Search NASA⌕ Search

SEARCH · Search NASA

Results for “supervised 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 19 records
All sourcesNASA NTRSDOE OSTI
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 aerial wildfire operations reports to better understand the risks present. Another use-case is the possibility of extracting airspace procedures and constraints currently written in documents such as Letters of Agreement. These applications can benefit from the use of state-of-the-art natural language processing techniques when adapted to the language/phraseology specific to the aviation domain. This paper evaluates the viability of adaptation of NLP tools to the aviation domain by fine-tuning transformer based models using aviation data sets. In 2018, a novel language model based on neural units (also called transformers) was created and became known as “Bidirectional Encoder Representations from Transformers” or BERT. This architecture combined with large amounts of English training data and innovative semi-supervised training tasks set the standard for what would later emerge as Large Language Models. The performance of these models was further improved by hyperparameter tuning and refinement of the semi-supervised training task and resulted in “Robustly Optimized BERT Pre-training Approach through hyperparameter tuning” or RoBERTa models. These pre-trained Large Language Models proved to be useful for a wide variety of natural language processing tasks such as text classification and question answering through a process called fine-tuning. The transformer architecture with pre-trained weights served as the basis with the last few layers replaced with layers fine-tuned to perform a new task e.g., a layer that provides a label for the entire input text. This process of fine-tuning can also be used to adapt the models to new domains; e.g., BioBERT started with the pre-trained BERT model and was completed by additional fine-tuning and training on biomedical documents. Transformer-based architectures can also be used to create rich representations of text called embeddings which can serve as the input to other machine learning models. This allows simpler algorithms such as logistic regression to use context-rich representations of the text while still remaining quick to train and evaluate. In the world of aviation, there is a growing demand for natural language processing and understanding but the domain presents unique challenges. Due to the technical content (and specialized language) of most aviation documents, fine-tuning pre-trained Large Language Models to specific tasks has not met the benchmark on natural language processing tasks set by simpler models trained from scratch on the data. To address this deficiency, this paper evaluates the improvements from fine-tuning a Large Language Model on a large set of aviation documents using the original semi-supervised training tasks before performing specific natural language tasks. In fine-tuning, a domain-specific dataset is used on the original training task but with the pre-trained Large Language Model instead of starting from a random initialization. This approach allows the model to be adapted to the specific domain language without discarding the information gained from training on general English data. This paper utilized two major dataset types to train and assess the RoBERTa fine-tuning performance. The first are 7,057 Letters of Agreement which are Federal Aviation Administration (FAA) documents that formalize airspace operations across the national airspace system. They contain many examples of ‘aviation English’ using domain specific terminology and phrasing which serves as a representative basis to perform the semi-supervised fine-tuning. The second type is the 494 document classification labels to be used for evaluation. This down-stream evaluation aims to show the performance of the fine-tuned model, better understand how much data is needed for an effective fine-tuning, and how fine-tuning can be adapted for different applications in-the domain. After semi-supervised training, evaluation begins by encoding the documents for classification using the fine-tuned RoBERTa model. Then a logistic regression classifier is trained to label the document type and compared against our ground truth labels. This currently leads to a 82.8% accuracy on 10-fold cross validation showing improvement over baseline RoBERTa which achieved 81.0%. We plan to measure the improvements on additional tasks and it is expected that these improvements will lead to more robust models that can tackle the natural language processing challenges present in aviation datasets.

ATM↗
DOE OSTI2025

FM4NPP: A Scaling Foundation Model for Nuclear and Particle Physics

Large language models have revolutionized artificial intelligence by enabling large, generalizable models trained through self-supervision. This paradigm has inspired the development of scientific foundation models (FMs). However, applying this capability to experimental particle physics is challenging due to the sparse, spatially distributed nature of detector data, which differs dramatically from natural language. This work addresses if an FM for particle physics can scale and generalize across diverse tasks. We introduce a new dataset with more than 11 million particle collision events and a suite of downstream tasks and labeled data for evaluation. We propose a novel self-supervised training method for detector data and demonstrate its neural scalability with models that feature up to 188 million parameters. With frozen weights and task-specific adapters, this FM consistently outperforms baseline models across all downstream tasks. The performance also exhibits robust data-efficient adaptation. Further analysis reveals that the representations extracted by the FM are task-agnostic but can be specialized via a single linear mapping for different downstream tasks.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2024

Graph learning for particle accelerator operations

Particle accelerators play a crucial role in scientific research, enabling the study of fundamental physics and materials science, as well as having important medical applications. This study proposes a novel graph learning approach to classify operational beamline configurations as good or bad. By considering the relationships among beamline elements, we transform data from components into a heterogeneous graph. We propose to learn from historical, unlabeled data via our self-supervised training strategy along with fine-tuning on a smaller, labeled dataset. Additionally, we extract a low-dimensional representation from each configuration that can be visualized in two dimensions. Leveraging our ability for classification, we map out regions of the low-dimensional latent space characterized by good and bad configurations, which in turn can provide valuable feedback to operators. This research demonstrates a paradigm shift in how complex, many-dimensional data from beamlines can be analyzed and leveraged for accelerator operations.

