel (SS).↗

SOLAR MODELS WITH NEW LOW METAL ABUNDANCES

In the past decade, the photospheric abundances of the Sun had been revised several times by many observers. The standard solar models constructed with the new low-metal abundances disagree with helioseismic results and detected neutrino fluxes. The solar model problem has puzzled some stellar physicists for more than 10 years. Rotation, enhanced diffusion, convection overshoot, and magnetic fields are used to reconcile the new abundances with helioseismology. The too low helium subsurface abundance in enhanced diffusion models can be improved by the mixing caused by rotation and magnetic fields. The problem of the depth of the convective zone in rotating models can be resolved by convection overshoot. Consequently, the Asplund–Grevesse–Sauval rotation model including overshooting (AGSR) reproduces the seismically inferred sound-speed and density profiles and the convection zone depth as well as the Grevesse and Sauval model computed before. But this model fails to reproduce the surface helium abundance, which is 0.2393 (2.6 σ away from the seismic value), and neutrino fluxes. The magnetic model called AGSM keeps the agreement of the AGSR and improves the prediction of the surface helium abundance. The observed separation ratios r {sub 02} and r {sub 13} are reasonably reproduced by AGSM. Moreover, neutrino fluxes calculated by this model are not far from the detected neutrino fluxes and the predictions of previous works.

79 ASTRONOMY AND ASTROPHYSICS↗