Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Pre-training”

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 145 records · Page 8
All sourcesNASA NTRSDOE OSTI
NASA NTRS2024

Enhancing Metal Additive Manufacturing Training with the Advanced Vision Language Model: A Pathway to Immersive Augmented Reality Training for Non-Experts

This paper introduces an innovative training system for the Renishaw AM400 metal printer, leveraging the synergy of the advanced Vision Language Model (VLM) with Augmented Reality (AR) within the Digital Twins (DT) framework. Aimed at overcoming the limitations of conventional training methods in metal additive manufacturing (AM), our system integrates AR to provide an immersive learning environment, enhancing the real-world experience with interactive digital overlays. The core of the system lies in its use of VLM, which, pre-trained on diverse datasets, excels in processing multi-modal data, thereby offering nuanced and contextually relevant guidance for trainees. Key experiments demonstrate the system’s effectiveness, particularly highlighting the usage of VLM as an Artificial Intelligence (AI) agent to integrate external tools like YOLO-v7 for valve state classification and CRAFT for control panel text recognition. This approach significantly improves recognition accuracy, operational understanding, and human–machine interaction, especially for non-expert users, making complex metal AM operations more accessible. The research not only showcases the potential of AR and VLM in industrial training but also sets a new standard for smart manufacturing practices, indicating broader applications in various industrial domains.

Metal additive manufacturing↗
NASA NTRSDate not supplied

Towards an Aviation Large Language Model by Fine-tuning and Evaluating Transformers

In the aviation domain, there are many applications for machine learning and artificial intelligence tools that utilize natural language. For example, there is a desire to know the commonalities in written safety reports such as voluntary post incidents reports or create more accurate transcripts of air traffic management conversations. Another use-case is the possibility of extracting airspace procedures and constraints currently written in documents such as Letters of Agreement (LOA) which is used as the evaluation case in this paper. These applications can benefit from the use of state-of-the-art Natural Language Processing (NLP) techniques when adapted to the language/phraseology specific to the aviation domain. This paper evaluates the viability of transferring pre-trained large language models to the aviation domain by adapting transformer based models using aviation datasets. This paper utilized two datasets to adapt a ‘Robustly Optimized Bidirectional Encoder Representations from Transformers Approach’ (RoBERTa) model and two down-stream classification tasks to assess its performance. These datasets are all built upon Letters of Agreement which are Federal Aviation Administration (FAA) documents that formalize airspace operations across the national airspace system. The first two datasets are used for the adaptation of RoBERTa to the aviation domain and were of different sizes to assess the number of documents needed to adapt to the aviation domain. They contain many examples of ‘aviation English’ using domain specific terminology and phrasing which serves as a representative basis to perform the unsupervised adaptation. The second dataset is a separate set of LOA documents with two sets of classification labels to be used for evaluation; one at the document level and one at the line level. These down-stream evaluations allowed the measurement of improvement by adapting RoBERTa. The accuracy increased by 4-6% on both tasks and the F1 score on the class of interest increased by 4-8% from the adaptation.

Air Traffic Management↗
NASA NTRS2024

AI Foundation Model for Heliophysics: Applications, Design, and Implementation

Deep learning-based methods have been widely researched in the areas of language and vision, demonstrating their capacity to understand long sequences of data and their usefulness in numerous helio-physics applications. Foundation models (FMs), which are pre-trained on a large-scale datasets, form the basis fora variety of downstream tasks. These models, especially those based on trans-formers in vision and language, show exceptional potential for adapting to a wide range of downstream applications. In this paper, we provide our perspective on the criteria for designing a FM for heliophysic and associated challenges and applications using the Solar Dynamics Observatory (SDO) dataset. We believe that this is the first study to design a foundation model in the domain of heliophysics.

