SEARCH · Search NASA

Results for “network function”

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.

SourceResearch connectionFrom yearThrough year

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 649 records · Page 36

All sources NASA NTRS DOE OSTI

DOE OSTI2024

Accurate and Data‐Efficient Micro X‐ray Diffraction Phase Identification Using Multitask Learning: Application to Hydrothermal Fluids

Traditional analysis of highly distorted micro X‐ray diffraction (μ‐XRD) patterns from hydrothermal fluid environments is a time‐consuming process, often requiring substantial data preprocessing and labeled experimental data. Herein, the potential of deep learning with a multitask learning (MTL) architecture to overcome these limitations is demonstrated. MTL models are trained to identify phase information in μ‐XRD patterns, minimizing the need for labeled experimental data and masking preprocessing steps. Notably, MTL models show superior accuracy compared to binary classification convolutional neural networks. Additionally, introducing a tailored cross‐entropy loss function improves MTL model performance. Most significantly, MTL models tuned to analyze raw and unmasked XRD patterns achieve close performance to models analyzing preprocessed data, with minimal accuracy differences. This work indicates that advanced deep learning architectures like MTL can automate arduous data handling tasks, streamline the analysis of distorted XRD patterns, and reduce the reliance on labor‐intensive experimental datasets.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2026

Learning interpretable surface elasticity properties from bulk properties via neural network equation learners

Surface elasticity is central to understanding the mechanics and stability of surfaces and interfaces. It is characterized by quantities such as surface tension, residual surface stress, and surface stiffness. However their analytical expressions are typically difficult to derive from atomistic data, and depend strongly on modeling choices. This work presents a neural network-based equation learner which combines customized activation functions and connection-based pruning to discover parsimonious, closed-form equations for surface elasticity from atomistic simulations. Applying the method to seven face-centered cubic (FCC) metals, our equation learner uncovers interpretable equations that describe both low-Miller index and high-Miller index surface properties, capturing long-tail property distributions accurately. The discovered expressions are decoupled into two components: a universal, geometry-driven orientation function, and material-specific baseline coefficients. We find that lower-order properties such as surface tension are fundamentally geometry dependent, while higher-order properties such as surface stress and elasticity show more complex geometry and material dependence. We also relate material dependent coefficients to bulk properties, forming a clear map from bulk material properties to surface elasticity. Overall, this approach demonstrates that interpretable neurosymbolic machine learning can bridge the gap between atomistic simulations and physical laws, enabling the discovery of generalizable structure–property relationships for materials science phenomena such as surface elasticity.

Equation learning↗

DOE OSTI2024

Modeling inclusive electron-nucleus scattering with Bayesian artificial neural networks

We introduce a Bayesian protocol based on artificial neural networks that is suitable for modeling inclusive electron-nucleus scattering on a variety of nuclear targets with quantified uncertainties. Unlike previous applications in the field, which directly parameterize the cross sections, our approach employs artificial neural networks to represent the longitudinal and transverse response functions. In contrast to cross sections, which depend on the incoming energy, scattering angle, and energy transfer, the response functions are determined solely by the energy and momentum transfer to the system, allowing the angular component to be treated analytically. We assess the accuracy and predictive power of our framework against the extensive data in the quasielastic inclusive electron-scattering database. Additionally, we present novel extractions of the longitudinal and transverse response functions and compare them with previous experimental analysis and nuclear ab-initio calculations.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

