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 469 records · Page 26

The Effect of Geocenter Motion on Jason-2 Orbits and the Mean Sea Level

We compute a series of Jason-2 GPS and SLR/DORIS-based orbits using ITRF2005 and the std0905 standards (Lemoine et al. 2010). Our GPS and SLR/DORIS orbit data sets span a period of 2 years from cycle 3 (July 2008) to cycle 74 (July 2010). We extract the Jason-2 orbit frame translational parameters per cycle by the means of a Helmert transformation between a set of reference orbits and a set of test orbits. We compare the annual terms of these time-series to the annual terms of two different geocenter motion models where biases and trends have been removed. Subsequently, we include the annual terms of the modeled geocenter motion as a degree-1 loading displacement correction to the GPS and SLR/DORIS tracking network of the POD process. Although the annual geocenter motion correction would reflect a stationary signal in time, under ideal conditions, the whole geocenter motion is a non-stationary process that includes secular trends. Our results suggest that our GSFC Jason-2 GPS-based orbits are closely tied to the center of mass (CM) of the Earth consistent with our current force modeling, whereas GSFC's SLR/DORIS-based orbits are tied to the origin of ITRF2005, which is the center of figure (CF) for sub-secular scales. We quantify the GPS and SLR/DORIS orbit centering and how this impacts the orbit radial error over the globe, which is assimilated into mean sea level (MSL) error, from the omission of the annual term of the geocenter correction. We find that for the SLR/DORIS std0905 orbits, currently used by the oceanographic community, only the negligence of the annual term of the geocenter motion correction results in a 4.67 plus or minus 3.40 mm error in the Z-component of the orbit frame which creates 1.06 plus or minus 2.66 mm of systematic error in the MSL estimates, mainly due to the uneven distribution of the oceans between the North and South hemisphere.

Melachroinos, S. A.↗

Accelerating massively parallel hemodynamic models of coarctation of the aorta using neural networks

Comorbidities such as anemia or hypertension and physiological factors related to exertion can influence a patient’s hemodynamics and increase the severity of many cardiovascular diseases. Observing and quantifying associations between these factors and hemodynamics can be difficult due to the multitude of co-existing conditions and blood flow parameters in real patient data. Machine learning-driven, physics-based simulations provide a means to understand how potentially correlated conditions may affect a particular patient. Here, we use a combination of machine learning and massively parallel computing to predict the effects of physiological factors on hemodynamics in patients with coarctation of the aorta. We first validated blood flow simulations against in vitro measurements in 3D-printed phantoms representing the patient’s vasculature. We then investigated the effects of varying the degree of stenosis, blood flow rate, and viscosity on two diagnostic metrics – pressure gradient across the stenosis (ΔP) and wall shear stress (WSS) - by performing the largest simulation study to date of coarctation of the aorta (over 70 million compute hours). Using machine learning models trained on data from the simulations and validated on two independent datasets, we developed a framework to identify the minimal training set required to build a predictive model on a per-patient basis. We then used this model to accurately predict ΔP (mean absolute error within 1.18 mmHg) and WSS (mean absolute error within 0.99 Pa) for patients with this disease.

59 BASIC BIOLOGICAL SCIENCES↗

Surface daytime net radiation estimation using artificial neural networks

Net all-wave surface radiation (R n ) is one of the most important fundamental parameters in various applications. However, conventional R n measurements are difficult to collect because of the high cost and ongoing maintenance of recording instruments. Therefore, various empirical R n estimation models have been developed. This study presents the results of two artificial neural network (ANN) models (general regression neural networks (GRNN) and Neuroet) to estimate R n globally from multi-source data, including remotely sensed products, surface measurements, and meteorological reanalysis products. R n estimates provided by the two ANNs were tested against in-situ radiation measurements obtained from 251 global sites between 1991–2010 both in global mode (all data were used to fit the models) and in conditional mode (the data were divided into four subsets and the models were fitted separately). Based on the results obtained from extensive experiments, it has been proved that the two ANNs were superior to linear-based empirical models in both global and conditional modes and that the GRNN performed better and was more stable than Neuroet. The GRNN estimates had a determination coefficient (R 2 ) of 0.92, a root mean square error (RMSE) of 34.27 W·m –2 , and a bias of –0.61 W·m –2 in global mode based on the validation dataset. In conclusion, ANN methods are a potentially powerful tool for global R n estimation.

