Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Predictive Modeling”

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 1,081 records · Page 60
All sourcesNASA NTRSDOE OSTI
DOE OSTI2023

Explainability and extrapolation of machine learning models for predicting the glass transition temperature of polymers

Abstract Machine learning (ML) offers promising tools to develop surrogate models for polymers' structure–property relations. Surrogate models can be built upon existing polymer data and are useful for rapidly predicting the properties of unknown polymers. The accuracy of such ML models appears to depend on the feature space representation of polymers, the range of training data, and learning algorithms. Here, we establish connections between these factors for predicting the glass transition temperature (T g ) of polymers. Our analysis suggests linear models with fewer fitting parameters are as accurate as nonlinear models with many hidden and unexplainable parameters. Also, the performance of a monomer topology‐based ML model is found to be qualitatively identical to that of a physicochemical descriptor‐based ML model. We find that the ML models's performance in the extrapolative region is enhanced as the property range of the training data increases. Moreover, we establish newT g – polymer chemistry correlations via ML. Our work illustrates how ML can advance the fundamental understanding of polymer structure–property correlations and its efficacy for extrapolation problems.

Polymer Science↗
DOE OSTI2017

Strong Stellar-driven Outflows Shape the Evolution of Galaxies at Cosmic Dawn

We study galaxy mass assembly and cosmic star formation rate (SFR) at high redshift (z ≳ 4), by comparing data from multiwavelength surveys with predictions from the GAlaxy Evolution and Assembly (gaea) model. gaea implements a stellar feedback scheme partially based on cosmological hydrodynamical simulations, which features strong stellar-driven outflows and mass-dependent timescales for the re-accretion of ejected gas. In previous work, we have shown that this scheme is able to correctly reproduce the evolution of the galaxy stellar mass function (GSMF) up to z ∼ 3. We contrast model predictions with both rest-frame ultraviolet (UV) and optical luminosity functions (LFs), which are mostly sensitive to the SFR and stellar mass, respectively. We show that gaea is able to reproduce the shape and redshift evolution of both sets of LFs. We study the impact of dust on the predicted LFs, and we find that the required level of dust attenuation is in qualitative agreement with recent estimates based on the UV continuum slope. The consistency between data and model predictions holds for the redshift evolution of the physical quantities well beyond the redshift range considered for the calibration of the original model. In particular, we show that gaea is able to recover the evolution of the GSMF up to z ∼ 7 and the cosmic SFR density up to z ∼ 10.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2019

Investigating the Dynamic Compaction Behavior of Brittle Powders

The compression of porous materials to full density is a complex physical and mechanical process. Modeling efforts to capture the compaction behavior of distended solids (e.g., porous materials or powders) have produced a variety of compaction models, each functionalized to address specific compaction mechanisms. Of the available models, those suited for high-strain-rate deformation associated with shock loading have generally been developed for ductile materials. Compaction models for brittle materials have only been developed for quasistatic loading conditions. No predictive models currently exist that successfully capture the physical processes and mechanics for shock compaction of brittle distended materials, such as sand and oxide powders. The primary hindrance in producing a dynamic compaction model for brittle distended materials is the lack of availability of high-fidelity, high-precision shock compaction data for validation. The proposed work is aimed at alleviating this issue by developing a high-precision testing method in combination with high-fidelity analysis methods to accurately and precisely determine the shocked state of an ideal test material, ceria powder, under uniaxial strain dynamic compaction. The measured shock compaction data from these brittle powder experiments is then used in initial computations to design a cylindrically converging shock compaction experiment within situ time-resolved shocked density measurements, employing proton radiography. The preliminary experimental and computational results obtained from these uniaxial strain dynamic compaction and cylindrically converging shock compaction experiments are presented. An experimental and computational path forwards to predictive model development is then proposed.