DOE OSTI2023

Automatic detection of cataclysmic variables from SDSS images

Abstract Investigating rare and new objects have always been an important direction in astronomy. Cataclysmic variables (CVs) are ideal and natural celestial bodies for studying the accretion process of semi-detached binaries with accretion processes. However, the sample size of CVs must increase because a lager gap exists between the observational and the theoretical expanding CVs. Astronomy has entered the big data era and can provide massive images containing CV candidates. CVs as a type of faint celestial objects, are highly challenging to be identified directly from images using automatic manners. Deep learning has rapidly developed in intelligent image processing and has been widely applied in some astronomical fields with excellent detection results. YOLOX, as the latest YOLO framework, is advantageous in detecting small and dark targets. This work proposes an improved YOLOX-based framework according to the characteristics of CVs and Sloan Digital Sky Survey (SDSS) photometric images to train and verify the model to realise CV detection. We use the Convolutional Block Attention Module to increase the number of output features with the feature extraction network and adjust the feature fusion network to obtain fused features. Accordingly, the loss function is modified. Experimental results demonstrate that the improved model produces satisfactory results, with average accuracy (mean average Precision at 0.5) of 92.0%, Precision of 92.9%, Recall of 94.3%, and $F1-score$ of 93.6% on the test set. The proposed method can efficiently achieve the identification of CVs in test samples and search for CV candidates in unlabeled images. The image data vastly outnumber the spectra in the SDSS-released data. With supplementary follow-up observations or spectra, the proposed model can help astronomers in seeking and detecting CVs in a new manner to ensure that a more extensive CV catalog can be built. The proposed model may also be applied to the detection of other kinds of celestial objects.

Astronomy & Astrophysics↗

DOE OSTI2020

Small- and Wide-Angle X-ray Scattering Studies of Liquid–Liquid Phase Separation in Silicate Melts

Incongruent liquid-liquid phase separation is a common phenomenon in molten oxides, but there are few structural studies due to the high temperatures involved ca. >1600oC. In this work, we present a high-energy x-ray combined small/wide angle scattering (SAXS/WAXS) method that can directly probe non-equilibrium phase diagrams. The Porod exponent in the SAXS signal is extracted, which measures the roughness of the interface formed between different phases. Problematic volatilization of silica in Al 2 O 3 -, CaO-, and MgO-bearing silica-rich liquids were minimized using levitation, laser heating and rapid time-resolved measurements (lasting tens of seconds), to probe the kinetics of the phase separation process. The WAXS measurement simultaneously probes the local atomic structure of the liquid state and shows that the primary structural changes are associated with the SiO 2 network. Cation coordination numbers extracted from pair distribution functions support the model that the origin of phase separation in binary silicate systems is due to Coulombic repulsions between poorly screened cations. For CaO-SiO 2 , the liquid-liquid phase separation is found to correlate with a pause in the temperature dependent atomic disorder associated with SiO4 tetrahedra.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

DOE OSTI2025

Reversible Physical Gelation of Thermotropic Liquid Crystals Driven by Nanoplate Self-Assembly

Physically gelled soft materials, driven by the self-assembly of low-molecular-mass gelators (LMGs), have emerged as a platform for designing advanced gels that exhibit reversible gelation and property tunability. Liquid crystal (LC) gels are of great interest due to their supramolecular orderings as gel hosts and their enhanced electro-optical properties. In this study, we demonstrate the physical gelation of a nematic LC driven by nanoplate self-assembly, expanding the concept of gelators from small molecules to nanoparticles. These nanoplates are functionalized with promesogenic ligands and form a fibrillar network in LCs with face-to-face interplate stacking, resembling LMGs. The critical gelation volume fraction in the tilt test is only 0.14 v %, comparable to values reported for LMGs. Rheological analyses confirm viscoelastic properties characteristic of gelation. In situ small-angle X-ray scattering (SAXS) characterizes the formation of nanoplate networks in the LC with decreasing temperature, wherein LC mesogens become trapped in pores. Molecular dynamics (MD) simulations reveal that the interaction between ligand-coated nanoplates and LC-forming mesogens induces a multidomain LC structure, increasing friction between LC domains and stabilizing the gel. This study establishes direct relationships among molecular interactions, nanostructures, and mechanical properties in physically gelled LCs. In conclusion, the findings inspire the future gelator design of both LMGs and nanoplates, with potential applicability in bioscaffold engineering and liquid crystalline nanocomposites.

