Search NASA⌕ Search

SEARCH · Search NASA

Results for “machine learning framework”

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 325 records · Page 18
All sourcesNASA NTRSDOE OSTI
DOE OSTI2026

Leveraging large language models to address data scarcity in machine learning for graphene synthesis

Machine learning in experimental materials science faces significant challenges due to the scarcity of data, which are costly and time-consuming to generate, particularly when relying on in-house experiments. Literature data mining offers a potential solution but introduces issues like mixed data quality, inconsistent formats, and non-uniform reporting of synthesis parameters, resulting in partially missing and heterogeneous features across the dataset. Here, we propose data imputation and feature engineering methods that employ pre-trained large language models (LLMs) to enhance machine learning performance on scarce, heterogeneous datasets, demonstrated on graphene CVD synthesis data and the ML-HydPARK hydrogen storage dataset. GPT models perform data imputation via tailored prompting and semantic normalization of inconsistently reported features through embeddings, for example, to harmonize the complex nomenclature of CVD substrates. Beyond yielding more diverse and richer feature representations than traditional methods such as K-nearest neighbors (KNN) and Multivariate Imputation by Chained Equations (MICE), LLM-based data imputation is evaluated against dataset characteristics and prompting strategies. We vary the level of autonomy granted to the LLM, from generic prompting that leverages pre-trained knowledge for autonomous data generation to data-informed prompting that constrains outputs using target-specific information, and demonstrate which level of autonomy yields superior imputation performance across datasets and feature types. The proposed data engineering methods markedly improve downstream performance; for example, in graphene layer number classification using a support vector machine (SVM), binary accuracy increases from 39% to 65% and ternary accuracy from 52% to 72%. Fine-tuning experiments on both datasets show that combining our proposed LLM-based data imputation and feature encoding methods with numerical machine learning predictors outperforms standalone fine-tuned LLM predictors in data-scarce settings. The proposed strategies emphasize data enhancement techniques rather than refining learning architectures or regularizing loss functions, offering a broadly applicable framework for improving machine learning performance on scarce, inhomogeneous datasets.

Chemical vapor deposition↗
DOE OSTI2025

Digital twin framework for PIP-II linac: AI-driven multi-scale modeling from ion source to 800 MeV

The PIP-II superconducting linac at Fermilab is designed to deliver multi-megawatt proton beams for neutrino physics and other high-intensity applications. To expedite commissioning and enhance operational reliability, we have developed an EPICS-based data flow framework that seamlessly integrates digital twins (DT) with physical twins (PT). These digital twins comprise high-fidelity beam dynamics models or data-driven surrogate models connected to their physical counterparts through real-time diagnostics and advanced machine-learning algorithms.Central to this framework is Linac_Gen, an accelerated simulation tool that incorporates convolutional neural networks, random forests, and genetic algorithms to provide up to a tenfold speedup in optimizing the accelerator geometry model. An EPICS translator layer ensures interoperability by efficiently mapping lattice parameters across diverse simulation platforms.Our EPICS-based framework supports multiple operational modes—monitoring, passive learning, closed-loop control, and online learning—covering the entire machine lifecycle. By leveraging HPC resources and multi-objective optimization techniques, the digital twin enables adaptive trajectory correction, real-time fault detection, and predictive modeling of beam stability. This comprehensive approach paves the way for robust, high-intensity operation and data-driven accelerator R&D at Fermilab.

Pathak, Abhishek [Fermilab]↗
DOE OSTI2025

Cluster-Graph Fingerprinting: A Framework for Quantitative Analysis of Machine-Learned Interatomic Model Training and Simulation Data

Machine-learned interatomic models represent a significant advancement in simulation methods, extending the predictive ability of first-principles methods to previously inaccessible length and time scales. However, the data-driven nature of these models can lead to difficult-to-detect errors that can compromise prediction accuracy. To address this challenge, we introduce a novel fingerprinting approach based on the Chebyshev Interaction Model for Efficient Simulation (ChIMES) ML-IAM graph-based descriptor. Our strategy enables efficient and statistically rigorous analysis of system configurations used in ML-IAM training and those generated by their application, e.g., in molecular dynamics simulations. We demonstrate that these fingerprints can effectively assess novelty of a configuration relative to an existing data set and determine dissimilarity among individual configurations, which are two key tasks in workflows for active learning-based ML-IAM training, data set curation, and on-the-fly uncertainty quantification.

