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 307 records · Page 17

Geomechanics-Based Stochastic Analysis of Injection- Induced Seismicity

The production of geothermal energy from dry and low permeability reservoirs is achieved by water circulation in natural and/or man-made fractures, and is referred to as enhanced or engineered geothermal systems (EGS). Often, the permeable zones have to be created by stimulation, a process which involves fracture initiation and/or activation of discontinuities such as faults and joints due to pore pressure and the in-situ stress perturbations. The stimulation of a rock mass is often accompanied by multiple microseismic events. Micro-seismic events associated with rock failure in shear, and shear slip on new or pre-existing fracture planes and possibly their propagations. The microseismic signals contain information about the sources of energy that can be used for understanding the hydraulic fracturing process and the created reservoir properties. Detection and interpretation of microseismic events is useful for estimating the stimulated zone, created reservoir permeability and fracture growth, and geometry of the geological structures and the in-situ stress state. The process commonly is referred to as seismicity-based reservoir characterization (SBRC). Although, progress has been made by scientific & geothermal communities for quantitative and qualitative analysis of reservoir stimulation using SBRC several key questions remain unresolved in the analysis of micro-seismicity namely, variation of seismic activity with injection rate, delayed micro-seismicity, and the relation of stimulated zone to the injected volume and its rate, and the resulting reservoir permeability. In addition, the current approach to SBRC does not consider the full range of relevant poroelastic and thermoelastic phenomena and neglects the uncertainty in rock properties and in-situ stress in the data inversion process. The objective of this research and technology developments was to develop a 3D SBRC model that addresses these shortcomings by taking into account hydro-thermo-poro-mechanical mechanisms associated with injection and utilizing a state-of-the-art stochastic inversion procedure. The approach proposed herein is innovative and significantly improves the existing SBCR technology (e.g., Shapiro et al. 2003) for geothermal reservoirs in several ways. First, the current scope of the SBRC is limited with respect to the physical processes considered and the rock properties used. Usually, the geomechanics analyses within SBRC is limited to the pore pressure diffusion in the rock mass, which is modeled using a time-dependent parabolic equation and solved using a finite element algorithm with either a line or a point source. However, water injection induces both poroelastic and thermoelastic stresses in the rock mass which affect the stress state. In fact, it has been suggested that thermoelastic stresses can play a dominant role in reservoir seismicity (Ghassemi et al., 2007). We include these important effects by using a fully-coupled poro-thermoelastic constitutive equations for the rock mass which will be solved using a 3D finite element model with more realistic injection geometries such as multiple injection/extraction sources (and in fractures), uncertainty in the material parameters and the in-situ stress distribution to better reflect the pore pressure and stress distributions. In addition, we developed a 3D stochastic fracture network model to study MEQ generation in fracture rocks. The model was verified using laboratory experiments, and calibrated and applied to Newberry EGS stimulation. In previous SBRC approaches, the triggering of micro-seismicity is modeled base on the assumption that the prior stochastic criticality model of the rock mass is a valid and adequate description. However, this assumption often does not hold in the field. Thus, we improved upon the current SBRC approach by using the micro-seismic responses to estimate the hydraulic diffusivity as well as the criticality distribution itself within the field. In this way, instead of relying on our a priori knowledge of criticality distribution, we combine an initial probabilistic description of criticality with the information contained in microseismic measurements to arrive at criticality solutions that are conditioned on both field data and our prior knowledge. Previous SBRC have relied upon a deterministic inversion approach to estimate the permeability, and the extent of the stimulated zone, whereas a stochastic inversion algorithm that recognizes and quantifies the uncertainties in the prior model, the time evolution of pore pressure distributions (modeling errors), and the observed seismic events is developed and used herein to realistically assess the quality of the solution. Finally, we developed a technique for processing discrete MEQ data to estimate fracture network properties such as dip and dip directions. The approach was successfully applied to the Fenton Hill HRD experiment and the Newberry EGS with results in good agreement with field observations.

15 GEOTHERMAL ENERGY↗

Calibration of the Total Carbon Column Observing Network using Aircraft Profile Data

The Total Carbon Column Observing Network (TCCON) produces precise measurements of the column average dry-air mole fractions of CO{sub 2}, CO, CH{sub 4}, N{sub 2}O and H{sub 2}O at a variety of sites worldwide. These observations rely on spectroscopic parameters that are not known with sufficient accuracy to compute total columns that can be used in combination with in situ measure ments. The TCCON must therefore be calibrated to World Meteorological Organization (WMO) in situ trace gas measurement scales. We present a calibration of TCCON data using WMO-scale instrumentation aboard aircraft that measured profiles over four TCCON stations during 2008 and 2009. The aircraft campaigns are the Stratosphere-Troposphere Analyses of Regional Transport 2008 (START-08), which included a profile over the Park Falls site, the HIAPER Pole-to-Pole Observations (HIPPO-1) campaign, which included profiles over the Lamont and Lauder sites, a series of Learjet profiles over the Lamont site, and a Beechcraft King Air profile over the Tsukuba site. These calibrations are compared with similar observations made during the INTEX-NA (2004), COBRA-ME (2004) and TWP-ICE (2006) campaigns. A single, global calibration factor for each gas accurately captures the TCCON total column data within error.

