SEARCH · Search NASA

Results for “computational data”

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 127 records · Page 7

All sources NASA NTRS DOE OSTI

DOE OSTI2022

ZFS Interface For Accelerators

As data volume increases in HPC centers, storing data in reasonable amounts of space and time while maintaining data integrity and recoverability becomes ever more difficult. ZFS is a filesystem that provides these features, among many others, that make it attractive for usage in HPC environments. It has the ability to compress data, compute checksums, and compute redundancy codes within the same runtime, rather than compute each separately, without knowledge of the underlying structure of the filesystem. However, measurements have shown that compression on CPUs can be incredibly inefficient and significantly reduce the performance of ZFS. The ZFS Interface for Accelerators (Z.I.A.) was developed to provide an interface to route data to accelerators while being processed by ZFS, so that the ZFS infrastructure and features are maintained, while allowing for ZFS administrators to provide faster implementations of compression, or other features, to their instance of ZFS.

Lee, Jason↗

DOE OSTI2024

A Science Gateway for the Repeatable Analysis of Machine Learning Predicted Gravity Anomalies

In recent years, deep learning has become an increasingly popular alternative for modeling in geoscience applications due to its scalability and efficiency. However, the interpretability, compute, data volume, and hyperparameter tuning requirements of deep learning models make development and monitoring difficult. Furthermore, model explainability and communicating results obtained by these models to users or domain experts is a challenge, as domain experts in geoscience also need to have a deep understanding of how those models function in order to support their scientific works. Here, we describe a science gateway and machine learning pipeline for predicting gravity anomalies from geophysical data. The gateway, built on open-source technologies, provides a holistic view of the pipeline through interactive visualizations aimed at enabling efficient exploratory data analysis. The repeatability, reproducibility, and monitoring capabilities of this overall system allow us to iterate and analyze at scale. Using this pipeline and gateway, we can repeatedly produce accurate high-resolution gravity anomaly datasets. By describing the underlying technologies, implementation, and results, here we provide a foundation for the broader adoption of science gateways into cross-cutting geoscience and machine learning research projects as a means to improve the scientific discovery and collaboration in the geophysics and computational sciences community.

58 GEOSCIENCES↗

DOE OSTI2021

Data Reduction for Science: Brochure from the Advanced Scientific Computing Research Workshop

Data reduction for science holds promise for addressing the challenges of moving, storing, and processing massive data sets produced by the scientific community. Pursuing the PRDs outlined here will enable advances in data streaming, fast feedback and/or autonomous control of experiments, and faster time to scientific insight. These advances will result in a significant improvement in the ability to transport, store, process and interpret experimental, observational, and computational data.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2021

Transformative Materials for High-Efficiency Thermochemical Production of Solar Fuels (Final Report)

Metal oxide-based two-step solar thermochemical (STC) H 2 O and CO 2 -splitting cycles are a promising route to convert solar thermal energy into fuels. The metal oxide materials are reduced at high temperatures (Step 1), and then at low (but still elevated) temperatures, the reduced oxide is used to split H 2 O or CO 2 (Step 2). However, current applications of these cycles are limited by the efficiency of the metal oxide materials. A lower temperature for reduction is desirable, but that brings a concomitant reduction in the driving force for gas splitting. So, designing novel, high-efficiency materials is challenging. Here, we devised and performed a joint computational-experimental project, combined with materials design strategies and high-throughput approaches with the goal to quickly discover and demonstrate novel thermochemical materials with superior properties. Our approach involves an active feedback loop between experimental and computational research. We have use our previously developed materials design map, to efficiently screen results from high-throughput first- principles computation to predict new compositions and subsequently to experimentally study the properties of novel, predicted materials. Experimental measurements of the thermodynamic properties of selected materials serve as a critical benchmark, not only in evaluating the STCH properties of synthesized compounds, but also serving as a validation dataset for computational approaches. We experimentally explored a set of predicted ABO3 perovskites and focus on obtaining high quality thermodynamic properties for validation of computational prediction of enthalpy and entropy of reduction. These thermodynamic quantities play a major role in designing materials with reduced temperatures of reduction but sufficient gas-splitting rates. Finding good validation between experimental and computational data for enthalpies of reduction, we turn to promising ABO3 materials modified by A and B site substitutions, opening an enormous combinatorial space of materials. We use our high-throughput approach to “tune in” the desired solar thermochemical (STC) properties for STC. This vast composition space can only be reasonably explored using the high-throughput approaches, both computational and experimental, of this proposal. Several promising novel oxide materials have been predicted, synthesized, and verified using our materials design approach.