36 MATERIALS SCIENCE↗
DOE OSTI2018

Magnetic Inflation and Stellar Mass. II. On the Radii of Single, Rapidly Rotating, Fully Convective M-Dwarf Stars

Main-sequence, fully convective M dwarfs in eclipsing binaries are observed to be larger than stellar evolutionary models predict by as much as 10%–15%. A proposed explanation for this discrepancy involves effects from strong magnetic fields, induced by rapid rotation via the dynamo process. Although, a handful of single, slowly rotating M dwarfs with radius measurements from interferometry also appear to be larger than models predict, suggesting that rotation or binarity specifically may not be the sole cause of the discrepancy. We test whether single, rapidly rotating, fully convective stars are also larger than expected by measuring their Rsin i distribution. We combine photometric rotation periods from the literature with rotational broadening (vsin i) measurements reported in this work for a sample of 88 rapidly rotating M dwarf stars. Using a Bayesian framework, we find that stellar evolutionary models underestimate the radii by 10%--15%{sub −2.5}{sup +3}, but that at higher masses (0.18 < M < 0.4 M {sub Sun}), the discrepancy is only about 6% and comparable to results from interferometry and eclipsing binaries. At the lowest masses (0.08 < M < 0.18 M {sub Sun}), we find that the discrepancy between observations and theory is 13%–18%, and we argue that the discrepancy is unlikely to be due to effects from age. Furthermore, we find no statistically significant radius discrepancy between our sample and the handful of M dwarfs with interferometric radii. We conclude that neither rotation nor binarity are responsible for the inflated radii of fully convective M dwarfs, and that all fully convective M dwarfs are larger than models predict.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2018

A Two-Stage Physical-Based Model for Predicting Flow Stress of As-cast TiAl Alloy Under Hot Deformation Conditions

The hot deformation behavior of Ti-30Al-4.2Mn-4.5Nb-0.2B alloy was investigated using the isothermal compression experiment at temperatures of 1020-1200 °C and strain rates of 0.001-1 s{sup −1}. The flow stress was sensitive to the deformation parameters like temperature and strain rate, which decreases with the increase in temperature and decrease in strain rates. Based on the true stress-true strain data, a two-stage physical-based model was proposed to describe the flow stress curve of as-cast TiAl alloy during hot deformation process. For establishing the model, at first, the flow curves of dynamic recovery (DRV) were modeled by employing stress-dislocation relation and adjusting dislocation annihilation coefficient Ω. Then, the flow curves of dynamic recrystallization (DRX) were modeled by considering the dynamic softening behavior into Avrami equation. Finally, the flow curves in the entire deformation stages could be described by embedding the predicted data of DRV model (i.e., flow stress before the critical strain) into the predicted data by DRX model (i.e., flow stress after the critical strain). The critical strain for initiation of DRX was determined by the double-differentiation method. To evaluate the applicability and effectiveness of DRX kinetics equation, the DRX curves were calculated and were consistent with the microstructure observation. Comparison between the experimental and predicted data shows that the proposed physical-based model can well forecast the flow stress under a wide working domain.

36 MATERIALS SCIENCE↗
DOE OSTI2015

SPATIALLY RESOLVED l-C{sub 3}H{sup +} EMISSION IN THE HORSEHEAD PHOTODISSOCIATION REGION: FURTHER EVIDENCE FOR A TOP-DOWN HYDROCARBON CHEMISTRY

Small hydrocarbons, such as C{sub 2}H, C{sub 3}H, and C{sub 3}H{sub 2} are more abundant in photo-dissociation regions (PDRs) than expected based on gas-phase chemical models. To explore the hydrocarbon chemistry further, we observed a key intermediate species, the hydrocarbon ion l-C{sub 3}H{sup +}, in the Horsehead PDR with the Plateau de Bure Interferometer at high-angular resolution (6″). We compare with previous observations of C{sub 2}H and c-C{sub 3}H{sub 2} at similar angular resolution and new gas-phase chemical model predictions to constrain the dominant formation mechanisms of small hydrocarbons in low-UV flux PDRs. We find that at the peak of the HCO emission (PDR position), the measured l-C{sub 3}H{sup +}, C{sub 2}H, and c-C{sub 3}H{sub 2} abundances are consistent with current gas-phase model predictions. However, in the first PDR layers, at the 7.7 μm polycyclic aromatic hydrocarbon band emission peak, which are more exposed to the radiation field and where the density is lower, the C{sub 2}H and c-C{sub 3}H{sub 2} abundances are underestimated by an order of magnitude. At this position, the l-C{sub 3}H{sup +} abundance is also underpredicted by the model but only by a factor of a few. In addition, contrary to the model predictions, l-C{sub 3}H{sup +} peaks further out in the PDR than the other hydrocarbons, C{sub 2}H and c-C{sub 3}H{sub 2}. This cannot be explained by an excitation effect. Current gas-phase photochemical models thus cannot explain the observed abundances of hydrocarbons, in particular, in the first PDR layers. Our observations are consistent with a top-down hydrocarbon chemistry, in which large polyatomic molecules or small carbonaceous grains are photo-destroyed into smaller hydrocarbon molecules/precursors.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2023

