Search NASA⌕ Search

SEARCH · Search NASA

Results for “training 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 217 records · Page 12
All sourcesNASA NTRSDOE OSTI
NASA NTRSDate not supplied

Neural Network Atmospheric Correction of Remote Sensing Imagery Over Water Using a Synthetic Dataset

Remote sensing atmospheric correction methods have primarily focused on imagery over land. However, accurate correction over water is important for monitoring and research of aquatic environments. More research in this area is ongoing, though one of the biggest challenges is enough quality data to develop and validate correction methods. This is especially true for neural network (NN) -based models which have shown promise in this area given enough quality data. To address this deficiency of data, we are leveraging a synthetic dataset produced by a model called SWIPE that uses radiative transfer modeling to simulate the atmospheric effects on water-leaving (WL) reflectance to estimate top-of-atmosphere (TOA) reflectance. This allows us to produce almost unlimited pairs of WL reflectance and corresponding TOA reflectance for model training across a variety of atmospheric conditions. We use two approaches for our atmospheric correction model. One uses a conditional variational autoencoder (VAE) to estimate a single WL reflectance value from a single TOA reflectance value. The second is based on a UNET architecture and estimates an array of WL reflectance values from an array of TOA reflectance values. The goal of the second method is to capture atmospheric effects that occur spatially between values within the array as compared to the first method.

deep learning↗
NASA NTRSDate not supplied

Curating AI-Ready Datasets for Equity and Environmental Justice: A Data-Centric AI Case Study

An equitable and environmentally just community is essentialin order to avoid disproportionate burden borne by vulnerablecommunities. This need becomes pressing in the aftermathof an extreme event such as disaster or hazard when it is diffi-cult for the governing bodies to implement resource allocationas per the need. Artificial Intelligence (AI) algorithms canhelp surface Equity and Environmental Justice (EEJ) issueswhen trained on EEJ datasets. However, curating AI-readyEEJ training datasets is challenging due to differences in fac-tors such as heterogeneity, resolution, modality, and level ofexpertise in labeling. Additionally, EEJ issues involve sensi-tive information where uncertainties and errors could degradethe performance of AI algorithms. For eg. Error in seasonalcrop yield information can highly affect the prediction of an-nual crop yield. To address these challenges, Data-centricAI (DCAI) methods are employed, which enhance AI algo-rithm performance even with limited training samples. DCAIprioritizes data quality, thereby reducing the adverse effectsof uncertainties and errors during the model training process.This research proposes a novel dataset and benchmark for an-alyzing the effect of the Maui Wildfire of 2023 for Equityand Environmental Justice (EEJ) issues. The proposed datasetaligns with the concepts of DCAI such as annotation quality,data preprocessing, privacy, feature engineering, governanceand provenance. We firmly believe that the proposed datasetwould lay a foundation to implement robust and reliable mod-ern AI algorithms for addressing EEJ issues.

Paridhi Parajuli↗
DOE OSTI2024

Addressing bias in bagging and boosting regression models

As artificial intelligence (AI) becomes widespread, there is increasing attention on investigating bias in machine learning (ML) models. Previous research concentrated on classification problems, with little emphasis on regression models. This paper presents an easy-to-apply and effective methodology for mitigating bias in bagging and boosting regression models, that is also applicable to any model trained through minimizing a differentiable loss function. Our methodology measures bias rigorously and extends the ML model's loss function with a regularization term to penalize high correlations between model errors and protected attributes. We applied our approach to three popular tree-based ensemble models: a random forest model (RF), a gradient-boosted model (GBT), and an extreme gradient boosting model (XGBoost). We implemented our methodology on a case study for predicting road-level traffic volume, where RF, GBT, and XGBoost models were shown to have high accuracy. Despite high accuracy, the ML models were shown to perform poorly on roads in minority-populated areas. Our bias mitigation approach reduced minority-related bias by over 50%.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2025

Quantum optimal control of superconducting qubits based on machine-learning characterization

