Search NASA⌕ Search

SEARCH · Search NASA

Results for “Network parameter error”

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 199 records · Page 11

Using neural network ensembles to separate ocean biogeochemical and physical drivers of phytoplankton biogeography in Earth system models

Abstract. Earth system models (ESMs) are useful tools for predicting and understanding past and future aspects of the climate system. However, the biological and physical parameters used in ESMs can have wide variations in their estimates. Even small changes in these parameters can yield unexpected results without a clear explanation of how a particular outcome was reached. The standard method for estimating ESM sensitivity is to compare spatiotemporal distributions of variables from different runs of a single ESM. However, a potential pitfall of this method is that ESM output could match observational patterns because of compensating errors. For example, if a model predicts overly weak upwelling and low nutrient concentrations, it might compensate for this by allowing phytoplankton to have a high sensitivity to nutrients. Recently, we demonstrated that neural network ensembles (NNEs) are capable of extracting relationships between predictor and target variables within ocean biogeochemical models. Being able to view the relationships between variables, along with spatiotemporal distributions, allows for a more mechanistically based examination of ESM outputs. Here, we investigated whether we could apply NNEs to help us determine why different ESMs produce different spatiotemporal distributions of phytoplankton biomass. We tested this using three cases. The first and second case used different runs of the same ESM, except that the physical circulations differed between them in the first case, while the biological equations differed between them in the second. Our results indicated that the NNEs were capable of extracting the relationships between variables for different runs of a single ESM, allowing us to distinguish between differences due to changes in circulation (which do not change relationships) from changes in biogeochemical formulation (which do change relationships). In the third case, we applied NNEs to two different ESMs. The results of the third case highlighted the capability of NNEs to contrast the apparent relationships of different ESMs and some of the challenges it presents. Although applied specifically to the ocean components of an ESM, our study demonstrates that Earth system modelers can use NNEs to separate the contributions of different components of ESMs. Specifically, this allows modelers to compare the apparent relationships across different ESMs and observational datasets.

54 ENVIRONMENTAL SCIENCES↗

Virtual sensing-enabled digital twin framework for real-time monitoring of nuclear systems leveraging deep neural operators

Abstract Real-time monitoring is a foundation of nuclear digital twin technology, crucial for detecting material degradation and maintaining nuclear system integrity. Traditional physical sensor systems face limitations, particularly in measuring critical parameters in hard-to-reach or harsh environments, often resulting in incomplete data coverage. Machine learning-driven virtual sensors offer a transformative solution by complementing physical sensors in monitoring critical degradation indicators. This paper introduces the use of Deep Operator Networks (DeepONet) to predict key thermal-hydraulic parameters in the hot leg of pressurized water reactor. DeepONet acts as a virtual sensor, mapping operational inputs to spatially distributed system behaviors without requiring frequent retraining. Our results show that DeepONet achieves low mean squared and Relative L2 error, making predictions 1400 times faster than traditional CFD simulations . These characteristics enable DeepONet to function as a real-time virtual sensor, synchronizing with the physical system to track degradation conditions and provide insights within the digital twin framework for nuclear systems.

Hossain, Raisa↗

Local primordial non-Gaussianity from the large-scale clustering of photometric DESI luminous red galaxies

ABSTRACT We use angular clustering of luminous red galaxies from the Dark Energy Spectroscopic Instrument (DESI) imaging surveys to constrain the local primordial non-Gaussianity parameter fNL. Our sample comprises over 12 million targets, covering 14 000 deg2 of the sky, with redshifts in the range 0.2 < z < 1.35. We identify Galactic extinction, survey depth, and astronomical seeing as the primary sources of systematic error, and employ linear regression and artificial neural networks to alleviate non-cosmological excess clustering on large scales. Our methods are tested against simulations with and without fNL and systematics, showing superior performance of the neural network treatment. The neural network with a set of nine imaging property maps passes our systematic null test criteria, and is chosen as the fiducial treatment. Assuming the universality relation, we find $f_{\rm NL} = 34^{+24(+50)}_{-44(-73)}$ at 68 per cent (95 per cent) confidence. We apply a series of robustness tests (e.g. cuts on imaging, declination, or scales used) that show consistency in the obtained constraints. We study how the regression method biases the measured angular power spectrum and degrades the fNL constraining power. The use of the nine maps more than doubles the uncertainty compared to using only the three primary maps in the regression. Our results thus motivate the development of more efficient methods that avoid overcorrection, protect large-scale clustering information, and preserve constraining power. Additionally, our results encourage further studies of fNL with DESI spectroscopic samples, where the inclusion of 3D clustering modes should help separate imaging systematics and lessen the degradation in the fNL uncertainty.

