Search NASA⌕ Search

SEARCH · Search NASA

Results for “fine tuning”

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 109 records · Page 6
All sourcesNASA NTRSDOE OSTI
DOE OSTI2026

ChatMPI: LLM-Driven MPI Code Generation for HPC Workloads

The Message Passing Interface (MPI) standard plays a crucial role in enabling scientific applications for parallel computing and is an essential component in high-performance computing (HPC). However, implementing MPI code manually—especially applying a proper domain decomposition and communication pattern—is a challenging and error-prone task. We present ChatMPI, an AI assistant for MPI parallelization of sequential C codes. In our analysis, we focus on testing six essential HPC workloads, which are based on Basic Linear Algebra Subprograms levels 1, 2, and 3 as well as sparse, stencil, and iterative operations. We analyze the process of creating ChatMPI by using the ChatHPC library. This lightweight large language model (LLM)–based infrastructure enables HPC experts to efficiently create and supervise trustworthy AI capabilities for critical HPC software tasks. We study the data required for training (fine-tuning) ChatMPI to generate parallel codes that not only use MPI syntax correctly but also apply HPC techniques to reduce memory communication and maximize performance by using proper work decomposition. With a relatively small training dataset composed of a few dozen prompts and fewer than 15 minutes of fine-tuning on one node equipped with two NVIDIA H100 GPUs, ChatMPI elevates trustworthiness for MPI code generation of current LLMs (e.g., Code Llama, ChatGPT-4o and ChatGPT 5). Additionally, we evaluate the performance of the MPI codes generated by ChatMPI in comparison with the ones generated by ChatGPT-4o and ChatGPT-5. The codes generated by ChatMPI provide up to a 4 × boost in performance by using better problem decomposition, communication patterns, and HPC techniques (e.g., communication avoiding).

Valero Lara, Pedro [ORNL] (ORCID:0000000214794310)↗
DOE OSTI2025

Edge AI-Enhanced Traffic Monitoring and Anomaly Detection Using Multimodal Large Language Models

This paper addresses the challenge of traffic monitoring and incident detection in remote areas, utilizing multimodal large language models (LLMs) deployed on edge AI devices. The key novelty of the LLM is to convert real-time video streams into descriptive texts, enabling low-bandwidth transmissions and reliable detection of anomalies and incidents in environments of intermittent connectivity. The model is developed based on fine-tuning open-source LLMs and extending it with multi-modal capabilities to analyze video frames. Our work also involves deploying this model on edge devices such as Nvidia IGX Orin and is planned to be tested in realistic environments in future work. The methodology includes data set curation, iterative model fine-tuning and compression, and hardware-based optimization. This approach aims to enhance traffic safety and response speed in remote areas, marking a significant advancement in the application of AI for traffic monitoring and safety management.

Peruski, Ryan [University of Tennessee, Knoxville ↗
DOE OSTI2023

Adaptive Data-Driven Model Predictive Control for Heat Pipe Microreactors

To establish a technical basis for self-regulating microreactors, a model predictive control (MPC) system is investigated to proactively respond to anomalies and disturbances in anticipation of potential deviations from operating setpoints. Due to the difficulty of developing a physics-based surrogate model that can accurately match plant data in various operating conditions, machine learning algorithms are used in MPC, which allow for learning from both simulation and operation data, thus efficiently describing the targeted transient with arbitrary accuracy. However, one of the biggest concerns in applying ML algorithms like artificial neural networks (ANNs) is that the predictive capabilities of ANN are limited by training data. If there are gaps between the training and target domain, the accuracy of an ANN can degrade significantly when it is used to predict unseen data. To improve the predictive capability of ANN and enable a confident use of data-driven MPCs outside the training data, this study proposes an adaptive data-driven MPC framework. The system will monitor the discrepancy between plant responses and surrogate predictions, fine-tune the ANN-based surrogate when a large discrepancy is detected, and continue MPC operation with updated surrogates. The framework is demonstrated on a point kinetic model for microreactors. The hyperparameters of the update strategy, including layers to update, error thresholds, learning rate discount, and number of data points used for fine-tuning, are optimized so the simulated microreactor is able to follow changes in setpoint with the smallest of deviations.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗
DOE OSTI2023