Sujit Roy↗
NASA NTRSDate not supplied

Fast Machine Learning Lidar Surrogate Simulator: Pristine Clear Sky

The simulations of lidar signals and retrievals rely on a range of optic-physical models, such as radiative transfer models, particle scattering and absorption models, along with the output data from atmospheric physical models. Integrating these different models to represent signals of a lidar system is computationally expensive, and performing backward retrievals can be complex and ambiguous. However, with the advantages of Machine Learning, there is a new potential for building effective lidar signal database linked to corresponding atmospheric profiles. For this project, we are developing a fast pre-trained neural network as the lidar surrogate simulator using simulated data for a CALIPSO-like lidar (355 nm, 532nm, and 1064nm), and a CO2 differential absorption lidar (DIAL) near 1571nm. Specifically, we utilize a long short-term memory (LSTM) model to map the relationships between atmospheric profiles (pressure, temperature, air density and CO2 mixing ratio) and lidar signals. This approach allows us to build machine learning based simulators that can reconstruct lidar signals at specific bands from MERRA reanalysis data, and perform retrievals of atmospheric profiles using lidar signals at various wavelengths. As a first step, the results show the potential of this method to establish a foundational model for sensor signals. This model offers the promise of enabling both accurate predictions and rapid retrievals, providing a more efficient approach to signal processing and analysis.

Shan Zeng↗
NASA NTRSDate not supplied

Improving Satellite-Based Hotspot Detection Through Deep Learning-Enabled Smoke Recognition

While geostationary satellites, such as the GOES-R series, provide wildland fire hotspot readings at a high temporal resolution, they are prone to false negative readings and decreased confidence. One cause of decreased hotspot confidence is cloud contamination. Smoke produced from wildfire is often misinterpreted as cloud contamination, resulting in inaccurate and unsure sensor readings. To this end, we built a deep learning image segmentation model to identify smoke and cloud in true color satellite images. The model is pre-trained using self-supervised learning on over 10,000 GOES-R images to learn the underlying structure of satellite imagery. Then, the model is fine-tuned on a set of 130 labeled documents using supervised learning. The resulting model performs multi-class image segmentation with 85% accuracy and runs in under a minute on a standard personal computer. When paired alongside hotspot data, the model’s outputs can help increase confidence in wildfire location by identifying cases of cloud contamination that are due to smoke. The resulting model can be deployed in a stand-alone application or bundled in an Open Data Integration for wildland fire management (ODIN) application.

Earth observation↗
NASA NTRSDate not supplied

Contextualizing Air Traffic Management Conversations using Natural Language Understanding

Efficient management of air traffic and mitigation of delays depend on extracting actionable information from unstructured data, such as dialogues from the Federal Aviation Administration’s (FAA’s) Air Traffic Control System Command Center (ATCSCC) telecons. This study presents a pipeline utilizing Natural Language Processing (NLP) methods for Intent Classification (IC) and Slot Filling (SF) to identify and extract Traffic Management Initiatives (TMIs) from aviation-specific dialogues. We leveraged DeBERTa, a pre-trained transformer model, and fine-tuned it to the nuances of the aviation domain. Despite challenges posed by annotation complexities, the IC model achieved promising results with a weighted average F1-score of 0.81. Our results are close to those of human annotators, which demonstrates the model’s strong alignment with human-level performance. The SF model also showed strong performance, achieving a weighted F1-score of 0.97, which demonstrates its effectiveness in accurately predicting key slots. Our analysis revealed limitations in handling less frequent intents and slot labels due to data sparsity, motivating future efforts to adopt joint IC-SF modeling and data augmentation strategies. This research highlights the potential of domain-specific NLP to streamline decision-making in the aviation industry and improve the management of TMIs.

