Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “machine learning models”

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 1,063 records · Page 59
All sourcesNASA NTRSDOE OSTI
DOE OSTI2026

Generative Models for Crystalline Materials

Understanding structure-property relationships in materials is fundamental in condensed matter physics and materials science. Over the past few years, machine learning (ML) has emerged as a powerful tool for advancing this understanding and accelerating materials discovery. Early ML approaches primarily focused on constructing and screening large material spaces to identify promising candidates for various applications. More recently, research efforts have increasingly shifted toward generating crystal structures using end-to-end generative models. This review analyzes the current state of generative modeling for crystal structure prediction and de novo generation. It examines crystal representations, outlines the generative models used to design crystal structures, and evaluates their respective strengths and limitations. Furthermore, the review highlights experimental considerations for evaluating generated structures and provides recommendations for suitable existing software tools. Emerging topics, such as modeling disorder and defects, integration in advanced characterization, incorporating synthetic feasibility constraints, and model explainability are explored. Ultimately, this work aims to inform both experimental scientists looking to adapt suitable ML models to their specific circumstances and ML specialists seeking to understand the unique challenges related to inverse materials design and discovery.

Metni, Houssam [Karlsruhe Inst. of Technology (KIT↗
DOE OSTI2026

Search for Beyond the Standard Model physics with anomaly detection in multilepton final states in pp collisions at s=13TeV with the ATLAS detector

A model-agnostic search for Beyond the Standard Model physics is presented, targeting final states with at least four light leptons (electrons or muons). The search regions are separated by event topology and unsupervised machine learning is used to identify anomalous events in the full 140 fb-1$$^{-1}$$ of proton–proton collision data collected with the ATLAS detector during Run 2. No significant excess above the Standard Model background expectation is observed. Model-agnostic limits are presented in each topology, along with limits on several benchmark models including vector-like leptons, wino-like charginos and neutralinos, or smuons. Limits are set on the flavourful vector-like lepton model for the first time.

Aad, G↗
DOE OSTI2025

System and Machine Learning-Guided Materials Design for High-Pressure Hydrogen Compression

Cost-effective and reliable hydrogen compression remains a challenging barrier in the widespread adoption of hydrogen as an energy carrier. The prevailing technology of mechanical compression suffers from several drawbacks, some of which can be addressed by nonmechanical compression strategies (e.g., electrochemical or metal hydride-based thermal compression). Thermally driven metal hydride compression strategies typically rely on multistage metal hydride-based compressors; however, discovering or optimizing low-stability metal hydrides that can pressurize hydrogen upward of 1000 bar is difficult, both with respect to computational predictions and experimental validation. Here, in this study, we (1) demonstrate that simple machine learning-derived design rules can inform the rational design of alloying strategies yielding low-stability hydrides, (2) validate their experimental pressure–composition–temperature (PCT) isotherms up to 875 bar, and (3) utilize a dynamic system-level model of a metal hydride compressor design to evaluate their performance under realistic operating conditions. Importantly, this analysis yields predicted operational efficiencies of both 2-stage (90–875 bar) and 3-stage (20–875 bar) metal hydride compressors to enable further evaluation of this technology and its techno-economic outlook.

alloy optimization↗
DOE OSTI2026

Deposition Height Prediction in Directed Energy Deposition

Using 316L stainless steel as a model material, reduced-order models are developed to predict capture efficiency, deposition height, and site-specific hardness in directed energy deposition. Capture efficiency is predicted over a 15 to 55 pct range using a dimensionless number derived from processing conditions and thermophysical properties. Deposition height is predicted over a 0.3 to 1.3 mm range without in situ sensing or prior training data, using two models based on the same mass and energy-balance principles. Predictions are compared with machine learning approaches. A quantitative relationship links deposition height, primary dendrite arm spacing (PDAS), and hardness: heights of 0.3 to 1.1 mm correspond to PDAS values of 2.7 to 5.1 µm and Vickers hardness (HV) of 160 to 219. Thinner layers cool more rapidly, producing finer microstructures and higher hardness. Samples fabricated with in situ variations in deposition height exhibited up to 55 HV differences between thick and thin regions, demonstrating that local control of deposition height enables predictive, site-specific hardness within a single build. These results establish deposition height prediction as a pathway for a priori process design and property control in directed energy deposition for 316L stainless steel.