08 HYDROGEN↗

DOE OSTI2025

Defect Diffusion Graph Neural Networks for Materials Discovery in High-Temperature Energy Applications

Here, the migration of crystallographic defects dictates material properties and performance for a plethora of technological applications. Density functional theory (DFT)-based nudged elastic band (NEB) calculations are a powerful computational technique for predicting defect migration activation energy barriers, yet they become prohibitively expensive for high-throughput screening of defect diffusivities. Without introducing hand-crafted (i.e., chemistry- or structure-specific) descriptors, we propose a generalized deep learning approach to train surrogate models for NEB energies of vacancy migration by hybridizing graph neural networks with transformer encoders and simply using pristine host structures as input. With sufficient training data, computationally efficient and simultaneous inference of vacancy defect thermodynamics and migration activation energies can be obtained to compute temperature-dependent vacancy diffusivities and to down-select candidates for more thorough DFT analysis or experiments. Thus, as we specifically demonstrate for potential water-splitting materials, candidates with desired defect thermodynamics, kinetics, and host stability properties can be more rapidly targeted from open-source databases of experimentally validated or hypothetical materials.

14 SOLAR ENERGY↗

DOE OSTI2020

Retrieval of energy spectra for all flavours of neutrinos from core-collapse supernova with multiple detectors

ABSTRACT We present a new method by which to retrieve energy spectrum for all falvours of neutrinos from core-collapse supernova (CCSN). In the retrieval process, we do not assume any analytic formulas to express the energy spectrum of neutrinos but rather take a direct way of spectrum reconstruction from the observed data; the singular value decomposition algorithm with a newly developed adaptive energy-gridding technique is adopted. We employ three independent reaction channels having different flavour sensitivity to neutrinos. Two reaction channels, inverse beta decay on proton and elastic scattering on electrons, from a water Cherenkov detector such as Super-Kamiokande (SK) and Hyper-Kamiokande (HK), and a charged current reaction channel with Argon from the Deep Underground Neutrino Experiment (DUNE) are adopted. Given neutrino oscillation models, we iteratively search the neutrino energy spectra at the CCSN source until they provide the consistent event counts in the three reaction channels. We test the capability of our method by demonstrating the spectrum retrieval to a theoretical neutrino data computed by our recent three-dimensional CCSN simulation. Although the energy spectrum with either electron-type or electron-type antineutrinos at the CCSN source has relatively large error compared to that of other species, the joint analysis with HK + DUNE or SK + DUNE will provide precise energy spectrum of all flavours of neutrinos at the source. Finally, we discuss perspectives for improvements of our method by using neutrino data of other detectors.

79 ASTRONOMY AND ASTROPHYSICS↗

DOE OSTI2022

VWC-BERT: Scaling Vulnerability–Weakness–Exploit Mapping on Modern AI Accelerators

Defending cybersystems needs accurate mapping of software and hardware vulnerabilities to generalized descriptions of weaknesses, and weaknesses to exploits. These mappings enable cyber defenders to build plans for effective defense and assessment of potential risks to a cybersystem. With close to 170k vulnerabilities, manual mapping is not a feasible option. However, automated mapping is challenging due to limited training data, computational intractability, and limitations in computational natural language processing. Tools based on breakthroughs in Transformer-based language models have been demonstrated to classify vulnerabilities with high accuracy. We make three key contributions in this paper: (1) We present a new framework, \VWCBERT, that augments the Transformer-based hierarchical multi-class classification framework of Das et al. (\textsc{V2W-BERT}) with the ability to map weaknesses to exploits. (2) We implement \VWCBERT~ on modern AI accelerator platforms using two data parallel techniques for the pre-training phase and demonstrate nearly linear speedups across NVIDIA and Graphcore accelerator platforms. We observe nearly linear speedups for up to 16 V100 and 8 A100 GPUs, and about 3.4$\times$ speedup for A100 relative to V100 GPUs. We also observe excellent speedups on Graphcore, with $5.7\times$ speedup on 128 IPUs relative to 16 IPUs. Enabled by scaling, we also demonstrate higher accuracy using a larger language model, RoBERTa-Large. We show up to 87\% accuracy for strict and up to 98\% accuracy for relaxed classification. (3) We develop a novel parallel link manager for the link prediction phase and demonstrate up to 21$\times$ speedup with 16 V100 GPUs relative to one V100 GPU, and thus reducing the runtime from 2.5 hours to 10 minutes. We believe that generalizability and scalability of \VWCBERT~ will benefit both the theoretical development and practical deployment of novel cyberdefense solutions and vulnerability classification.