Implementing fast and high-fidelity quantum operations using open-loop quantum optimal control relies on having an accurate model of the quantum dynamics. Any deviations between this model and the complete dynamics of the device, such as the presence of spurious modes or pulse distortions, can degrade the performance of optimal controls in practice. Here, we propose an experimentally simple approach to realize optimal quantum controls tailored to the device parameters and environment while specifically characterizing this quantum system. Concretely, we use physics-inspired machine learning to infer an accurate model of the dynamics from experimentally available data and then optimize our experimental controls on this trained model. We show the power and feasibility of this approach by optimizing arbitrary single-qubit operations in detailed numerical simulations of a superconducting transmon qubit. Furthermore, we demonstrate that this framework produces an accurate description of the device dynamics under arbitrary controls, together with the precise pulses achieving arbitrary single-qubit gates with a high fidelity of ∼99.99%.

Artificial neural networks↗
DOE OSTI2026

RxnRover/amlro

AMLRO (Active Machine Learning Reaction Optimizer) is an open-source framework designed to accelerate chemical reaction optimization using active learning with classical machine learning regression models. AMLRO integrates space-filling sampling strategies (e.g., Sobol and Latin Hypercube sampling) with iterative model training, prediction, and experiment selection to efficiently navigate complex reaction spaces. The platform supports multiple regression models, flexible multi-objective definitions, and user-defined parameter bounds, enabling data-efficient optimization from small initial datasets. AMLRO is designed for ease of use by experimentalists and can operate as a standalone decision-support tool or be integrated into closed-loop automated experimentation workflows.

Kulathunga, Dulitha Prasanna [Iowa State Universit↗
NASA NTRS2020

Study of Antarctic Blowing Snow Storms Using MODIS and CALIOP Observations With a Machine Learning Model

As a common phenomenon over Antarctica, blowing snow (BLSN), especially the large BLSN storms, play an important role in the Antarctic surface mass balance, radiation budget, and planetary boundary layer processes. This study presents the work on BLSN storm identification and analysis with observations from the Moderate Resolution Imaging Spectroradiometer (MODIS) onboard the Aqua satellite. Spectral analysis shows that BLSN identification is feasible with MODIS daytime data. A random forest machine learning model is developed and observations from the Cloud‐Aerosol Lidar with Orthogonal Polarization are used for training. Model performance results show that machine‐learning based classification can achieve over 90% overall accuracy when classifying MODIS pixels into cloud, clear, and BLSN categories. The machine learning model is applied to MODIS observations during the month of October 2009 for BLSN storm analysis. Results show that the size of BLSN storms has a large spectrum and can reach hundreds of thousands km2. The MODIS based BLSN storm frequency map extends the Cloud‐Aerosol Lidar and Infrared Pathfinder Satellite Observations coverage limit from 82°S to the South Pole. A BLSN storm belt, which extends from the South Pole region to the coastal area between 130°E and 160°E along the Transantarctic Mountains, provides a potential pathway of snow transport. These results are important in improving the understanding of BLSN impact on Antarctic surface mass balance and boundary layer processes.

Antarctic↗
DOE OSTI2025

Unsupervised Clustering and Supervised Regression Learning to Select High Temperature Oxidation-Resistant Materials

High temperature oxidation and corrosion degradation mechanisms dictate the lifetime of materials critical to energy production. The combination of modeling and experimental approaches such as machine learning (ML) and data analytics, with sufficient experimental data, can accelerate the development of new materials while limiting its cost. In the present work, ML will be applied to two high temperature oxidation data libraries (Oak Ridge National Laboratory and National Air and Space Administration) that comprised of about 5000 mass change sample datasheets for a variety of materials and temperatures in dry air and air + 10 % H2O. A python code was developed to prepare the data for machine learning by collecting and formatting oxidation rate constants, alloy compositions and environment of exposure into a single data frame. Scikit-learn library and Statistics and Machine Learning Toolbox within MathWorks were then used to perform unsupervised clustering and supervised regression learning. The impact of dataset distribution on the performance of the developed ML models was evaluated. Potential strategies to improve the predictions and enhance extrapolative capability of the previously trained model were investigated.