Adaptable Data Driven Model Predictive Control for Heat Pipe Microreactors

To establish a technical basis for self-regulating microreactors, a model predictive control (MPC) system is investigated to proactively respond to anomalies and disturbances in anticipation of potential deviations from operating setpoints. Due to the difficulty of developing a physics-based surrogate model that can accurately match plant data in various operating conditions, machine learning algorithms are used in MPC, which allow for learning from both simulation and operation data, thus efficiently describing the targeted transient with arbitrary accuracy. However, one of the biggest concerns in applying ML algorithms like artificial neural networks (ANNs) is that the predictive capabilities of ANN are limited by training data. If there are gaps between the training and target domain, the accuracy of an ANN can degrade significantly when it is used to predict unseen data. To improve the predictive capability of ANN and enable a confident use of data-driven MPCs outside the training data, this study proposes an adaptive data-driven MPC framework. The system will monitor the discrepancy between plant responses and surrogate predictions, fine-tune the ANN-based surrogate when a large discrepancy is detected, and continue MPC operation with updated surrogates. The framework is demonstrated on a point kinetic model for microreactors. The hyperparameters of the update strategy, including layers to update, error thresholds, learning rate discount, and number of data points used for fine-tuning, are optimized so the simulated microreactor is able to follow changes in setpoint with the smallest of deviations.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗
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 OSTI2025

A Risk-Informed Approach to Trustworthiness Assessment in Digital Twins-Based Autonomous Control

In autonomous control systems, digital twins (DTs) are used to perform diagnostic and prognostic functions. The trustworthiness of these DTs is dependent on quality and coverage of the training data, model accuracy and integrity of sensor data. This work introduces a methodology to determine the trustworthiness of a DT system given faulty sensor data using a risk informed approach. Bayesian Belief Networks (BBNs) are used to propagate uncertainties and determine the probability of trustable recommendations. The decision to trust the control action provided by the DT is based on the DT output, expert opinion, and severity of problems. The performance of DTs is reliant on the data they are trained on. When they encounter out of distribution data, the trustworthiness of the recommendations decreases. To address this issue, we include an expert component that provides input on sensor degradation. For this, we utilize a generative artificial intelligence (AI) model, such as Generative Pretrained Transformer (GPT). The GPT functions as an expert with broad knowledge. The GPT is fine-tuned to understand and discriminate sensor degradation scenarios using manufactured data. This methodology is demonstrated through a case study on a Nearly Autonomous Management and Control System (NAMAC) during a steady state scenario. Various sensor degradation types with different severity levels are considered. Degraded sensor data is processed by the DT system and the fine-tuned GPT. Finally, using the BBN, we combine the GPT information and the DT output with its sources of uncertainty. This provides an output regarding the trustworthiness of the DT recommendation.

22 - GENERAL STUDIES OF NUCLEAR REACTORS↗
DOE OSTI2026

Computer vision-based rock bolt detection in orthomosaic imagery obtained in the Waste Isolation Pilot Plant underground facility

Assessing structural integrity of large underground tunnel facilities is often a time consuming and human-labor intensive task. Thus, research using various modes of sensing and automated detection of key structural components in mines is posed to aid in safety assessments and establishing overall structural health. We propose an approach utilizing off-the-shelf camera and lidar technology fixed to a custom sensing platform, image stitching techniques, fine-tuned object detection models, and specialized model-inference methods to automatically detect, count, and map roof bolts for assessment of structural safety in man-made underground tunnels. Results show a novel workflow for effective object counting in orthomosaic tunnel ceiling images generated from collections in GPS-denied mining environments. Additionally, we demonstrate effective fine-tuning of EfficientDet object detectors utilizing state-of-the-art image augmentation techniques known as the mosaic and mixup transformations. Our work is demonstrated on sensed data and imagery collected from the Department of Energy (DOE) Waste Isolation Pilot Plant (WIPP) where miles of tunnel ceiling must be assessed for structural integrity.