Kunkel, William [Univ. of Wisconsin, Madison, WI (↗
DOE OSTI2025

Detectable ship tracks account for just 5% of aerosol indirect forcing from ship emissions

Ship emissions are a major source of aerosols over oceans, affecting both air quality and energy balance of the climate. However, estimates of their climate forcing diverge between studies relying on visible ship-tracks and those based on models. Here we show that forcing due to visible ship-tracks accounts for just 5% of the total forcing over the southeast Atlantic shipping-lane. Most forcing from ship emissions comes from aerosols that do not form detectable ship-tracks. They are only tips of the iceberg. We make three forcing calculations, one bottom-up based on visible ship-tracks, one top-down based on spatial relationships, and a hybrid approach that combines top-down or model estimated cloud droplet number concentration changes and cloud adjustments. Although the forcing based on machine learning detected ship tracks is an order of magnitude greater than prior results using manually detected ship-tracks, it remains only 5% of that inferred by top-down or cloud adjustment based methods for pre-2020 shipping. The top-down and the combined cloud adjustments methods show similar forcing for the post-2020 reduction in ships’ sulfur emission, although the methods have important regional differences in cloud adjustments that need further investigation. Our results reconcile a long-standing discrepancy in the literature and have important implications for aerosol indirect forcing and marine cloud brightening.

Yuan, Tianle [NASA Goddard Space Flight Center (GS↗
DOE OSTI2025

Computing chemical potentials with machine-learning-accelerated simulations to accurately predict thermodynamic properties of molten salts

The successful design and deployment of next-generation nuclear technologies heavily rely on thermodynamic data for relevant molten salt systems. However, the lack of accurate force fields and efficient methods has limited the quality of thermodynamic predictions from atomistic simulations. Here we propose an efficient free energy framework for computing chemical potentials, which is the central free energy quantity behind many thermodynamic properties. We accelerate our simulations without sacrificing accuracy by using machine learning interatomic potentials trained on density functional theory (DFT) data. Using lithium chloride as our model system, we compute chemical potentials with DFT-accuracy for solid and liquid phases by transmuting ions into noninteracting particles. Notably, in the liquid phase, we demonstrate consistency whether we transmute one ion pair or the entire system into ideal gas particles. By locating the temperature where the chemical potential of solid and liquid phases cross, we predict a melting point of 880 ± 18 K for lithium chloride, which is remarkably close to the experimental value of 883 K. With this successful demonstration, we lay the foundation for high-throughput thermodynamic predictions of many properties that can be derived from the chemical potentials of the minority and majority components in molten salts.

Gibson, Luke D. [Oak Ridge National Laboratory (OR↗
DOE OSTI2025

Machine learning neutrino-nucleus cross sections

Neutrino-nucleus scattering cross sections are critical theoretical inputs for long-baseline neutrino oscillation experiments. However, robust modeling of these cross sections remains challenging. For a simple but physically motivated toy model of the DUNE experiment, we demonstrate that an accurate neural-network model of the cross section—leveraging only Standard-Model symmetries—can be learned from near-detector data. We perform a neutrino oscillation analysis with simulated far-detector events, finding that oscillation analysis results enabled by our data-driven cross-section model approach the theoretical limit achievable with perfect prior knowledge of the cross section. We further quantify the effects of flux shape and detector resolution uncertainties as well as systematics from cross-section mismodeling. This proof-of-principle study highlights the potential of future neutrino near-detector datasets and data-driven cross-section models.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2025

Automated RF Phase Adjustment for Beam Stabilization in the Fermilab Linac

The Fermilab Linac experiences longitudinal beam phase drift, leading to increased particle loss, conventionally corrected through labor-intensive manual RF adjustments. This project explores machine learning-based automation for drift correction, employing a prototype-based classification approach. Our model utilizes a 34-dimensional feature set (RF settings and BPM readings) and leverages a 7x27 response matrix for system modeling. To overcome limited real-world data, we generate synthetic data, enhancing model training and generalizability. Custom loss functions, including a surrogate energy-consistent loss and a temporal smoothness constraint, ensure physically plausible drift predictions. The goal is a robust system for autonomous phase adjustments, ensuring stable beam acceleration and reduced manual intervention.