14 SOLAR ENERGY↗

Determination of GPS orbits to submeter accuracy

Orbits for satellites of the Global Positioning System (GPS) were determined with submeter accuracy. Tests used to assess orbital accuracy include orbit comparisons from independent data sets, orbit prediction, ground baseline determination, and formal errors. One satellite tracked 8 hours each day shows rms error below 1 m even when predicted more than 3 days outside of a 1-week data arc. Differential tracking of the GPS satellites in high Earth orbit provides a powerful relative positioning capability, even when a relatively small continental U.S. fiducial tracking network is used with less than one-third of the full GPS constellation. To demonstrate this capability, baselines of up to 2000 km in North America were also determined with the GPS orbits. The 2000 km baselines show rms daily repeatability of 0.3 to 2 parts in 10 to the 8th power and agree with very long base interferometry (VLBI) solutions at the level of 1.5 parts in 10 to the 8th power. This GPS demonstration provides an opportunity to test different techniques for high-accuracy orbit determination for high Earth orbiters. The best GPS orbit strategies included data arcs of at least 1 week, process noise models for tropospheric fluctuations, estimation of GPS solar pressure coefficients, and combine processing of GPS carrier phase and pseudorange data. For data arc of 2 weeks, constrained process noise models for GPS dynamic parameters significantly improved the situation.

Bertiger, W. I.↗

Comment on"Sensitivity of the active fracture model parameter to fracture network orientation and injection scenarios" by Basagaoglu et al. (2009)

Basagaoglu et al. (2009) present a study on detailed unsaturated flow behavior in two-dimensional fracture networks using numerical experiments (simulations) based on the lattice-Boltzmann method. Their results are valuable for improving our understanding of unsaturated flow processes and evaluating the active fracture model (AFM) that was developed for capturing large-scale preferential flow in fractured rocks (Liu et al., 1998; 2003). As indicated in Basagaoglu et al. (2009), a previous study was conducted to evaluate the AFM with numerical experiments (Seol et al., 2003). However, the methodology used in that study and the corresponding conclusions are highly questioned for the following two reasons. First, the evaluation relies on a condition that simulated water flow processes in a fracture network are adequately represented with a continuum approach, because they draw their conclusions by comparing simulation results with those obtained from a dual-continuum model based on the AFM. No effort was made by Seol et al. (2003) to justify the validity of the continuum approach for their specific fracture network that includes a small number of fractures only. (The analyses of Basagaoglu et al. (2009) do not need the similar condition.) Second, Seol et al. (2003) use numerical dispersion to represent the matrix diffusion process. This treatment is not valid simply because numerical dispersion results from numerical errors and is not a physical process.

54 ENVIRONMENTAL SCIENCES↗

Fast and accurate reduced-order modeling of a MOOSE-based additive manufacturing model with operator learning

One predominant challenge in additive manufacturing (AM) is to achieve specific material properties by manipulating manufacturing process parameters during the runtime. Such manipulation tends to increase the computational load imposed on existing simulation tools employed in AM. The goal of the present work is to construct a fast and accurate reduced-order model (ROM) for an AM model developed within the Multiphysics Object-Oriented Simulation Environment (MOOSE) framework, ultimately reducing the time/cost of AM control and optimization processes. Our adoption of the operator learning (OL) approach enabled us to learn a family of differential equations produced by altering process variables in the laser’s Gaussian point heat source. More specifically, we used the Fourier neural operator (FNO) and deep operator network (DeepONet) to develop ROMs for time-dependent responses. Furthermore, we benchmarked the performance of these OL methods against a conventional deep neural network (DNN)-based ROM. Ultimately, we found that OL methods offer comparable performance and, in terms of accuracy and generalizability, even outperform DNN at predicting scalar model responses. The DNN-based ROM afforded the fastest training time. Furthermore, all the ROMs were faster than the original MOOSE model yet still provided accurate predictions. FNO had a smaller mean prediction error than DeepONet, with a larger variance for time-dependent responses. Unlike DNN, both FNO and DeepONet were able to simulate time series data without the need for dimensionality reduction techniques. Finally, the present work can help facilitate the AM optimization process by enabling faster execution of simulation tools while still preserving evaluation accuracy.