Air Traffic Control Management↗
NASA NTRSDate not supplied

Enhancing Dataset Discovery and Usage Tracking in Earth Sciences: Integrating Knowledge Graphs and Large Language Models

NASA's Data Active Archive Centers (DAACs) have played a crucial role in supporting a wide range of applied research in Earth and Environmental sciences. To date, over 20,000 publications have been collected, citing more than 3,000 NASA Earth science datasets. We present an innovative approach that links datasets and collected publications through a knowledge graph (KG). This KG enables the tracking of dataset citations throughout the dataset's lifecycle, revealing patterns of dataset usage across various applied research areas. We fine-tuned the pre-trained NASA IMPACT INDUS-Base Retriever Large Language Model (LLM) using a set of labeled publication abstracts. Our results indicate that 87% of the publications were classified into one of twenty applied research areas, while the remaining 13% were categorized into non-applied research areas. The classified publications linked to datasets are used to discover datasets by users interested in specific applied research and by dataset providers to determine dataset usage for applications.

open-source↗
NASA NTRS2026

Incremental Learning for Passive Microwave Precipitation Retrievals using Advanced Technology Microwave Sounder

Spaceborne passive microwave (PMW) radiometry is central to global precipitation monitoring, yet retrieval uncertainties remain substantial, particularly for cross-track sounders whose variable footprints and channel configurations are optimized for atmospheric temperature and moisture profiling rather than precipitation. Consequently, existing operational products often exhibit angular-dependent biases, limited effective swath utilization, unrealistic rainfall probability distributions, and systematic misclassification of precipitation phase. These limitations are further compounded by the scarcity of globally accurate and representative precipitation observations, as training data from the Dual-frequency Precipitation Radar (DPR) and the Cloud Profiling Radar (CPR) are spatially sparse, lack uniform global coverage, and exhibit heterogeneous error characteristics across precipitation regimes. To address these challenges, this study presents a supervised retrieval algorithm that incrementally trains an ensemble of extreme gradient-boosted decision trees by augmenting base learners with pre-training on reanalysis data and post-training on coincident DPR and CPR observations matched with the Advanced Technology Microwave Sounder (ATMS). By transferring prior information from reanalysis to posterior constraints from radar observations and adopting a sequential detection–estimation strategy for precipitation phase and rate retrieval, the proposed approach yields retrievals across the full ATMS swath that are largely free from persistent deficiencies in current Global Precipitation Measurement (GPM) passive microwave operational products. In particular, the method resolves bimodal artifacts in rainfall retrievals and mitigates systematic high-latitude snowfall biases, including overestimation across the Arctic and underestimation across the Antarctic. Validation against independent Multi-Radar Multi-Sensor (MRMS) data over the Contiguous United States (CONUS) further demonstrates improved performance in precipitation phase detection and rate estimation relative to both reanalysis and current GPM PMW products.

Mahyar Garshasbi↗
DOE OSTI2024

Generating An Advanced Cross-section Library For HTGR Pebble Bed Depletion Calculations Using Reduced-Order Model Generation Techniques

For code development, Advanced Reactor Technologies - Gas Cooled Reactors Program (ART-GCR) rely on a collaboration with the Nuclear Energy Advanced Modeling and Simulation (NEAMS) program, but the cross sections generation and the methodology definition is part of this program area goals. Based on previous studies in FY23, the size of microscopic cross section libraries increases rapidly with the number of tabulations, requiring significant amount of memory and drastically slowing down the Griffin calculations when evaluating cross sections via the multivariate linear interpolation approach. Rising to these challenges, this work investigates constructing Reduced-order Models (ROMs) for the multi-group microscopic cross sections to accelerate the cross section evaluation in Griffin. A database of multigroup cross sections is first collected considering all possible parameters that a designer could change for optimization. Down-selection of the ROM techniques afterward shows Deep Neural Network (DNN) as the best candidate when jointly consider memory efficiency, predictive accuracy, computational cost, scalability, flexibility and ease of implementation of the algorithms in comparison to the multidimensional interpolation. This work develops a specific interface that enables the cross section predictions using pre-trained DNN models into Griffin leveraging the existing ROM capabilities. DNNs have been trained for all isotopes for use in Griffin. Preliminary Griffin testing shows that DNNs exhibit exceptional predictive accuracy and the use of DNNs provides orders of magnitude improvement in memory efficiency compared to conventional interpolation techniques. With such ROM techniques, it holds great promise to further increase the fidelity of the Pebble Bed Reactor (PBR) simulation by increasing the number of tabulations/state variables during cross section evaluation, while maintaining the computational cost affordable in Griffin.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗
DOE OSTI2024