Chichili, R. R. [Illinois U., Chicago]↗
DOE OSTI2025

Machine Learning Neutrino-Nucleus Cross Sections

Neutrino-nucleus scattering cross sections are critical theoretical inputs for long-baseline neutrino oscillation experiments. However, robust modeling of these cross sections remains challenging. For a simple but physically motivated toy model of the DUNE experiment, we demonstrate that an accurate neural-network model of the cross section -- leveraging Standard Model symmetries -- can be learned from near-detector data. We then perform a neutrino oscillation analysis with simulated far-detector events, finding that the modeled cross section achieves results consistent with what could be obtained if the true cross section were known exactly. This proof-of-principle study highlights the potential of future neutrino near-detector datasets and data-driven cross-section models.

Wagman, Michael L. [Fermilab] (ORCID:0000000176701↗
DOE OSTI2025

Automated RF Phase Adjustment for Beam Stabilization in the Fermilab Linac

The Fermilab Linac experiences longitudinal beam phase drift, leading to increased particle loss, conventionally cor- rected through labor-intensive manual RF adjustments. This project explores machine learning-based automation for drift correction, employing a prototype-based classification approach. Our model utilizes a 34-dimensional feature set (RF settings and BPM readings) and leverages a 7x27 response matrix for system modeling. To overcome limited real-world data, we generate synthetic data, enhancing model training and generalizability. Custom loss functions, including a sur- rogate energy-consistent loss and a temporal smoothness constraint, ensure physically plausible drift predictions. The goal is a robust system for autonomous phase adjustments, ensuring stable beam acceleration and reduced manual intervention.

Chichili, R. R. [U. Illinois, Chicago]↗
DOE OSTI2026

Machine Learning Neutrino-Nucleus Cross Sections

Neutrino-nucleus scattering cross sections are critical theoretical inputs for long-baseline neutrino oscillation experiments. However, robust modeling of these cross sections remains challenging. For a simple but physically motivated toy model of the DUNE experiment, we demonstrate that an accurate neural-network model of the cross section—leveraging only Standard-Model symmetries— can be learned from near-detector data. We perform a neutrino oscillation analysis with simulated far-detector events, finding that oscillation analysis results enabled by our data-driven cross-section model approach the theoretical limit achievable with perfect prior knowledge of the cross section. We further quantify the effects of flux shape and detector resolution uncertainties as well as systematics from cross-section mismodeling. This proof-of-principle study highlights the potential of future neutrino near-detector datasets and data-driven cross-section models.

Tame-Narvaez, Karla [Fermilab] (ORCID:000000022249↗
DOE OSTI2026

Learning thermodynamic master equations for open quantum systems

The characterization of Hamiltonians and other components of open quantum dynamical systems plays a crucial role in quantum computing and other applications. Scientific machine learning techniques have been applied to this problem in a variety of ways, including by modeling with deep neural networks. However, the majority of mathematical models describing open quantum systems are linear, and the natural nonlinearities in learnable models have not been incorporated using physical principles. We present a data-driven model for open quantum systems that includes learnable, thermodynamically consistent terms. The trained model is interpretable, as it directly estimates the system Hamiltonian and linear components of coupling to the environment. We validate the model on synthetic two and three-level data, as well as experimental two-level data collected from a quantum device at Lawrence Livermore National Laboratory.