Das, Siddhartha Shankar↗

DOE OSTI2024

District heating utilizing waste heat of a data center: High-temperature heat pumps

Data centers are energy-intensive facilities with substantial low-grade waste heat. High-temperature heat pumps can be critical in boosting the data center’s waste heat for district heating, improving the system-level energy efficiency of data centers, and reducing CO 2 emissions in district heating. This study built thermodynamic models to assess high-temperature heat pumps with six configurations using low global warming potential refrigerants to supply heat up to 120 °C. The heat pump configurations include single-stage or two-stage cycles with advanced components, such as internal heat exchanger, economizer, flash tank, or parallel compressor. The refrigerants include R1234ze(Z), R1233ed(E), R1224yd(Z), R600, and R600a, and R245fa is used as a reference. A case study was carried out to recover the waste heat from the Frontier high-performance computing data center and provide hot water for district heating at the US Department of Energy’s Oak Ridge National Laboratory campus. The optimized performance of high-temperature heat pumps is characterized with various effectiveness of internal heat exchangers, and the operating parameters of economizer or flash tank, as well as their combination. The results show that the configurations of two-stage cycles with internal heat exchanger + flash tank and internal heat exchanger + economizer/parallel-compressor provide the highest coefficient of performance under scenarios of the maximum allowable value and a fixed value (0.3) of the internal heat exchangers’ effectiveness, respectively. R1234ze(Z) and R600a are the most promising refrigerants, considering trade-offs between the coefficient of performance and the volumetric heating capacity. The single-stage cycle with internal heat exchanger + economizer/parallel-compressor using R1234ze(Z) is recommended for utilizing Fronter’s waste heat in district heating. A one mega-watt high-temperature heat pump will reduce 33,100–33,200 metric tons of CO2 emission annually, corresponding to 85.4 %–85.6 % of equivalent CO2 emissions from natural gas boilers. Here, this study provides good guidelines for designing and deploying high-temperature heat pumps to support sustainable data centers and decarbonize district heating in the US.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗

DOE OSTI2024

Using intrahost single nucleotide variant data to predict SARS-CoV-2 detection cycle threshold values

Over the last four years, each successive wave of the COVID-19 pandemic has been caused by variants with mutations that improve the transmissibility of the virus. Despite this, we still lack tools for predicting clinically important features of the virus. In this study, we show that it is possible to predict the PCR cycle threshold (Ct) values from clinical detection assays using sequence data. Ct values often correspond with patient viral load and the epidemiological trajectory of the pandemic. Using a collection of 36,335 high quality genomes, we built models from SARS-CoV-2 intrahost single nucleotide variant (iSNV) data, computing XGBoost models from the frequencies of A, T, G, C, insertions, and deletions at each position relative to the Wuhan-Hu-1 reference genome. Our best model had an R 2 of 0.604 [0.593–0.616, 95% confidence interval] and a Root Mean Square Error (RMSE) of 5.247 [5.156–5.337], demonstrating modest predictive power. Overall, we show that the results are stable relative to an external holdout set of genomes selected from SRA and are robust to patient status and the detection instruments that were used. This study highlights the importance of developing modeling strategies that can be applied to publicly available genome sequence data for use in disease prevention and control.

COVID19↗

DOE OSTI2025

MS25: Materials Science-Focused Benchmark Data Set for Machine Learning Interatomic Potentials