43 PARTICLE ACCELERATORS↗
DOE OSTI2023

MetaBAT-LR v1.0.0

MetaBAT-LR is an extension to the metaBAT program, which adds functionalities to leverage various datasets (long-reads, Hi-C) to improve the completeness of metagenome binning while keeping contamination levels low. It trains a random forest model using the self-supervised training paradigm to predict linkage information among metagenome scaffolds, then uses this information to recruit unbinned scaffolds and merge incomplete bins that are from the same species.

Wang, Zhong↗
DOE OSTI2025

Exploring Data Set Bias and Decision Support with Predictive Uncertainty Through Bayesian Approximations and Convolutional Neural Networks

Individual seismic catalogs can contain multiscale observations from fault level to global scales and associated waveforms from discrete events reflect crustal structure across many different scales and locations. Seismic network aperture, geographic location, and observation distance may not provide informative guidance or intuition on how different catalogs will behave across models trained under different conditions. We rely on uncertainty to provide guardrails for when to trust model decisions, but understanding when our uncertainty is trustworthy is an open challenge. Here, in this work, we explore Bayesian approximation methods for assigning predictive uncertainty in seismic event classification problems. We find that computationally expensive Bayesian approximations do not outperform simple ensemble methods. We also find that when exploiting multiple seismic event catalogs, joint training with data from all the catalogs combined with Bayesian approximations and supervised training for classification can obscure bias and result in less robust uncertainty while also not providing substantial performance benefits compared to training individual models for each catalog.

58 GEOSCIENCES↗
NASA NTRS1994

Classification of asteroid spectra using a neural network

The 52-color asteroid survey (Bell et al., 1988) together with the 8-color asteroid survey (Zellner et al., 1985) provide a data set of asteroid spectra spanning 0.3-2.5 micrometers. An artificial neural network clusters these asteroid spectra based on their similarity to each other. We have also trained the neural network with a categorization learning output layer in a supervised mode to associate the established clusters with taxonomic classes. Results of our classification agree with Tholen's classification based on the 8-color data alone. When extending the spectral range using the 52-color survey data, we find that some modification of the Tholen classes is indicated to produce a cleaner, self-consistent set of taxonomic classes. After supervised training using our modified classes, the network correctly classifies both the training examples, and additional spectra into the correct class with an average of 90% accuracy. Our classification supports the separation of the K class from the S class, as suggested by Bell et al. (1987), based on the near-infrared spectrum. We define two end-member subclasses which seem to have compositional significance within the S class: the So class, which is olivine-rich and red, and the Sp class, which is pyroxene-rich and less red. The remaining S-class asteroids have intermediate compositions of both olivine and pyroxene and moderately red continua. The network clustering suggests some additional structure within the E-, M-, and P-class asteroids, even in the absence of albedo information, which is the only discriminant between these in the Tholen classification. New relationships are seen between the C class and related G, B, and F classes. However, in both cases, the number of spectra is too small to interpret or determine the significance of these separations.

Howell, E. S.↗
DOE OSTI2025

Self-Supervised and Interpretable Anomaly Detection Using Network Transformers

Machine learning and deep neural networks (DNNs) have been proposed as a tool to identify anomalies in computer network communications. However, due the obfuscated nature of off-the-shelf machine learning models, their output often does not provide enough information to isolate the source of the anomaly to take corrective measures. In this article, we introduce the network transformer (NeT), a DNN model for anomaly detection that incorporates the graph structure of the communication network in order to improve interpretability. Further, the presented approach has the following advantages: first, enhanced interpretability by incorporating the graph structure of computer networks; second, provides a hierarchical set of features that enables analysis at different levels of granularity; second, self-supervised training that does not require labeled data. The NeT model was evaluated on a set of anomalous scenarios executed in a real industrial control system. The presented approach successfully identified the anomalies, the devices affected, and the specific connections causing the anomalies, providing a data-driven hierarchical approach to analyze the behavior of a cyber network.

97 MATHEMATICS AND COMPUTING↗
NASA NTRS1983

LANDSAT-4 image data quality analysis

Seven heterogeneous areas within the entire Des Moines, Iowa test site were selected to define candidate spectral training classes using a clustering algorithm. In addition to the 91 cluster nonsupervised classes, three supervised training classes were defined. The original candidate training classes were reduced to 42 spectrally separable training classes. The minimum and average transformed divergence values for the 42 spectral classes and for the best subsets of Y TM spectral bands are shown in a table. The best spectral band for any combination of 1 through 7 bands is the first middle IR band. The next best band is the near IR, followed by the red band and than the thermal IR. The best combination of four bands includes one from each of the four regions of the spectrum (visible, near IR, middle IR, and thermal IR).

Anuta, P. E.↗
NASA NTRS1983

LANDSAT-4 image data quality analysis

Seven heterogeneous areas within the Des Moines, Iowa area test site were selected to define candidate spectral training classes using a clustering algorithm. In addition to the 91 cluster (nonsupervised) classes, three supervised training classes were defined and subsequently included in the training statistics file. The identity of all 94 candidate classes were determined using available reference data. Through analysis of the interclass separabilities, the original 94 candidate training classes were reduced to 42 spectrally separable final classes. The minimum average transformed divergence values for the 42 spectral classes and for the best subsets of TM spectral bands are shown in a table.

