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 19 records
All sourcesNASA NTRSDOE OSTI
DOE OSTI2025

ATTNChecker: Highly-Optimized Fault Tolerant Attention for Large Language Model Training

Large Language Models (LLMs) have demonstrated remarkable performance in various natural language processing tasks. However, the training of these models is computationally intensive and susceptible to faults, particularly in the attention mechanism, which is a critical component of transformer-based LLMs. In this paper, we investigate the impact of faults on LLM training, focusing on INF, NaN, and near-INF values in the computation results with systematic fault injection experiments. We observe the propagation patterns of these errors, which can trigger non-trainable states in the model and disrupt training, forcing the procedure to load from checkpoints. To mitigate the impact of these faults, we propose ATTNChecker, the first Algorithm-Based Fault Tolerance (ABFT) technique tailored for the attention mechanism in LLMs. ATTNChecker is designed based on fault propagation patterns of LLM and incorporates performance optimization to adapt to both system reliability and model vulnerability while providing lightweight protection for fast LLM training. Evaluations on four LLMs show that ATTNChecker on average incurs on average 7% overhead on training while detecting and correcting all extreme errors. Compared with the state-of-the-art checkpoint/restore approach, ATTNChecker reduces recovery overhead by up to 49×.

Liang, Yuhang [University of Alabama - Birmingham]↗
DOE OSTI2025

Intelligent Sampling of Extreme-Scale Turbulence Datasets for Accurate and Efficient Spatiotemporal Model Training

With the end of Moore’s law and Dennard scaling, efficient training increasingly requires rethinking data volume. Can we train better models with significantly less data via intelligent subsampling? To explore this, we develop SICKLE, a sparse intelligent curation framework for efficient learning, featuring a novel maximum entropy (MaxEnt) sampling approach, scalable training, and energy benchmarking. We compare MaxEnt with random and phase-space sampling on large direct numerical simulation (DNS) datasets of turbulence. Evaluating SICKLE at scale on Frontier, we show that subsampling as a preprocessing step can, in many cases, improve model accuracy and substantially lower energy consumption, with observed reductions of up to 38×.

Brewer, Wes [ORNL] (ORCID:0000000236393956)↗
DOE OSTI2024

An Efficient Checkpointing System for Large Machine Learning Model Training

As machine learning models increase in size and complexity rapidly, the cost of checkpointing in ML training became a bottleneck in storage and performance (time). For example, the latest GPT-4 model has massive parameters at the scale of 1.76 trillion. It is highly time and storage consuming to frequently writes the model to checkpoints with more than 1 trillion floating point values to storage. This work aims to understand and attempt to mitigate this problem. First, we characterize the checkpointing interface in a collection of representative large machine learning/language models with respect to storage consumption and performance overhead. Second, we propose the two optimizations: i) A periodic cleaning strategy that periodically cleans up outdated checkpoints to reduce the storage burden; ii) A data staging optimization that coordinates checkpoints between local and shared file systems for performance improvement.

machine learning, artificial intelligence↗
DOE OSTI2026

Forest aboveground biomass estimation through integration of sentinel-2 and PALSAR-2 time series: assessing models trained on GEDI and field inventory benchmarks

Accurate and spatially explicit forest Aboveground Biomass (AGB) mapping through remote sensing is critical for quantifying terrestrial carbon stocks and informing effective forest management strategies. However, AGB estimation in dense forests with complex terrain remains challenging due to satellite sensor signal saturation problem (saturation issue occurs in high biomass forests), structural complexity, and limited ground truth for calibration. This study presents a novel framework that integrates multi-temporal Sentinel-2 optical imagery, ALOS PALSAR-2 Synthetic Aperture Radar (SAR) data, and topographic variables with explainable Machine Learning to map AGB across mountainous forests within subtropical and temperate oceanic climate zones of Mexico. We evaluate the effects of temporal granularity and sensor synergy by comparing multiple temporal inputs and sensor configurations (Sentinel-2, PALSAR-2, and their fusion), and assess model performance using two reference datasets: NASA GEDI LiDAR-derived biomass and Mexico’s National Forest and Soil Inventory (INFyS). Our results showed that models trained on INFyS consistently outperformed those trained on GEDI, highlighting limitations in GEDI’s reliability in biomass estimates within this study region. Furthermore, the integration of Sentinel-2 and PALSAR-2 provided improved predictions compared to single-sensor models, particularly when combined with temporally explicit yearly statistics. The best-performing model, which was trained on INFyS data, and considered both Sentinel-2 and PALSAR-2 yearly statistics, as well as topographic variables, achieved an R2 of 0.64, RMSE of 51.10 Mg/ha, and relative RMSE (rRMSE) of 58.69%. Explainable ML analysis identified Sentinel-2 spectral indices and topographic features as key predictors, while PALSAR-2 metrics provided complementary information, partially mitigating saturation effects in high-biomass areas. Specifically, integrating both sensors substantially improved AGB estimation in high biomass forest (≥200 Mg/ha), yielding 98% gains over optical-only model, with resulting estimates exceeding GEDI L4B by 29% and ESA-CCI-BIOMASS by 174%. Terrain-stratified analysis indicated close agreement with GEDI in low-slope areas, with increasing divergence as slope steepness increased, while estimates remained consistently higher than ESA-CCI-BIOMASS across all slope classes. The proposed approach advances multi-sensor fusion and temporal feature engineering for AGB mapping using open-access satellite datasets, providing a scalable and reproducible framework for annual biomass monitoring in topographically complex mountainous forests. The resulting 25 m resolution biomass product has the potential to provide spatially detailed information for forest monitoring and may support applications in carbon accounting and forest management.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2024