Measurement of the properties of Higgs boson production at $\sqrt{s}$ = 13 TeV in the H → γγ channel using 139 fb -1 of pp collision data with the ATLAS experiment

Measurements of Higgs boson production cross-sections are carried out in the diphoton decay channel using 139 fb -1 of pp collision data at $\sqrt{s}$ = 13 TeV collected by the ATLAS experiment at the LHC. The analysis is based on the definition of 101 distinct signal regions using machine-learning techniques. The inclusive Higgs boson signal strength in the diphoton channel is measured to be $1.04^{+0.10}_{-0.09}$. Cross-sections for gluon-gluon fusion, vector-boson fusion, associated production with a W or Z boson, and top associated production processes are reported. An upper limit of 10 times the Standard Model prediction is set for the associated production process of a Higgs boson with a single top quark, which has a unique sensitivity to the sign of the top quark Yukawa coupling. Higgs boson production is further characterized through measurements of Simplified Template Cross-Sections (STXS). In total, cross-sections of 28 STXS regions are measured. The measured STXS cross-sections are compatible with their Standard Model predictions, with a p-value of 93%. The measurements are also used to set constraints on Higgs boson coupling strengths, as well as on new interactions beyond the Standard Model in an effective field theory approach. No significant deviations from the Standard Model predictions are observed in these measurements, which provide significant sensitivity improvements compared to the previous ATLAS results.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2016

Galaxies in X-Ray Selected Clusters and Groups in Dark Energy Survey Data. I. Stellar Mass Growth of Bright Central Galaxies Since z ~ 1.2

Using the science verification data of the Dark Energy Survey for a new sample of 106 X-ray selected clusters and groups, we study the stellar mass growth of bright central galaxies (BCGs) since redshift z ~ 1.2. Compared with the expectation in a semi-analytical model applied to the Millennium Simulation, the observed BCGs become under-massive/under-luminous with decreasing redshift. Here, we incorporate the uncertainties associated with cluster mass, redshift, and BCG stellar mass measurements into an analysis of a redshift-dependent BCG-cluster mass relation, $m_*$ $∝ \huge{(}$$\frac{M_{200}}{1.5x10^{14}M_⊙}\huge{)}$$^{0.24±0.08}$ $(1 + z)$$^{-0.19±0.34}$, and compare the observed relation to the model prediction. We estimate the average growth rate since z = 1.0 for BCGs hosted by clusters of M 200,z = 10 13.8 M ⊙ ; at z = 1.0: m * , BCG appears to have grown by 0.13 ± 0.11 dex, in tension at the ~2.5σ significance level with the 0.40 dex growth rate expected from the semi-analytic model. We show that the build-up of extended intracluster light after z = 1.0 may alleviate this tension in BCG growth rates.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2016

Bottom-up coarse-grained models with predictive accuracy and transferability for both structural and thermodynamic properties of heptane-toluene mixtures