36 MATERIALS SCIENCE↗

DOE OSTI2022

Density of states prediction for materials discovery via contrastive learning from probabilistic embeddings

Abstract Machine learning for materials discovery has largely focused on predicting an individual scalar rather than multiple related properties, where spectral properties are an important example. Fundamental spectral properties include the phonon density of states (phDOS) and the electronic density of states (eDOS), which individually or collectively are the origins of a breadth of materials observables and functions. Building upon the success of graph attention networks for encoding crystalline materials, we introduce a probabilistic embedding generator specifically tailored to the prediction of spectral properties. Coupled with supervised contrastive learning, our materials-to-spectrum (Mat2Spec) model outperforms state-of-the-art methods for predicting ab initio phDOS and eDOS for crystalline materials. We demonstrate Mat2Spec’s ability to identify eDOS gaps below the Fermi energy, validating predictions with ab initio calculations and thereby discovering candidate thermoelectrics and transparent conductors. Mat2Spec is an exemplar framework for predicting spectral properties of materials via strategically incorporated machine learning techniques.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2023

Boosting the interfacial superionic conduction of halide solid electrolytes for all-solid-state batteries

Designing highly conductive and (electro)chemical stable inorganic solid electrolytes using cost-effective materials is crucial for developing all-solid-state batteries. Here, we report halide nanocomposite solid electrolytes (HNSEs) ZrO 2 (-ACl)-A 2 ZrCl 6 (A = Li or Na) that demonstrate improved ionic conductivities at 30 °C, from 0.40 to 1.3 mS cm -1 and from 0.011 to 0.11 mS cm -1 for Li + and Na + , respectively, compared to A 2 ZrCl 6 , and improved compatibility with sulfide solid electrolytes. The mechanochemical method employing Li 2 O for the HNSEs synthesis enables the formation of nanostructured networks that promote interfacial superionic conduction. Via density functional theory calculations combined with synchrotron X-ray and 6 Li nuclear magnetic resonance measurements and analyses, we demonstrate that interfacial oxygen-substituted compounds are responsible for the boosted interfacial conduction mechanism. Compared to state-of-the-art Li 2 ZrCl 6 , the fluorinated ZrO 2 -2Li 2 ZrCl 5 F HNSE shows improved high-voltage stability and interfacial compatibility with Li 6 PS 5 Cl and layered lithium transition metal oxide-based positive electrodes without detrimentally affecting Li + conductivity. We also report the assembly and testing of a Li-In||LiNi 0.88 Co 0.11 Mn 0.01 O 2 all-solid-state lab-scale cell operating at 30 °C and 70 MPa and capable of delivering a specific discharge of 115 mAh g -1 after almost 2000 cycles at 400 mA g -1 .

36 MATERIALS SCIENCE↗

DOE OSTI2022

Bridging microscopy with molecular dynamics and quantum simulations: an atomAI based pipeline

Recent advances in (scanning) transmission electron microscopy have enabled a routine generation of large volumes of high-veracity structural data on 2D and 3D materials, naturally offering the challenge of using these as starting inputs for atomistic simulations. In this fashion, the theory will address experimentally emerging structures, as opposed to the full range of theoretically possible atomic configurations. However, this challenge is highly nontrivial due to the extreme disparity between intrinsic timescales accessible to modern simulations and microscopy, as well as latencies of microscopy and simulations per se. Addressing this issue requires as a first step bridging the instrumental data flow and physics-based simulation environment, to enable the selection of regions of interest and exploring them using physical simulations. Here we report the development of the machine learning workflow that directly bridges the instrument data stream into Python-based molecular dynamics and density functional theory environments using pre-trained neural networks to convert imaging data to physical descriptors. Additionally, the pathways to ensure structural stability and compensate for the observational biases universally present in the data are identified in the workflow. This approach is used for a graphene system to reconstruct optimized geometry and simulate temperature-dependent dynamics including adsorption of Cr as an ad-atom and graphene healing effects. However, it is universal and can be used for other material systems.

