Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “model discovery”

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 235 records · Page 13
All sourcesNASA NTRSDOE OSTI
DOE OSTI2023

Rapid discovery of high hardness multi-principal-element alloys using a generative adversarial network model

Multi-principal element alloys (MPEAs) continue to gain research prominence due to their promising high-temperature microstructural and mechanical properties. Recently, machine learning (ML) and materials informatics have been used extensively for screening MPEAs, however, most of these efforts were focused on constructing classification and regression models for predicting phase stability and mechanical properties of known compositions. These approaches may accelerate the screening process but optimizing new compositions with desirable properties within a practical time frame from an infinitely large design space of MPEA systems remains a grand challenge. To tackle this composition optimization challenge, a generative adversarial network coupled with a neural-network ML model was utilized to design MPEAs by filtering compositions that have high hardness. Even in a high-dimensional space with 18 elements as descriptors, the ML model was able to generate optimized compositions from which one composition was found to have 10% higher hardness (941 HV) than the maximum in the training data (857 HV). Density-functional theory was used to provide thermodynamic and electronic insights to higher hardness of the new MPEA found. The present work can optimize compositions from a wide design space of 18 elements (including W, Ta and Nb) that presents an opportunity to synthesize new compositions for applications ranging from corrosion-resistant alloys to nuclear materials. Here the findings suggest that generative ML can greatly accelerate materials discovery by identifying novel compositions, which can serve as a data-informed tool to guide experiments.

36 MATERIALS SCIENCE↗
DOE OSTI2023

Development of molecular cluster models to probe pyrite surface reactivity

Abstract The recent discovery that anaerobic methanogens can reductively dissolve pyrite and utilize dissolution products as a source of iron and sulfur to meet their biosynthetic demands for these elements prompted the development of atomic‐scale nanoparticle models, as maquettes of reactive surface sites, for describing the fundamental redox steps that take place at the mineral surface during reduction. The given report describes our computational approach for modeling n (FeS 2 ) nanoparticles originated from mineral bulk structure. These maquettes contain a comprehensive set of coordinatively unsaturated Fe (II) sites that are connected via a range of persulfide (S 2 2− ) ligation. In addition to the specific maquettes with n = 8, 18, and 32 FeS 2 units, we established guidelines for obtaining low‐energy structures by considering the pattern of ionic, covalent, and magnetic interactions among the metal and ligand sites. The developed models serve as computational nano‐reactors that can be used to describe the reductive dissolution mechanism of pyrite to better understand the reactive sites on the mineral, where microbial extracellular electron‐transfer reactions can occur.

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

Beyond the Hype: Navigating the Promise and Pitfalls of Multi-Modal Models for Materials Science

Multi-modal models offer great potential for accelerating discovery in materials and chemical systems, but their adoption raises crucial questions: What materials science challenges are best addressed by multi-modal approaches? How do we weigh the benefits against the resource investment required for multi-modal data acquisition? And critically, how can we optimize experimental workflows to leverage these models effectively? In this presentation, I will delve into the development of multi-modal characterization and analytics, focusing on their application in the demanding fields of next-generation microelectronics and energy storage materials. I will share challenges encountered in designing these workflows, highlighting lessons learned and posing questions that remain unanswered.

AI↗
DOE OSTI2026

A generative machine learning model for designing metal hydrides applied to hydrogen storage

Developing new metal hydrides is a critical step toward efficient hydrogen storage in carbon-neutral energy systems. However, existing materials databases, such as the Materials Project, contain a limited number of well-characterized hydrides, which constrains the discovery of optimal candidates. This work presents a framework that integrates causal discovery with a lightweight generative machine learning model to generate novel metal hydride candidates that may not exist in current databases. Using a dataset of 450 samples (270 training, 90 validation, and 90 testing), the model generates 1000 candidates. After ranking and filtering, six previously unreported chemical formulas and crystal structures are identified, four of which are validated by density functional theory simulations and show strong potential for future experimental investigation. Overall, the proposed framework provides a scalable and time-efficient approach for expanding hydrogen storage datasets and accelerating materials discovery.