This work investigates the promise of a “bottom-up” extended ensemble framework for developing coarse-grained (CG) models that provide predictive accuracy and transferability for describing both structural and thermodynamic properties. We employ a force-matching variational principle to determine system-independent, i.e., transferable, interaction potentials that optimally model the interactions in five distinct heptane-toluene mixtures. Similarly, we employ a self-consistent pressure-matching approach to determine a system-specific pressure correction for each mixture. The resulting CG potentials accurately reproduce the site-site rdfs, the volume fluctuations, and the pressure equations of state that are determined by all-atom (AA) models for the five mixtures. Furthermore, we demonstrate that these CG potentials provide similar accuracy for additional heptane-toluene mixtures that were not included their parameterization. Surprisingly, the extended ensemble approach improves not only the transferability but also the accuracy of the calculated potentials. Additionally, we observe that the required pressure corrections strongly correlate with the intermolecular cohesion of the system-specific CG potentials. Moreover, this cohesion correlates with the relative “structure” within the corresponding mapped AA ensemble. Finally, the appendix demonstrates that the self-consistent pressure-matching approach corresponds to minimizing an appropriate relative entropy.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2025

Towards a Deeper Fundamental Understanding of (Al,Sc)N Ferroelectric Nitrides

Density functional theory (DFT) calculations, within the virtual crystal alloy approximation, are performed, along with the development of a Landau-type model employing a symmetry-allowed analytical expression of the internal energy and having parameters determined from first principles, to investigate properties and energetics of Al1-xScxN ferroelectric nitrides in their hexagonal forms. These DFT computations and this model predict the existence of two different types of minima, namely, the fourfold-coordinated wurtzite (WZ) polar structure and a five-fold coordinated paraelectric hexagonal phase (denoted as H5), for any Sc composition up to 40%. The H5 minimum progressively becomes the lowest-energy state within hexagonal symmetry as the Sc concentration increases from 0 to 0.4. Furthermore, the model points to several key findings. Examples include the crucial role of the coupling between polarization and strains to create the WZ minimum, in addition to polar and elastic energies, and that the origin of the H5 state overcoming the WZ phase as the global minimum within hexagonal symmetry when increasing the Sc composition mostly lies in the compositional dependency of only two parameters-one linked to the polarization and another one being purely elastic in nature. Other examples are that forcing Al1-xScxN systems to have no or a weak change in lattice parameters when heating them allows us to reproduce their finite-temperature polar properties well and that a value of the axial ratio close to that of the ideal WZ structure implies a large polarization at low temperatures but not necessarily at high temperatures because of the ordered-disordered character of the temperature-induced formation of the WZ state. Such findings should allow for a better fundamental understanding of (Al,Sc)N ferroelectric nitrides, which may be used to design efficient devices having, e.g., low operating voltages.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2020

Building thermal load prediction through shallow machine learning and deep learning

Building thermal load prediction informs the optimization of cooling plant and thermal energy storage. Physics-based prediction models of building thermal load are constrained by the model and input complexity. In this study, we developed 12 data-driven models (7 shallow learning, 2 deep learning, and 3 heuristic methods) to predict building thermal load and compared shallow machine learning and deep learning. The 12 prediction models were compared with the measured cooling demand. It was found XGBoost (Extreme Gradient Boost) and LSTM (Long Short Term Memory) provided the most accurate load prediction in the shallow and deep learning category, and both outperformed the best baseline model, which uses the previous day's data for prediction. Then, we discussed how the prediction horizon and input uncertainty would influence the load prediction accuracy. Major conclusions are twofold: first, LSTM performs well in short-term prediction (1 h ahead) but not in long term prediction (24 h ahead), because the sequential information becomes less relevant and accordingly not so useful when the prediction horizon is long. Second, the presence of weather forecast uncertainty deteriorates XGBoost's accuracy and favors LSTM, because the sequential information makes the model more robust to input uncertainty. Training the model with the uncertain rather than accurate weather data could enhance the model's robustness. Finally, our findings have two implications for practice. First, LSTM is recommended for short-term load prediction given that weather forecast uncertainty is unavoidable. Second, XGBoost is recommended for long term prediction, and the model should be trained with the presence of input uncertainty.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗
DOE OSTI2017