36 MATERIALS SCIENCE↗

DOE OSTI2025

Anomalous softening of 3D printed elastomeric foam irradiated under compressive strain

Elastomeric foam is an essential component in many industrial and technological settings, primarily as thermal insulators and as positional/mechanical support cushions. In particular, silicone foam is utilized in harsh environments due to exceptional thermal and chemical stability. Under service conditions within certain applications such material gets exposed to a high dosage of gamma radiation, which can permanently alter the material’s structural and mechanical response properties. Most studies on gamma-exposure under inert or oxidative atmosphere indicate hardening of silicone foam, which is attributed to radiation-induced enhancement in chemical cross-linking. Here we report two contrasting effects depending on whether (non-oxidative) radiation exposure is carried out with the foam under zero or finite compressive strain. While in the former case we observe radiation-hardening consistent with previous studies, in the latter case (50% porous foam under 30% uniaxial compression) we see a monotonic decrease in Young’s modulus with increasing dosage, although solvent swelling experiments on the constituent rubber indicate a net increase in cross-link density independent of the state of strain. We quantitatively model all dose-dependent data using the Ogden Hyperfoam strain-energy function within the framework of Tobolsky two-network scheme and attribute the above anomaly to a combined effect of radiation-induced thickness change (compression set) and inherent nonlinearity in the foam’s stress-strain response.

Coarse-grained models↗

DOE OSTI2020

Solvent oligomerization pathways facilitated by electrolyte additives during solid-electrolyte interphase formation

The solid–electrolyte interphase (SEI) layer formation is known to play an important role in determining the lifetime of lithium-ion batteries. A thin, stable SEI layer is linked to overall improved battery performance and longevity, however, the factors and mechanisms that lead to optimal SEI morphology and composition are not well understood. Inclusion of electrolyte additives (fluoroethylene carbonate, FEC; and vinylene carbonate, VC) is often necessary for improving SEI characteristics. To understand how these electrolyte additives impact SEI formation, we employed molecular dynamics (MD) and density functional theory (DFT) simulations to study the reaction networks and oligomerization pathways, respectively, for three systems containing ethylene carbonate (EC), a lithium ion, and FEC or VC. MD simulations suggest radical oligomerization pathways analogous to traditional oligomerization with nucleophilic alkoxide species via SN1 reaction mechanisms. Both S N 1 and S N 2 mechanisms were studied for all three systems using DFT. Oligomerization reactions were studied with both a standard alkoxide species and a ring-opened EC radical as the nucleophiles and EC, FEC, and VC as the electrophiles. For all cases, FEC and VC exhibited lower free energy barriers and more stable adducts when compared with EC. We conclude that one of the role of additives is to modify the oligomerization process of EC by introducing branching points (FEC) or termination points (VC).

25 ENERGY STORAGE↗

DOE OSTI2021

Bond order predictions using deep neural networks

Machine learning is an extremely powerful tool for the modern theoretical chemist since it provides a method for bypassing costly algorithms for solving the Schrödinger equation. Already, it has proven able to infer molecular and atomic properties such as charges, enthalpies, dipoles, excited state energies, and others. Most of these machine learning algorithms proceed by inferring properties of individual atoms, even breaking down total molecular energy into individual atomic contributions. In this paper, we introduce a modified version of the Hierarchically Interacting Particle Neural Network (HIP-NN) capable of making predictions on the bonds between atoms rather than on the atoms themselves. We train the modified HIP-NN to infer bond orders for a large number of small organic molecules as computed via the Natural Bond Orbital package. We demonstrate that the trained model is extensible to molecules much larger than those in the training set by studying its performance on the COMP6 dataset. This method has applications in cheminformatics and force field parameterization and opens a promising future for machine learning models to predict other quantities that are defined between atoms such as density matrix elements, Hamiltonian parameters, and molecular reactivities.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

DOE OSTI2022

Representations and strategies for transferable machine learning improve model performance in chemical discovery