Mathematics and Computing↗
DOE OSTI2025

FedOSAA: Improving Federated Learning with One-Step Anderson Acceleration

Federated learning (FL) is a distributed machine learning approach that enables multiple local clients and a central server to collaboratively train a model while keeping the data on their own devices. First-order methods, particularly those incorporating variance reduction techniques, are the most widely used FL algorithms due to their simple implementation and stable performance. However, these methods tend to be slow and require a large number of communication rounds to reach the global minimizer. We propose FedOSAA, a novel approach that preserves the simplicity of first-order methods while achieving the rapid convergence typically associated with second-order methods. Our approach applies one Anderson acceleration (AA) step following classical local updates based on first-order methods with variance reduction, such as FedSVRG and SCAFFOLD, during local training. This AA step is able to leverage curvature information from the history points and gives a new update that approximates the Newton-GMRES direction, thereby significantly improving the convergence. We establish a local linear convergence rate to the global minimizer of FedOSAA for smooth and strongly convex loss functions. Numerical comparisons show that FedOSAA substantially improves the communication and computation efficiency of the original first-order methods, achieving performance comparable to second-order methods like GIANT.

Feng, Xue [University of California, Davis]↗
DOE OSTI2026

Conformalized-KANs: Uncertainty Quantification with Coverage Guarantees for Kolmogorov-Arnold Networks (KANs) in Scientific Machine Learning

This paper explores uncertainty quantification (UQ) methods in the context of Kolmogorov–Arnold Networks (KANs). We apply an ensemble approach to KANs to obtain a heuristic measure of UQ, enhancing interpretability and robustness in modeling complex functions. Building on this, we introduce Conformalized-KANs, which integrate conformal prediction, a distribution-free UQ technique, with KAN ensembles to generate calibrated prediction intervals with guaranteed coverage.} Extensive numerical experiments are conducted to evaluate the effectiveness of these methods, focusing particularly on the robustness and accuracy of the prediction intervals under various hyperparameter settings. We show that the conformal KAN predictions can be applied to recent extensions of KANs, including Finite Basis KANs (FBKANs) and multifideilty KANs (MFKANs). The results demonstrate the potential of our approaches to significantly improve the reliability and applicability of KANs in scientific machine learning.

• Artificial intelligence (AI) / machine learning ↗
DOE OSTI2025

Machine Learning-Based Process Control for Injection Molding of Recycled Polypropylene

The increased interest in artificial intelligence in manufacturing has driven the adoption of machine learning to optimize processes and improve efficiency. A key challenge in injection molding is the variability of recycled materials, which affects part quality and processing stability. This study presents a novel closed-loop process control approach for injection molding, leveraging machine learning to adaptively predict processing inputs and quality outcomes. The methodology was tested on five blends of recycled polypropylene (rPP), using artificial neural networks (ANNs), linear regression, and polynomial regression to model the relationships between material properties and process parameters. The dataset was split 80/20 into training and testing sets. The ANN model was implemented using TensorFlow and Keras, with six hidden layers of 32 neurons per layer, ReLU activation, and an Adam optimizer. Empirical tuning and early stopping were used to optimize performance and prevent overfitting. Predictions were evaluated based on mean absolute error (MAE), mean squared error (MSE), and percentage error. The results showed that yield stress, ultimate elongation, and part weight were accurately predicted within a 5% error for linear and polynomial regression models and within a 10% error for the ANN. However, modulus predictions were less reliable, with errors of ~11% for ANN and linear regression and ~40% for polynomial regression, reflecting the inherent variability of this property in rPP blends. Predictions of processing inputs had errors ranging from 3% to 25%, depending on the model and response variable. No single modeling approach was consistently superior across all responses, highlighting the complexity of the relationship between material properties, process parameters, and quality metrics. Overall, the work demonstrates that closed-loop process control, powered by machine learning, can effectively predict key quality parameters in injection molding of recycled materials. The proposed approach can improve process stability and material utilization, facilitating increased adoption of sustainable materials.