42 ENGINEERING↗
DOE OSTI2021

An Introduction to Word Embeddings and Language Models

Language models have advanced at a phenomenal pace over the past decade. This document provides a short introduction to terminology, word embeddings (aka low-dimensional representations), and popular large-scale language models (LMs). Word embeddings are used to represent words as numerical vectors and are context-independent, meaning a word can only have a single representation (e.g., club can only be club sandwich, not golf club ). Language models can determine the probability of a given sequence of words occurring in a sentence and can provide context to distinguish between words and phrases that sound similar. LMs are context-dependent (e.g., club can be club sandwich or golf club ) and largely fall in two main classes – autoregressive and autoencoding models. Autoregressive models are pretrained on the classic language modeling task: guess the next token having read all the previous ones. Those models can be fine-tuned and achieve great results on many tasks, the most natural application is text generation. A typical example of such models is GPT, but others include GPT-2, GPT-3, CTLR, TRANSFORMER-XL, REFORMER, XLNET. Autoencoding models are pretrained by corrupting the input tokens in some way and trying to reconstruct the original sentence. They can be fine-tuned and achieve great results on many tasks such as text generation, but their most natural application is sentence classification or token classification. A typical example of such models is BERT, but others include ROBERTA, ALBERT, XML, XML-ROBERTA, FLAUBERT AND LONGFORMER.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2022

Tuning Fluorination of Linear Carbonate for Lithium-Ion Batteries

Liquid electrolyte engineering plays a critical role in modern lithium-ion batteries. However, the existing electrolytes fall short when used with some trending battery chemistries such as high-voltage and high-energy-density electrodes. Fluorination of electrolyte solvents has been identified as an effective approach for improved cyclability, but few works systematically studied the effects of fluorination extent of carbonate solvents on battery performance. Here we design and synthesize a family of fluorinated ethyl methyl carbonates. Different numbers of F atoms are finely tuned to yield monofluoroethyl methyl carbonate (F1EMC), difluoroethyl methyl carbonate (F2EMC) and trifluoroethyl methyl carbonate (F3EMC). The cycling behavior of several types of lithium-ion pouch cells, including graphite (Gr)/single-crystalline LiNi 0.8 Mn 0.1 Co 0.1 O 2 (SC-NMC811), Gr-SiO x /LiNi 0.6 Mn 0.2 Co 0.2 O 2 (NMC622), high-voltage Gr/LiNi 0.5 Mn 1.5 O 4 (LNMO), Gr/layered Li-rich Mn-based oxide (LLMO) and fast-charging Gr/NMC622, were systematically investigated to understand the impact of fluorination degree. Compared to the commercially available F3EMC, we found that the partially-fluorinated F1EMC and F2EMC in some cases showed improved cycling stability, which we attribute to their locally-polar –CH 2 F and –CHF 2 groups and thus fast ion conduction than –CF 3 . This work suggests that highly or fully fluorinated solvents are not necessarily desirable; instead, fluorination degree needs to be rationally and finely tuned for optimized lithium-ion cell performance.