Strategies for machine-learning (ML)-accelerated discovery that are general across material composition spaces are essential, but demonstrations of ML have been primarily limited to narrow composition variations. By addressing the scarcity of data in promising regions of chemical space for challenging targets such as open-shell transition-metal complexes, general representations and transferable ML models that leverage known relationships in existing data will accelerate discovery. Over a large set (~1000) of isovalent transition-metal complexes, we quantify evident relationships for different properties (i.e., spin-splitting and ligand dissociation) between rows of the Periodic Table (i.e., 3d/4d metals and 2p/3p ligands). We demonstrate an extension to the graph-based revised autocorrelation (RAC) representation (i.e., eRAC) that incorporates the group number alongside the nuclear charge heuristic that otherwise overestimates dissimilarity of isovalent complexes. To address the common challenge of discovery in a new space where data are limited, we introduce a transfer learning approach in which we seed models trained on a large amount of data from one row of the Periodic Table with a small number of data points from the additional row. We demonstrate the synergistic value of the eRACs alongside this transfer learning strategy to consistently improve model performance. Analysis of these models highlights how the approach succeeds by reordering the distances between complexes to be more consistent with the Periodic Table, a property we expect to be broadly useful for other material domains.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

DOE OSTI2024

An experimental and computational view of the photoionization of diol–water clusters

In the interstellar medium, diols and other prebiotic molecules adsorb onto icy mantles surrounding dust grains. Water in the ice may affect the reactivity and photoionization of these diols. Ethylene glycol (EG), 1,2-propylene glycol, and 1,3-propylene glycol clusters with water clusters were used as a proxy to study these interactions. The diol–water clusters were generated in a continuous supersonic molecular beam, photoionized by synchrotron-based vacuum ultraviolet light from the Advanced Light Source, and subsequently detected by reflectron time-of-flight mass spectrometry. The appearance energies for the detected clusters were determined from the mass spectra, collected at increasing photon energy. Clusters of both diol fragments and unfragmented diols with water were detected. The lowest energy geometry optimized conformers for the observed EG–water clusters and EG fragment–water clusters have been visualized using density functional theory (DFT), providing insight into hydrogen bonding networks and how these affect fragmentation and appearance energy. As the number of water molecules clustered around EG fragments (m/z 31 and 32) increased, the appearance energy for the cluster decreased, indicating a stabilization by water. This trend was supported by DFT calculations. Fragment clusters from 1,2-propylene glycol exhibited a similar trend, but with a smaller energy decrease, and no trend was observed from 1,3-propylene glycol. In conclusion, we discuss and suggest that the reactivity and photoionization of diols in the presence of water depend on the size of the diol, the location of the hydroxyl group, and the number of waters clustered around the diol.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

DOE OSTI2024

Machine learning assisted search for Fe–Co–C ternary compounds with high magnetic anisotropy

We employ a machine learning (ML)-guided framework to explore rare earth free magnetic materials, specifically focusing on Fe–Co–C ternary compounds for potential use in permanent magnets. Utilizing a specifically trained crystal graph convolutional neural network model, we efficiently screen a vast space of nearly a million substitutional structures to select 620 promising structures for further investigation by first-principles calculation. We predict five low-energy metastable Fe–Co–C compounds with formation energy less than 150 meV/atom above the convex hull. These compounds exhibit high magnetization (Js > 1.0 T) and significant magnetic anisotropy (K1 > 1.0 MJ/m3), making them promising candidates for permanent magnet applications. The phonon calculations indicate these compounds are dynamically stable. Our ML-guided framework demonstrates the utility of rapidly identifying novel materials with tailored magnetic properties.