generative model↗
DOE OSTI2023

Clarifying trust of materials property predictions using neural networks with distribution-specific uncertainty quantification

It is critical that machine learning (ML) model predictions be trustworthy for high-throughput catalyst discovery approaches. Uncertainty quantification (UQ) methods allow estimation of the trustworthiness of an ML model, but these methods have not been well explored in the field of heterogeneous catalysis. Herein, we investigate different UQ methods applied to a crystal graph convolutional neural network to predict adsorption energies of molecules on alloys from the Open Catalyst 2020 dataset, the largest existing heterogeneous catalyst dataset. We apply three UQ methods to the adsorption energy predictions, namely k-fold ensembling, Monte Carlo dropout, and evidential regression. The effectiveness of each UQ method is assessed based on accuracy, sharpness, dispersion, calibration, and tightness. Evidential regression is demonstrated to be a powerful approach for rapidly obtaining tunable, competitively trustworthy UQ estimates for heterogeneous catalysis applications when using neural networks. Recalibration of model uncertainties is shown to be essential in practical screening applications of catalysts using uncertainties.

36 MATERIALS SCIENCE↗
DOE OSTI2026

Transplatformer: translating toxicogenomic profiles between generations of platforms

Background Transcriptomic profiling technologies have advanced the analysis of biological and toxicological responses. However, substantial differences in probe design, dynamic range, gene coverage, and preprocessing pipelines across platforms introduce artifacts that limit cross-study integration and hinder the reuse of historical datasets. We aim to develop computational methods for accurate cross-platform translation to maximize the value of legacy resources. Results We present TransPlatformer a deep learning framework for translating gene expression profiles across heterogeneous toxicogenomics platforms. TransPlatformer employs a novel attention-based architecture to map high-dimensional fold-change vectors from legacy microarray technologies to current platforms. Models are trained and evaluated using DrugMatrix, spanning three technological generations. We investigate mixed-tissue, single-tissue, and cross-tissue training paradigms and benchmark performance against multilayer perceptron and matrix-completion baselines. In mixed-tissue training, TransPlatformer achieves a greater than 50% reduction in mean absolute error (0.043 vs. 0.09) and nearly doubles Pearson correlation ( ≈ 0.71 vs. 0.37) relative to baseline methods. Importantly, TransPlatformer preserves rare but biologically meaningful over- and under-expressed signals, with mean absolute error below 0.22. Single-tissue models yield further improvements for well-represented organs, such as a 10% reduction in liver mean absolute error, while underscoring the need for data augmentation strategies in low-sample tissues.ra Conclusions TransPlatformer provides an effective and scalable computational solution for cross-platform transcriptomic translation. By enabling biologically faithful harmonization of gene expression data, the proposed approach facilitates the reuse of legacy toxicogenomics datasets, enhances downstream biomarker discovery, and supports more reproducible predictive modeling in toxicology.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2021

Computational catalyst discovery: Active classification through myopic multiscale sampling

We report the recent boom in computational chemistry has enabled several projects aimed at discovering useful materials or catalysts. We acknowledge and address two recurring issues in the field of computational catalyst discovery. First, calculating macro-scale catalyst properties is not straightforward when using ensembles of atomic-scale calculations [e.g., density functional theory (DFT)]. We attempt to address this issue by creating a multi-scale model that estimates bulk catalyst activity using adsorption energy predictions from both DFT and machine learning models. The second issue is that many catalyst discovery efforts seek to optimize catalyst properties, but optimization is an inherently exploitative objective that is in tension with the explorative nature of early-stage discovery projects. In other words, why invest so much time finding a “best” catalyst when it is likely to fail for some other, unforeseen problem? We address this issue by relaxing the catalyst discovery goal into a classification problem: “What is the set of catalysts that is worth testing experimentally?” Here, we present a catalyst discovery method called myopic multiscale sampling, which combines multiscale modeling with automated selection of DFT calculations. It is an active classification strategy that seeks to classify catalysts as “worth investigating” or “not worth investigating” experimentally. Our results show an ~7–16 times speedup in catalyst classification relative to random sampling. These results were based on offline simulations of our algorithm on two different datasets: a larger, synthesized dataset and a smaller, real dataset.