54 ENVIRONMENTAL SCIENCES↗

Beyond Price Taker: Conceptual Design and Optimization of Integrated Energy Systems Using Machine Learning Market Surrogates

Future electricity generation systems must be optimized to provide flexibility that counteracts the variability of non-dispatchable renewable energy sources and ensures the reliability and safety of critical infrastructure, including the electric grid. The current state-of-the-art is to co-optimize the design and operation of integrated energy systems (IES) treating historical or predicted time-series electricity prices as fixed parameters. Recent literature has shown the limitations of this price taker assumption, which neglects how IES optimization decisions influence market outcomes. As such, this paper proposes a new optimization formulation that uses machine learning surrogate models, trained from a library of annual market operation simulations, to embed IES market interactions into the co-optimization problem directly. Using a thermal generator example built in the open-source IDAES computational environment, we show that the price taker approach routinely over-predicts annual revenues by 8% or more compared to a validation simulation, where the proposed approach has a typical relative error of 1% or less.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗

Calibration of the Diffusivity Predictions of Centipede Using Approximate Bayesian Computation and Applications in Nyx (Engineering Scale) and Xolotl-MARMOT (Meso-Scale) Simulations

Fission gas evolution and release in UO 2 nuclear fuel are important fuel performance metrics and occur in several distinct stages: 1) nucleation, growth and resolution of intra-granular bubbles, 2) diffusion to grain boundaries and 3) nucleation and growth of bubbles at grain boundaries, which eventually form a connected network (percolation) enabling release of gas from grain boundaries through connections to triple junctions, grain edges or free surfaces. The NE-SciDAC project is developing several computational tools to model this problem, which are connected in a hierarchical multi-scale framework. The information transfer in the multi-scale framework is a critical step that, in addition to best-estimates, should include uncertainty quantification. Despite taking a first-principles multi-scale approach, there is a need to perform parameter calibration to ensure consistency with available experimental data. In the present study, uncertainty quantification (UQ) and parameter calibration is demonstrated for one of the lower length scale codes in the multi-scale framework (Centipede) and then the results, including instances of the propagated uncertainties, are used in other codes within the framework, specifically Nyx and Xolotl-MARMOT. We calibrated the model parameters in Centipede, a computer code used to predict diffusivities of uranium (U) and xenon (Xe) in the context of the simulation of fission gas in uranium oxide (UO 2 ) nuclear fuel. The Centipede code depends on 183 parameters, all of which are subject to uncertainty. The three data sets used in our calibration effort are taken from the literature. This data is available as a set of measurements, including measurement errors. Our goal is to calibrate a statistical model that predicts both the value of the measurement and the uncertainty associated with the measurement. We perform a Bayesian calibration of the model parameters using a dedicated approximate Bayesian computation (ABC) likelihood function. To avoid excessive computational costs, we replace the expensive Centipede simulation code by a higher-order surrogate model, constructed using only the 9 most important parameters. These important parameters are identified by a preliminary global sensitivity analysis (GSA) study. Among the important parameters are T0 (the temperature at which UO 2 is perfectly stoichiometric) and Hf_pO2 (the temperature dependence of the oxygen (O) partial pressure) that should be considered as operating conditions to be estimated along with the other parameters. We consider two different cases: one where we define one set of these operating conditions for all data sets, and one where we define distinct operating condition parameters for each data set. The Xe diffusivities predicted by the latter case show distinct features that could not be observed in the former. Next, we use the diffusivity predictions by Centipede as input to Nyx, a reduced order fuel performance code focused on gas behavior alone, in order to estimate quantities associated with inter-granular bubble formation at conditions specified by the experiments. Finally, the diffusivities obtained from the calibrated Centipede runs were used in coupled Xolotl-MARMOT simulations of intra- and inter-granular gas evolution. The results are compared to simulations using the baseline diffusivities from Turnbull et al.

11 NUCLEAR FUEL CYCLE AND FUEL MATERIALS↗

Optical measure of disorder: Why Urbach analysis works for amorphous silicon but fails for amorphous carbon

We investigate the basis for the Paradox where the Urbach-slope disorder parameter disagrees with the Raman width in amorphous diamond-like carbon (DLC) materials (lower Urbach-Eo yet greater Raman width). We examined the bandgap and Urbach-slope measurement issues. While significant errors are identified, ultimately these cannot resolve the Paradox. This resolution involves large changes in shape of DLC's absorption band resulting from large energy shifts. To solidify the understanding of band energy shifts, we examined their properties using a-Si:H, well known for its agreement between Raman and Urbach-slope disorder parameters. Using Tauc-Lorentz (T-L) dispersion functions, the Urbach method works for a-Si:H because small changes in shape occur, as measured by (i) peak position, (ii) peak width, (iii) peak amplitude, and (iv) and gap energies. Moreover, for a-Si:H, a 5th condition (v) there is no other feature below the principal band to interfere with its fall. All 5 of these conditions fail for DLCs. Because T-L dispersions accommodate asymmetry, we traced the Paradox to a steepening of the band shape as it pushes toward lower energy. This steepening is unrelated to disorder, but to a boundary value problem where energy cannot be negative. We conclude that Urbach analysis is invalid for DLC materials, but the T-L width is a good measure instead. We also examined another disorder measure, where π bonds should be considered as disorder relative to the σ bonds in an idealized “amorphous diamond” sp 3 network: superconvergence can be used to quantify these π transitions. Finally, further molecular orbital calculations are needed to properly interpret the changes in T-L widths.