25 ENERGY STORAGE↗
DOE OSTI2026

BrickQA: Bridging the Semantic Gap in Building Operations with Dynamic Graph Exploration

While standardized ontologies like the Brick schema address data heterogeneity in Building Automation Systems (BAS), accessing this semantic data remains a challenge as domain experts often lack the expertise to formulate complex SPARQL queries. To bridge this gap, we present BrickQA, a Large Language Model (LLM)-based framework that translates natural language into executable SPARQL queries through structured query decomposition, dynamic schema exploration, and inline validation. BrickQA utilizes an iterative reasoning agent to actively navigate graph topology through dynamic exploration actions without requiring exhaustive context injection or model fine-tuning. This approach effectively mitigates hallucinations, particularly in large-scale building knowledge graphs. Empirical evaluation on BuildingQA, a standardized benchmark, demonstrates that BrickQA significantly outperforms ReAct baselines, delivering a 0.291–0.355 absolute F1 improvement while achieving 3 × –12.7 × higher token cost-efficiency. Beyond these metrics, the framework maintains structural fidelity across heterogeneous buildings and remains resilient to ambiguous queries without requiring site-specific fine-tuning. Furthermore, a case study on operational analytics validates the framework’s capability to handle temporal and aggregation constraints, effectively transforming abstract semantic models into actionable facility management insights.1

Ko, Yun-Dam↗
DOE OSTI2024

Multiscale Modeling of Vinyl-Addition Polynorbornenes: The Effect of Stereochemistry

Vinyl-addition polynorbornenes are candidates for designing high-performance polymers due to unique characteristics, which include a high glass transition temperature associated with a rigid backbone. Recent studies have established that the processability and properties of these polymers can be fine-tuned by using targeted substitutions. However, synthesis with different catalysts results in materials with distinct properties, potentially due to the presence of various stereoisomers that are difficult to quantify experimentally. Herein, we develop all-atom models of polynorbornene oligomers based on classical force fields and density functional theory. To establish the relationship between chemical architecture, chain conformations, and melt structure, we perform detailed molecular dynamics simulations with the fine-tuned atomistic force field and propose simpler coarse-grained descriptions to address the high molecular weight limit. All-atom simulations of oligomers suggest high glass transition temperatures in the range of 550–600 K. In the melt state (800 K), meso chains form highly rigid extended coils (C∞≈11) with amorphous structural characteristics similar to the X-ray diffraction data observed in the literature. In contrast, simulations with racemo chains predict highly helical tubular chain conformations that could promote assembly into crystalline structures.

Polymer Science↗
DOE OSTI2025

Leveraging Natural Language Processing and Generative Models in Molecular Chemistry: Property Prediction and Novel Compound Generation

The accurate prediction of molecular properties is important for the rational design and the advancement of green chemistry and sustainable materials research. However, the predictive power of traditional computational chemistry methods is limited due to computational restrictions. Here, in this study, we examine an alternative approach to the accurate prediction of properties of organic compounds: natural language processing (NLP)-based molecular embedding. Using viscosity, partition coefficient (log P), and enthalpy of vaporization as test properties through a survey of comprehensive datasets comprising 5695 data points for viscosity, 25 870 data points for log P, and 2296 data points for enthalpy of vaporization. These are important properties for the design of greener, safer, and sustainable chemical processes. Models were trained using NLP methods such as Mol2vec and fine-tuned ChemBERTa, and results were compared with traditional input featurization techniques such as Morgan fingerprints and quantum chemistry derived sigma profiles and DFT features. Among the various machine learning models, Mol2vec demonstrated superior predictive capabilities, achieving the highest correlation coefficient (R 2 = 0.945) and lowest RMSE (0.106 mPa s) for viscosity, as well as high accuracy for log P and enthalpy of vaporization predictions. These findings establish the Mol2vec featurization technique, graph-convolutional neural networks (GCNN), and fine-tuned ChemBERTa model as powerful tools for predictive modeling of organic compounds properties, offering a significant improvement over previously used featurization techniques and opening up strategies for very-high-throughput computational screening. Finally, we integrated ML models with hybrid language-model-based generative adversarial networks (LM-GAN) to generate novel molecular sequences with desirable properties for different research applications. The ability to computationally design solvents with lower viscosity, lower log P, and lower enthalpy of vaporization offers a data-driven route to accelerating the discovery of sustainable alternatives to traditionally toxic solvents.

