Search NASA⌕ Search

SEARCH · Search NASA

Results for “Tensor train”

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 109 records · Page 6
All sourcesNASA NTRSDOE OSTI
DOE OSTI2022

Deep Neural Network Algorithm for CMC Microstructure Characterization and Variability Quantification

Microstructure characterization and variability quantification are crucial for understanding ceramic matrix composites (CMCs) mechanical behavior and deformation mechanisms across length scales. Traditionally, analyses of the micrographs obtained from microscopy are labor-intensive. However, with the vast improvement in computer vision (CV) and deep learning (DL), an automated algorithm can be designed to extract essential microstructure variability from micrographs which can then be used to construct a statistically representative volume element (SRVE). The DL-based algorithm spans the taxonomy of microstructure analyses, including semantic segmentation of microstructure constituents, secondary phases, matrix/fiber interface, and defects, and quantifying the microstructure variability in terms of probability distributions. In this work, C/SiNC and SiC/SiNC CMCs microstructures are semantically segmented through a deep convolutional neural network, followed by variability quantification through the implementation of a fully connected regression layer, hence forming a deep regression network. The deep regression network operates in a feedforward regime, in which the neuron output signal traverses through the network in a unidirectional manner. The weight tensor associated with each layer is updated through a backpropagation stochastic gradient descent approach. The input gray-scale image obtained through in-house scanning electron microscope and confocal microscope micrographs is augmented through affine transformations to increase the training set size, which is then processed through four strided convolutional layers. This compresses the image resolution by half at each layer while increasing the image depth by applying different filters (image encoding). The class activation maps (CAMs) corresponding to the applied filters highlight the key architectural features and assist with the semantic segmentation of the microstructure.

Hamza, Mohamed H.↗
DOE OSTI2022

Proxy-Based Bayesian Inversion Of Poroelastic Simulations To Interpret Strain Tensor Data Measured During Well Testing

The long runtimes of 3D poroelastic numerical simulators makes it impractical to interpret deformation datasets using many inversion schemes. Recent advances in instrumentation have made it possible to measure the strain tensor during well testing, but the lack of robust inversion methods is limiting the ability to interpret these data. We have developed an inversion workflow that reduces the number of computations required to complete a Bayesian inversion using DREAMzs. The workflow trains a KNN model using output from the poroelastic simulator, and then uses the KNN model as a proxy for the simulator during inversion. The workflow also includes a strategy for ensuring the results from the proxy model converge to the results from the simulator, ensuring the accuracy of the final results. An idealized example configured to represent a well test in a deep aquifer is used to verify that the workflow correctly identifies parameters and characterizes noise. Field data measured using strainmeters during an injection test at an oil reservoir in Oklahoma are used to evaluate performance with a real dataset. The workflow identified 265 history matching solutions out of 1240 total simulation runs (21% acceptance ratio), and the results are used to characterize posterior parameter distribution and evaluate the prediction uncertainty. This approach makes it feasible to invert strain data measured during well testing and this has the potential to improve the characterization of aquifers and reservoirs.

Roudini, Soheil↗
DOE OSTI2021

Cholesky-based experimental design for Gaussian process and kernel-based emulation and calibration.

Gaussian processes and other kernel-based methods are used extensively to construct approximations of multivariate data sets. The accuracy of these approximations is dependent on the data used. This paper presents a computationally efficient algorithm to greedily select training samples that minimize the weighted L p error of kernel-based approximations for a given number of data. The method successively generates nested samples, with the goal of minimizing the error in high probability regions of densities specified by users. The algorithm presented is extremely simple and can be implemented using existing pivoted Cholesky factorization methods. Training samples are generated in batches which allows training data to be evaluated (labeled) in parallel. For smooth kernels, the algorithm performs comparably with the greedy integrated variance design but has significantly lower complexity. Numerical experiments demonstrate the efficacy of the approach for bounded, unbounded, multi-modal and non-tensor product densities. We also show how to use the proposed algorithm to efficiently generate surrogates for inferring unknown model parameters from data using Bayesian inference.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2026

AnisONet: A deep neural operator-based anisotropic permeability upscaler from pore to Darcy scale