36 MATERIALS SCIENCE↗

Current Limitations on VLBI Accuracy

The contribution of VLBI to geophysics and geodesy arises from its ability to measure distances between stations in a network and to determine the orientation of stations in the network as well as the orientation of the network with respect to the external reference frame of extragalactic radio objects. Integrating nearly two decades of observations provides useful information about station positions and velocities and the orientation of the Earth, but the complications of the real world and the limitations of observing, modeling and analysis prevent recovery of all effects. Of the factors that limit the accuracy of seemingly straightforward geodetic parameters, the neutral propagation medium has been subject to the greatest scrutiny, but the treatment of the mapping function, the wet component and spatial/temporal inhomogeneities is still improving. These affect both the terrestrial scale and consistency over time. The modeling of non-secular site motions (tides and loading) has increased in sophistication, but there are some differences between the models and the observations. VLBI antennas are massive objects, so their behavior is quite unlike GPS monuments, but antenna deformations add some (generally) unmodeled signal. Radio sources used in geodetic VLBI observations are selected for strength and (relative) absence of structure, but apparent changes in position can leak into geodetic parameters. A linear rate of change of baseline or site parameters is the simplest model and its error improves with time span. However, in most cases the VLBI data distribution is insufficient to look for real non-linear behavior that might affect the average rate. A few sites have multiple VLBI antennas, and some show small differences in rate. VLBI intrinsically measures relative positions and velocities, but individual site positions and velocities are generally more useful. The creation of the VLBI terrestrial reference frame, which transforms relative information into individual results, is an empirical process that has intrinsic errors. While UT1 is uniquely measured by VLBI, the geographical distribution and availability of VLBI stations, especially in the southern hemisphere, and the consistency of the VLBI terrestrial reference frame may limit the accuracy of Earth orientation measurements. The effects of particular error sources on geodetic and geophysical parameters derived from VLBI data will be illustrated.

Ma, Chopo↗

Knowledge-based prediction of three-dimensional dose distributions for external beam radiotherapy

Purpose: To demonstrate knowledge-based 3D dose prediction for external beam radiotherapy. Methods: Using previously treated plans as training data, an artificial neural network (ANN) was trained to predict a dose matrix based on patient-specific geometric and planning parameters, such as the closest distance (r) to planning target volume (PTV) and organ-at-risks (OARs). Twenty-three prostate and 43 stereotactic radiosurgery/radiotherapy (SRS/SRT) cases with at least one nearby OAR were studied. All were planned with volumetric-modulated arc therapy to prescription doses of 81 Gy for prostate and 12–30 Gy for SRS. Using these clinically approved plans, ANNs were trained to predict dose matrix and the predictive accuracy was evaluated using the dose difference between the clinical plan and prediction, δD = D{sub clin} − D{sub pred}. The mean (〈δD{sub r}〉), standard deviation (σ{sub δD{sub r}}), and their interquartile range (IQR) for the training plans were evaluated at a 2–3 mm interval from the PTV boundary (r{sub PTV}) to assess prediction bias and precision. Initially, unfiltered models which were trained using all plans in the cohorts were created for each treatment site. The models predict approximately the average quality of OAR sparing. Emphasizing a subset of plans that exhibited superior to the average OAR sparing during training, refined models were created to predict high-quality rectum sparing for prostate and brainstem sparing for SRS. Using the refined model, potentially suboptimal plans were identified where the model predicted further sparing of the OARs was achievable. Replans were performed to test if the OAR sparing could be improved as predicted by the model. Results: The refined models demonstrated highly accurate dose distribution prediction. For prostate cases, the average prediction bias for all voxels irrespective of organ delineation ranged from −1% to 0% with maximum IQR of 3% over r{sub PTV} ∈ [ − 6, 30] mm. The average prediction error was less than 10% for the same r{sub PTV} range. For SRS cases, the average prediction bias ranged from −0.7% to 1.5% with maximum IQR of 5% over r{sub PTV} ∈ [ − 4, 32] mm. The average prediction error was less than 8%. Four potentially suboptimal plans were identified for each site and subsequent replanning demonstrated improved sparing of rectum and brainstem. Conclusions: The study demonstrates highly accurate knowledge-based 3D dose predictions for radiotherapy plans.