Evaluating the Use of Foundational Chemical Language Models in Multimodal Graph Fusion

Rapid and accurate prediction of the physicochemical properties of molecules given their structures remains a key challenge in cheminformatics. Machine learning approaches offer high-throughput options, but the optimality of inductive biases and data representations are up for debate. For example, BERT-based masked language models (MLMs) can be trained in a self-supervised way on hundreds of millions to billions of readily available SMILES strings. Another option is graph neural networks (GNNs), which can operate directly on molecular structures. Yet, generating accurate molecular geometry is computationally expensive, leading to a relative scarcity in data compared to SMILES strings. It is attractive to combine these two paradigms by pre-training an LM on a large corpus of SMILES strings and embedding these representation into a geometric graph neural network. Despite the promise of such an approach, and contrary to previous studies, we find mixed results with the combination of the LMs and GNNs on several molecule datasets. In particular, we found evidence for improvement on the FreeSolv and QM7 benchmarks, but degraded performance on the ESOL, LIPO and QM9 datasets compared to a GNN baseline.

Francel, Collin [University of Alabama]↗
DOE OSTI2024

VLM4Bio: A Benchmark Dataset to Evaluate Pretrained Vision-Language Models for Trait Discovery from Biological Images

Images are increasingly becoming the currency for documenting biodiversity on the planet, providing novel opportunities for accelerating scientific discoveries in the field of organismal biology, especially with the advent of large vision-language models (VLMs). We ask if pre-trained VLMs can aid scientists in answering a range of biologically relevant questions without any additional fine-tuning. In this paper, we evaluate the effectiveness of 12 state-of-the-art (SOTA) VLMs in the field of organismal biology using a novel dataset, VLM4Bio, consisting of 469K question8 answer pairs involving 30K images from three groups of organisms: fishes, birds, and butterflies, covering five biologically relevant tasks. We also explore the effects of applying prompting techniques and tests for reasoning hallucination on the performance of VLMs, shedding new light on the capabilities of current SOTA VLMs in answering biologically relevant questions using images

Maruf, M [Virginia Tech, Blacksburg]↗
DOE OSTI2025

GeoLoRA: Geometric integration for parameter efficient fine-tuning

Low-Rank Adaptation (LoRA) has become a widely used method for parameter-efficient fine-tuning of large-scale, pre-trained neural networks. However, LoRA and its extensions face several challenges, including the need for rank adaptivity, robustness, and computational efficiency during the fine-tuning process. We introduce GeoLoRA, a novel approach that addresses these limitations by leveraging dynamical low-rank approximation theory. GeoLoRA requires only a single backpropagation pass over the small-rank adapters, significantly reducing computational cost as compared to similar dynamical low-rank training methods and making it faster than popular baselines such as AdaLoRA. This allows GeoLoRA to efficiently adapt the allocated parameter budget across the model, achieving smaller low-rank adapters compared to heuristic methods like AdaLoRA and LoRA, while maintaining critical convergence, descent, and error-bound theoretical guarantees. The resulting method is not only more efficient but also more robust to varying hyperparameter settings. We demonstrate the effectiveness of GeoLoRA on several state-of-the-art benchmarks, showing that it outperforms existing methods in both accuracy and computational efficiency.

Schotthoefer, Steffen [ORNL] (ORCID:00000002156965↗
DOE OSTI2026

Artificial Intelligence for Event Reconstruction and Higgs Physics at CMS and Future Colliders