Directional permeability variations, which govern directional fluid flow in porous media with anisotropy, are important to accurately predict flow behavior, reactive transport, and fluid–solid interactions for various processes such as enhanced geothermal systems, energy storage devices, and biological systems. However, the intricate architecture of porous media makes it difficult to predict directional permeabilities. In this work, we present a novel machine learning (ML) framework, AnisONet, built upon an integration of a convolutional neural network, Swin transformer, and the deep operator network architecture, designed to predict anisotropic permeability and upscale predictions to larger spatial domains. First, AnisONet was evaluated with three classes of two-dimensional (2D) porous media, including synthetic circular and elliptical grains and natural sandstone grains from micro-computed tomography images. A lattice Boltzmann model (LBM) was used to calculate directional permeabilities at every 10° angle, producing 19 data points per image of porous media. AnisONet is then trained to predict permeability as a function of rotation angle. AnisONet showed strong predictive capability of directional permeability. Second, we tested our model for five upscaling cases with a large image size in the finite-element method (FEM) for 2D Darcy flow with various permeability tensor construction methods. Overall, upscaled permeability tensors in FEM simulations produce a reasonably good match with LBM results, highlighting the importance of selecting appropriate tensor formation strategies for accurate permeability upscaling. AnisONet, as a directional permeability estimator, could be further developed for more complex geometries, with the potential to develop a foundational ML model for various applications in porous media.

42 ENGINEERING↗
DOE OSTI2020

Predicting the proximity to macroscopic failure using local strain populations from dynamic in situ X-ray tomography triaxial compression experiments on rocks

Predicting the proximity of large-scale dynamic failure is a critical concern in the engineering and geophysical sciences. Here we use evolving contractive, dilatational, and shear strain deformation preceding failure in dynamic X-ray tomography experiments to examine which strain components best predict the proximity to failure. We develop machine learning models to predict the proximity to failure using time series of three-dimensional local incremental strain tensor fields acquired in rock deformation experiments under stress conditions of the upper crust. Three-dimensional scans acquired in situ throughout triaxial compression experiments provide a distribution of density contrasts from which we estimate the three-dimensional incremental strain that accumulates between each scan acquisition. Training machine learning models on multiple experiments of six rock types provides suites of feature importance that indicate the predictive power of each feature. Comparing the average importance of groups of features that include information about each strain component quantifies the ability of the contractive, dilatational and shear strain to predict the proximity of macroscopic failure. A total of 24 models of four machine learning algorithms with six rock types indicate that 1) the dilatational strain provides the best predictive power of the strain components, and 2) the intermediate values (25th-75th percentile) of the strain population provide the best predictive power of the statistics of the strain populations. In addition, the success of the predictions of models trained on one rock type and tested on other rock types quantifies the similarities and differences of the precursory strain accumulation process in the six rock types. These similarities suggest the potential existence of a unified theory of brittle rock deformation for a range of rock types.

58 GEOSCIENCES↗
DOE OSTI2020

Active- and transfer-learning applied to microscale-macroscale coupling to simulate viscoelastic flows