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

A roadmap toward scaling, reasoning and self-evolving foundation models for nuclear and particle physics

Foundation models have revolutionized artificial intelligence, with Large Language Models demonstrating unprecedented capabilities in multimodal understanding, reasoning and tool use. Nuclear and particle physics stands at a critical juncture where similar transformative potential awaits realization. The field generates exabytes of experimental data, exascale simulations, and decades of theoretical insights — yet these remain largely disconnected from modern Artifical Intelligence (AI) capabilities, with most physics AI applications confined to narrow, task-specific models that suffer from domain shifting when applied to real experimental data. We present a roadmap for FM4NPP (Foundation Model for Nuclear and Particle Physics), systematically scaling from current proof-of-concept models to trillion-parameter architectures capable of autonomous discovery. Our approach advances three critical frontiers: unified data infrastructure integrating detector data, scientific knowledge and computational tools across global facilities; multi-facility foundation models enabling cross-experiment knowledge transfer and accelerated discovery; and agentic AI capabilities for reasoning and autonomous tool use. The resulting self-evolving FM4NPP will transform physics research by converting time-intensive data analysis, theory derivation and computational bottlenecks into rapid AI–human collaborative discovery. This paradigm shift promises to fundamentally accelerate scientific progress in nuclear and particle physics, enabling researchers to focus on high-level insights while AI handles routine analysis and explores vast parameter spaces beyond human capacity.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2022

Magnetic anisotropy in two-orbital models

Motivated by the recent first-principle discovery of giant perpendicular magnetic anisotropy (PMA) in Fe/III–V nitride thin films, we theoretically study magnetic crystalline anisotropy(MCA) in a series of lattices with trigonal symmetry. Due to the trigonal crystal field, MCA in these lattices is dominated by first-order perturbation of the spin–orbit coupling (SOC) in the atomic limit, instead of second-order in conventional transition metal materials. In particular, the proportionality between MCA and SOC is robust in Kagome and pyrochlore lattices due to the flat bands therein. While in triangle lattice the second-order relation is restored under the bandwidth effect. Furthermore, these findings give rise to a new understanding of magnetic anisotropy and provide a guide for the future hunting of high PMA materials.

36 MATERIALS SCIENCE↗
DOE OSTI2022

Validation and parameterization of a novel physics-constrained neural dynamics model applied to turbulent fluid flow

We report, in fluid physics, data-driven models to enhance or accelerate time to solution are becoming increasingly popular for many application domains, such as alternatives to turbulence closures, system surrogates, or for new physics discovery. In the context of reduced order models of high-dimensional time-dependent fluid systems, machine learning methods grant the benefit of automated learning from data, but the burden of a model lies on its reduced-order representation of both the fluid state and physical dynamics. In this work, we build a physics-constrained, data-driven reduced order model for Navier–Stokes equations to approximate spatiotemporal fluid dynamics in the canonical case of isotropic turbulence in a triply periodic box. The model design choices mimic numerical and physical constraints by, for example, implicitly enforcing the incompressibility constraint and utilizing continuous neural ordinary differential equations for tracking the evolution of the governing differential equation. We demonstrate this technique on a three-dimensional, moderate Reynolds number turbulent fluid flow. In assessing the statistical quality and characteristics of the machine-learned model through rigorous diagnostic tests, we find that our model is capable of reconstructing the dynamics of the flow over large integral timescales, favoring accuracy at the larger length scales. More significantly, comprehensive diagnostics suggest that physically interpretable model parameters, corresponding to the representations of the fluid state and dynamics, have attributable and quantifiable impact on the quality of the model predictions and computational complexity.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗
DOE OSTI2020