Validation Assessment of a Glass-to-Metal Seal Finite-Element Model

Sealing glasses are ubiquitous in high pressure and temperature engineering applications, such as hermetic feed-through electrical connectors. A common connector technology are glass-to-metal seals where a metal shell compresses a sealing glass to create a hermetic seal. Though finite-element analysis has been used to understand and design glass-to-metal seals for many years, there has been little validation of these models. An indentation technique was employed to measure the residual stress on the surface of a simple glass-to-metal seal. Recently developed rate- dependent material models of both Schott 8061 and 304L VAR stainless steel have been applied to a finite-element model of the simple glass-to-metal seal. Model predictions of residual stress based on the evolution of material models are shown. These model predictions are compared to measured data. Validity of the finite- element predictions is discussed. It will be shown that the finite-element model of the glass-to-metal seal accurately predicts the mean residual stress in the glass near the glass-to-metal interface and is valid for this quantity of interest.

42 ENGINEERING↗
DOE OSTI2018

A semi-empirical NO x model for LES in pulverized coal air-staged combustion

Numerical simulation of pulverized coal combustion with the large eddy simulation (LES) method can provides important instructions on the design optimization of boilers. Because of its huge computational cost, a simple but reliable NO x prediction model is required in LES. Through the air-staged combustion experiments of six kinds of coals which conducted in an electric heated down-fired furnace (DFF), the relationship between NO x reduction and CO+H 2 generation in the fuel-rich zone was identified. Based on this observation, a semi-empirical modeling strategy was proposed: instead of CHi which is difficult to calculate, the concentration of CO+H 2 is used to quantify NO homogeneous reduction. An integrated NO x prediction model was proposed and implemented into LES simulation. Here, the results proved the new model can accurately predict different NO x evolution characteristics under various conditions. Furthermore, the comparison indicated the LES method performs better on NO x prediction than the RANS method, especially in the area where the turbulent fluctuation is relatively stronger.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2021

Data-driven enhancement of coherent structure-based models for predicting instantaneous wall turbulence

Predictions of the spatial representation of instantaneous wall-bounded flows, via coherent structure-based models, are highly sensitive to the geometry of the representative structures employed by them. In this study, we propose a methodology to extract the three-dimensional (3-D) geometry of the statistically significant eddies from multi-point wall-turbulence datasets, for direct implementation into these models to improve their predictions. The methodology is employed here for reconstructing a 3-D statistical picture of the inertial wall coherent turbulence for all canonical wall-bounded flows, across a decade of friction Reynolds number (Re T ). These structures are responsible for the Re T -dependence of the skin-friction drag and also facilitate the inner-outer interactions, making them key targets of structure-based models. The empirical analysis brings out the geometric self-similarity of the large-scale wall-coherent motions and also suggests the hairpin packet as the representative flow structure for all wall-bounded flows, thereby aligning with the framework on which the attached eddy model (AEM) is based. The same framework is extended here to also model the very-large-scaled motions, with a consideration of their differences in internal versus external flows. Implementation of the empirically-obtained geometric scalings for these large structures into the AEM is shown to enhance the instantaneous flow predictions for all three velocity components. Finally, an active flow control system driven by the same geometric scalings is conceptualized, towards favourably altering the influence of the wall coherent motions on the skin-friction drag.

42 ENGINEERING↗
DOE OSTI2018

Coupling of organic and inorganic aerosol systems and the effect on gas&ndash;particle partitioning in the southeastern US