Active- and transfer-learning are applied to microscale dynamics of polymer flows for the multiscale discovery of effective constitutive approximations required in viscoelastic flow simulation. The result is macroscopic rheology directly connected to a microstructural model. Micro and macroscale simulations are adaptively coupled by means of Gaussian process regression (GPR) to run the expensive microscale computations only as necessary. This multiscale method is demonstrated with flows of a polymer solution as a model system. At the microscale level dissipative particle dynamics (DPD) is employed to model the fluid as a suspension of bead-spring micro-structures subjected to steady shear flow. The results yield the non-Newtonian viscosity and the first normal stress difference at strain rates as training data used in a GPR model. DPD parameters are calibrated with respect to experimental data for a real polymer solution. Compliance with these data requires adjustment of the DPD model's cutoff radius, which then becomes a function of the second invariant of the strain rate tensor. The FENE-P model is chosen for the macroscale description using the spectral element method (SEM) to simulate channel flow and flow past a circular cylinder. The DPD results at the lowest possible shear strain rate yield an estimate of the zero-shear rate viscosity, which allows the initiation of the macroscale flow by SEM as a Newtonian fluid. The resulting strain-rate field is surveyed to determine additional shear strain rate sampling points for the DPD system. This new information allows an initial fitting of parameters of the constitutive equation followed by new SEM simulations at the macroscale. Additionally, guided by active-learning GPR to select new sampling points, this process continues until convergence is achieved. The effectiveness of this new simulation paradigm for viscoelastic flows is tested with different macroscale operating conditions. The effective closure learned in the channel simulation is then transferred directly to the flow past a circular cylinder at low Reynolds number, where the results show that only two additional DPD simulations are required to achieve a satisfactory constitutive model. With an increase of the Reynolds number, the active-learning scheme automatically detects the inaccuracy of the learned constitutive model, and initiates additional DPD simulations for the extra data needed to once again close the microscale-macroscale coupled system. This new paradigm of active- and transfer-learning for multiscale modeling is readily applicable to other microscale-macroscale coupled simulations of complex fluids and other materials. Furthermore, the coupling between microscale and macroscale solvers can be seamlessly implemented with our open source multiscale universal interface (MUI) library.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗
DOE OSTI2022

Inference-Optimized AI and High Performance Computing for Gravitational Wave Detection at Scale

We introduce an ensemble of artificial intelligence models for gravitational wave detection that we trained in the Summit supercomputer using 32 nodes, equivalent to 192 NVIDIA V100 GPUs, within 2 h. Once fully trained, we optimized these models for accelerated inference using NVIDIA TensorRT. We deployed our inference-optimized AI ensemble in the ThetaGPU supercomputer at Argonne Leadership Computer Facility to conduct distributed inference. Using the entire ThetaGPU supercomputer, consisting of 20 nodes each of which has 8 NVIDIA A100 Tensor Core GPUs and 2 AMD Rome CPUs, our NVIDIA TensorRT-optimized AI ensemble processed an entire month of advanced LIGO data (including Hanford and Livingston data streams) within 50 s. Our inference-optimized AI ensemble retains the same sensitivity of traditional AI models, namely, it identifies all known binary black hole mergers previously identified in this advanced LIGO dataset and reports no misclassifications, while also providing a 3X inference speedup compared to traditional artificial intelligence models. We used time slides to quantify the performance of our AI ensemble to process up to 5 years worth of advanced LIGO data. In this synthetically enhanced dataset, our AI ensemble reports an average of one misclassification for every month of searched advanced LIGO data. We also present the receiver operating characteristic curve of our AI ensemble using this 5 year long advanced LIGO dataset. This approach provides the required tools to conduct accelerated, AI-driven gravitational wave detection at scale.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2022

E(3)-equivariant graph neural networks for data-efficient and accurate interatomic potentials

Abstract This work presents Neural Equivariant Interatomic Potentials (NequIP), an E(3)-equivariant neural network approach for learning interatomic potentials from ab-initio calculations for molecular dynamics simulations. While most contemporary symmetry-aware models use invariant convolutions and only act on scalars, NequIP employs E(3)-equivariant convolutions for interactions of geometric tensors, resulting in a more information-rich and faithful representation of atomic environments. The method achieves state-of-the-art accuracy on a challenging and diverse set of molecules and materials while exhibiting remarkable data efficiency. NequIP outperforms existing models with up to three orders of magnitude fewer training data, challenging the widely held belief that deep neural networks require massive training sets. The high data efficiency of the method allows for the construction of accurate potentials using high-order quantum chemical level of theory as reference and enables high-fidelity molecular dynamics simulations over long time scales.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2024

HydraGNN_Predictive_GFM_2024 - Ensemble of predictive graph foundation models for ground state atomistic materials modeling