36 MATERIALS SCIENCE↗
DOE OSTI2025

Framework and Tool for Artificial Intelligence & Machine Learning (AI/ML) Enabled Automated Non-Destructive Inspection of Composites Aerostructures Manufacturing

Vehicles and systems in the field of aerospace have two major requirements: a high demand for a large quantity and an expectation to perform for their lifetime with little to no failures. Thus, there is a need for a fast production rate of aerospace products with high quality. Improvements to production rate have many benefits, including a reduction in energy consumption per unit manufactured. This would be from factory energy usage, which is required to build and verify a product. Manufacturing process specifications require inspection of parts to determine if any flaws are present. Depending on factory planning and product quality, especially at higher rates, the evaluation process can pose a production rate bottleneck. This project was comprised of using artificial intelligence and machine learning (AI/ML) methods on inspection evaluations with the objective of reducing the required time to produce an aerospace structure or product and without reducing the final quality.

42 ENGINEERING↗
DOE OSTI2025

Machine learning-assisted design of metal–organic frameworks for hydrogen storage: A high-throughput screening and experimental approach

Various theoretical approaches, including big data and high-throughput screening techniques, have been explored in developing new materials due to their significant potential time-saving advantages. However, it remains a significant challenge to experimentally realize new materials that are predicted. In this study, we propose a novel materials design strategy that utilizes machine-learning (ML) techniques to predict new porous materials that show promise for hydrogen storage and are likely to be feasible to synthesize. By leveraging ML techniques and metal–organic framework (MOF) databases, we are able to predict the synthesizability of MOF structures. This is evidenced by the successful synthesis of a new vanadium-based MOF that exhibits excellent performance for cryogenic H 2 storage. Notably, the total gravimetric and volumetric H 2 uptakes are as high as 9.0 wt% and 50.0 g/L at 77 K and 150 bar. This ML-assisted materials design offers an efficient and promising approach for developing hydrogen storage materials.

08 HYDROGEN↗
DOE OSTI2024

Machine Learned Force Field Modeling of Metal Organic Frameworks for CO2 Direct Air Capture

Direct air capture (DAC) is a method for removing CO2 directly from air. Metal organic frameworks (MOFs) have been studied as DAC sorbent materials because of their structural and chemical diversity. Thermodynamic calculations using classical force fields are often used to evaluate MOFs for their performance in separations such as CO2 capture. Machine-learned force fields (MLFFs) can use machine learning to form quantitative relationships between a material’s chemical structure and the forces and energies predicted by more accurate quantum mechanical calculations, such as dispersion-corrected density functional theory (DFT). These descriptions of forces and energies can be used to improve the accuracy of adsorption calculations. In this work, classical models were used to pre-screen MOFs for CO2 capture. DFT calculations were then used to examine the adsorption mechanism. Next, MLFF models were developed for MOFs to achieve DFT-level accuracy for the forces and energies associated with MOF flexibility and CO2 adsorption. These methods were parametrized based on thousands of DFT calculations of CO2 in flexible MOFs and used to predict MOF structural properties as well as CO2 adsorption properties.

Findley, John↗
DOE OSTI2024

A machine learning approach for particle accelerator errant beam prediction using spatial phase deviation

Particle accelerators are extremely complex systems that are expected to operate on high availability. Predicting impending failures only by utilizing data collected from diagnostic equipment already on board can help operators to avoid installing expensive sensors, unscheduled downtime and associated costs. For this purpose we explore the predictive power of Machine Learning algorithms to detect faulty beams prior to the failure. In this study, we propose a Machine Learning approach to model mapping from a pair of sensors located across the accelerator. While the model is trained to represent normal operation, we evaluate the predictive performance on known faulty beam pulses. We also investigate the model performance on unseen data through k-fold cross-validation. Then we recap the analysis with a neural architecture search and hyperparameter optimization study to fine tune our initial model. In conclusion, this paper will also introduce a sustainable framework that can standardize Machine Learning workflow applied to particle accelerators.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
DOE OSTI2024