Here, we present MS25, a benchmark data set for evaluating machine learning interatomic potentials (MLIPs) across diverse materials-relevant systems including MgO surfaces, liquid water, zeolites, a catalytic Pt surface reaction, high-entropy alloys (HEAs), and disordered Zr-oxides. Five MLIP architectures (MACE, NequIP, Allegro, MTP, and Torch-ANI) are trained and tested, focusing not only on traditional metrics (energies, forces, and stresses) but also explicitly validating derived physical observables such as lattice constants, volumes, and reaction barriers. We find that most models reach comparable accuracy on standard error metrics across the simple systems, although equivariant MLIPs offer 1.5–2× improvements over nonequivariant MLIPs in energy and force error for structurally complex or compositionally disordered environments such as HEAs and Zr–O systems. Our analysis highlights that low errors in energy and force predictions do not guarantee reliable observables, emphasizing the necessity of explicit validation. We demonstrate limitations in cross-framework transferability, as models trained on one zeolite framework (CHA) fail to reliably generalize to predictions of structurally distinct frameworks (e.g., MFI). Size-extensive tests show some dependence on system size for MgO, resulting from forced periodicity. The HEA and Zr–O data sets are identified as challenging tests for future benchmarks and MLIP model architecture developments as they show significant differentiation in error between MLIP architectures and are still relatively difficult at 1000 training images. Moving forward, we recommend that benchmarking efforts shift their focus from marginal accuracy improvements in energy and force errors toward identifying and understanding model failure modes, rigorously assessing transferability, and evaluating how their errors affect observable predictions. For researchers looking to choose an MLIP architecture, we suggest selecting equivariant MLIP architectures if the complexity of the system is a challenge. For simple materials problems, auxiliary features such as integration with molecular dynamics engines, trade-offs between computational data set generation cost vs MLIP inference speed, and framework integration may play a more important decision factor than small differences in error metrics that are unlikely to matter for production-level research.

chemical structure↗

DOE OSTI2022

End-to-end optimization for battery materials and molecules by combining graph neural networks and reinforcement learning

The National Renewable Energy Laboratory (NREL), together with the Colorado School of Mines (CSM) and Colorado State University (CSU), has developed a machine learning-enhanced approach to design new battery materials. Currently, such materials are designed in part via numerous expensive high-fidelity computational simulations that predict the performance of a given composition. Even with computational screening tools, the vast landscape of possible molecular or crystal structures exceeds current and future computational capacity. Improving the efficiency by which new materials can be optimized will therefore disrupt the cost, risk, and time required to bring new energy solutions to the marketplace. Predicting the properties of an organic molecule or periodic crystalline material given its structure has grown increasingly common. These approaches leverage large-scale computational and experimental databases and ML approaches such as graph neural networks. The inverse design problem of finding a material that possesses desired properties is substantially more challenging, since enumerating all valid material structures is not feasible. In this project, we leveraged recent success in reinforcement learning to efficiently navigate this high-dimensional search space. Just as algorithms can find the optimal chess moves from nearly limitless options, we train an approach to evolve a simple starting structure into a complex structure that possess the desired properties. Our solution has been demonstrated by applying it to two related design application tasks for short- and long-term energy storage, respectively: (1) the design of solid-state ion conductors and (2) the design of organic redox-active materials. The project has resulted an open-source software library for material design, documented examples of applying the library to both organic and inorganic material optimization, and peer-reviewed publications detailing the data, computational models, and resulting candidate materials.

25 ENERGY STORAGE↗

DOE OSTI2022

End-to-End Optimization for Battery Materials and Molecules by Combining Graph Neural Networks and Reinforcement Learning

The National Renewable Energy Laboratory (NREL), together with the Colorado School of Mines (CSM) and Colorado State University (CSU), has developed a machine learning-enhanced approach to the design of new battery materials. Currently, such materials are designed in part via numerous expensive high-fidelity computational simulations that predict the performance of a given composition. Even with computational screening tools, the vast landscape of possible molecular or crystal structures exceeds current and future computational capacity. Improving the efficiency by which new materials can be optimized will therefore disrupt the cost, risk, and time required to bring new energy solutions to the marketplace. Predicting the properties of an organic molecule or periodic crystalline material given its structure has grown increasingly common. These approaches leverage large-scale computational and experimental databases and ML approaches such as graph neural networks. The inverse design problem of finding a material that possesses desired properties is substantially more challenging, since enumerating all valid material structures is not feasible. In this project, we leveraged recent success in reinforcement learning to efficiently navigate this high-dimensional search space. Just as algorithms can find the optimal chess moves from nearly limitless options, we train an approach to evolve a simple starting structure into a complex structure that possess the desired properties. Our solution has been demonstrated by applying it to two related design application tasks for short- and long-term energy storage, respectively: (1) the design of solid-state ion conductors and (2) the design of organic redox-active materials. The project has resulted an open-source software library for material design, documented examples of applying the library to both organic and inorganic material optimization, and peer-reviewed publications detailing the data, computational models, and resulting candidate materials.