We provide the ensemble of fifteen pre-trained graph foundation models (GFMs) for atomistic materials modeling applications. Each one of the fifteen GFMs has been trained on five open-source datasets that (once aggregated) amount to over 154 million atomistic structures, which cover over two-thirds of the natural elements of the periodic table and that comprises a broad set of organic and inorganic compounds. This vast set of atomistic structures comprises ground state configurations that are dynamically stable (i.e., equilibrated structures with atomic forces approximately close to zero values) as well as dynamically unstable structures (i.e., non-equilibrium structures with non-negligible non-zero values of atomic forces). The ensemble of datasets aggregated does NOT include excited states. The datasets have been curated to remove atomistic structures with spectral norm of the force tensor above 100 eV/angstrom. Moreover, a linear term of the energy was computed for each dataset using a linear regression model that uses the chemical concentration of each natural element as regressor. The linear term predicted by the linear regression model has been subtracted from each original energy value to perform a re-alignment of the energy values across different electronic structures approximation theories performed to generate the diverse multi-source, multi-fidelity datasets. The folder "ADIOS_files" 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 "ADIOS_files" directory contains 6 sub-directories named as follows: - ANI1x-v3.bp - MPTrj-v3.bp - OC2020-20M-v3.bp - OC2020-v3.bp - OC2022-v3.bp - qm7x-v3.bp Each sub-directory contains the pre-processed datasets converted in Adaptable I/O System (ADIOS) format (https://www.exascaleproject.org/research-project/adios/) that have been used to the development, training, and performance testing of the ensemble go predictive graph foundation models. Each GFM was developed using HydraGNN (https://github.com/ORNL/HydraGNN) as underlying graph neural network (GNN) architecture. The multi-task learning (MTL) capability of HydraGNN was used to simultaneously train the GFMs on labeled values for direct predictions of energy (a total system property of an atomistic structure that measures the chemical stability) and atomic forces (an atomic level property of an atomistic structure that measures the dynamical stability). The hyper parameters of the GFM have been tuned using scalable hyperparameter optimization (HPO) algorithms implemented in the software DeepHyper (https://github.com/deephyper/deephyper). The pre-training of each HPO trial was performed using distributed data parallelism (DDP) to scale the training across 128 compute nodes of the exascale OLCF supercomputer Frontier. Each HPO trial was trained only for 10 epochs and an early stopping was performed to avoid wasting significant computational resources on GNN architectures that were clearly underperforming. For each HPO trial, the 'omnistat' tool developed by (AMD Research - Advanced Micro Device) was used to measure the total energy consumption in kWh. The ensemble of GFMs was obtained by selecting the fifteen best performing HPO trials. Four models have been selected for their clear advantage in accuracy, and these are the GFMs with IDs 229, 156, 147, 260. Additional eleven models have been selected based on judicious balance between accuracy and energy consumption needed for training, and these are the GFMs with IDs 165, 78, 137, 1, 175, 171, 181, 67, 179, 167, 351. Each selected GFM of the ensemble was continued to cumulate a total of at most 30 epochs. In some cases, the total number of epochs actually performed was les than 30 due to two combined factors: (1) the size of the GFM (i.e., the number of model parameters to train) and (2) the total wall-clock time for which the computational resources could be allocated on OLCF-Frontier. The "Ensemble_of_models" directory contains 15 sub-directories named as follows: - gfm_0.229 - gfm_0.156 - gfm_0.147 - gfm_0.260 - gfm_0.165 - gfm_0.78 - gfm_0.137 - gfm_0.1 - gfm_0.175 - gfm_0.171 - gfm_0.181 - gfm_0.67 - gfm_0.179 - gfm_0.167 - gfm_0.351 Each one of these sub-directories refers to one of the fifteen HPO trials that have been selected to continue the pre-training with at most 30 epochs. With each sub-directory associated with a specific HPO trial, the following files can be found: - config.json: file for argument parsing to develop and train an HydraGNN architecture - gfm_0.ID_epoch_N.pk: file with model parameters for HPO ID trial after N epochs of training The ensemble of fifteen GFM architectures was used for (1) ensemble averaging to stabilize the predictions of energy and atomic forces after pre-training for post-processing analysis and (2) ensemble uncertainty quantification (UQ). The code used to develop, pre-train, and load the pre-trained models for post-processing analysis is available on the ORNL-GitHub at the following link: https://github.com/ORNL/HydraGNN/tree/Predictive_GFM_2024

36 MATERIALS SCIENCE↗
DOE OSTI2024

Chapter 4: Physically informed deep learning networks for simulating microstructure evolution of 3D polycrystals