61 RADIATION PROTECTION AND DOSIMETRY↗

AutoSourceID-Classifier: Star-galaxy classification using a convolutional neural network with spatial information

Aims.Traditional star-galaxy classification techniques often rely on feature estimation from catalogs, a process susceptible to introducing inaccuracies, thereby potentially jeopardizing the classification’s reliability. Certain galaxies, especially those not manifesting as extended sources, can be misclassified when their shape parameters and flux solely drive the inference. We aim to create a robust and accurate classification network for identifying stars and galaxies directly from astronomical images. Methods.The AutoSourceID-Classifier (ASID-C) algorithm developed for this work uses 32x32 pixel single filter band source cutouts generated by the previously developed AutoSourceID-Light (ASID-L) code. By leveraging convolutional neural networks (CNN) and additional information about the source position within the full-field image, ASID-C aims to accurately classify all stars and galaxies within a survey. Subsequently, we employed a modified Platt scaling calibration for the output of the CNN, ensuring that the derived probabilities were effectively calibrated, delivering precise and reliable results. Results.We show that ASID-C, trained on MeerLICHT telescope images and using the Dark Energy Camera Legacy Survey (DECaLS) morphological classification, is a robust classifier and outperforms similar codes such as SourceExtractor. To facilitate a rigorous comparison, we also trained an eXtreme Gradient Boosting (XGBoost) model on tabular features extracted by SourceExtractor. While this XGBoost model approaches ASID-C in performance metrics, it does not offer the computational efficiency and reduced error propagation inherent in ASID-C’s direct image-based classification approach. ASID-C excels in low signal-to-noise ratio and crowded scenarios, potentially aiding in transient host identification and advancing deep-sky astronomy.

Astronomy & Astrophysics↗

Satellite Data Sets in the Polar Regions

We have generated about two decades of consistently derived geophysical parameters in the polar regions. The key parameters are sea ice concentration, surface temperature, albedo, and cloud cover statistics. Sea ice concentrations were derived from the Scanning Multichannel Microwave Radiometer (SMMR) data and the Special Scanning Cl Microwave Imager (SSM/I) data from several platforms using the enhanced Bootstrap Algorithm for the period 1978 through 1999. The new algorithm reduces the errors associated with spatial and temporal variations in the emissivity and surface temperatures of sea ice. Also, bad data at ocean/land interfaces are identified and deleted in an unsupervised manner. Surface ice temperature, albedo and cloud cover statistics are derived simultaneously from the Advanced Very High Resolution Radiometer (AVHRR) data from 1981 through 1999 and mapped at a higher resolution but the same format as the ice concentration data. The technique makes use these co-registered ice concentration maps to enable cloud masking to be done separately for open ocean, sea ice and land areas. The effect of inversion is minimized by taking into consideration the expected changes in the effect of inversion with altitude, especially in the Antarctic. A technique for ice type regional classification has also been developed using multichannel cluster analysis and a neural network. This provide a means to identify large areas of thin ice, first year ice, and older ice types. The data sets have been shown to be coherent with each other and provide a powerful tool for in depth studies of the currently changing Arctic and Antarctic environment.

Comiso, Josefino C.↗

Characterizing particle-scale equilibrium adsorption and kinetics of uranium(VI) desorption from U-contaminated sediments

Rates of contaminant U(VI) release from individual size fractions of a composite sediment from the seasonally saturated lower vadose zone of the Hanford 300-Area were examined in flow-through batch reactors to maintain quasi-constant chemical conditions. Variability in equilibrium adsorption among the various size fractions was determined in static batch reactors and analyzed using the surface complexation modeling approach. The estimated stoichiometric coefficients of U(VI) surface complexation reactions with respect to pH and carbonate concentrations varied with size fractions. This source of variability significantly increased the uncertainty in U(VI) conditional equilibrium constants over that estimated from experimental errors alone. A minimum difference between conditional equilibrium constants was established in order to evaluate statistically significant differences between sediment adsorption properties. A set of equilibrium and kinetic expressions for cation exchange, calcite dissolution, aerobic respiration, and silica dissolution were incorporated in a reaction-rate model to describe the temporal evolution of solute concentrations observed during the flow-through batch experiments. Parameters in the reaction-rate model, calibrated using experimental data for select size fractions, predicted the changes in solute concentrations for the bulk, <2 mm, sediment sample. Kinetic U(VI) desorption was well described using a multi-rate surface complexation model with an assumed lognormal distribution for the rate constants. The estimated mean and standard deviation were the same for all < 2mm size fractions, but differed in the 2-8mm size fraction. Micropore volumes in the varied size fractions were also similar as assessed using t-plots to analyze N2 desorption data. These findings provide further support for the link between microporosity and particle-scale mass transfer rates controlling kinetic U(VI) adsorption/desorption and for the utility of N2 desorption isotherms for characterizing pore networks that influence mass transfer rates.