This dissertation charts a trajectory in which advances in artificial intelligence (AI) play a central role in pushing the high-energy physics frontier, complementing progress driven by higher collision energies and larger colliders. The discovery potential of the LHC and future colliders relies on accurate reconstruction of increasingly complex particle collision events. In the CMS experiment, this task is performed by the particle-flow (PF) algorithm. This dissertation presents the first implementation of a machine-learning-based particle-flow (MLPF) reconstruction in the CMS detector based on transformer architectures. In simulated top quark--antiquark pair (ttbar) events under LHC Run~3 (2023--2024) conditions, MLPF improves jet energy resolution by 10--20\% compared to standard PF for jets with transverse momentum between 30--100\GeV. Runtime performance is evaluated using simulated multijet events, with a median inference time of 20\unit{ms} per event on an NVIDIA L4 GPU, compa red to approximately 110\unit{ms} for standard PF. The MLPF algorithm is also validated on Run~3 collision data, representing the first data-validated ML-based reconstruction pipeline at any LHC experiment. We then extend MLPF toward future electron--positron colliders and introduce the first full-simulation cross-detector transfer learning workflow for PF reconstruction. The model is pre-trained on simulated events from the Compact Linear Collider detector (CLICdet) and fine-tuned on the CLIC-like detector (CLD) proposed for the Future Circular Collider (FCC). This approach achieves up to a 40\% improvement in jet energy resolution over rule-based reconstruction while reducing the required training dataset size by an order of magnitude, demonstrating the potential of AI to accelerate detector development and optimization. This dissertation also demonstrates how modern AI techniques enhance the sensitivity of LHC physics analyses. A CMS search for highly Lorentz-boosted Higgs bosons decaying to \textrm{W} boson pairs is presented, focusing on the single-lepton final state. A dedicated fine-tuning strategy for \ParT yields an approximately 70\% increase in expected sensitivity relative to the baseline model. The analysis uses proton--proton collision data at a center-of-mass energy of \ensuremath{\sqrt{s}=13\TeV} collected by CMS between 2016 and 2018, corresponding to an integrated luminosity of 138\ensuremath{\ \mathrm{fb}^{-1}}. The expected significance of the search is $1.86\sigma$, with an observed signal strength of $-0.19^{+0.48}_{-0.46}$. Finally, explainable AI techniques are applied to the MLPF and \ParticleNet algorithms using layerwise relevance propagation, showing that both models base their predictions on physically meaningful features consistent with our physics intuition. Together, these results demonstrate how advanced AI methods can enhance reconstruction, analysis sensitivity, and interpretability, shaping the next era of experimental parti cle physics.

Mokhtar, Farouk [UC, San Diego]↗
DOE OSTI2025

A geometric framework for momentum-based optimizers for low-rank training

Low-rank pre-training and fine-tuning have recently emerged as promising techniques for reducing the computational and storage costs of large neural networks. Training low-rank parameterizations typically relies on conventional optimizers such as heavy ball momentum methods or Adam. In this work, we identify and analyze potential difficulties that these training methods encounter when used to train low-rank parameterizations of weights. In particular, we show that classical momentum methods can struggle to converge to a local optimum due to the geometry of the underlying optimization landscape. To address this, we introduce novel training strategies derived from dynamical low-rank approximation, which explicitly account for the underlying geometric structure. Our approach leverages and combines tools from dynamical low-rank approximation and momentum-based optimization to design optimizers that respect the intrinsic geometry of the parameter space. We validate our methods through numerical experiments, demonstrating faster convergence, and stronger validation metrics at given parameter budgets.

Schotthoefer, Steffen [ORNL] (ORCID:00000002156965↗
DOE OSTI2025

Automated Waterbox Inspection for Nuclear Power Plants Using Computer Vision - Based Change Detection

Nuclear power plant waterboxes require regular inspection for leaks, missing components, and structural damage during maintenance outages. Traditional manual inspection is time-consuming and poses safety risks from confined space entry. We developed an automated computer vision system for drone-based waterbox inspection in partnership with Florida Light and Power. Our approach uses feature detection and matching to identify critical changes between baseline and current inspection images, automatically flagging additions (leaks/debris), removals (missing plugs), and translations (displaced components) while compensating for drone movement and environmental variations. We systematically evaluated six feature matching methods, from classical approaches (SIFT+BF) to state-of-the-art neural networks (SuperPoint+SuperGlue), using both standard benchmarks (HPatches) and waterbox-specific validation with real-world augmentations. SuperPoint+SuperGlue achieved superior performance with 7.82 pixels RMSE and 100% success rate—2.8x better accuracy than our baseline. While the pre-trained model has commercial licensing restrictions for nuclear deployment, our findings validate this architecture for custom training. We implemented a real-time GUI demonstrating the SIFT+BF approach for immediate deployment, processing drone feeds at 30 FPS with color-coded change visualization. Future work includes training a custom SuperPoint+SuperGlue model on waterbox data and integrating Vision-Language Models for automated reporting and maintenance guidance.