36 MATERIALS SCIENCE↗

Deep learning based x-ray spectrometer for high repetition rate characterization of betatron radiation

Betatron radiation produced from a laser-wakefield accelerator is a broadband, hard x-ray (>1 keV) source that has been used in a variety of applications in medicine, engineering, and fundamental science. Further development and optimization of stable, high repetition rate (HRR) (>1 Hz) betatron sources will provide a means to extend their application base to include single-shot dynamical measurements of ultrafast processes or dense materials. Recent advances in laser technology used in such experiments have enabled increases in shot-rate and system stability, providing improved statistical analysis and detailed parameter scans. However, unique challenges exist at high repetition rate, where data throughput and source optimization are now limited by diagnostic acquisition rates and analysis. Here, we present the development of a machine-learning algorithm for the real-time analysis of betatron radiation. We report on the fielding of this deep learning algorithm for online source characterization at the Institut National de la Recherche Scientifique's Advanced Laser Light Source. By fine-tuning an algorithm originally trained on a fully synthetic dataset using a subset of experimental data, the algorithm can predict the betatron critical energy with a percent error of 7.2 % with a reconstruction time of 1.5 ms, providing a valuable tool for real-time, multi-objective optimization at HRR.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗

HydraGNN_Predictive_GFM_2026 - Ensemble of predictive graph foundation models for atomistic materials modeling