Machine-Learned Force Field Modeling of Metal Organic Frameworks for CO2 Direct Air Capture

To cope with legacy greenhouse gas emissions and to achieve net-zero emissions by 2050, the U.S. Department of Energy (DOE) is funding efforts to develop direct air capture (DAC), a method for removing CO2 directly from air. Metal organic frameworks (MOFs) have been studied as DAC sorbent materials because of their structural and chemical diversity. Thermodynamic calculations using classical force fields are often used to screen MOFs for their performance in separations such as CO2 capture. Machine-learned force fields (MLFFs) can use machine learning to form quantitative relationships between a material’s chemical structure and the forces and energies predicted by more accurate quantum mechanical calculations, such as dispersion-corrected density functional theory (DFT). These descriptions of forces and energies can be used to improve the accuracy of adsorption calculations. In this work, MLFF models were developed for MOFs to achieve DFT-level accuracy for the forces and energies associated with MOF flexibility and CO2 adsorption. These methods were parametrized based on thousands of DFT calculations of CO2 in flexible MOFs and used to predict MOF structural properties as well as CO2 adsorption properties.

Findley, John↗
DOE OSTI2022

Physics-informed machine learning with differentiable programming for heterogeneous underground reservoir pressure management

Abstract Avoiding over-pressurization in subsurface reservoirs is critical for applications like CO $$_2$$ 2 sequestration and wastewater injection. Managing the pressures by controlling injection/extraction are challenging because of complex heterogeneity in the subsurface. The heterogeneity typically requires high-fidelity physics-based models to make predictions on CO $$_2$$ 2 fate. Furthermore, characterizing the heterogeneity accurately is fraught with parametric uncertainty. Accounting for both, heterogeneity and uncertainty, makes this a computationally-intensive problem challenging for current reservoir simulators. To tackle this, we use differentiable programming with a full-physics model and machine learning to determine the fluid extraction rates that prevent over-pressurization at critical reservoir locations. We use DPFEHM framework, which has trustworthy physics based on the standard two-point flux finite volume discretization and is also automatically differentiable like machine learning models. Our physics-informed machine learning framework uses convolutional neural networks to learn an appropriate extraction rate based on the permeability field. We also perform a hyperparameter search to improve the model’s accuracy. Training and testing scenarios are executed to evaluate the feasibility of using physics-informed machine learning to manage reservoir pressures. We constructed and tested a sufficiently accurate simulator that is 400 000 times faster than the underlying physics-based simulator, allowing for near real-time analysis and robust uncertainty quantification.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2024

Real-time tracking of structural evolution in 2D MXenes using theory-enhanced machine learning

In situ Electron Energy Loss Spectroscopy (EELS) combined with Transmission Electron Microscopy (TEM) has traditionally been pivotal for understanding how material processing choices affect local structure and composition. However, the ability to monitor and respond to ultrafast transient changes, now achievable with EELS and TEM, necessitates innovative analytical frameworks. Here, we introduce a machine learning (ML) framework tailored for the real-time assessment and characterization of in operando EELS Spectrum Images (EELS-SI). We focus on 2D MXenes as the sample material system, specifically targeting the understanding and control of their atomic-scale structural transformations that critically influence their electronic and optical properties. This approach requires fewer labeled training data points than typical deep learning classification methods. By integrating computationally generated structures of MXenes and experimental datasets into a unified latent space using Variational Autoencoders (VAE) in a unique training method, our framework accurately predicts structural evolutions at latencies pertinent to closed-loop processing within the TEM. This study presents a critical advancement in enabling automated, on-the-fly synthesis and characterization, significantly enhancing capabilities for materials discovery and the precision engineering of functional materials at the atomic scale.