Romedenne, Marie [ORNL] (ORCID:0000000317936561)↗
DOE OSTI2026

D$e^+e^-$ffusion: Capturing the Beam-Beam Physics of $e^+e^-$ Collisions with Diffusion Models

Beam-induced backgrounds at high-luminosity $e^+e^-$ colliders, such as the FCC-ee, are dominated by incoherent pair creation (IPC), and require computationally expensive simulations with dedicated Monte Carlo (MC) event generators. Reliable detector and machine-detector interface studies necessitate event samples that are several orders of magnitude larger than what is practically attainable with existing MC. To alleviate this bottleneck, we present D$e^+e^-$ffusion, a denoising diffusion probabilistic model that operates as a permutation-equivariant, set-valued surrogate for fast IPC simulation. Trained on a small GuineaPig++ sample, D$e^+e^-$ffusion faithfully reproduces the marginal and joint kinematic, angular, and positional distributions of all three IPC production processes. In addition, we assess the fidelity at the detector level by propagating both Geant4 and D$e^+e^-$ffusion events through a Geant4 simulation of the CLD vertex detector and by training a transformer-based two-sample classifier; the classifier achieves an area under the ROC curve of $0.553 \pm 0.016$. The trained model generates events nearly four orders of magnitude faster than Geant4, paving the way for a fast-simulation surrogate for FCC-ee design studies.

Chahine, Antonio [Imperial Coll., London]↗
DOE OSTI2024

Inverse Design of Photonic Surfaces via High throughput Femtosecond Laser Processing and Tandem Neural Networks

Abstract This work demonstrates a method to design photonic surfaces by combining femtosecond laser processing with the inverse design capabilities of tandem neural networks that directly link laser fabrication parameters to their resulting textured substrate optical properties. High throughput fabrication and characterization platforms are developed that generate a dataset comprising 35280 unique microtextured surfaces on stainless steel with corresponding measured spectral emissivities. The trained model utilizes the nonlinear one‐to‐many mapping between spectral emissivity and laser parameters. Consequently, it generates predominantly novel designs, which reproduce the full range of spectral emissivities (average root‐mean‐squared‐error < 2.5%) using only a compact region of laser parameter space 25 times smaller than what is represented in the training data. Finally, the inverse design model is experimentally validated on a thermophotovoltaic emitter design application. By synergizing laser‐matter interactions with neural network capabilities, the approach offers insights into accelerating the discovery of photonic surfaces, advancing energy harvesting technologies.

36 MATERIALS SCIENCE↗
DOE OSTI2024

DASEventNet: AI‐Based Microseismic Detection on Distributed Acoustic Sensing Data From the Utah FORGE Well 16A (78)‐32 Hydraulic Stimulation

Abstract Distributed acoustic sensing (DAS) has emerged as a promising seismic technology for monitoring microearthquakes (MEQs) with high spatial resolution. Efficient algorithms are needed for processing large DAS data volumes. This study introduces a deep learning (DL) model based on a Residual Convolutional Neural Network (ResNet) for detecting MEQs using DAS data, named as DASEventNet. The test data were collected from the Utah FORGE 16A (78)‐32 hydraulic stimulation experiments conducted in April 2022. The DASEventNet model achieves a remarkable accuracy of 100% when discriminating MEQs from noise in the raw test set of 260 examples. Surprisingly, the model identified weak MEQ signatures that have been manually categorized as noise. The decision‐making process with the model is decoded by the classic activation map, which illuminates learning features of the DASEventNet model. These features provide clear illustrations of weak MEQs and varied noise types. Finally, we apply the trained model to the entire period (∼7 days) of continuous DAS recordings and find that it discovers >5,700 new MEQs, previously unregistered in the public Silixa DAS catalog. The DASEventNet model significantly outperforms the traditional seismic method Short‐Term Average/Long‐Term Average (STA/LTA), which detected only 1,307 MEQs. The DASEventNet detection threshold is M w −1.80 compared to the minimum magnitude of M w −1.14 detected by STA/LTA. The spatiotemporal distribution of the newly identified MEQs defines an extensive stimulation zone and more accurately characterizes fracture geometry. Our results highlight the potential of DL for long‐term, real‐time microseismic monitoring that can improve enhanced geothermal systems and other activities that include subsurface hydraulic fracturing.