This release contains data and parameters of HydraGNN-based graph foundation models trained as a result of the work published in the pre-print "Exascale Multi-Task Graph Foundation Models for Imbalanced, Multi-Fidelity Atomistic Data" by M. Lupo Pasini et al. (https://arxiv.org/abs/2604.15380). We jointly train on 16 open first-principles datasets (544+ million structures covering 85+ elements) using a multi-task architecture with per-dataset heads and a scalable ADIOS2/DDStore data pipeline. On Frontier, we execute six large-scale DeepHyper hyperparameter optimization campaigns in FP64 and promote the top-performing message-passing models to sustained 2,048-node training, yielding a PaiNN-based lead model. The version of HydraGNN used to generate the outputs provided in this release is HydraGNN v5.0 (https://github.com/ORNL/HydraGNN/releases/tag/v5.0) The list of datasets used for the training of the graph foundation model is the following: 1) Alexandria [1] 2) ANI1x [2] 3) MPTrj [3] 4) Open Catalyst 2020 (OC20) [4] 5) Open Catalyst 2022 (OC22) [5] 6) Open Catalyst 2025 (OC25) [6] 7) Open Direct ir Capture 2023 (ODAC23) [7] 8) Open Materials 2024 (OMat24) [8] 9) Open Molecules 2025 (OMol25) [9] 10) OMol25-neutral (subset of OMol25 that contains only molecules with zero total charge) 11) OMol25-non-neutral (subset of OMol25 that contains only molecules with non-zero total charge) 12) Open Polymers 2026 (OPoly2026) [10] 13) Nabla2DFT [11] 14) QCML [12] 15) QM7X [reference 13] 16) transition1x [14] Dataset references: [1] J. Schmidt et al., “A dataset of 175k stable and metastable materials calculated with the PBEsol and SCAN functionals,” Scientific Data, vol. 9, p. 64, 2022. [2] J. S. Smith et al., “The ANI-1ccx and ANI-1x data sets, coupled-cluster and density functional theory properties for molecules,” Scientific Data, vol. 7, p. 134, 2020. [Online]. Available: https: //www.nature.com/articles/s41597-020-0473-z [3] A. Jain et al., “Commentary: The Materials Project: A materials genome approach to accelerating materials innovation,” APL Materials, vol. 1, no. 1, p. 011002, 07 2013. [Online]. Available: https://doi.org/10.1063/1.4812323 [4] L. Chanussot et al., “Open catalyst 2020 (oc20) dataset and community challenges,” ACS Catalysis, vol. 11, no. 10, pp. 6059–6072, 2021. [Online]. Available: https://doi.org/10.1021/acscatal.0c04525 [5] K. Tran et al., “Open catalyst 2022 (oc22) dataset and challenges for oxidation electrocatalysts,” ACS Catalysis, vol. 13, no. 5, pp. 3066–3084, 2023. [Online]. Available: https://doi.org/10.1021/acscatal.2c05426 [6] S. J. Sahoo et al., “The open catalyst 2025 (oc25) dataset and models for solid-liquid interfaces,” arXiv preprint arXiv:2509.17862, 2025. [Online]. Available: https://arxiv.org/abs/2509.17862 [7] A. Sriram et al., “The open DAC 2023 dataset and challenges for sorbent discovery in direct air capture,” ACS Central Science, vol. 10, no. 5, pp. 923–941, 2024. [8] L. Barroso-Luque et al., “Open materials 2024 (omat24) inorganic materials dataset and models,” 2024. [Online]. Available: https://arxiv.org/abs/2410.12771 [9] D. S. Levine et al., “The open molecules 2025 (OMol25) dataset, evaluations, and models,” 2025. [Online]. Available: https://arxiv.org/abs/2505.08762 [10] D. S. Levine et al., The open polymers 2026 (OPoly26) dataset and evaluations,” arXiv preprint arXiv:2512.23117, 2025. [Online]. Available: https://arxiv.org/abs/2512.23117 [11] K. Khrabrov et al., “Nabla2dft: A universal quantum chemistry dataset of drug-like molecules and a benchmark for neural network potentials,” in NeurIPS 2024 Datasets and Benchmarks Track, 2024. [Online]. Available: https://openreview.net/forum?id=ElUrNM9U8c [12] S. Ganscha et al., “The QCML dataset, quantum chemistry reference data from 33.5M DFT and 14.7B semi-empirical calculations,” Scientific Data, vol. 12, p. 406, 2025. [13] J. Hoja et al., “QM7-X, a comprehensive dataset of quantum-mechanical properties spanning the chemical space of small organic molecules,” Scientific Data, vol. 8, p. 43, 2021. [Online]. Available: https://www.nature.com/articles/s41597-021-00812-2 [14] M. Schreiner et al., “Transition1x - a dataset for building generalizable reactive machine learning potentials,” Scientific Data, vol. 9, p. 779, 2022. The folder "datasets_ADIOS2_format" contains the set of pre-processed datasets in Adaptable I/O System (ADIOS) format (https://www.exascaleproject.org/research-project/adios/) that have been used for the development and training of GFMs in this work. The "datasets_ADIOS2_format" directory contains 2 sub-directories, one for the version "v1" of the datasets and one for the version "v2" of the datasets. The version "v1" of the datasets provides values of the total energy as they are extracted from the original data as it was released by the respective institutions. The version "v2" of the datasets provides values of the energy that have been realigned. The realignment was performed by training a linear regression model that predicts the total energy as a function of the chemical composition of the atomistic structure, and then subtract such prediction from the original value of the total energy. Both folders "v1" and "v2" contain 16 sub-directories, each corresponding to an ADIOS2-formatted dataset The folder "DeepHyper-results" contains the configurational files and model's parameters for all the 186 HPO trials that were successfully completed by the scalable hyperparameter optimization (HPO) runs on Frontier. The content of the folder "DeepHyper-results" I structured as follows: 1) task-list.txt: list of mpnn name, jobid, and deephyper task id 2) gfm_${MPNN}_${JOBID}_0.${TASKID}: run directory with checkpoint files 3) gfm_${MPNN}: deephyper summary directory (*.csv) for each specific MPNN type 4) deephyper-experiment-${JOBID}: output and error logs for each job The file "deephyper-sorted.csv" contains the details of each HydraGNN model built and tested by HPO, obtained by merging the (*.csv) filed from each HPO run executed. Out of all the HPO trials, we selected 10 to continue the training of the respective HydraGNN models. Due to limited computational budget available in the LRN070 allocation we could not complete the training till convergence for all these 10 selected models. The folder "models" contains multiple sub-folders, one per each HydraGNN model trained. Each model sub-folder contains the parameters of each HydraGNN model, with multiple checkpoint-restarts. The list of sub-folders are as follows: 1) multidataset_hpo-BEST1-fp64 2) multidataset_hpo-BEST2-fp64 3) multidataset_hpo-BEST3-fp64 4) multidataset_hpo-BEST4-fp64 5) multidataset_hpo-BEST5-fp64 6) multidataset_hpo-BEST6-fp64 7) multidataset_hpo-BEST7-fp64 8) multidataset_hpo-BEST8-fp64 9) multidataset_hpo-BEST9-fp64 10) multidataset_hpo-BEST10-fp64 Within each one of these folders, additional auxiliary log files are provided with descriptions about how the training proceeded. The lead PaiNN-model is contained inside "multidataset_hpo-BEST6-fp64". The file "mlp_branch_weights" contains the parameters of the multi-layer perceptron (MLP) used to reconcile the predictions of the 16 output decoding heads of the HydragNN architectures. The MLP takes in input the chemical composition of the atomistic structure and predicts averaging weights to linearly mix the predictions of each output decoding head toward consolidating them into a single one. The folder "1.1billion-structure-inference" contains 1.1 billion atomistic structures randomly generated. Each structures is associated with energy and forces predicted with the lead-PaiNN model combined with the MLP model for reconciliation of the multi-branch predictions generated by the 16 output decoding heads. The folder "1.1billion-structure-inference" contains 9,300 (*.tar.gz) subdirectories, one per Frontier compute node used to execute the inference at exascale. Once uncompressed, each (*.tar.gz) subdirectory contains an ADIOS2 (*.bp) file container, where each atomistic structure is stored as a PyTorch-Geometric Data object. The file "export_dataset_environment_variables.sh" contains the environment variables that need to be set before running the HydraGNN code to reproduce the results provided in this dataset release. The code that can be used to load the ADIOS2 files, load HydraGNN models, and run inference is available at: https://github.com/ORNL/HydraGNN/releases/tag/v5.0

36 MATERIALS SCIENCE↗

Towards Generalizable and Efficient Circuit Topology Design: A Graph-Transformer-based Surrogate Model with Curriculum Learning