79 ASTRONOMY AND ASTROPHYSICS↗

MAGSAT data processing: A report for investigators

The in-flight attitude and vector magnetometer data bias recovery techniques and results are described. The attitude bias recoveries are based on comparisons with a magnetic field model and are thought to be accurate to 20 arcsec. The vector magnetometer bias recoveries are based on comparisons with the scalar magnetometer data and are thought to be accurate to 3 nT or better. The MAGSAT position accuracy goals of 60 m radially and 300 m horizontally were achieved for all but the last 3 weeks of Magsat lifetime. This claim is supported by ephemeris overlap statistics and by comparisons with ephemerides computed with an independent orbit program using data from an independent tracking network. MAGSAT time determination accuracy is estimated at 1 ms. Several errors in prelaunch assumptions regarding data time tags, which escaped detection in prelaunch data tests, and were discovered and corrected postlaunch are described. Data formats and products, especially the Investigator-B tapes, which contain auxiliary parameters in addition to the basic magnetometer and ephemeris data, are described.

Langel, R. A.↗

Documentation for the token ring network simulation system

A manual is presented which describes the language features of the Token Ring Network Simulation System. The simulation system is a powerful simulation tool for token ring networks which allows the specification of various Medium Access Control (MAC) layer protocols as well as the specification of various features of upper layer ISO protocols. In addition to these features, it also allows the user to specify message and station classes virtually to any degree of detail desired. The choice of a language instead of an interactive system to specify network parameters was dictated by both flexibility and time considerations. The language was developed specifically for the simulation system, and is very simple. It is also user friendly in that language elements which do not apply to the case at hand are ignored rather than treated as errors.

Peden, Jeffery H.↗

Estimating Parameters of Delaminations in GRP Pipes Using Thermal NDE and ANN

Thermographic Non-Destructive Evaluation (TNDE) is one of the techniques that have been widely used over the decades to evaluate the integrity of structures. To meet the increased demand for robust and effective inspection in complex TNDE tasks, Artificial Neural Networks (ANNs) have been recently deployed in many problems. The aim of the paper is to adopt an inverse technique using ANNs in the field of TNDE to estimate various parameters of delamination in Glass Reinforced Polymer (GRP) pipes by supplying thermal contrast evolution data as input. A Radial Basis Network (RBN) is employed with 80 input and 3 output neurons. The estimation capability of the network was evaluated with the data obtained from numerical simulations. The overall absolute errors show that the estimation capability of ANN is good.

42 ENGINEERING↗

Statistical structure of convective periods derived from satellite ground based data

The documentation of characteristics of Vertical Atmospheric Soundings (VAS) through the use of statistical structure and correlation functions is presented. A measure of random error is also provided. Rawinsonde data from various periods is analyzed. Structure and correlation functions are used to compare VAS retrievals obtained using a physical algorithm with those from a regression technique. Results from both procedures are evaluated against those from a mesoscale network of rawinsonde stations. The parameters documented include temperature, mixing ratio, geopotential height, thickness, and precipitable water. Calculation are performed at several layers in the lower and upper troposphere.

Meyer, P. J.↗

An Optimal-Estimation-Based Aerosol Retrieval Algorithm Using OMI Near-UV Observations