25 ENERGY STORAGE↗

DOE OSTI2026

Opportunities in AI/ML for the Rubin LSST Dark Energy Science Collaboration

The Vera C. Rubin Observatory's Legacy Survey of Space and Time (LSST) will produce unprecedented volumes of heterogeneous astronomical data (images, catalogs, and alerts) that challenge traditional analysis pipelines. The LSST Dark Energy Science Collaboration (DESC) aims to derive robust constraints on dark energy and dark matter from these data, requiring methods that are statistically powerful, scalable, and operationally reliable. Artificial intelligence and machine learning (AI/ML) are already embedded across DESC science workflows, from photometric redshifts and transient classification to weak lensing inference and cosmological simulations. Yet their utility for precision cosmology hinges on trustworthy uncertainty quantification, robustness to covariate shift and model misspecification, and reproducible integration within scientific pipelines. This white paper surveys the current landscape of AI/ML across DESC's primary cosmological probes and cross-cutting analyses, revealing that the same core methodologies and fundamental challenges recur across disparate science cases. Since progress on these cross-cutting challenges would benefit multiple probes simultaneously, we identify key methodological research priorities, including Bayesian inference at scale, physics-informed methods, validation frameworks, and active learning for discovery. With an eye on emerging techniques, we also explore the potential of the latest foundation model methodologies and LLM-driven agentic AI systems to reshape DESC workflows, provided their deployment is coupled with rigorous evaluation and governance. Finally, we discuss critical software, computing, data infrastructure, and human capital requirements for the successful deployment of these new methodologies, and consider associated risks and opportunities for broader coordination with external actors.

Aubourg, Eric [APC, Paris] (ORCID:000000025592023X↗

DOE OSTI2025

Vision Foundation Models in Remote Sensing: A survey

Artificial intelligence (AI) technologies have profoundly transformed the field of remote sensing (RS), revolutionizing data collection, processing, and analysis. Traditionally reliant on manual interpretation and task-specific models, RS research has been significantly enhanced by the advent of foundation models (FMs)—large-scale pretrained AI models capable of performing a wide array of tasks with unprecedented accuracy and efficiency. This article provides a comprehensive survey of FMs in the RS domain. We categorize these models based on their architectures, pretraining datasets, and methodologies. Through detailed performance comparisons, we highlight emerging trends and the significant advancements achieved by those FMs. Additionally, we discuss technical challenges, practical implications, and future research directions, addressing the need for high-quality data, computational resources, and improved model generalization. Our research also finds that pretraining methods, particularly self-supervised learning (SSL) techniques like contrastive learning (CL) and masked autoencoders (MAEs), remarkably enhance the performance and robustness of FMs. This survey aims to serve as a resource for researchers and practitioners by providing a panorama of advances and promising pathways for the continued development and application of FMs in RS.

data models↗

DOE OSTI2024

Divalent Titanium via Reductive N−C Coupling of a Ti IV Nitrido with π ‐Acids

The nitrido-ate complex [(PN) 2 Ti(N){μ 2 -K(OEt 2 )}] 2 (1) (PN − =(N-(2-P i Pr 2 -4-methylphenyl)-2,4,6-Me 3 C 6 H 2 ) reductively couples CO and isocyanides in the presence of DME or cryptand (Kryptofix222), to form rare, five-coordinate Ti II complexes having a linear cumulene motif, [K(L)][(PN) 2 Ti(NCE)] (E=O, L=Kryptofix222, (2); E=NAd, L=3 DME, (3); E=N t Bu, L=3 DME, (4); E=NAd, L=Kryptofix222, (5)). Oxidation of 2–5 with [Fc][OTf] afforded an isostructural Ti III center containing a neutral cumulene, [(PN) 2 Ti(NCE)] (E=O, (6); E=NAd (7), N t Bu (8)) and characterization by CW X-band EPR spectroscopy, revealed unpaired electron to be metal centric. Moreover, 1e − reduction of 6 and 7 in the presence of Kryptofix222cleanly reformed corresponding discrete Ti II complexes 2 and 5, which were further characterized by solution magnetization measurements and high-frequency and -field EPR (HFEPR) spectroscopy. Furthermore, oxidation of 7 with [Fc*][B(C 6 F 5 ) 4 ] resulted in a ligand disproportionated Ti IV complex having transoid carbodiimides, [(PN) 2 Ti(NCNAd) 2 ] (9). Comparison of spectroscopic, structural, and computational data for the divalent, trivalent, and tetravalent systems, including their 15 N enriched isotopomers demonstrate these cumulenes to decrease in order of backbonding as Ti II →Ti III →Ti IV and increasing order of π-donation as Ti II →Ti III →Ti IV , thus displaying more covalency in Ti III species. Lastly, we show a synthetic cycle whereby complex 1 can deliver an N-atom to CO and CNAd.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