46 - INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AN↗
DOE OSTI2026

Neural Scaling Laws for Jet Generation

Recently observed empirical scaling laws describe the performance of foundation-type models as three independent key quantities -- dataset size, compute, and model parameters -- are modified. Extracting these scaling laws informs the training of large complex models for which the tuning of hyperparameters in traditional ways is not feasible. This work for the first time explores if scaling laws can also be observed for the task of particle jet generation -- both relevant as a pre-training objective for foundation models and as in-situ simulation by itself. We indeed replicate the key logarithmic scaling law behavior for model-size scaling. Beyond studying the next token prediction validation loss of the generative model, we also study the sliced Wasserstein distance of five physical quantities that are not immediately available to the model during training. Our study shows that this quantity is monotonically related to the next token prediction validation loss, meaning that this loss is indeed a good proxy for the physics performance. For the scaling with dataset size and compute, we observe substantially weaker scaling behavior of both the loss and the sliced Wasserstein distance. We analyze this behavior by introducing the concept of a learnable window, and argue that autoregressive next token prediction on jet constituents exhibits comparatively rapid saturation relative to language-model studies. We discuss possible origins of this behavior, including the stochastic nature of QCD radiation and differences between generative and supervised learning tasks in collider physics.

Amram, Oz [Fermilab]↗
DOE OSTI2026

Self-supervised and multi-fidelity learning for extended predictive soil spectroscopy

Infrared spectroscopy is a cost-effective, non-destructive, and environmentally benign technology that is increasingly recognized as an important solution for meeting the global demand for soil data. While both near-infrared (NIR) and mid-infrared (MIR) diffuse reflectance spectroscopy enable rapid estimation of soil properties, they present a significant trade-off: NIR offers superior scalability and lower operational costs, whereas MIR provides higher analytical fidelity by capturing fundamental molecular vibrations. In this study, we propose a self-supervised, multi-fidelity learning framework designed to bridge this gap. Our approach leverages large-scale MIR spectral libraries to learn a compact, transferable latent representation, into which NIR spectra are subsequently aligned for downstream prediction. The workflow consists of pretraining a latent model on a large MIR library, adapting the representation using a smaller paired NIR–MIR dataset, and evaluating generalization on an independent external test set. Across a range of chemical and physical soil properties, we found that MIR-derived embeddings improved prediction accuracy relative to baseline models that used raw MIR inputs. Predictions derived from the spectrum conversion (NIR to MIR) task did not match the performance of the original MIR spectra but were similar or superior to predictive performance of NIR-only models, suggesting the unified spectral latent space can effectively leverage the larger and more diverse MIR dataset for prediction of soil properties not well represented in current NIR libraries.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2025

Extracting Material Property Measurements from Scientific Literature with Limited Annotations

Extracting material property data from scientific text is pivotal for advancing data-driven research in chemistry and materials science; however, the extensive annotation effort required to produce training data for named entity recognition (NER) models for this task often makes it a barrier to extracting specialized data sets. Here, in this work, we present a comparative study of the conventional, supervised NER methodology to alternative few-shot learning architectures and large language model (LLM)-based approaches that mitigate the need to label large training data sets. We find that the best-performing LLM (GPT-4o) not only excels in directly extracting relevant material properties based on limited examples but also enhances supervised learning through data augmentation. We supplement our findings with error and data quality assessments to provide a nuanced understanding of factors that impact property measurement extraction.

36 MATERIALS SCIENCE↗