As discussed in the previous chapter, high energy diffraction microscopy (HEDM) is used to study the micromechanical evolution of a material during in situ loading. HEDM experiments have been used to verify crystal plasticity (CP) simulations [119, 91, 90, 120], for experimental planning, material design, and to further analyze experimental results. However, Fast Fourier transform-based CP (CP-FFT) or finite element-based CP (CP-FE) methods are often too slow to be used in real-time during an experiment. CP-FFT is faster than CP-FE simulations due to the absence of meshing, but can still take hours to simulate the response of a single volume depending on the size and number of strain steps [127]. Reducing computation time would create a larger exploration space in planning and design, and enable faster analysis of experimental results and real-time feedback during an experiment. This research expands upon previous works to develop a workflow for predicting the full-field evolution of a 3D polycrystal. The workflow is simplified from previous works to predict only orientation and elastic strain tensors (from which stress tensors are calculated). The network is physically informed through loss functions and network architecture for a more robust model. The orientation predictions are informed about the cubic crystal symmetry of the material by incorporating disorientation and misorientation information into the network architecture and loss. The Von Mises stress is used to enforce the correct stress-strain trends in the strain tensor predictions. Additional total strain steps from the elastic and elastoplastic region are included to better capture the stress-strain evolution at smaller total strain steps. Material and hardening parameters are additional inputs into the networks to further inform the network and to study the network’s ability to predict different materials other than those used for training.

36 MATERIALS SCIENCE↗
DOE OSTI2023

AdversarialTensors

This library builds a framework for defending ML models against adversarial attacks. The library will be developed at various stages leading to publication and software release at each stage. We employ tensor decomposition strategies as preprocessing stages for the first stage to provide robustness against the prominent adversarial noise. In the second stage, we develop a latent noise generator capable of generating novel adversarial noise that threatens the existing state-of-the-art defense strategy. In the third stage, we develop a UNSUP-GAN model, where the generator is trained to denoise against latent noise and most adversarial noises. This generator can provide a robust adversarial attack against any unseen attack.

Bhattarai, Manish↗
NASA NTRS2014

Physiological Observations and Omics to Develop Personalized Sensormotor Adaptability Countermeasures Using Bed Rest and Space Flight Data

Astronauts experience sensorimotor disturbances during the initial exposure to microgravity and during the re-adapation phase following a return to an earth-gravitational environment. These alterations may disrupt the ability to perform mission critical functional tasks requiring ambulation, manual control and gaze stability. Interestingly, astronauts who return from space flight show substantial differences in their abilities to readapt to a gravitational environment. The ability to predict the manner and degree to which individual astronauts would be affected would improve the effectiveness of countermeasure training programs designed to enhance sensorimotor adaptability. For such an approach to succeed, we must develop predictive measures of sensorimotor adaptability that will allow us to foresee, before actual space flight, which crewmembers are likely to experience the greatest challenges to their adaptive capacities. The goals of this project are to identify and characterize this set of predictive measures that include: 1) behavioral tests to assess sensory bias and adaptability quantified using both strategic and plastic-adaptive responses; 2) imaging to determine individual brain morphological and functional features using structural magnetic resonance imaging (MRI), diffusion tensor imaging, resting state functional connectivity MRI, and sensorimotor adaptation task-related functional brain activation; 3) genotype markers for genetic polymorphisms in Catechol-O-Methyl Transferase, Dopamine Receptor D2, Brain-derived neurotrophic factor and genetic polymorphism of alpha2-adrenergic receptor that play a role in the neural pathways underlying sensorimotor adaptation. We anticipate these predictive measures will be significantly correlated with individual differences in sensorimotor adaptability after long-duration space flight and an analog bed rest environment. We will be conducting a retrospective study leveraging data already collected from relevant ongoing/completed bed rest and space flight studies. These data will be combined with predictor metrics that will be collected prospectively - behavioral, brain imaging and genomic measures; from these returning subjects to build models for predicting post-mission (bed rest - non-astronauts or space flight - astronauts) adaptive capability as manifested in their outcome measures. Comparisons of model performance will allow us to better design and implement sensorimotor adaptability training countermeasures that are customized for each crewmember's sensory biases, adaptive capacity, brain structure and functional capacities, and genetic predispositions against decrements in post-mission adaptive capability. This ability will allow more efficient use of crew time during training and will optimize training prescriptions for astronauts to ensure expected outcomes.