Stoliker, Deborah L.↗

Deep Moonquake Focal Mechanisms: Recovery and Implications

A defining characteristic of deep moonquakes is their tendency to occur with tidal periodicity, prompting previous studies to infer that they are related to the buildup and release of tidal stress within the Moon. In studies of tidal forcing, a key constraint is the focal mechanism: the fault parameters describing the type of failure moonquakes represent. The quality of the lunar seismic data and the limited source/receiver geometries of the Apollo seismic network prohibit the determination of deep moonquake fault parameters using first-motion polarities, as is typically done in terrestrial seismology. Without being able to resolve tidal stress onto a known failure plane, we can examine only gross qualities of the tidal stress tensor with respect to moonquake occurrence, so we cannot fully address the role of tidal stress in moonquake generation. We will examine the extent to which shear (S) and compression (P) wave amplitude ratios can constrain moonquake fault geometry by determining whether, for a given cluster, there exists a focal mechanism that can produce a radiation pattern consistent with the amplitudes measured by the Apollo instruments. Amplitudes are read in the ray coordinate frame, directly from seismograms for which the P and S arrivals are clearly identifiable on all long-period channels of the four Apollo stations. We apply an empirical station correction to account for site effects and the differences between P- and S-wave attenuation. Instead of focusing on the best fitting solution only, we formulate the inverse problem using a falsification criterion: all source orientations that do not reproduce the observed SV/P ratios within an error margin derived from the uncertainty of amplitude readings are rejected. All others are accepted as possible solutions. The inversion is carried out using an exhaustive grid search on a regular grid with predefined step size, encompassing all possible combinations of strike, dip and slip. To assess the sensitivity of the inversion for the uncertainty of the lunar interior structure, we carry out repeated inversions with different velocity structures. Our data set consist of a total of 106 events from 25 deep moonquake clusters. The largest contribution of 37 events originates from the most active cluster, A001, while other clusters are represented by 1 to 9 events. Since the definition of a cluster implies that all events share the same source orientation, a comparison of the inversion results of all events from one cluster will reduce ambiguities of the inversion. Once we obtain a suite of fault parameters for a given source, we can attempt to further constrain the focal mechanism with refined analyses of tidal stresses and predictions based on synthetic seismograms.

Knapmeyer, Martin↗

Benefits of Ka-band GaN MMIC High Power Amplifiers With Wide Bandwidth and High Spectral/Power Added Efficiencies for Cognitive Radio Platforms

A cognitive radio on a future NASA near-Earth spacecraft will be capable of sensing its environment and dynamically adapting its operating parameters to provide the desired SATCOM service to the mission. A key component that can enable this type of operation is a high-power amplifier (HPA) that resides on the radio platform. In this paper, we present the RF performance characteristics of a Ka-band gallium nitride (GaN) monolithic microwave integrated circuit (MMIC) based HPA for cognitive radio platforms. These characteristics include the output power, gain, power added efficiency (PAE), RMS error vector magnitude (EVM), spectral efficiency, 3rd-order intermodulation distortion (IMD) products, spectrum, spectral regrowth, noise figure (NF), and phase noise. The data presented indicates that the HPA meets NTIA, military, and commercial spectral mask requirements. In addition, we discuss the benefits offered by the above performance characteristics toward the design and implementation of a cognitive radio platform. Furthermore, as examples, we discuss three potential use cases that apply artificial intelligence (AI) and machine learning (ML) techniques and exploit the performance characteristics discussed above to provide a knowledge-based cognitive radio platform design for SATCOM. Thus, cognitive radios with performance flexibility can enable roaming and provide seamless interoperability autonomously in the future between NASA, commercial, and other space networks owned by U.S. government agencies.