Krantz, Joshua↗
DOE OSTI2025

A Data-Agnostic, Continuous Machine Learning Framework for Application in High Energy Physics and Beyond: Phase 1 Final Scientific/Technical Report

This Phase 1 effort has focused on the development of continual learning frameworks for use in machine learning, specifically in the applied context of High Energy Physics (HEP). Machine learning (ML) is a transformative technology by which computers, typically through the use of neural networks, are able to perform tasks with proficiency that rivals or surpasses that of human users. Model Degradation & Catastrophic Forgetting are two undesired phenomena which can occur in ML where the performance of a model degrades when either deployed on novel data streams, or trained on novel data which are sufficiently different than the data the models were initially trained on. A natural example where these sorts of effects can be observed is in the performance of detectors in harsh environments, where the detector signature may change over the lifetime of the detector as it ages and deteriorates — precisely what occurs in the experiments conducted in HEP. Real world HEP data is therefore an excellent test-ground and use-case for Continual Learning paradigms, which are techniques used in ML to counteract these problems. Ensemble learning is one such technique, where multiple smaller models are trained on subsets of the overall data and are ensembled together during inference. The intuition behind this technique is that, although there are shifts in the distributions which govern the incoming data streams, these shifts are not expected to be homogeneous or global. If a sufficient diversity in solutions within the various sub-models has been achieved, then at least one sub-model is expected to retain its performance within the overall ensemble. One further strength of this approach is that the architectures of the various models do not need to be identical, and in fact even different modalities of data can naturally be combined in this way. This work focused on applying ensemble learning techniques to derive results using two main datasets, anomaly detection in HEP data & time-series forecasting in semiconductor manufacturing data. Semiconductor manufacturing involves data with surprising similarity to that of HEP (e.g. wafer maps look very similar to digi-occupancy maps) and Cerium Lab’s prominence within the semiconductor industry makes semiconductor manufacturing a natural opportunity for commercialization of this work. Our efforts have led to two strong results. The first is that we evaluated the proposed ensembling techniques using previously proposed machine learning architectures for use in anomaly detection, namely AutoEncoder based models and their derivatives. We also developed new architectures which have not been evaluated in this context before. In fact, this work marks the first use of Vision Transformers for anomaly detection in HEP. Second, we demonstrated that ensemble learning significantly improves model performance in scenarios prone to degradation, validating its effectiveness across both HEP and semiconductor datasets. These results further support ensemble learning as a powerful strategy for mitigating catastrophic forgetting and maintaining robust performance in evolving data environments.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2025

Scaling High-Resolution Soil Organic Matter Composition to Improve Predictions of Potential Soil Respiration Across the Continental United States

Despite the importance of microbial soil organic matter (SOM) respiration in regulating the flux of carbon between soils and the atmosphere, soil carbon cycling models remain primarily based on climate and soil properties, leading to large uncertainty in predictions. To address this knowledge gap, we analyzed high-resolution water-extractable SOM profiles from soil cores collected across the United States by the 1,000 Soils Pilot of the Molecular Observation Network. Our innovation lies in using machine learning to distill thousands of SOM formula into tractable units; and it enables integrating data from molecular measurements into soil respiration models. In surface soils, SOM chemistry provided better estimates of potential soil respiration than soil physicochemistry, and using them combined yielded the best prediction. Overall, we identify specific subsets of organic molecules that may improve predictions of global soil respiration and create a strong basis for developing new representations in process-based models.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2025

Machine Learning Prediction of Tritium‐Helium Groundwater Ages in the Central Valley, California, USA

Abstract Groundwater ages provides insight into recharge rates, flow velocities, and vulnerability to contaminants. The ability to predict groundwater ages based on more accessible parameters via Machine Learning (ML) would advance our ability to guide sustainable management of groundwater resources. In this study, ML models were trained and tested on a large data set of tritium concentrations and tritium‐helium groundwater ages from the California Central Valley, a large groundwater basin with complex land use, irrigation, and water management practices. The ML models were trained on 63 features, including location, well construction information, landscape characteristics, and climate variables, water chemistry, and stable isotopes. The Bagging regressor method can accurately classify (F1‐score = 0.91) groundwater samples as either modern or pre‐modern whereas the accuracy of the ML prediction of continuous tritium‐helium groundwater ages is limited and explains only of the variability in this data set. In general, ML groundwater age prediction relies mostly on features related to (a) the source of groundwater recharge, (b) contaminant history, (c) aquifer materials, (d) well construction, and (e) geochemical reactions along flow paths.

54 ENVIRONMENTAL SCIENCES↗