Unlike circuit parameter and sizing optimizations, the automated design of analog circuit topologies poses significant challenges for learning-based approaches. One challenge arises from the combinatorial growth of the topology space with circuit size, which limits the topology optimization efficiency. Moreover, traditional circuit evaluation methods are time-consuming, while the presence of data discontinuity in the topology space makes the accurate prediction of circuit performance exceptionally difficult for unseen topologies. To tackle these challenges, we design a novel Graph-Transformer-based Network (GTN) as the surrogate model for circuit evaluation, offering a substantial acceleration in the speed of circuit topology optimization without sacrificing performance. Our GTN model architecture is designed to embed voltage changes in circuit loops and current flows in connected devices, enabling accurate performance predictions for circuits with unseen topologies. To address the cold start problem when scaling GTN to large-scale circuits, we further introduce a curriculum learning strategy that progressively trains GTN from small-scale to large-scale circuits. This approach enables the model to first learn fundamental physical principles from simpler topologies and gradually adapt to complex configurations, effectively bridging the circuit complexity gap and improving prediction accuracy. Taking the power converter circuit design as an experimental task, our GTN model significantly outperforms an analytical approach and baseline methods directly utilizing graph neural networks. Furthermore, GTN achieves less than 5% relative error and 196× speed-up compared with high-fidelity simulation. Notably, our GTN surrogate model empowers an automatic circuit design framework to discover circuits of comparable quality to those identified through high-fidelity simulation while reducing the time required by up to 98.2%. With curriculum learning, the enhanced GTN achieves a 51% improvement for performance prediction of large-scale circuits compared to the GTN model without this strategy. These advancements establish GTN as a scalable framework for automated analog circuit design across varying circuit complexity levels.

Lu, Haoshu [New Jersey Institute of Technology (NJ↗

Improving Subsurface Stress Characterization for Carbon Dioxide Storage Projects by Incorporating Machine Learning Techniques

The overall objective of this project is to develop a framework for reliable characterization and prediction of the state of stress in the overburden and underburden (including the basement) in CO 2 storage reservoirs using machine learning and integrated geomechanics and geophysical methods. Specifically, we propose to develop workflow encompassing of technologies and/or methods to predict stress and pressure changes due to CO 2 injection in an active tertiary recovery site and their impacts on subtle fault activation, fractures and occurrence of microseismic events and compare responses to field observations. In this project, we anticipate using dataset from the Farnsworth field Unit (FWU) which is operated by Purdure Petroleum. A novel elastic-waveform VSP inversion technique will be used to estimate high-resolution spatial and temporal changes of elastic moduli in CO 2 storage reservoirs, which will be combined with velocity-stress relationship derived from laboratory tests to obtain subsurface pressure and stress. Clustered microseismic data will be jointly inverted for improved focal mechanisms. Least-squares reverse-time migration of microseismic waveform data will be performed to directly image fracture/fault zones. Additionally, a deep neural network machine learning technique with convolutional and recurrent layers will be used for learning the spectro-temporal structures in microseismic waveforms. The results of this geotechnical data analysis will be integrated to develop a high-resolution 3D mechanical earth model extending from the overburden sealing formations to the underburden including the basement. Mechanical properties will be derived through integration of mechanical logs, tests, available results from chemo-mechanical laboratory tests, and elastic inversion of seismic data using a combination of Bayesian and stochastic methods as well as machine learning technique. Failure features (faults/fractures) will be represented and/or modeled based on seismic and core data analysis. A transient hydrodynamic-geomechanical model will be developed through coupling with the calibrated FWU reservoir simulation model. The full physics coupled model will be used to train a reduced order proxy model using machine learning algorithm for estimating stress which will then be used with appropriate constitutive relationships and forward seismological models to simulate pressure changes and induced microseismicity. An advanced optimization framework will be developed to perform a history match to minimize error between field observations and simulated. The history matched proxy model will be verified against the full-physics equivalent. The field observations that will be used in the coupled model calibration process include pressure/stress inverted from VSP, moment magnitude from microseismic analysis, real time downhole pressure measurements, production and injection data. Parameter sensitivity and uncertainty analysis will be performed to characterize the impact of model parameter uncertainty on stress estimates. The proposed project will have significant impact on future field implementation of the proposed technology. Because the project field site is an ongoing CO 2 EOR development, the value of the new technology will be demonstrated in an operational context and evaluated as a viable risk mitigation strategy. Cost/benefit will be evaluated together with the various commercial incentives for CO 2 sequestration available to oil and gas operators. The extensive available dataset and ongoing data acquisition under the SWP Phase III work plan provides flexibility for investigation of multiple approaches and reduces technical risk.

58 GEOSCIENCES↗

Intercomparison of Deep Learning Model Architectures for Atmospheric River Prediction

With a rapid surge in the application of machine learning (ML) for a diverse range of tasks in climate science, the present study addresses a challenge for climate scientists when selecting the optimal ML or deep learning (DL) architecture for a given application. In particular, a DL intercomparison study was performed with a focus on forecasting the position of atmospheric rivers (ARs) on short-range time scales (up to 5-day lead times). AR predictions from multiple DL architectures, including various types of convolutional autoencoders and a vision transformer (ViT), were compared against ECMWF ERA5 reanalysis and hindcasts from a global climate model. DL models with similar trainable parameters were trained on ERA5 reanalysis data and AR positions derived from a thresholding algorithm to ensure a fair comparison among the DL models. Each model’s performance and accuracy in forecasting AR location and key input fields within a 5-day window were assessed using metrics of root-mean-square error, anomaly correlation, and mean intersection over union. The ViT architecture outperformed other autoencoder models in most of the metrics. Incorporating additional meteorological fields only yielded slight improvements in forecasting certain fields at longer lead times. The results also suggest that a smaller number of input time steps or smaller number of autoregressive steps can achieve better prediction skills, while also improving the overall computational efficiency. This research offers valuable insights into the strengths and weaknesses of different DL techniques for AR forecasting, hopefully guiding the development of improved models for forecasting this phenomenon.