DOE OSTI2023

CP decomposition for tensors via alternating least squares with QR decomposition

The CP tensor decomposition is used in applications such as machine learning and signal processing to discover latent low-rank structure in multidimensional data. Computing a CP decomposition via an alternating least squares (ALS) method reduces the problem to several linear least squares problems. The standard way to solve these linear least squares subproblems is to use the normal equations, which inherit special tensor structure that can be exploited for computational efficiency. However, the normal equations are sensitive to numerical ill-conditioning, which can compromise the results of the decomposition. In this paper, we develop versions of the CP-ALS algorithm using the QR decomposition and the singular value decomposition, which are more numerically stable than the normal equations, to solve the linear least squares problems. Our algorithms utilize the tensor structure of the CP-ALS subproblems efficiently, have the same complexity as the standard CP-ALS algorithm when the input is dense and the rank is small, and are shown via examples to produce more stable results when ill-conditioning is present. Our MATLAB implementation achieves the same running time as the standard algorithm for small ranks, and we show that the new methods can obtain lower approximation error.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2021

The role of precursor decomposition in the formation of samarium doped ceria nanoparticles via solid-state microwave synthesis

The impact on the final morphology of ceria (CeO 2 ) nanoparticles made from different precursors (commercial: cerium acetate/nitrate) and in house: cerium tri(methylsilyl)amide (Ce-TMSA)) via a microwave solid state reaction has been determined. In all instances, powder X-ray diffraction indicated that the cubic fluorite CeO 2 phase (PDF# 04–004-9150, with the space group Fm-3 m) had formed. Scanning electron microscopy (SEM) images revealed spherical nanoparticles were produced from the Ce-TMSA precursor. The commercial acetate and nitrate precursors produced particles with irregular morphology. The roles of the precursor decomposition and binding energy in the synthesis of the nanocrystals with various morphologies, as well as a possible growth mechanism, were evaluated based on experimental and computational data. The formation of spherical shaped nanoparticles was determined to be due to the preferential single-step decomposition of the Ce-TMSA as well as the low activation energy to overcome decomposition. Due to the complicated decomposition of the commercial precursors and high activation energy the resulting particles adopted an irregular morphology. Highly uniform samarium doped ceria (Sm x Ce 1-x O 2-δ ) nanospheres were also synthesized from Ce-TMSA and samarium tri(methylsilyl)amide (Sm-TMSA). The effects of reaction time and temperature, on the final morphology were observed through SEM. The rapid single-step decomposition of TMSA-based precursors as observed through thermogravimetric analysis (TGA) and confirmed through the calculation of potential energy surfaces and binding energies from density functional theory (DFT) calculations, indicated that nanoparticle formation follows LaMer’s classical nucleation theory.

36 MATERIALS SCIENCE↗

DOE OSTI2025

DuctGPT: A Generative Transformer for Forward Screening of Ductile Refractory Multi-Principal Element Alloys

Designing ductile materials for extreme environments such as fusion reactors requires a deep understanding of the complex interplay between electronic structure, mechanical stability, and wide compositional space. Here, in this work, we introduce DuctGPT, a physics-informed, GPT-powered machine learning platform that enables rapid and accurate prediction of ductility across a wide range of refractory multi-principal element alloys (MPEAs). Trained on both experimental and high-fidelity computational data, DuctGPT integrates descriptors such as density of states at the Fermi level, elastic constants, and valence electron concentration to capture the fundamental mechanisms governing ductile versus brittle behavior. Using this framework, we screen over 1000 compositions in of body-centered cubic (BCC) MPEAs, including two new alloy classes, i.e., NbTa-rich (NbTa $>$ 50 at.%) NbTa-Ti-V and W-rich ($>$ 50 at.%) W-Ti-V MPEAs, to rapidly identify promising alloy compositions with enhanced ductility. Validation against experimental data confirms the model's ability to predict ductility with high fidelity and low uncertainty. By leveraging conversational AI and robust physical modeling, DuctGPT provides a blueprint for the next generation of alloy design assistants, enabling human-AI collaboration in the accelerated discovery of ductile, high-performance materials for fusion, aerospace, and advanced manufacturing.

AI/ML↗