An optimal-estimation(OE)-based aerosol retrieval algorithm using the OMI (Ozone Monitoring Instrument) near-ultraviolet observation was developed in this study. The OE-based algorithm has the merit of providing useful estimates of errors simultaneously with the inversion products. Furthermore, instead of using the traditional lookup tables for inversion, it performs online radiative transfer calculations with the VLIDORT (linearized pseudo-spherical vector discrete ordinate radiative transfer code) to eliminate interpolation errors and improve stability. The measurements and inversion products of the Distributed Regional Aerosol Gridded Observation Network campaign in northeast Asia (DRAGON NE-Asia 2012) were used to validate the retrieved aerosol optical thickness (AOT) and single scattering albedo (SSA). The retrieved AOT and SSA at 388 nm have a correlation with the Aerosol Robotic Network (AERONET) products that is comparable to or better than the correlation with the operational product during the campaign. The OEbased estimated error represented the variance of actual biases of AOT at 388 nm between the retrieval and AERONET measurements better than the operational error estimates. The forward model parameter errors were analyzed separately for both AOT and SSA retrievals. The surface reflectance at 388 nm, the imaginary part of the refractive index at 354 nm, and the number fine-mode fraction (FMF) were found to be the most important parameters affecting the retrieval accuracy of AOT, while FMF was the most important parameter for the SSA retrieval. The additional information provided with the retrievals, including the estimated error and degrees of freedom, is expected to be valuable for relevant studies. Detailed advantages of using the OE method were described and discussed in this paper.

Air Pollution↗

Dynamic Performance Enhancement for Nonlinear Stochastic Systems Using RBF Driven Nonlinear Compensation with Extended Kalman Filter

In this paper, a novel hybrid control method is proposed to enhance the control performance of the PI based control system for a class of nonlinear and non-Gaussian stochastic dynamic processes with unmeasurable states. Firstly, to enhance the tracking performance of the PI controller where the PI parameters are fixed in many actual control systems, the compensative signal is formed using the extended Kalman filter(EKF) based state estimator and driven by the radial basis function (RBF) neural network based compensator. In addition, the weights of RBF is trained to minimize the entropy criterion of tracking error as the process is subjected to non-Gaussian disturbances. Meanwhile, since the precise statistical property of noises is hard to obtain for many industrial processes, the kernel density estimation (KDE) technique is employed in this paper to estimate the entropy. The convergence of RBF network is discussed and the stability of the resulted closed-loop hybrid control system is analyzed in mean square sense. Finally, a numerical example and a practical system testing are given to illustrate the effectiveness of the proposed control method.

stochastic systems, PI Controller, Entropy, Extend↗

Adaptive hyperparameter updating for training restricted Boltzmann machines on quantum annealers

Restricted Boltzmann Machines (RBMs) have been proposed for developing neural networks for a variety of unsupervised machine learning applications such as image recognition, drug discovery, and materials design. The Boltzmann probability distribution is used as a model to identify network parameters by optimizing the likelihood of predicting an output given hidden states trained on available data. Training such networks often requires sampling over a large probability space that must be approximated during gradient based optimization. Quantum annealing has been proposed as a means to search this space more efficiently which has been experimentally investigated on D-Wave hardware. D-Wave implementation requires selection of an effective inverse temperature or hyperparameter (β) within the Boltzmann distribution which can strongly influence optimization. Here, we show how this parameter can be estimated as a hyperparameter applied to D-Wave hardware during neural network training by maximizing the likelihood or minimizing the Shannon entropy. We find both methods improve training RBMs based upon D-Wave hardware experimental validation on an image recognition problem. Neural network image reconstruction errors are evaluated using Bayesian uncertainty analysis which illustrate more than an order magnitude lower image reconstruction error using the maximum likelihood over manually optimizing the hyperparameter. The maximum likelihood method is also shown to out-perform minimizing the Shannon entropy for image reconstruction.

97 MATHEMATICS AND COMPUTING↗

Monitoring global geodynamical parameter variations with GPS and low earth satellites

A low earth satellite enhances global geodynamical parameters determination with GPS in two ways. First, it improves the GPS orbits, which in turn improve the estimates of other parameters. Secondly, a low earth satellite completes an orbit cycle in far shorter time (90 to 120 minutes) than do GPS satellites (12 hours); it observes more GPS satellites than a ground receiver does in shorter time and increases the correlation between GPS orbit errors. This reduces the error in the determination of nonrotational coordinate parameters, i.e., geocentric offset of ground tracking sites. Covariance results with the global geodynamical parameters modeled as constants, and as random-walk parameters to closer reflect the actual variations, are compared. The effects of using different GPS data quality and different ground tracking network are studied. The case of using two earth satellites in orthogonal orbital planes is also investigated.