54 ENVIRONMENTAL SCIENCES↗

NSFnets (Navier-Stokes flow nets): Physics-informed neural networks for the incompressible Navier-Stokes equations

In the last 50 years there has been a tremendous progress in solving numerically the Navier-Stokes equations using finite differences, finite elements, spectral, and even meshless methods. Yet, in many real cases, we still cannot incorporate seamlessly (multi-fidelity) data into existing algorithms, and for industrial-complexity applications the mesh generation is time consuming and still an art. Moreover, solving ill-posed problems (e.g., lacking boundary conditions) or inverse problems is often prohibitively expensive and requires different formulations and new computer codes. Here, we employ physics-informed neural networks (PINNs), encoding the governing equations directly into the deep neural network via automatic differentiation, to overcome some of the aforementioned limitations for simulating incompressible laminar and turbulent flows. We develop the Navier-Stokes flow nets (NSFnets) by considering two different mathematical formulations of the Navier-Stokes equations: the velocity-pressure (VP) formulation and the vorticity-velocity (VV) formulation. Since this is a new approach, we first select some standard benchmark problems to assess the accuracy, convergence rate, computational cost and flexibility of NSFnets; analytical solutions and direct numerical simulation (DNS) databases provide proper initial and boundary conditions for the NSFnet simulations. The spatial and temporal coordinates are the inputs of the NSFnets, while the instantaneous velocity and pressure fields are the outputs for the VP-NSFnet, and the instantaneous velocity and vorticity fields are the outputs for the VV-NSFnet. This is unsupervised learning and, hence, no labeled data are required beyond boundary and initial conditions and the fluid properties. The residuals of the VP or VV governing equations, together with the initial and boundary conditions, are embedded into the loss function of the NSFnets. No data is provided for the pressure to the VP-NSFnet, which is a hidden state and is obtained via the incompressibility constraint without extra computational cost. Unlike the traditional numerical methods, NSFnets inherit the properties of neural networks (NNs), hence the total error is composed of the approximation, the optimization, and the generalization errors. Here, we empirically attempt to quantify these errors by varying the sampling (“residual”) points, the iterative solvers, and the size of the NN architecture. For the laminar flow solutions, we show that both the VP and the VV formulations are comparable in accuracy but their best performance corresponds to different NN architectures. The initial convergence rate is fast but the error eventually saturates to a plateau due to the dominance of the optimization error. For the turbulent channel flow, we show that NSFnets can sustain turbulence at , but due to expensive training we only consider part of the channel domain and enforce velocity boundary conditions on the subdomain boundaries provided by the DNS data base. We also perform a systematic study on the weights used in the loss function for balancing the data and physics components, and investigate a new way of computing the weights dynamically to accelerate training and enhance accuracy. In the last part, we demonstrate how NSFnets should be used in practice, namely for ill-posed problems with incomplete or noisy boundary conditions as well as for inverse problems. We obtain reasonably accurate solutions for such cases as well without the need to change the NSFnets and at the same computational cost as in the forward well-posed problems. As a result, we also present a simple example of transfer learning that will aid in accelerating the training of NSFnets for different parameter settings.

97 MATHEMATICS AND COMPUTING↗

TU-AB-BRC-05: Creation of a Monte Carlo TrueBeam Model by Reproducing Varian Phase Space Data

Purpose: To create a Varian TrueBeam 6 MV FFF Monte Carlo model using BEAMnrc/EGSnrc that accurately reproduces the Varian representative dataset, followed by tuning the model’s source parameters to accurately reproduce in-house measurements. Methods: A BEAMnrc TrueBeam model for 6 MV FFF has been created by modifying a validated 6 MV Varian CL21EX model. Geometric dimensions and materials were adjusted in a trial and error approach to match the fluence and spectra of TrueBeam phase spaces output by the Varian VirtuaLinac. Once the model’s phase space matched Varian’s counterpart using the default source parameters, it was validated to match 10 × 10 cm{sup 2} Varian representative data obtained with the IBA CC13. The source parameters were then tuned to match in-house 5 × 5 cm{sup 2} PTW microDiamond measurements. All dose to water simulations included detector models to include the effects of volume averaging and the non-water equivalence of the chamber materials, allowing for more accurate source parameter selection. Results: The Varian phase space spectra and fluence were matched with excellent agreement. The in-house model’s PDD agreement with CC13 TrueBeam representative data was within 0.9% local percent difference beyond the first 3 mm. Profile agreement at 10 cm depth was within 0.9% local percent difference and 1.3 mm distance-to-agreement in the central axis and penumbra regions, respectively. Once the source parameters were tuned, PDD agreement with microDiamond measurements was within 0.9% local percent difference beyond 2 mm. The microDiamond profile agreement at 10 cm depth was within 0.6% local percent difference and 0.4 mm distance-to-agreement in the central axis and penumbra regions, respectively. Conclusion: An accurate in-house Monte Carlo model of the Varian TrueBeam was achieved independently of the Varian phase space solution and was tuned to in-house measurements. KO acknowledges partial support by the CREATE Medical Physics Research Training Network grant of the Natural Sciences and Engineering Research Council (Grant number: 432290).