Abstract. Several models were used to describe the partitioning of ammonia, water, and organic compounds between the gas and particle phases for conditions in the southeastern US during summer 2013. Existing equilibrium models and frameworks were found to be sufficient, although additional improvements in terms of estimating pure-species vapor pressures are needed. Thermodynamic model predictions were consistent, to first order, with a molar ratio of ammonium to sulfate of approximately 1.6 to 1.8 (ratio of ammonium to 2 × sulfate, R N/2S ≈ 0.8 to 0.9) with approximately 70 % of total ammonia and ammonium (NH x ) in the particle. Southeastern Aerosol Research and Characterization Network (SEARCH) gas and aerosol and Southern Oxidant and Aerosol Study (SOAS) Monitor for AeRosols and Gases in Ambient air (MARGA) aerosol measurements were consistent with these conditions. CMAQv5.2 regional chemical transport model predictions did not reflect these conditions due to a factor of 3 overestimate of the nonvolatile cations. In addition, gas-phase ammonia was overestimated in the CMAQ model leading to an even lower fraction of total ammonia in the particle. Chemical Speciation Network (CSN) and aerosol mass spectrometer (AMS) measurements indicated less ammonium per sulfate than SEARCH and MARGA measurements and were inconsistent with thermodynamic model predictions. Organic compounds were predicted to be present to some extent in the same phase as inorganic constituents, modifying their activity and resulting in a decrease in [H + ] air (H + in µg m -3 air), increase in ammonia partitioning to the gas phase, and increase in pH compared to complete organic vs. inorganic liquid&ndash;liquid phase separation. In addition, accounting for nonideal mixing modified the pH such that a fully interactive inorganic&ndash;organic system had a pH roughly 0.7 units higher than predicted using traditional methods (pH = 1.5 vs. 0.7). Particle-phase interactions of organic and inorganic compounds were found to increase partitioning towards the particle phase (vs. gas phase) for highly oxygenated (O : C ≥ 0.6) compounds including several isoprene-derived tracers as well as levoglucosan but decrease particle-phase partitioning for low O : C, monoterpene-derived species.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2026

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↗
DOE OSTI2016

Investigation on porosity and permeability change of Mount Simon sandstone (Knox County, IN, USA) under geological CO 2 sequestration conditions: a numerical simulation approach

In this paper, a numerical model was developed to simulate reactive transport with porosity and permeability change of Mount Simon sandstone (samples from Knox County, IN) after 180 days of exposure to CO 2 -saturated brine under CO 2 sequestration conditions. The model predicted formation of a high-porosity zone adjacent to the surface of the sample in contact with bulk brine, and a lower porosity zone just beyond that high-porosity zone along the path from sample/bulk brine interface to sample core. The formation of the high porosity zone was attributed to dissolution of quartz and muscovite/illite, while the formation of the lower porosity zone adjacent to the aforementioned high porosity zone was attributed to precipitation of kaolinite and feldspar. The model predicted a 40% permeability increase for the Knox sandstone sample after 180 days of exposure to CO 2 -saturated brine, which was consistent with laboratory-measured permeability results. Model-predicted solution chemistry results were also found to be consistent with laboratory-measured solution chemistry data. Finally, initial porosity, initial feldspar content and the exponent n value (determined by pore structure and tortuosity) used in permeability calculations were three important factors affecting permeability evolution of sandstone samples under CO 2 sequestration conditions.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2026

Spatiotemporal Learning in Power Modules: Wavelet-Enhanced Forecasting of Thermomechanical Degradation

Detecting internal defects in power electronics packages is critical for their performance and reliability, especially under extreme operating conditions, as these defects can lead to catastrophic failure if not properly addressed. Confocal scanning acoustic microscopy (C-SAM) plays a key role in the nondestructive evaluation of bond layer degradation within a power electronics package by detecting defects such as delamination, voids, and cracks. However, accurately quantifying and predicting these defects from C-SAM images remains a significant challenge due to the low noise-to-signal ratio, which typically arises from both imaging process and bond patterns itself. In this paper, we explore machine learning strategies for processing C-SAM images and providing predictive models of defect growth. We use C-SAM images of sintered copper and sintered silver samples, which are obtained under accelerated thermal experiments, as the representative dataset for our study. We investigate the effect of Fourier transforms and wavelet transforms on these datasets to remove high-frequency noise and address noise across multiple scales with histogram equalization to enhance the contrast and improve the visibility of defects. As a result, defect boundaries can be clearly distinguished, enabling more accurate tracking of their growth over time. We then employ different time-series forecasting algorithms on the denoised images to formulate an image-based lifetime prediction model. Statistical models and deep-learning techniques are trained on images obtained in the early stages of thermal shock, and defect growth in the later stages is predicted. Our work serves as a preliminary attempt to improve the accuracy of lifetime prediction models of power electronics packages, which is critical under extreme operating environments.

24 POWER TRANSMISSION AND DISTRIBUTION↗