Mulavara, A. P.↗
DOE OSTI2023

Reduced Order Model to Predict Dispersion of Flammable Refrigerant into a Space

As the HVAC&R industry mobilizes to deploy more low-GWP refrigerants, relevant standards are being continually reviewed and updated. Those include the general safety standards ISO 5149 and ASHRAE 15, and the equipment standards IEC and UL. The standards systematically set the allowable maximum amount of refrigerant that should be used in different equipment types and different applications. To do so, they rely on predictions of how a leaked refrigerant mass will disperse into a space. Dispersion characteristics, such as total flammable volume and its residence time, determine the risk associated with the presence of the flammable refrigerant. The standards have included provisions for the use of flammable refrigerants for approximately two decades. They relied on limited analytical analyses and test cases in their development. Dispersion of a refrigerant into a space is complex. Computational fluid dynamics (CFD) are the most accurate in predicting a given problem. However, CFD is computationally expensive and requires specialized expertise and resources and is not suitable for use by standards development working group as prediction tool. This paper presents the development of a reduced order model (ROM) that predicts the key dispersion characteristics relevant to the dispersion of a leaked refrigerant into a space for any combination of input variables. The inputs are the refrigerant release height, the total released refrigerant mass and its release flow rate, the refrigerant molecular weight, the ventilation flow rate, the floor area and height of the space, recirculation air flow rate, and the tightness of the space. The outputs are histograms of volume fraction of the room in prescribed concentration bins and the total mass of the refrigerant in each bin normalized by the total refrigerant charge at 13 prescribed simulation time stamps between 1 and 900 seconds. The ROM is constructed from a set of CFD simulations with carefully chosen combinations of input parameters. The selection if done using a multidimensional sparse grid which is a generalization of the classical tensor approach but offers additional flexibility and thus can be more carefully tuned towards a specific model. The tuning is done to improve the accuracy, measured in the difference between the output values of the ROM and the CFD model, while minimizing the computational cost, measured in number of CFD simulations which is orders of magnitude more expensive than the processing the training data.

Edwards, Dean↗
NASA NTRS2017

Behavioral, Brain Imaging and Genomic Measures to Predict Functional Outcomes Post-Bed Rest and Space Flight

Astronauts experience sensorimotor disturbances during their initial exposure to microgravity and during the re-adaptation phase following a return to an Earth-gravitational environment. These alterations may disrupt crewmembers' ability to perform mission critical functional tasks requiring ambulation, manual control and gaze stability. Interestingly, astronauts who return from spaceflight show substantial differences in their abilities to readapt to a gravitational environment. The ability to predict the manner and degree to which individual astronauts are affected will improve the effectiveness of countermeasure training programs designed to enhance sensorimotor adaptability. For such an approach to succeed, we must develop predictive measures of sensorimotor adaptability that will allow us to foresee, before actual spaceflight, which crewmembers are likely to experience greater challenges to their adaptive capacities. The goals of this project are to identify and characterize this set of predictive measures. Our approach includes: 1) behavioral tests to assess sensory bias and adaptability quantified using both strategic and plastic-adaptive responses; 2) imaging to determine individual brain morphological and functional features, using structural magnetic resonance imaging (MRI), diffusion tensor imaging, resting state functional connectivity MRI, and sensorimotor adaptation task-related functional brain activation; and 3) assessment of genetic polymorphisms in the catechol-O-methyl transferase, dopamine receptor D2, and brain-derived neurotrophic factor genes and genetic polymorphisms of alpha2-adrenergic receptors that play a role in the neural pathways underlying sensorimotor adaptation. We anticipate that these predictive measures will be significantly correlated with individual differences in sensorimotor adaptability after long-duration spaceflight and exposure to an analog bed rest environment. We will be conducting a retrospective study, leveraging data already collected from relevant ongoing or completed bed rest and spaceflight studies. This data will be combined with predictor metrics that will be collected prospectively (as described for behavioral, brain imaging and genomic measures) from these returning subjects to build models for predicting post spaceflight and bed rest adaptive capability. In this presentation we will discuss the optimized set of tests for predictive metrics to be used for evaluating post mission adaptive capability as manifested in their outcome measures. Comparisons of model performance will allow us to better design and implement sensorimotor adaptability training countermeasures against decrements in post-mission adaptive capability that are customized for each crewmember's sensory biases, adaptive ability, brain structure, brain function, and genetic predispositions. The ability to customize adaptability training will allow more efficient use of crew time during training and will optimize training prescriptions for astronauts to mitigate the deleterious effects of spaceflight.