Enlarging the scope of resonant di-Higgs searches: hunting for Higgs-to-Higgs cascades in 4b final states at the LHC and future colliders

We extend the coverage of resonant di-Higgs searches in the $b\bar{b}b\bar{b}$ final state to the process $pp → H_1 → H_2H_2 → b\bar{b}b\bar{b}$, where both $H_{1,2}$ are spin-0 states beyond the Standard Model. Such a process constitutes a joint discovery mode for the new states $H_1$ and $H_2$. We present the first sensitivity study of this channel, using public LHC data to validate our analysis. We also provide a first estimate of the sensitivity of the search for the HL-LHC and future facilities like the HE-LHC and FCC-hh. We analyze the discovery potential of this search for several non-minimal scalar sector scenarios: an extension of the SM with two extra singlet scalar fields, the two-Higgs-doublet model and a two-Higgs doublet model plus a singlet, which captures the scalar potential features of the NMSSM. We find that this channel represents a novel, very powerful probe for extended Higgs sectors, offering complementary sensitivity to existing analyses.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2022

Discovering mechanisms for materials microstructure optimization via reinforcement learning of a generative model

Abstract The design of materials structure for optimizing functional properties and potentially, the discovery of novel behaviors is a keystone problem in materials science. In many cases microstructural models underpinning materials functionality are available and well understood. However, optimization of average properties via microstructural engineering often leads to combinatorically intractable problems. Here, we explore the use of the reinforcement learning (RL) for microstructure optimization targeting the discovery of the physical mechanisms behind enhanced functionalities. We illustrate that RL can provide insights into the mechanisms driving properties of interest in a 2D discrete Landau ferroelectrics simulator. Intriguingly, we find that non-trivial phenomena emerge if the rewards are assigned to favor physically impossible tasks, which we illustrate through rewarding RL agents to rotate polarization vectors to energetically unfavorable positions. We further find that strategies to induce polarization curl can be non-intuitive, based on analysis of learned agent policies. This study suggests that RL is a promising machine learning method for material design optimization tasks, and for better understanding the dynamics of microstructural simulations.

36 MATERIALS SCIENCE↗
DOE OSTI2024

Hierarchical Conditioning of Diffusion Models Using Tree-of-Life for Studying Species Evolution

A central problem in biology is to understand how organisms evolve and adapt to their environment by acquiring variations in the observable characteristics or traits of species across the tree of life. With the growing availability of large-scale image repositories in biology and recent advances in generative modeling, there is an opportunity to accelerate the discovery of evolutionary traits automatically from images. Toward this goal, we introduce Phylo-Diffusion, a novel framework for conditioning diffusion models with phylogenetic knowledge represented in the form of HIERarchical Embeddings (HIER-Embeds). We also propose two new experiments for perturbing the embedding space of Phylo-Diffusion: trait masking and trait swapping, inspired by counterpart experiments of gene knockout and gene editing/swapping. Our work represents a novel methodological advance in generative modeling to structure the embedding space of diffusion models using tree-based knowledge. Our work also opens a new chapter of research in evolutionary biology by using generative models to visualize evolutionary changes directly from images. We empirically demonstrate the usefulness of Phylo-Diffusion in capturing meaningful trait variations for fishes and birds, revealing novel insights about the biological mechanisms of their evolution. (Model and code can be found at imageomics.github.io/phylo-diffusion)

Khurana, Mridul↗
DOE OSTI2025

Machine Learning Thermodynamics And Kinetics of Defects For Accelerated Materials Discovery

Atomistic defects play a pivotal role in functional and structural materials’ performance across a myriad of technology applications. Quantitative prediction of the thermodynamics and kinetics of defect formation and migration, respectively, typically requires accurate but expensive first-principles approaches, such as density functional theory (DFT). Their computational expense limits the throughput needed to perform high-throughput materials discovery/screening exercises or to perform materials modeling tasks relying on extensive sampling techniques. Therefore, in this Sandia National Laboratories Laboratory Directed Research and Development (LDRD) project (Project #229366), we developed a variety of machine learning techniques, trained on density functional theory calculations, to accelerate the discovery and modeling of materials in which vacancy and interstitial defects primarily dictate material performance. These include applications such as metal oxides for water-splitting or mixed ionic-electronic conduction, metal hydrides for hydrogen storage, and transition metal dichalcogenides for electronics, and the approaches developed herein can further be applied to many other domains that similarly depend on materials’ thermodynamic and kinetic defect properties for their desired functionality.