Hamiltonian learning using machine-learning models trained with continuous measurements

Here, we build upon recent work on the use of machine-learning models to estimate Hamiltonian parameters using continuous weak measurement of qubits as input. We consider two settings for the training of our model: (1) supervised learning, where the weak-measurement training record can be labeled with known Hamiltonian parameters, and (2) unsupervised learning, where no labels are available. The first has the advantage of not requiring an explicit representation of the quantum state, thus potentially scaling very favorably to a larger number of qubits. The second requires the implementation of a physical model to map the Hamiltonian parameters to a measurement record, which we implement using an integrator of the physical model with a recurrent neural network to provide a model-free correction at every time step to account for small effects not captured by the physical model. We test our construction on a system of two qubits and demonstrate accurate prediction of multiple physical parameters in both the supervised context and the unsupervised context. We demonstrate that the model benefits from larger training sets, establishing that it is “learning,” and we show robustness regarding errors in the assumed physical model by achieving accurate parameter estimation in the presence of unanticipated single-particle relaxation.

97 MATHEMATICS AND COMPUTING↗
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 OSTI2026

Mechanical, Electrochemical & Thermal Models - Training (CRADA CRD-19-00798 Final Report)

Under the proposed effort in partnership with Hyundai Motor Company (HMC), the National Renewable Energy Laboratory (NLR) will host Dr. Jaeyoung Lim from HMC for a period of one year to jointly develop mathematical models for battery cells and modules subject to mechanical crush. NLR will assist with the development of mathematical models that Dr. Lim will incorporate into his research effort on new concepts of mobility with electric vehicles.

33 ADVANCED PROPULSION SYSTEMS↗
DOE OSTI2025

Oak Ridge National Laboratory Evaluation of Stream-Trained Models in Practice

The goal of this integration is to replicate the results from the original paper Autonomous Utility Pole Identification on different camera hardware and integrate the model into a live video stream provided by the unmanned aerial system (UAS) itself while in operation. This involves retraining the original model and validating its efficacy on multiple camera modules to select the most effective device for installation. Moreover, this integration requires writing software to handle the reception of a real-time streaming protocol stream from the UAS and run each frame through the model while allowing a user to monitor the camera feed.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2026

Machine-learning interatomic potentials for interfaces in all-solid-state batteries: Perspectives on training data, model selection, and validation

Interfaces play a pivotal role in dictating the performance and reliability of all-solid-state batteries (ASSBs), where complex electro-chemo-mechanical phenomena at grain boundaries (GBs) and interfaces can lead to degradation and failure. Traditional atomistic simulation methods, such as first-principles calculations and classical molecular dynamics, face limitations in modeling these interfaces due to either high computational cost or insufficient transferability to the diverse atomic environments evolving at interfaces. Machine-learning interatomic potentials (MLIPs) have emerged as a transformative approach, enabling large-scale, high-accuracy simulations of disordered and chemically complex systems by leveraging the predictability of machine learning models trained on first-principles data. Recent applications of MLIPs have demonstrated their ability to capture intricate behaviors at ASSB interfaces, including ion transport, interfacial evolution, and degradation mechanisms, with accuracy and efficiency unattainable by conventional methods. This prospective paper presents comprehensive analysis and practical guidance for MLIP development for GBs and interfaces in ASSBs, with a focus on three key pillars: data generation, model selection, and validation. Here, we review the current state of MLIP applications for GBs and interfaces in both general and ASSB-specific materials, highlighting best practices and challenges in constructing diverse and representative datasets, choosing appropriate machine learning architectures, and rigorously validating model performance. We also discuss emerging strategies and opportunities for improved reliability and efficiency of MLIPs to simulate realistic interfaces in ASSBs.