Wu, S. C.↗

The Prospect for Remote Sensing of Cirrus Clouds with a Submillimeter-Wave Spectrometer

Given the substantial radiative effects of cirrus clouds and the need to validate cirrus cloud mass in climate models, it is important to measure the global distribution of cirrus properties with satellite remote sensing. Existing cirrus remote sensing techniques, such as solar reflectance methods, measure cirrus ice water path (IWP) rather indirectly and with limited accuracy. Submillimeter/wave radiometry is an independent method of cirrus remote sensing based on ice particles scattering the upwelling radiance emitted by the lower atmosphere. A new aircraft instrument, the Far Infrared Sensor for Cirrus (FIRSC), is described. The FIRSC employs a Fourier Transform Spectrometer (FTS). which measures the upwelling radiance across the whole submillimeter region (0.1 1.0-mm wavelength). This wide spectral coverage gives high sensitivity to most cirrus particle sizes and allows accurate determination of the characteristic particle size. Radiative transfer modeling is performed to analyze the capabilities of the submillimeter FTS technique. A linear inversion analysis is done to show that cirrus IWP, particle size, and upper-tropospheric temperature and water vapor may be accurately measured, A nonlinear statistical algorithm is developed using a database of 20000 spectra simulated by randomly varying most relevant cirrus and atmospheric parameters. An empirical orthogonal function analysis reduces the 500-point spectrum (20 - 70/cm) to 15 "pseudo-channels" that are then input to a neural network to retrieve cirrus IWP and median particle diameter. A Monte Carlo accuracy study is performed with simulated spectra having realistic noise. The retrieval errors are low for IWP (rms less than a factor of 1.5) and for particle sizes (rins less than 30%) for IWP greater than 5 g/sq m and a wide range of median particle sizes. This detailed modeling indicates that there is good potential to accurately measure cirrus properties with a submillimeter FTS.

Evans, K. Franklin↗

UAV Trajectory Modeling Using Neural Networks

Massive small unmanned aerial vehicles are envisioned to operate in the near future. While there are lots of research problems need to be addressed before dense operations can happen, trajectory modeling remains as one of the keys to understand and develop policies, regulations, and requirements for safe and efficient unmanned aerial vehicle operations. The fidelity requirement of a small unmanned vehicle trajectory model is high because these vehicles are sensitive to winds due to their small size and low operational altitude. Both vehicle control systems and dynamic models are needed for trajectory modeling, which makes the modeling a great challenge, especially considering the fact that manufactures are not willing to share their control systems. This work proposed to use a neural network approach for modelling small unmanned vehicle's trajectory without knowing its control system and bypassing exhaustive efforts for aerodynamic parameter identification. As a proof of concept, instead of collecting data from flight tests, this work used the trajectory data generated by a mathematical vehicle model for training and testing the neural network. The results showed great promise because the trained neural network can predict 4D trajectories accurately, and prediction errors were less than 2:0 meters in both temporal and spatial dimensions.

Neural Networks↗

The Ground Flash Fraction Retrieval Algorithm Employing Differential Evolution: Simulations and Applications

The ability to estimate the fraction of ground flashes in a set of flashes observed by a satellite lightning imager, such as the future GOES-R Geostationary Lightning Mapper (GLM), would likely improve operational and scientific applications (e.g., severe weather warnings, lightning nitrogen oxides studies, and global electric circuit analyses). A Bayesian inversion method, called the Ground Flash Fraction Retrieval Algorithm (GoFFRA), was recently developed for estimating the ground flash fraction. The method uses a constrained mixed exponential distribution model to describe a particular lightning optical measurement called the Maximum Group Area (MGA). To obtain the optimum model parameters (one of which is the desired ground flash fraction), a scalar function must be minimized. This minimization is difficult because of two problems: (1) Label Switching (LS), and (2) Parameter Identity Theft (PIT). The LS problem is well known in the literature on mixed exponential distributions, and the PIT problem was discovered in this study. Each problem occurs when one allows the numerical minimizer to freely roam through the parameter search space; this allows certain solution parameters to interchange roles which leads to fundamental ambiguities, and solution error. A major accomplishment of this study is that we have employed a state-of-the-art genetic-based global optimization algorithm called Differential Evolution (DE) that constrains the parameter search in such a way as to remove both the LS and PIT problems. To test the performance of the GoFFRA when DE is employed, we applied it to analyze simulated MGA datasets that we generated from known mixed exponential distributions. Moreover, we evaluated the GoFFRA/DE method by applying it to analyze actual MGAs derived from low-Earth orbiting lightning imaging sensor data; the actual MGA data were classified as either ground or cloud flash MGAs using National Lightning Detection Network[TM] (NLDN) data. Solution error plots are provided for both the simulations and actual data analyses.