Gallium nitride↗

Benefits of Ka-band GaN MMIC High Power Amplifiers With Wide Bandwidth and High Spectral/Power Added Efficiencies for Cognitive Radio Platforms

A cognitive radio on a future NASA near-Earth spacecraft will be capable of sensing its environment and dynamically adapting its operating parameters to provide the desired SATCOM service to the mission. A key component that can enable this type of operation is a high-power amplifier (HPA) that resides on the radio platform. In this report, we present the RF performance characteristics of a Ka-band gallium nitride (GaN) monolithic microwave integrated circuit (MMIC) based HPA for cognitive radio platforms. These characteristics include the output power, gain, power added efficiency (PAE), RMS error vector magnitude (EVM), spectral efficiency, 3rdorder intermodulation distortion (IMD) products, spectrum, spectral regrowth, noise figure (NF), phase noise, and group delay. The data presented indicates that the HPA meets NTIA, military, and commercial spectral mask requirements. In addition, we discuss the benefits offered by the above performance characteristics toward the design and implementation of a cognitive radio platform. Furthermore, as examples, we discuss three potential use cases that apply artificial intelligence (AI) and machine learning (ML) techniques and exploit the performance characteristics discussed above to provide a knowledge-based cognitive radio platform design for SATCOM. Thus, cognitive radios with performance flexibility can enable roaming and provide seamless interoperability autonomously in the future between NASA, commercial, and other space networks owned by U.S. government agencies.

Gallium nitride↗

Attention-based 3D – convolutional neural network model for mechanical property predictions using visible light images in metal additive manufacturing

Additive manufacturing (AM), while commonly used for rapid prototyping and creating components with complex geometries, has not been widely adopted for critical applications across the aerospace, automotive, defense, energy, and medical industries. This is, in part, due to the challenges of controlling flaws and uncertainty in the mechanical behavior of additively manufactured components. In recent years, there has been an increase in research aimed at predicting the final mechanical properties of additively manufactured components during the printing process. To address these issues, a 3D-CNN model was trained using low-cost in situ visible-light camera data, anomaly classifications, and the chosen process parameters to predict the ultimate tensile strength (UTS), yield strength (YS), total elongation (TE), and uniform elongation (UE). The 3D-CNN layers of the model employed attention mechanisms to prioritize features in the data, thereby improving prediction accuracy. Furthermore, the effect of each process parameter and anomaly class is investigated using attention-based dynamic sigmoid weighted gates to interpret the influence each class has on the final prediction. Different combinations of the in situ data were fed into the 3D-CNN, with varying amounts of image layers, to determine the ideal combination for predicting mechanical properties in situ. Here, the 3D-CNN model achieved mean absolute percentage errors (MAPE) below 5% for both UTS and YS while using only a single camera input and under half of the available image layers.

36 MATERIALS SCIENCE↗

Deep Learning Approaches to Surrogates for Solving the Diffusion Equation for Mechanistic Real-World Simulations

In many mechanistic medical, biological, physical, and engineered spatiotemporal dynamic models the numerical solution of partial differential equations (PDEs), especially for diffusion, fluid flow and mechanical relaxation, can make simulations impractically slow. Biological models of tissues and organs often require the simultaneous calculation of the spatial variation of concentration of dozens of diffusing chemical species. One clinical example where rapid calculation of a diffusing field is of use is the estimation of oxygen gradients in the retina, based on imaging of the retinal vasculature, to guide surgical interventions in diabetic retinopathy. Furthermore, the ability to predict blood perfusion and oxygenation may one day guide clinical interventions in diverse settings, i.e., from stent placement in treating heart disease to BOLD fMRI interpretation in evaluating cognitive function (Xie et al., 2019; Lee et al., 2020). Since the quasi-steady-state solutions required for fast-diffusing chemical species like oxygen are particularly computationally costly, we consider the use of a neural network to provide an approximate solution to the steady-state diffusion equation. Machine learning surrogates, neural networks trained to provide approximate solutions to such complicated numerical problems, can often provide speed-ups of several orders of magnitude compared to direct calculation. Surrogates of PDEs could enable use of larger and more detailed models than are possible with direct calculation and can make including such simulations in real-time or near-real time workflows practical. Creating a surrogate requires running the direct calculation tens of thousands of times to generate training data and then training the neural network, both of which are computationally expensive. Often the practical applications of such models require thousands to millions of replica simulations, for example for parameter identification and uncertainty quantification, each of which gains speed from surrogate use and rapidly recovers the up-front costs of surrogate generation. We use a Convolutional Neural Network to approximate the stationary solution to the diffusion equation in the case of two equal-diameter, circular, constant-value sources located at random positions in a two-dimensional square domain with absorbing boundary conditions. Such a configuration caricatures the chemical concentration field of a fast-diffusing species like oxygen in a tissue with two parallel blood vessels in a cross section perpendicular to the two blood vessels. To improve convergence during training, we apply a training approach that uses roll-back to reject stochastic changes to the network that increase the loss function. The trained neural network approximation is about 1000 times faster than the direct calculation for individual replicas. Because different applications will have different criteria for acceptable approximation accuracy, we discuss a variety of loss functions and accuracy estimators that can help select the best network for a particular application. We briefly discuss some of the issues we encountered with overfitting, mismapping of the field values and the geometrical conditions that lead to large absolute and relative errors in the approximate solution.