36 MATERIALS SCIENCE↗
DOE OSTI2026

SetGo: Metadata Readiness for Scientific AI Datasets

Scientific datasets intended for AI use require both computational readiness for model training and metadata readiness for discovery, sharing, and reuse. The Readiness Engine for Data Integration (REDI) addresses computational readiness, but no corresponding tool evaluates whether a dataset’s metadata are sufficiently complete, governed, and standards-compliant for publication and agent-based consumption. Existing FAIR assessors operate only on published repository records, and no single system covers FAIR compliance, licensing, provenance, governance, reproducibility, and catalog readiness together. We present SetGo, an open-source Python toolkit that assesses and repairs metadata readiness across these six dimensions before a dataset is published or archived. Applied to four scientific corpora, SetGo surfaces deficiencies that general-purpose tools do not detect: ERA5 climate metadata scores 4% on ACDD 1.3 compliance; materials datasets fail OPTIMADE species-definition requirements; and PDB-derived proteomics data carries licensing terms incompatible with standard SPDX identifiers. Guided enrichment raises overall FAIR scores from 52–57% to 81–91%, and a single setgo publish command pushes to Hugging Face Hub, CKAN, or OpenMetadata with ML Commons Croissant 1.0 metadata sidecars. To support interactive and automated workflows, SetGo integrates with coding agents powered by large language models (LLMs) through a /setgo skill that enables natural-language execution of the full assess–enrich–publish loop, with user involvement limited to supplying missing metadata values.

Wilkinson, Sean [ORNL] (ORCID:0000000214437479)↗
DOE OSTI2021

Quasielastic electromagnetic scattering cross sections and world data comparisons in the GENIE Monte Carlo event generator

The usage of Monte Carlo neutrino event generators (MC$\textit{ν}$EGs) is a norm within the high-energy $\textit{ν}$ scattering community. The relevance of quasielastic (QE) energy regimes to $\textit{ν}$ oscillation experiments implies that accurate calculations of $\textit{ν}$A cross sections in this regime will be a key contributor to reducing the systematic uncertainties affecting the extraction of oscillation parameters. In spite of this, many MC$\textit{ν}$EGs utilize highly phenomenological, parametrized models of QE scattering cross sections. Moreover, a culture of validation of MC$\textit{ν}$EGs against prolific electron ($\textit{e}$) scattering data has been historically lacking. In this work, we implement new eA cross sections obtained from nuclear ab initio approaches in GENIE, the primary MC$\textit{ν}$EG utilized by the FNAL community. In particular, we utilize results from quantum MC methods which solve the many-body nuclear problem in the short-time approximation (STA), allowing consistent retention of two-nucleon dynamics which are crucial to explain available nuclear electromagnetic (electroweak) data over a wide range of energy and momentum transfers. This new implementation in GENIE is fully tested against the world QE electromagnetic data, finding agreement with available data below ~2 GeV of beam energy with the aid of a scaling function formalism. The STA is currently limited to study $\textit{A}$ ≤ 12 nuclei, however, its semi-inclusive multibody identity components are exportable to other many-body computational techniques such as auxiliary field diffusion MC which can reach $\textit{A}$ ≤ 40 systems while continuing to realize the factorization contained within the STA’s multinucleon dynamics. Together, these developments promise to make future experiments such as DUNE more accurate in their assessment of MC$\textit{ν}$EG systematics, $\textit{ν}$ properties, and potentially empower the discovery of physics beyond the Standard Model.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