ChemBERTa↗
DOE OSTI2025

Side Chain Engineering of Near-IR Aza-BODIPY Dyes Enables Processable Films with High Hole Mobility in Diodes

Boron chelated azadipyrromethene (Aza-BODIPY) derivatives are promising candidates for near-infrared optoelectronic applications due to their tunable absorption, electron-deficient core, and strong π-conjugation. Here, in this work, we synthesized and studied a series of 1-naphthylethynyl-substituted aza-BODIPY molecules featuring hexyl or hexyloxy solubilizing groups at either the proximal or the distal phenyl positions. These substitutions were designed to improve the solubility, film formation, and optoelectronic properties. We found that solubilizing groups not only enabled uniform solution-processed films but also fine-tuned key properties, such as absorption onset, oxidation potential, and energy levels. Charge transport analysis showed consistently high hole mobilities (∼10 –3 cm 2 /V s) across all substituted derivatives when CuI was used as the hole transport layer, regardless of film morphology. In contrast, electron mobilities tended to be low and inconsistent, partly because of the relatively poor-quality films on the ZnO electron transport layer. Overall, we have shown that solubilizing groups enable film solution-casting and can fine-tune the properties of these near-infrared aza-BODIPY derivatives.

36 MATERIALS SCIENCE↗
DOE OSTI2026

HydraGNN_GFM_FineTuning4Materials v1.0

This repository enables fine-tuning of the HydraGNN Predictive GFM 2026 — an open-source ensemble of pre-trained graph foundation models for atomistic materials modeling, developed at Oak Ridge National Laboratory. The GFM 2026 is freely available and downloadable via Globus from the OLCF Data Constellation (DOI: 10.13139/OLCF/2562660). Starting from these pre-trained weights, this repository provides a complete transfer learning pipeline for adapting the GFM ensemble to domain-specific molecular and materials property prediction tasks. It includes: 1) Utilities for ensemble fine-tuning with task-specific output heads 2) Example pipelines for eight widely-used materials and molecular datasets 3) Tools for model adaptation and head configuration 4) Data preprocessing utilities for each supported dataset 5) Benchmarking and evaluation scripts

Ungerboeck, Linda↗
DOE OSTI2025

Natural top quark condensation (a redux)

The Nambu--Jona-Lasinio (NJL) model involves a pointlike 4-fermion interaction. While it gives a useful description of chiral dynamics (mainly in QCD), it nonetheless omits the crucially important internal wave-function of a two-body bound state, $\phi(r)$. This becomes significant near critical coupling where $\phi(r)$ extends to large distance, leading to dilution and suppression of induced couplings $\propto \phi(0)$, such as the Yukawa and quartic couplings, as well as reduced fine-tuning of a hierarchy. In top quark condensation, where the BEH boson is a $\bar{t}t$ bound state and we have a UV completion such as topcolor, we must go beyond the NJL model and include effects of $\phi(r)$. We provide a formulation of this for the Brout-Englert-Higgs boson, and find that it leads to an extended $\phi(r)$, a significantly reduced and natural composite scale of $M_0 \sim 6$ TeV, a successful prediction for the quartic coupling, $\lambda$, and fine tuning that is reduced to a few percent, providing a compelling candidate solution to the naturalness problem of the BEH boson. The theory is testable and new physics should begin to emerge on the multi-TeV mass scales and possibly accessible to the LHC.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2022

Airborne hyperspectral imaging of cover crops through radiative transfer process-guided machine learning