15 GEOTHERMAL ENERGY↗
DOE OSTI2025

Inverse model based error detection in beamline optics

Optics tuning in transfer lines and LINACs can be challenging due to the fact that multiple combinations of machine settings can lead to the same diagnostic output. Moreover, the lack of a periodic solution can limit the ability to infer optics in the same way as rings from BPM signals. Model based approaches are often used to assist with the optics tuning in combination with optimization or parameter estimation. Here we have developed a novel approach using machine learning inverse models trained on a known configuration to detect variations in quadrupole settings without explicitly including them in the model. This paper shows a comparison of neural network models and linear models on both a simulation based study and experimental studies conducted at the AGS to RHIC transfer line at Brookhaven National Lab.

43 PARTICLE ACCELERATORS↗
DOE OSTI2025

Uncertainty quantification for neural network potential foundation models

Abstract For neural network potentials (NNPs) to gain widespread use, researchers must be able to trust model outputs. However, the blackbox nature of neural networks and their inherent stochasticity are often deterrents, especially for foundation models trained over broad swaths of chemical space. Uncertainty information provided at the time of prediction can help reduce aversion to NNPs. In this work, we detail two uncertainty quantification (UQ) methods. Readout ensembling, by finetuning the readout layers of an ensemble of foundation models, provides information about model uncertainty, while quantile regression, by replacing point predictions with distributional predictions, provides information about uncertainty within the underlying training data. We demonstrate our approach with the MACE-MP-0 model, applying UQ to the foundation model and a series of finetuned models. The uncertainties produced by the readout ensemble and quantile methods are demonstrated to be distinct measures by which the quality of the NNP output can be judged.

36 MATERIALS SCIENCE↗
DOE OSTI2024

Crustal permeability generated through microearthquakes is constrained by seismic moment

We link changes in crustal permeability to informative features of microearthquakes (MEQs) using two field hydraulic stimulation experiments where both MEQs and permeability evolution are recorded simultaneously. The Bidirectional Long Short-Term Memory (Bi-LSTM) model effectively predicts permeability evolution and ultimate permeability increase. Our findings confirm the form of key features linking the MEQs to permeability, offering mechanistically consistent interpretations of this association. Transfer learning correctly predicts permeability evolution of one experiment from a model trained on an alternate dataset and locale, which further reinforces the innate interdependency of permeability-to-seismicity. Models representing permeability evolution on reactivated fractures in both shear and tension suggest scaling relationships in which changes in permeability (Δk) are linearly related to the seismic moment (M) of individual MEQs as Δk ∝ M. This scaling relation rationalizes our observation of the permeability-to-seismicity linkage, contributes to its predictive robustness and accentuates its potential in characterizing crustal permeability evolution using MEQs.

15 GEOTHERMAL ENERGY↗
DOE OSTI2025

Low responsiveness of machine learning models to critical or deteriorating health conditions

Machine learning (ML) based mortality prediction models can be immensely useful in intensive care units. Such a model should generate warnings to alert physicians when a patient’s condition rapidly deteriorates, or their vitals are in highly abnormal ranges. Before clinical deployment, it is important to comprehensively assess a model’s ability to recognize critical patient conditions. We develop multiple medical ML testing approaches, including a gradient ascent method and neural activation map. We systematically assess these machine learning models’ ability to respond to serious medical conditions using additional test cases, some of which are time series. Guided by medical doctors, our evaluation involves multiple machine learning models, resampling techniques, and four datasets for two clinical prediction tasks. We identify serious deficiencies in the models’ responsiveness, with the models being unable to recognize severely impaired medical conditions or rapidly deteriorating health. For in-hospital mortality prediction, the models tested using our synthesized cases fail to recognize 66% of the injuries. In some instances, the models fail to generate adequate mortality risk scores for all test cases. Our study identifies similar kinds of deficiencies in the responsiveness of 5-year breast and lung cancer prediction models. Using generated test cases, we find that statistical machine-learning models trained solely from patient data are grossly insufficient and have many dangerous blind spots. Most of the ML models tested fail to respond adequately to critically ill patients. How to incorporate medical knowledge into clinical machine learning models is an important future research direction.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2026