Koshak, William↗

Digital Twin Framework for PIP-II Linac: AI-Driven Multi-Scale Modeling from Ion Source to 800 MeV

The PIP-II linac will enable >1.2 MW beam power for DUNE, requiring unprecedented operational reliability across its warm front-end (RFQ, MEBT) and five distinct SRF sections operating at 162.5/325/650 MHz. We present a comprehensive digital twin framework uniquely combining a fully differentiable fast beam transport code with neural network surrogates trained on high-fidelity PIC simulations, capturing space charge and nonlinear dynamics beyond traditional envelope codes while achieving 10⁴ speedup at <1% accuracy. End-to-end differentiability enables gradient-based optimization across 500+ parameters simultaneously previously impossible with conventional tools while the model incorporates static/dynamic errors and serves as a virtual commissioning platform for diverse hardware integration. The framework facilitates reinforcement learning for pulsed/CW mode transitions, predictive maintenance through anomaly detection, and autonomous tuning algorithm development with real-time execution capability. Validation against physics simulations shows excellent agreement for the front-end, with initial results demonstrating potential for 30% commissioning time reduction and proactive fault mitigation, providing a scalable blueprint for operating next-generation high-intensity accelerators.

Pathak, Abhishek [Fermilab] (ORCID:000000021704208↗

Digital Twin Framework for PIP-II Linac: AI-Driven Multi-Scale Modeling from Ion Source to 800 MeV

The PIP-II linac will enable >1.2 MW beam power for DUNE, requiring unprecedented operational reliability across its warm front-end (RFQ, MEBT) and five distinct SRF sections operating at 162.5/325/650 MHz. We present a comprehensive digital twin framework uniquely combining a fully differentiable fast beam transport code with neural network surrogates trained on high-fidelity PIC simulations, capturing space charge and nonlinear dynamics beyond traditional envelope codes while achieving 10⁴× speedup at <1% accuracy. End-to-end differentiability enables gradient-based optimization across 500+ parameters simultaneously—previously impossible with conventional tools—while the model incorporates static/dynamic errors and serves as a virtual commissioning platform for diverse hardware integration. The framework facilitates reinforcement learning for pulsed/CW mode transitions, predictive maintenance through anomaly detection, and autonomous tuning algorithm development with real-time execution capability. Validation against physics simulations shows excellent agreement for the front-end, with initial results demonstrating potential for 30% commissioning time reduction and proactive fault mitigation, providing a scalable blueprint for operating next-generation high-intensity accelerators.

Pathak, Abhishek [Fermilab] (ORCID:000000021704208↗

A Measurement‐Model Fusion Approach for Improved Wet Deposition Maps and Trends

Abstract Air quality models provide spatial fields of wet deposition (WD) and dry deposition that explicitly account for the transport and transformation of emissions from thousands of sources. However, many sources of uncertainty in the air quality model including errors in emissions and meteorological inputs (particularly precipitation) and incomplete descriptions of the chemical and physical processes governing deposition can lead to bias and error in the simulation of WD. We present an approach to bias correct Community Multiscale Air Quality model output over the contiguous United States using observation‐based gridded precipitation data generated by the Parameter‐elevation Regressions on Independent Slopes Model and WD observations at the National Atmospheric Deposition Program National Trends Network sites. A cross‐validation analysis shows that the adjusted annual accumulated WD for NO 3 − , NH 4 + , and SO 4 2− from 2002 to 2012 has less bias and higher correlation with observed values than the base model output without adjustment. Temporal trends in observed WD are captured well by the adjusted model simulations across the entire contiguous United States. Consistent with previous trend analyses, WD NO 3 − and SO 4 2− are shown to decrease during this period in the eastern half of the United States, particularly in the Northeast, while remaining nearly constant in the West. Trends in WD of NH 4 + are more spatially and temporally heterogeneous, with some positive trends in the Great Plains and Central Valley of CA and slightly negative trends in the south.

54 ENVIRONMENTAL SCIENCES↗