36 MATERIALS SCIENCE↗

DOE OSTI2020

Reynolds-Averaged Turbulence Modeling Using Deep Learning with Local Flow Features: An Empirical Approach

Reynolds-Averaged Navier-Stoke (RANS) models offer an alternative avenue in predicting flow characteristics when the corresponding experiments are difficult to achieve due to geometry complexity, limited budget, or knowledge. RANS models require the knowledge of subgrid scale physics to solve conservation equations for mass, energy, and momentum. Mechanistic turbulence models, such as k-epsilon, are generally evaluated and calibrated for specific flow conditions with various degrees of uncertainty. These models have limited capability to assimilate a substantial amount of data due to model form constraints. Meanwhile, deep learning (DL) has been proven to be universal approximators with the potential to assimilate available, relevant, and adequately evaluated data. Moreover, deep neural networks (DNNs) can create surrogate models without knowing function forms. Such a data-driven approach can be used in updating fluid models based on observations as opposed to hard-wiring models with precalibrated correlations. The paper presents progress in applying DNNs to model Reynolds stress using two machine learning (ML) frameworks. A novel flow feature coverage mapping is proposed to quantify the physics coverage of DL-based closures. It can be used to examine the sufficiency of training data and input flow features for data-driven turbulence models. The case of a backward-facing step is formulated to demonstrate that not only can DNNs discover underlying correlation behind fluid data but also they can be implemented in RANS to predict flow characteristics without numerical stability issues. Finally, the presented research is a crucial stepping-stone toward the data-driven turbulence modeling, which potentially benefits the design of data-driven experiments that can be used to validate fluid models with ML-based fluid closures.

42 ENGINEERING↗

DOE OSTI2025

Mitigating imaging systematics for DESI 2024 emission Line Galaxies and beyond

Emission Line Galaxies (ELGs) are one of the main tracers that the Dark Energy Spectroscopic Instrument (DESI) uses to probe the universe. However, they are afflicted by strong spurious correlations between target density and observing conditions known as imaging systematics. In this paper, we present the imaging systematics mitigation applied to the DESI Data Release 1 (DR1) large-scale structure catalogs used in the DESI 2024 cosmological analyses. We also explore extensions of the fiducial treatment. This includes a combined approach, through forward image simulations (Obiwan) in conjunction with neural network-based regression, to obtain an angular selection function that mitigates the imaging systematics observed in the DESI DR1 ELGs target density. We further derive a line of sight selection function from the forward model that removes the strong redshift dependence between imaging systematics and low redshift ELGs. Combining both angular and redshift-dependent systematics, we construct a three-dimensional selection function and assess the impact of all selection functions on clustering statistics. We quantify differences between these extended treatments and the fiducial treatment in terms of the measured 2-point statistics. We find that the results are generally consistent with the fiducial treatment and conclude that the differences are far less than the imaging systematics uncertainty included in DESI 2024 full-shape measurements. We extend our investigation to the ELGs at 0.6 < z < 0.8, i.e., beyond the redshift range (0.8 < z < 1.6) adopted for the DESI clustering catalog, and demonstrate that determining the full three-dimensional selection function is necessary in this redshift range. Our tests showed that all changes are consistent with statistical noise for BAO analyses indicating they are robust to even severe imaging systematics. Specific tests for the full-shape analysis will be presented in a companion paper.

79 ASTRONOMY AND ASTROPHYSICS↗

DOE OSTI2021

Point Adversarial Self-Mining: A Simple Method for Facial Expression Recognition

In this article, we propose a simple yet effective approach, called point adversarial self mining (PASM), to improve the recognition accuracy in facial expression recognition (FER). Unlike previous works focusing on designing specific architectures or loss functions to solve this problem, PASM boosts the network capability by simulating human learning processes: providing updated learning materials and guidance from more capable teachers. Specifically, to generate new learning materials, PASM leverages a point adversarial attack method and a trained teacher network to locate the most informative position related to the target task, generating harder learning samples to refine the network. The searched position is highly adaptive since it considers both the statistical information of each sample and the teacher network capability. Other than being provided new learning materials, the student network also receives guidance from the teacher network. After the student network finishes training, the student network changes its role and acts as a teacher, generating new learning materials and providing stronger guidance to train a better student network. Here, the adaptive learning materials generation and teacher/student update can be conducted more than one time, improving the network capability iteratively. Extensive experimental results validate the efficacy of our method over the existing state of the arts for FER.

97 MATHEMATICS AND COMPUTING↗