Energy - Storage↗
DOE OSTI2025

The role of chromatin state in intron retention: A case study in leveraging large scale deep learning models

Complex deep learning models trained on very large datasets have become key enabling tools for current research in natural language processing and computer vision. By providing pre-trained models that can be fine-tuned for specific applications, they enable researchers to create accurate models with minimal effort and computational resources. Large scale genomics deep learning models come in two flavors: the first are large language models of DNA sequences trained in a self-supervised fashion, similar to the corresponding natural language models; the second are supervised learning models that leverage large scale genomics datasets from ENCODE and other sources. We argue that these models are the equivalent of foundation models in natural language processing in their utility, as they encode within them chromatin state in its different aspects, providing useful representations that allow quick deployment of accurate models of gene regulation. We demonstrate this premise by leveraging the recently created Sei model to develop simple, interpretable models of intron retention, and demonstrate their advantage over models based on the DNA language model DNABERT-2. Our work also demonstrates the impact of chromatin state on the regulation of intron retention. Using representations learned by Sei, our model is able to discover the involvement of transcription factors and chromatin marks in regulating intron retention, providing better accuracy than a recently published custom model developed for this purpose.

Biochemistry & Molecular Biology↗
DOE OSTI2026

Sim-to-real supervised domain adaptation for radioisotope identification

Machine learning has the potential to improve the speed and reliability of radioisotope identification using gamma spectroscopy. However, meticulously labeling an experimental dataset for training is often prohibitively expensive, while training models purely on synthetic data is risky due to the domain gap between simulated and experimental measurements. In this research, we demonstrate that supervised domain adaptation can substantially improve the performance of radioisotope identification models by transferring knowledge between synthetic and experimental data domains. We consider two domain adaptation scenarios: (1) a simulation-to-simulation adaptation, where we perform multi-label proportion estimation using simulated high-purity germanium detectors, and (2) a simulation-to-experimental adaptation, where we perform multi-class, single-label classification using measured spectra from handheld lanthanum bromide (LaBr) and sodium iodide (NaI) detectors. We begin by pretraining a spectral classifier on synthetic data using a custom transformer-based neural network. After subsequent fine-tuning on just 64 labeled experimental spectra, we achieve a test accuracy of 96% in the sim-to-real scenario with a LaBr detector, far surpassing a synthetic-only baseline model (75%) and a model trained from scratch (80%) on the same 64 spectra. Furthermore, we demonstrate that domain-adapted models learn more human-interpretable features than experiment-only baseline models. Overall, our results highlight the potential for supervised domain adaptation techniques to bridge the sim-to-real gap in radioisotope identification, enabling the development of accurate and explainable classifiers even in real-world scenarios where access to experimental data is limited.

Lalor, Peter W.↗
DOE OSTI2025

Inferring fracture dilation and shear slip from surface deformation utilising trained surrogate models

An important task in energy and CO 2 storage (sequestration) in the subsurface is to verify that the surrounding fractures and faults are not activated, acting as leakage pathways. This is achievable through effective and efficient Measurement, Monitoring and Verification (MMV) plans. In this work, two surrogate models are trained to captures dilation (opening) and shear deformation of fractures, and the associated surface deformation. The trained surrogate model, based on conditional Generative-Adversarial Networks (cGAN) receives fracture apertures from dilational fractures together with fracture slips from shear fractures and predicts the combined surface deformation. An inversion algorithm based on Bayesian framework is proposed to identify the geometry of both types of fractures, as well as volume of dilational fractures and deformation moment induced by shear fractures, all from the measured surface deformation data. The inversion algorithm utilises the Differential Evolution (DE) optimisation technique that has the superior performance in finding the global minimum of cost function. The proposed surrogate-assisted inversion successfully inferred the unknown dip, dip direction and the volume of the dilational fractures as well as the induced deformation moment in shear fractures. The model was further tested for the inversion of a field hydraulic fracturing tilt dataset applying different scenarios with varying unknowns to show the model's performance, as well as incorporating shear deformation for better match with the observed data.