Mulavara, A. P.↗
NASA NTRS2016

Behavioral, Brain Imaging and Genomic Measures to Predict Functional Outcomes Post - Bed Rest and Spaceflight

Astronauts experience sensorimotor disturbances during their initial exposure to microgravity and during the re-adaptation phase following a return to an Earth-gravitational environment. These alterations may disrupt crewmembers' ability to perform mission critical functional tasks requiring ambulation, manual control and gaze stability. Interestingly, astronauts who return from spaceflight show substantial differences in their abilities to readapt to a gravitational environment. The ability to predict the manner and degree to which individual astronauts would be affected would improve the effectiveness of countermeasure training programs designed to enhance sensorimotor adaptability. For such an approach to succeed, we must develop predictive measures of sensorimotor adaptability that will allow us to foresee, before actual spaceflight, which crewmembers are likely to experience the greatest challenges to their adaptive capacities. The goals of this project are to identify and characterize this set of predictive measures. Our approach includes: 1) behavioral tests to assess sensory bias and adaptability quantified using both strategic and plastic-adaptive responses; 2) imaging to determine individual brain morphological and functional features, using structural magnetic resonance imaging (MRI), diffusion tensor imaging, resting state functional connectivity MRI, and sensorimotor adaptation task-related functional brain activation; and 3) assessment of genotypic markers of genetic polymorphisms in the catechol-O-methyl transferase, dopamine receptor D2, and brain-derived neurotrophic factor genes and genetic polymorphisms of alpha2-adrenergic receptors that play a role in the neural pathways underlying sensorimotor adaptation. We anticipate that these predictive measures will be significantly correlated with individual differences in sensorimotor adaptability after long-duration spaceflight and exposure to an analog bed rest environment. We will be conducting a retrospective study, leveraging data already collected from relevant ongoing or completed bed rest and spaceflight studies. These data will be combined with predictor metrics that will be collected prospectively (as described for behavioral, brain imaging and genomic measures) from these returning subjects to build models for predicting post-mission (bed rest - non-astronauts or space flight - astronauts) adaptive capability as manifested in their outcome measures. To date we have completed a study on 15 normal subjects with all of the above measures. In this presentation we will discuss the optimized set of tests for predictive metrics to be used for evaluating post mission adaptive capability as manifested in their outcome measures. Comparisons of model performance will allow us to better design and implement sensorimotor adaptability training countermeasures against decrements in post-mission adaptive capability that are customized for each crewmember's sensory biases, adaptive capacity, brain structure and functional capacities, and genetic predispositions. The ability to customize adaptability training will allow more efficient use of crew time during training and will optimize training prescriptions for astronauts to ensure expected outcomes.