47 OTHER INSTRUMENTATION↗
DOE OSTI2024

Machine-Learned Force Field Modeling of Metal Organic Frameworks for CO2 Direct Air Capture

To cope with legacy greenhouse gas emissions and to achieve net-zero emissions by 2050, the U.S. Department of Energy (DOE) is funding efforts to develop direct air capture (DAC), a method for removing CO2 directly from air. Metal organic frameworks (MOFs) have been well studied as DAC sorbent materials due to their tunable structural and compositional properties. Thermodynamic simulations using force fields are often used to provide predictions of a material’s performance in many separations. However, these force fields often make assumptions about bonds and the physics of the adsorption process. A new class of force fields called machine-learned force fields (MLFFs) use machine learning to form quantitative relationships between a material’s chemical structure and the forces and energies predicted by more accurate quantum mechanical calculations, such as dispersion-corrected density functional theory (DFT). In this work, models were developed to achieve DFT-level accuracy for the forces and energies associated with MOF flexibility and CO2 adsorption using MLFFs. These methods were parametrized based on thousands of DFT calculations of CO2 in flexible MOFs and used to predict MOF structural properties as well as CO2 adsorption in several MOFs.

Findley, John↗
DOE OSTI2020

Modular performance prediction for scientific workflows using Machine Learning

Scientific workflows provide an opportunity for declarative computational experiment design in an intuitive and efficient way. A distributed workflow is typically executed on a variety of resources, and it uses a variety of computational algorithms or tools to achieve the desired outcomes. Such a variety imposes additional complexity in scheduling these workflows on large scale computers. As computation becomes more distributed, insights into expected workload that a workflow presents become critical for effective resource allocation. In this paper, we present a modular framework that leverages Machine Learning for creating precise performance predictions of a workflow. The central idea is to partition a workflow in such a way that makes the task of forecasting each atomic unit manageable and gives us a way to combine the individual predictions efficiently. We recognize a combination of an executable and a specific physical resource as a single module. This gives us a handle to characterize workload and machine power as a single unit of prediction. Overall, our modular technique of creating atomic modules and deployment of longest-path approach to estimate workflow performance, allows the framework to adapt to highly complex nested directed acyclic workflows and scale to new scenarios, since it does not make assumptions of underlying workflow structure. We present performance estimation results of independent workflow modules executed on the XSEDE SDSC Comet cluster using various Machine Learning algorithms. The results provide insights into the behavior and effectiveness of different algorithms in the context of scientific workflow performance prediction.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2024

Machine Learned Force Field Modeling of Metal Organic Frameworks for CO2 Direct Air Capture

Metal organic frameworks (MOFs) are a large class of porous materials and have garnered significant interest due to their large surface areas and their tunable physical and chemical properties. Numerous prior studies have been performed to screen large databases of this material class for promising DAC sorbent materials. These studies have often relied on classical model potentials. While density functional theory (DFT) calculations have been shown to be very accurate for modeling the interaction of CO2 with MOFs, such calculations are too computationally demanding for statistically significant adsorption predictions. To overcome this barrier, we developed methods for training models to achieve DFT-level accuracy for the forces and energies associated with MOF flexibility and CO2 adsorption using machine learned force fields (MLFFs). These methods were parametrized based on DFT calculations of CO2 in a flexible MOF and used to predict MOF structural properties as well as CO2 adsorption in several MOFs.

Findley, John↗
DOE OSTI2025

Aging matrix visualizes complexity of battery aging across hundreds of cycling protocols

To reliably deploy lithium-ion batteries, a fundamental understanding of cycling aging behavior is critical. Battery aging consists of complex and highly coupled phenomena, making it challenging to develop a holistic interpretation. In this work, we generate a diverse battery cycling dataset with a broad range of degradation trajectories, consisting of 359 high energy density commercial Li(Ni,Co,Al)O 2 /graphite + SiO x cylindrical 21 700 cells cycled across 207 unique cycling protocols. We consolidate aging via 16 mechanistic state-of-health (SOH) metrics, including cell-level performance metrics, electrode-specific capacities/state-of-charges (SOCs), and aging trajectory metrics. We develop a framework using interpretable machine learning and explainable features to generate an aging matrix that visually deconvolutes the complex battery degradation behavior. This generalizable data-driven mechanistic framework simplifies the complex interplay between cycling conditions, degradation modes, and SOH, acting as a hypothesis-generation tool to aid battery users in identifying key degradation regimes for further study and experimentation.