60 APPLIED LIFE SCIENCES↗

Cosmological Constraints from Combining Photometric Galaxy Surveys and Gravitational Wave Observatories

Spatial variations in survey properties due to selection effects generate substantial systematic errors in large-scale structure measurements in optical galaxy surveys on very large scales. On such scales, the statistical sensitivity of optical surveys is also limited by their finite sky coverage. By contrast, gravitational wave (GW) sources appear to be relatively free of these issues, provided the angular sensitivity of GW experiments can be accurately characterized. We quantify the expected cosmological information gain from combining the forecast LSST 3$\times$2pt analysis (combination of three 2-point correlations of galaxy density and weak lensing shear fields) with the large-scale auto-correlation of GW sources from proposed next-generation GW experiments. We find that in $\Lambda$CDM and $w$CDM models, there is no significant improvement in cosmological constraints from combining GW with LSST 3$\times$2pt over LSST alone, due to the large shot noise for the former; however, this combination does enable a $\sim6\%$ constraint on the linear galaxy bias of GW sources. More interestingly, the optical-GW data combination provides tight constraints on models with primordial non-Gaussianity (PNG), due to the predicted scale-dependent bias in PNG models on large scales. Assuming that the largest angular scales that LSST will probe are comparable to those in Stage III surveys ($\ell_{\rm min}\sim50$), the inclusion of next-generation GW measurements could improve constraints on the PNG parameter $f_{\rm NL}$ by up to a factor of $\simeq6.6$ compared to LSST alone, yielding $\sigma(f_{\rm NL})=8.5$. These results assume the expected capability of a network of Einstein Telescope-like GW observatories, with a detection rate of $10^6$ events/year. We investigate the sensitivity of our results to different assumptions about future GW detectors as well as different LSST analysis choices.

79 ASTRONOMY AND ASTROPHYSICS↗

0.22 THz wideband sheet electron beam traveling wave tube amplifier: Cold test measurements and beam wave interaction analysis

In this paper, we describe micro-fabrication, RF measurements, and particle-in-cell (PIC) simulation modeling analysis of the 0.22 THz double-vane half period staggered traveling wave tube amplifier (TWTA) circuit. The TWTA slow wave structure comprised of two sections separated by two sever ports loaded by loss material, with integrated broadband input/output couplers. The micro-metallic structures were fabricated using nano-CNC milling and diffusion bonded in a three layer process. The 3D optical microscopy and SEM analysis showed that the fabrication error was within 2-3 {mu}m and surface roughness was measured within 30-50 nm. The RF measurements were conducted with an Agilent PNA-X network analyzer employing WR5.1 T/R modules with a frequency range of 178-228 GHz. The in-band insertion loss (S{sub 21}) for both the short section and long section (separated by a sever) was measured as {approx}-5 dB while the return loss was generally around {approx}-15 dB or better. The measurements matched well with the S-matrix simulation analysis that predicted a 3 dB bandwidth of {approx}45 GHz with an operating frequency at 220 GHz. However, the measured S{sub 21} was {approx}3 dB less than the design values, and is attributed to surface roughness and alignment issues. The confirmation measurements were conducted over the full frequency band up to 270 GHz employing a backward wave oscillator (BWO) scalar network analyzer setup employing a BWO in the frequency range 190 GHz-270 GHz. PIC simulations were conducted for the realistic TWT output power performance analysis with incorporation of corner radius of 127 {mu}m, which is inevitably induced by nano-machining. Furthermore, the S{sub 21} value in both sections of the TWT structure was reduced to correspond to the measurements by using a degraded conductivity of 10% International Annealed Copper Standard. At 220 GHz, for an elliptic sheet electron beam of 20 kV and 0.25 A, the average output power of the tube was predicted to be reduced from 90 W (for ideal conductivity/design S-parameters) to 70 W (for the measured S-parameters/inferred conductivity) for an average input power of 50 mW. The gain of the tube remains reasonable: {approx}31.4 dB with an electronic efficiency of {approx}1.4%. The same analysis was also conducted for several frequencies between 190 GHz-260 GHz. This detailed realistic PIC analysis demonstrated that this nano-machined TWT circuit has slightly reduced S-parameters and output power from design, but within an acceptable range and still have promising output power, gain, and band width as required. Thus, we expect to meet the specifications of 1000 W-GHz for the darpa program goals.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗

Augmenting machine learning of Grad–Shafranov equilibrium reconstruction with Green's functions

This work presents a method for predicting plasma equilibria in tokamak fusion experiments and reactors. The approach involves representing the plasma current as a linear combination of basis functions using principal component analysis of plasma toroidal current densities (J t ) from the EFIT-AI equilibrium database. Then utilizing EFIT's Green's function tables, basis functions are created for the poloidal flux (ψ) and diagnostics generated from the toroidal current (J t ). Similar to the idea of a physics-informed neural network (NN), this physically enforces consistency between ψ, J t , and the synthetic diagnostics. First, the predictive capability of a least squares technique to minimize the error on the synthetic diagnostics is employed. The results show that the method achieves high accuracy in predicting ψ and moderate accuracy in predicting J t with median R 2 = 0.9993 and R 2 = 0.978, respectively. A comprehensive NN using a network architecture search is also employed to predict the coefficients of the basis functions. The NN demonstrates significantly better performance compared to the least squares method with median R 2 = 0.9997 and 0.9916 for J t and ψ, respectively. The robustness of the method is evaluated by handling missing or incorrect data through the least squares filling of missing data, which shows that the NN prediction remains strong even with a reduced number of diagnostics. Additionally, the method is tested on plasmas outside of the training range showing reasonable results.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗

DeepAdversaries: examining the robustness of deep learning models for galaxy morphology classification

With increased adoption of supervised deep learning methods for work with cosmological survey data, the assessment of data perturbation effects (that can naturally occur in the data processing and analysis pipelines) and the development of methods that increase model robustness are increasingly important. In the context of morphological classification of galaxies, we study the effects of perturbations in imaging data. In particular, we examine the consequences of using neural networks when training on baseline data and testing on perturbed data. We consider perturbations associated with two primary sources: (a) increased observational noise as represented by higher levels of Poisson noise and (b) data processing noise incurred by steps such as image compression or telescope errors as represented by one-pixel adversarial attacks. We also test the efficacy of domain adaptation techniques in mitigating the perturbation-driven errors. We use classification accuracy, latent space visualizations, and latent space distance to assess model robustness in the face of these perturbations. For deep learning models without domain adaptation, we find that processing pixel-level errors easily flip the classification into an incorrect class and that higher observational noise makes the model trained on low-noise data unable to classify galaxy morphologies. On the other hand, we show that training with domain adaptation improves model robustness and mitigates the effects of these perturbations, improving the classification accuracy up to 23% on data with higher observational noise. Domain adaptation also increases up to a factor of ${\approx}2.3$ the latent space distance between the baseline and the incorrectly classified one-pixel perturbed image, making the model more robust to inadvertent perturbations. Successful development and implementation of methods that increase model robustness in astronomical survey pipelines will help pave the way for many more uses of deep learning for astronomy.

79 ASTRONOMY AND ASTROPHYSICS↗

A fast and accurate domain decomposition nonlinear manifold reduced order model

Here, this paper integrates nonlinear-manifold reduced order models (NM-ROMs) with domain decomposition (DD). NM ROMs approximate the full order model (FOM) state in a nonlinear-manifold by training a shallow, sparse autoencoder using FOM snapshot data. These NM-ROMs can be advantageous over linear-subspace ROMs (LS-ROMs) for problems with slowly decaying Kolmogorov n-width. However, the number of NM-ROM parameters that need to be trained scales with the size of the FOM. Moreover, for “extreme-scale” problems, the storage of high-dimensional FOM snapshots alone can make ROM training expensive. To alleviate the training cost, this paper applies DD to the FOM, computes NM-ROMs on each subdomain, and couples them to obtain a global NM-ROM. This approach has several advantages: Subdomain NM-ROMs can be trained in parallel, involve fewer parameters to be trained than global NM-ROMs, require smaller subdomain FOM dimensional training data, and can be tailored to subdomain specific features of the FOM. The shallow, sparse architecture of the autoencoder used in each subdomain NM-ROM allows application of hyper-reduction (HR), reducing the complexity caused by nonlinearity and yielding computational speedup of the NM-ROM. This paper provides the first application of NM-ROM (with HR) to a DD problem. In particular, this paper details an algebraic DD reformulation of the FOM, training a NM-ROM with HR for each sub domain, and a sequential quadratic programming (SQP) solver to evaluate the coupled global NM-ROM. Theoretical convergence results for the SQP method and a priori and a posteriori error estimates for the DD NM-ROM with HR are provided. The proposed DD NM-ROM with HR approach is numerically compared to a DD LS-ROM with HR on the 2D steady-state Burgers’ equation, showing an order of magnitude improvement in accuracy of the proposed DD NM-ROM over the DD LS-ROM.

97 MATHEMATICS AND COMPUTING↗

Learning model combining convolutional deep neural network with a self-attention mechanism for AC optimal power flow

Alternating current optimal power flow (OPF) analysis is critical for efficient and reliable operation of power systems. For large systems or repetitive computations, the traditional methods such as the direct and gradient methods, or non-traditional methods, such as the genetic algorithm and simulating annealing, are time-consuming and unsuitable for real-time computing. The work in this paper proposes a novel framework to obtain the optimal solution of power flow in real-time using a combination of convolutional neural networks and a self-attention mechanism. All parameters of the power networks are rearranged in an image-like shape of a multi-channel image where each channel is a two-dimensional matrix. The proposed approach is adaptive with every input size of power systems as well as frequent variations of network topologies without intervention to the framework core. The encompassment of all power system contexts in which all parameters of internal elements, generation costs, and topology information are included, contributes to the higher accuracy of inference compared to other current machine-learning-based OPF-solving methods. Besides, the proposed framework established on ubiquitous platforms is effortlessly integrated into current infrastructures of power systems, and the great efficiency along with the computation speed may serve as a critical point for practical implications, such as enabling faster decision-making during real-time operations, predicting system contingencies, and remedial actions based on an offline pre-trained model. Furthermore, this supervised learning process is applied to the dataset of four case studies of meshed power systems: the IEEE 5-bus system (IEEE-5), the IEEE 30-bus system (IEEE-30), the IEEE 39-bus system (IEEE-39), and the IEEE 57-bus system (IEEE-57) to prove the efficacy of the proposed method.

42 ENGINEERING↗