Cover cropping between cash crop growing seasons is a multifunctional conservation practice. Timely and accurate monitoring of cover crop traits, notably aboveground biomass and nutrient content, is beneficial to agricultural stakeholders to improve management and understand outcomes. Currently, there is a scarcity of spatially and temporally resolved information for assessing cover crop growth. Remote sensing has a high potential to fill this need, but conventional empirical regression operated with coarse-resolution multispectral data has large uncertainties. Therefore, this study utilized airborne hyperspectral imaging techniques and developed new process-guided machine learning approaches (PGML) for cover crop monitoring. Specifically, we deployed an airborne hyperspectral system covering visible to shortwave-infrared wavelengths (400–2400 nm) to acquire high spatial (0.5 m) and spectral (3–5 nm) resolution reflectance over 23 cover crop fields across Central Illinois in March and April of 2021. Airborne hyperspectral surface reflectance with high spectral and spatial resolution can be well matched with field data to quantify cover crop traits. Furthermore, the PGML models were pre-trained by synthetic data from soil-vegetation radiative transfer modeling (one million records), and then fine-tuned with field data of cover crop biomass and nutrient content. Results show that airborne hyperspectral data with PGML can achieve high accuracy to predict cover crop aboveground biomass (R 2 = 0.72, relative RMSE = 15.16%) and nitrogen content (R 2 = 0.69, relative RMSE = 16.59%) through leave-one-field-out cross-validation. Unlike the pure data-driven approach (e.g., partial least-squares regression), PGML incorporated radiative transfer knowledge and obtained higher predictive performance with fewer field data. Meanwhile, with field data for model fine-tuning, PGML predicted biomass more accurately than the inversion of radiative transfer models. Here we also found that the red edge has a high contribution in quantifying aboveground biomass and nitrogen content, followed by green and shortwave spectra. This study demonstrated the first attempt of utilizing hyperspectral remote sensing to accurately quantify cover crop traits. We highlight the strength of PGML in exploiting sensing data to quantify ecosystem variables to advance agroecosystem monitoring for sustainable agricultural management.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2025

A Preferences Corpus and Annotation Scheme for Human-Guided Alignment of Time-Series GPTs

The process of time-series forecasting such as predicting trajectories of silicon content in blast furnaces is a difficult task. Most time-series approaches today focus on scalar-type MSE loss optimization. This optimization approach, while widely common, could benefit from the use of human expert or process-level preferences. In this paper, we introduce a novel alignment and fine-tuning approach that involves learning from a corpus of preferred and dis-preferred time-series prediction trajectories. Our contributions include (1) a preference annotation pipeline for time-series forecasts, (2) the application of Score-based Preference Optimization (SPO) to train decoder-only transformers from preferences, and (3) results showing improvements in forecast quality. The approach is validated on both proprietary blast furnace data and the UCI Appliances Energy dataset. The proposed preference corpus and training strategy offer a new option for fine-tuning sequence models in industrial settings.

DPO↗
DOE OSTI2023

Towards an astronomical foundation model for stars with a transformer-based model

ABSTRACT Rapid strides are currently being made in the field of artificial intelligence using transformer-based models like Large Language Models (LLMs). The potential of these methods for creating a single, large, versatile model in astronomy has not yet been explored. In this work, we propose a framework for data-driven astronomy that uses the same core techniques and architecture as used by LLMs. Using a variety of observations and labels of stars as an example, we build a transformer-based model and train it in a self-supervised manner with cross-survey data sets to perform a variety of inference tasks. In particular, we demonstrate that a single model can perform both discriminative and generative tasks even if the model was not trained or fine-tuned to do any specific task. For example, on the discriminative task of deriving stellar parameters from Gaia XP spectra, we achieve an accuracy of 47 K in Teff, 0.11 dex in log g, and 0.07 dex in [M/H], outperforming an expert XGBoost model in the same setting. But the same model can also generate XP spectra from stellar parameters, inpaint unobserved spectral regions, extract empirical stellar loci, and even determine the interstellar extinction curve. Our framework demonstrates that building and training a single foundation model without fine-tuning using data and parameters from multiple surveys to predict unmeasured observations and parameters is well within reach. Such ‘Large Astronomy Models’ trained on large quantities of observational data will play a large role in the analysis of current and future large surveys.

Leung, Henry W. (ORCID:0000000200362752)↗