Dilation and shear↗
DOE OSTI2024

An Active Learning-Based Streaming Pipeline for Reduced Data Training of Structure Finding Models in Neutron Diffractometry

Structure determination workloads in neutron diffractometry are computationally expensive and routinely require several hours to many days to determine the structure of a material from its neutron diffraction patterns. The potential for machine learning models trained on simulated neutron scattering patterns to significantly speed up these tasks have been reported recently. However, the amount of simulated data needed to train these models grows exponentially with the number of structural parameters to be predicted and poses a significant computational challenge. To overcome this challenge, we introduce a novel batch-mode active learning (AL) policy that uses uncertainty sampling to simulate training data drawn from a probability distribution that prefers labelled examples about which the model is least certain. We confirm its efficacy in training the same models with ∼ 75% less training data while improving the accuracy. We then discuss the design of an efficient stream-based training workflow that uses this AL policy and present a performance study on two heterogeneous platforms to demonstrate that, compared with a conventional training workflow, the streaming workflow delivers ∼ 20% shorter training time without any loss of accuracy.

Wang, Tianle [Brookhaven National Laboratory (BNL)↗
DOE OSTI2025

Dataset, Code, and Models for Training Deep Learning Potentials for Low Temperature Plasma-Surface Interactions

This repository contains datasets, training scripts, and finished models, and test simulations used in the development of DeepREBO— a machine-learned interatomic potential trained to emulate the REBO2 empirical potential. The data was generated to study deep potential development for simulations of plasma-surface interactions. It uses an active learning framework, starting from a minimal dataset and iteratively expanding it. Included are those generated datasets, the trained models, and simulations used to evaluate the performance of the training process. This resource supports reproducibility and provides a reference framework for training deep potentials in plasma-surface interaction studies.

active learning↗
DOE OSTI2025

Transformers and Long Short-Term Memory Transfer Learning for GenIV Reactor Temperature Time Series Forecasting

Automated monitoring of the coolant temperature can enable autonomous operation of generation IV reactors (GenIV), thus reducing their operating and maintenance costs. Automation can be accomplished with machine learning (ML) models trained on historical sensor data. However, the performance of ML usually depends on the availability of large amount of training data, which is difficult to obtain for GenIV, as this technology is still under development. We propose the use of transfer learning (TL), which involves utilizing knowledge across different domains, to compensate for this lack of training data. TL can be used to create pre-trained ML models with data from small-scale research facilities, which can then be fine-tuned to monitor GenIV reactors. In this work, we develop pre-trained Transformer and long short-term memory (LSTM) networks by training them on temperature measurements from thermal hydraulic flow loops operating with water and Galinstan fluids at room temperature at Argonne National Laboratory. The pre-trained models are then fine-tuned and re-trained with minimal additional data to perform predictions of the time series of high temperature measurements obtained from the Engineering Test Unit (ETU) at Kairos Power. The performance of the LSTM and Transformer networks is investigated by varying the size of the lookback window and forecast horizon. The results of this study show that LSTM networks have lower prediction errors than Transformers, but LSTM errors increase more rapidly with increasing lookback window size and forecast horizon compared to the Transformer errors.

LSTM↗
DOE OSTI2026

Augmenting Molecular Graphs with Geometries via Machine Learning Interatomic Potentials

Accurate molecular property predictions require 3D geometries, which are typically obtained using expensive methods such as density functional theory (DFT). Here, we attempt to obtain molecular geometries by relying solely on machine learning interatomic potential (MLIP) models. To this end, we first curate a large-scale molecular relaxation dataset comprising 3.5 million molecules and 300 million snapshots. Then MLIP pre-trained models are trained with supervised learning to predict energy and forces given 3D molecular structures. Once trained, we show that the pre-trained models can be used in different ways to obtain geometries either explicitly or implicitly. First, it can be used to obtain approximate low-energy 3D geometries via geometry optimization. While these geometries do not consistently reach DFT-level chemical accuracy or convergence, they can still improve downstream performance compared to non-relaxed structures. To mitigate potential biases and enhance downstream predictions, we introduce geometry fine-tuning based on the relaxed 3D geometries. Second, the pre-trained models can be directly fine-tuned for property prediction when ground truth 3D geometries are available. Our results demonstrate that MLIP pre-trained models trained on relaxation data can learn transferable molecular representations to improve downstream molecular property prediction and can provide practically valuable but approximate molecular geometries that benefit property predictions. Our code is publicly available at: https://github.com/divelab/AIRS/.

Fu, Cong [Texas A & M Univ., College Station, TX (↗