Mulavara, A. P.↗
DOE OSTI2025

Multiplexing Focusing Analyzer for Efficient Stress-Strain Measurements

Statement of the problem or situation that is being addressed. Although thermal and cold neutron scattering is widely used and is critical for success in many areas of materials science and engineering, relatively low neutron fluxes severely limit applications of not only laboratory neutrons generators, but also large national neutron facilities. State-of-the-art thermal and cold neutron sources are large expensive national facilities, which serve diverse community of scientific and industrial users. The constant need to improve the instruments performance, stems from the fact that neutron methods are gaining in popularity, and becoming more and more powerful, while new neutron sources are not being constructed to keep pace with the developments and needs of the scientific community. Small research reactors at universities and National Labs, and laboratory-based neutron generators, are necessary not only for education and training, but also when samples cannot be transported to other facilities. However, the standard neutron techniques, which were developed for high-flux facilities, require much higher efficiencies to be used effectively with the low fluxes of small sources. Thus, the efficient use of neutron sources, such as with our proposed analyzer, is important for the progress and broader use of these neutron techniques. General statement of how this problem is being addressed. We propose to design and demonstrate novel diffractive optical device, which will enable very efficient residual stress neutron diffractometers. The proposed device will be a multi-foil analyzer, where each foil is constructed of focusing bent single crystals of Si. Such device will enable polychromatic residual stress neutron diffraction. At large national facilities, such as at Oak Ridge National Laboratory, these analyzers would enable very fast measurements for determining residual stress tensors, raster large samples or screen multiple samples. Commercial Applications and Other Benefits The outcome of this project would be the demonstration of commercial devices, novel neutron optical components, which could be utilized to improve the performance of existing instruments or build novel neutron scattering instruments at DOE neutron facilities and commercial laboratory neutron sources. These new devices will widen the scope of research conducted using neutrons and enable measurements not feasible at present. Summary for Members of Congress Thermal and cold neutron beams are a powerful materials science probe, which provide unique information about the structure of matter. The proposed innovations expand the reach of neutron-based investigations to new materials and industries by enabling new instrumentation capabilities, thereby greatly enhancing and expanding the role of small, laboratory-based neutron instrumentation, and improving education and training of neutron users.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
DOE OSTI2023

Machine Learning Full NMR Chemical Shift Tensors of Silicon Oxides with Equivariant Graph Neural Networks

The nuclear magnetic resonance (NMR) chemical shift tensor is a highly sensitive probe of the electronic structure of an atom and furthermore its local structure. Recently, machine learning has been applied to NMR in the prediction of isotropic chemical shifts from a structure. Current machine learning models, however, often ignore the full chemical shift tensor for the easier-to-predict isotropic chemical shift, effectively ignoring a multitude of structural information available in the NMR chemical shift tensor. Here we use an equivariant graph neural network (GNN) to predict full 29 Si chemical shift tensors in silicate materials. The equivariant GNN model predicts full tensors to a mean absolute error of 1.05 ppm and is able to accurately determine the magnitude, anisotropy, and tensor orientation in a diverse set of silicon oxide local structures. When compared with other models, the equivariant GNN model outperforms the state-of-the-art machine learning models by 53%. The equivariant GNN model also outperforms historic analytical models by 57% for isotropic chemical shift and 91% for anisotropy. The software is available as a simple-to-use open-source repository, allowing similar models to be created and trained with ease.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2024

Bridging the Gap Between LLMs and LNS with Dynamic Data Format and Architecture Codesign

Deep neural networks (DNNs) have achieved tremendous success in the past few years. However, their training and inference demand exceptional computational and memory resources. Quantization has been shown as an effective approach to mitigate the cost, with the mainstream data types reduced from FP32 to FP16/BF16 and recently FP8 in the latest NVIDIA H100 GPUs. With increasingly aggressive quantization, however, the conventional floating-point formats suffer from limited precision in representing numbers around zero. Recently, NVIDIA demonstrated the potential of using a Logarithmic Number System (LNS) for the next generation of tensor cores. While LNS mitigates the hurdles in representing small numbers, in this work we observed a mismatch between LNS and the emerging Large Language Models (LLM), where LLM exhibits significant outliers when directly adopting the LNS format. In this paper, we present a data-format/architecture codesign to bright this gap. On the format side, we propose a dynamic LNS format to flexibly represent outliers at a higher precision, by exploiting asymmetry in the LNS representation and identifying outliers through a per-vector basis. On the architecture side, for demonstration, we realize the dynamic LNS format in a systolic array, which can handle the irregularity of the outliers at runtime. We implement our approach on an Alveo U280 FPGA as a prototype. Experimental results show that our design can effectively handle the outliers and resolve the mismatch between LNS and LLM, contributing to an accuracy improvement of 15.4% and 16% over the floating-point and the original LNS baselines, using four state-of-the-art LLM models. Our observation and design lay a solid foundation for the large-scale adoption of the LNS format in the next-generation deep learning hardware.

Haghi, Pouya↗