60 APPLIED LIFE SCIENCES↗

An Investigation of LES Wall Modeling for Rayleigh–Bénard Convection via Interpretable and Physics-Aware Feedforward Neural Networks with DNS

Abstract The traditional approach of using the Monin–Obukhov similarity theory (MOST) to model near-surface processes in large-eddy simulations (LESs) can lead to significant errors in natural convection. In this study, we propose an alternative approach based on feedforward neural networks (FNNs) trained on output from direct numerical simulation (DNS). To evaluate the performance, we conduct both a priori and a posteriori tests. In the a priori (offline) tests, we compare the statistics of the surface shear stress and heat flux, computed from filtered DNS input variables, to the stress and flux obtained from the filtered DNS. Additionally, we investigate the importance of various input features using the Shapley additive explanations value and the conditional average of the filter grid cells. In the a posteriori (online) tests, we implement the trained models in the System for Atmospheric Modeling (SAM) LES and compare the LES-generated surface shear stress and heat flux with those in the DNS. Our findings reveal that vertical velocity, a traditionally overlooked flow quantity, is one of the most important input features for determining the wall fluxes. Increasing the number of input features improves the a priori test results but does not always improve the model performance in the a posteriori tests because of the differences in input variables between the LES and DNS. Last, we show that physics-aware FNN models trained with logarithmic and scaled parameters can well extrapolate to more intense convection scenarios than in the training dataset, whereas those trained with primitive flow quantities cannot. Significance Statement The traditional near-surface turbulence model, based on a shear-dominated boundary layer flow, does not represent near-surface turbulence in natural convection. Using a feedforward neural network (FNN), we can construct a more accurate model that better represents the near-surface turbulence in various flows and reveals previously overlooked controlling factors and process interactions. Our study shows that the FNN-generated models outperform the traditional model and highlight the importance of the near-surface vertical velocity. Furthermore, the physics-aware FNN models exhibit the potential to extrapolate to convective flows of various intensities beyond the range of the training dataset, suggesting their broader applicability for more accurate modeling of near-surface turbulence.

54 ENVIRONMENTAL SCIENCES↗

Interplanetary navigation using a continental baseline large antenna arrays

Navigation is a key component of interplanetary missions and must continue to be precise with the changing landscape of antenna design. Improvements for the Deep Space Network (DSN) may include the use of antenna arrays to simulate the power of a larger single antenna at much lower operating and construction costs. Therefore, it is necessary to test the performance of arrayed antennas from a navigational point-of-view. This initial investigation focuses on the performance of arrayed antennas from a navigational point-of-view. This initial investigation focuses on the performance of delta one-way range measurements using a shorter baseline with more data collection then current systems use. With all other parameter equal, the longer the baseline, the better the accuracy for navigation making the number of data packets very important. This trade study compares baseline distances ranging from 1 to 1000km with an in use baseline, looking at a due east baseline, a due north baseline at 45 degrees East of North. The precision of the baseline systems can be found through a simulated created for this purpose using the Jet Propulsion Lab based Monte navigation and mission design tool. The simulation combines the delta one-way range measurements with two-range and two-way Doppler measurements and puts the measurements through a Kalman filter to determine an orbit solution. Noise is added along with initial errors to give the simulation realism. This study is an important step towards the assessment of the utility of arrays for navigational purposes. The preliminary results have showed a decrease in reliability as the baseline is shortened but the larger continental baselines show comparable results t that of the current Goldstone to Canberra.

very long baseline interferometry (VLBI)↗