Multitask graph neural networks for elastoplastic response prediction in dual-phase polycrystals

Microstructure-sensitive prediction of elastoplastic response remains a recurring bottleneck in multiscale damage and fatigue modeling, where large ensembles of statistically distinct polycrystals are required to quantify variability and extreme-value behavior. In this work, we develop a multitask graph neural network (GNN) surrogate that maps dual-phase ferrite–martensite polycrystal microstructures to Statistical Volume Element (SVE)-level elastoplastic Quantities of Interest (QoIs). Each SVE is represented as a grain-adjacency graph, with node features encoding phase, geometry, and crystallographic orientation, and edge features encoding relative misorientation. A message-passing graph convolution generates node embeddings, which are pooled into a graph representation and passed to a multitask regression head that jointly predicts 10 scalar QoIs and vector-valued stress–strain responses in orthogonal loading directions across multiple martensite volume fractions and SVE sizes. Results show high accuracy for scalar QoIs and strong agreement for full stress–strain trajectories, with population envelopes reproducing both median behavior and finite-SVE variability across compositions and partition scales. A unified model trained on pooled volume-fraction data preserves most within-regime accuracy relative to regime-specific models while also capturing the broader cross-regime variation reflected in the pooled test set. Distributional comparisons further demonstrate that the surrogate preserves heterogeneity under SVE partitioning, enabling statistically consistent block-wise random-field construction for mesoscale analyses. Overall, the proposed grain-graph surrogate provides a practical pathway to accelerate ensemble-based studies of SVE-level constitutive variability in dual-phase polycrystals.

Crystal plasticity↗
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 OSTI2024

OPER: Optimality-Guided Embedding Table Parallelization for Large-scale Recommendation Model

With the sharp increasing volume of user data, Deep Learning Recommendation Model (DLRM) becomes an indispensable infrastructure in large technology companies. However, large-scale DLRM on the multi-GPU platform is still inefficient due to unbalanced workload partitioning and intensive inter-GPU communication. To this end, we propose OPER, an OPtimality guided Embedding table placement for large-scale Recommendation model training and inference. OPER explores the potential of mitigating remote memory access latency in DLRM through fine-grained embedding table placement. Specifically, OPER proposes a theoretical modeling that builds up the relationship between EMT placement and the embedding communication latency in both training and inference. OPER proves the NP hardness of finding the optimal embedding table placement and proposes a heuristic algorithm that yields near optimal placement. OPER implements a SHMEM-based embedding table training system and a unified embedding index mapping to support fine-grained embedding table sharding and placement. Comprehensive experiments reveal that OPER achieves on average 3.4× and 5.1× speedup on training and inference respectively over state-of-the-art DLRM frameworks.

Wang, Zheng↗
DOE OSTI2024

Comparative Study of Large Language Model Architectures on Frontier

Large language models (LLMs) have garnered significant attention in both the AI community and beyond. Among these, the Generative Pre-trained Transformer (GPT) has emerged as the dominant architecture, spawning numerous variants. However, these variants have undergone pre-training under diverse conditions, including variations in input data, data preprocessing, and training methodologies, resulting in a lack of controlled comparative studies. Here we meticulously examine two prominent open-sourced GPT architectures, GPT-NeoX and LLaMA, leveraging the computational power of Frontier, the world’s first Exascale supercomputer. Employing the same materials science text corpus and a comprehensive end-to-end pipeline, we conduct a comparative analysis of their training and downstream performance. Our efforts culminate in achieving state-of-the-art performance on a challenging materials science benchmark. Furthermore, we investigate the computation and energy efficiency, and propose a computationally efficient method for architecture design. To our knowledge, these pre-trained models represent the largest available for materials science. Our findings provide practical guidance for building LLMs on HPC platforms.

Yin, Junqi↗