25 ENERGY STORAGE↗
DOE OSTI2024

Human limits in machine learning: prediction of potato yield and disease using soil microbiome data

Abstract Background The preservation of soil health is a critical challenge in the 21st century due to its significant impact on agriculture, human health, and biodiversity. We provide one of the first comprehensive investigations into the predictive potential of machine learning models for understanding the connections between soil and biological phenotypes. We investigate an integrative framework performing accurate machine learning-based prediction of plant performance from biological, chemical, and physical properties of the soil via two models: random forest and Bayesian neural network. Results Prediction improves when we add environmental features, such as soil properties and microbial density, along with microbiome data. Different preprocessing strategies show that human decisions significantly impact predictive performance. We show that the naive total sum scaling normalization that is commonly used in microbiome research is one of the optimal strategies to maximize predictive power. Also, we find that accurately defined labels are more important than normalization, taxonomic level, or model characteristics. ML performance is limited when humans can’t classify samples accurately. Lastly, we provide domain scientists via a full model selection decision tree to identify the human choices that optimize model prediction power. Conclusions Our study highlights the importance of incorporating diverse environmental features and careful data preprocessing in enhancing the predictive power of machine learning models for soil and biological phenotype connections. This approach can significantly contribute to advancing agricultural practices and soil health management.

Aghdam, Rosa↗
DOE OSTI2026

Developing a complete AI-accelerated workflow for superconductor discovery

The quest to identify new superconducting materials with enhanced properties is hindered by the prohibitive cost of computing electron-phonon spectral functions, severely limiting the materials space that can be explored. Here, we introduce a Bootstrapped Ensemble of Equivariant Graph Neural Networks (BEE-NET), a machine-learning model trained to predict the Eliashberg spectral function and superconducting critical temperature with a mean-absolute-error of 0.87 K relative to DFT-based Allen-Dynes calculations. Intriguingly, BEE-NET achieves a true-negative-rate of 99.4%, enabling highly efficient screening for the rare property of superconductivity. Integrated into a multi-stage, AI-accelerated discovery pipeline that incorporates elemental-substitution strategies and machine-learned interatomic potentials, our workflow reduced over 1.3 million candidate structures to 741 dynamically and thermodynamically stable compounds with DFT-confirmed T c > 5 K. We report the successful synthesis and experimental confirmation of superconductivity in two of these previously unreported compounds. This study establishes a data-driven framework that integrates machine learning, quantum calculations, and experiments to systematically accelerate superconductor discovery.

Gibson, Jason B. [Quantum Formatics, Cambridge, MA↗
DOE OSTI2021

On the estimation of boundary layer heights: a machine learning approach

Abstract. The planetary boundary layer height (zi) is a key parameter used in atmospheric models for estimating the exchange of heat, momentum, and moisture between the surface and the free troposphere. Near-surface atmospheric and subsurface properties (such as soil temperature, relative humidity, etc.) are known to have an impact on zi. Nevertheless, precise relationships between these surface properties and zi are less well known and not easily discernible from the multi-year dataset. Machine learning approaches, such as random forest (RF), which use a multi-regression framework, help to decipher some of the physical processes linking surface-based characteristics to zi. In this study, a 4-year dataset from 2016 to 2019 at the Southern Great Plains site is used to develop and test a machine learning framework for estimating zi. Parameters derived from Doppler lidars are used in combination with over 20 different surface meteorological measurements as inputs to a RF model. The model is trained using radiosonde-derived zi values spanning the period from 2016 through 2018 and then evaluated using data from 2019. Results from 2019 showed significantly better agreement with the radiosonde compared to estimates derived from a thresholding technique using Doppler lidars only. Noteworthy improvements in daytime zi estimates were observed using the RF model, with a 50 % improvement in mean absolute error and an R2 of greater than 85 % compared to the Tucker method zi. We also explore the effect of zi uncertainty on convective velocity scaling and present preliminary comparisons between the RF model and zi estimates derived from atmospheric models.

54 ENVIRONMENTAL SCIENCES↗