Anuta, P. E.↗
DOE OSTI2024

Spectral Data Fusion From Handheld Laser-Induced Breakdown Spectroscopy (LIBS) and X-ray Fluorescence (XRF) Analyzers for Improved Detection of Cerium in a Simulated Dispersal Accident

Here, this work implements a mid-level data fusion methodology on spectral data from handheld X-ray fluorescence and laser-induced breakdown spectroscopy analyzers to quantify plutonium surrogate (CeO 2 ) contamination in soil samples for the first time. Spectral data from each analyzer were used independently to train supervised machine learning regressions to predict Ce concentration. Fused features from both data sets were then used to train the same models, comparing prediction performance by evaluating model precision and sensitivity. Fusing principal component scores from the two sensors yielded an order of magnitude improvement in precision and sensitivity of predictions made with an artificial neural network, compared to predictions made by models trained on independent sensor data. As a result, a boosted ensemble trained on the fused spectral features yielded an ideal predictor with root-mean-squared error on the order of 10 –6 and calculated limit of detection order 10 –5 wt %.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
DOE OSTI2020

Event Definition for the Automated Detection of Nuclear Proliferation Activities

In FY2020, Savannah River National Laboratory (SRNL) in collaboration with the Discovery Analytics Center (DAC) at Virginia Polytechnic Institute and State University (VT) began developing a demonstration prototype system that uses multiple machine learning and data analytic methods on largescale open data sources to identify new, developing, or undeclared nuclear programs. One of the most challenging aspects of applying machine learning techniques to such a problem is the high likelihood of extremely sparse data from disparate sources. To overcome this challenge, the current work will use a strategic combination of supervised, semi-supervised, and unsupervised learning techniques to ingest and fuse data streams to make a forecast of nuclear activities in a targeted geospatial location. Identifying potential data sources and training supervised learning algorithms is dependent upon the development of a robust foundation of targeted event domains that fundamentally define the nuclear activities of interest. This report documents the definition of a hierarchical structure for both nuclear activity and event domains that will be used to guide the research team in development or use of existing semantic dictionaries that are instrumental to searching, parsing, and categorizing events for the forecasting system’s use.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2025

Implementation of stacked ensemble machine learning for the detection of surrogate plutonium contamination in soil via LIBS

Supervised machine learning methods have demonstrated increased utility for the quantification of lanthanide and actinide elements in atomic spectroscopy applications. This study implements laser-induced breakdown spectroscopy (LIBS) for the identification of plutonium surrogate material (CeO 2 ) in soil matrices by training supervised machine learning methods on the recorded spectral data. A bagged ensemble using Random Forest yields the highest sensitivity predictions with a detection limit of 0.015 wt.% CeO 2 . However, high precision in Ce content prediction required the use of a stacked ensemble regression, which provided the superlative Ce quantification model with an error of 0.107% and a detection limit of 0.022 wt.%. Furthermore, the high performance of the stacked ensemble demonstrates its potential to enhance the accuracy and sensitivity of nuclear contaminant detection using field-deployable spectroscopic analyzers in real-world scenarios.

47 OTHER INSTRUMENTATION↗
DOE OSTI2021

Train Like a (Var)Pro: Efficient Training of Neural Networks with Variable Projection

Deep neural networks (DNNs) have achieved state-of-the-art performance across a variety of traditional machine learning tasks, e.g., speech recognition, image classification, and segmentation. The ability of DNNs to efficiently approximate high-dimensional functions has also motivated their use in scientific applications, e.g., to solve partial differential equations and to generate surrogate models. In this paper, we consider the supervised training of DNNs, which arises in many of the above applications. We focus on the central problem of optimizing the weights of the given DNN such that it accurately approximates the relation between observed input and target data. Devising effective solvers for this optimization problem is notoriously challenging due to the large number of weights, nonconvexity, data sparsity, and nontrivial choice of hyperparameters. To solve the optimization problem more efficiently, we propose the use of variable projection (VarPro), a method originally designed for separable nonlinear least-squares problems. Our main contribution is the Gauss--Newton VarPro method (GNvpro) that extends the reach of the VarPro idea to nonquadratic objective functions, most notably cross-entropy loss functions arising in classification. These extensions make GNvpro applicable to all training problems that involve a DNN whose last layer is an affine mapping, which is common in many state-of-the-art architectures. In our four numerical experiments from surrogate modeling, segmentation, and classification, GNvpro solves the optimization problem more efficiently than commonly used stochastic gradient descent (SGD) schemes. Finally, GNvpro finds solutions that generalize well, and in all but one example better than well-tuned SGD methods, to unseen data points.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2025

Explainable Machine Learning for Functional Data

Black-box machine learning models are recognized as useful tools for prediction applications, but the algorithmic complexity of some models causes interpretation challenges. Explainability methods have been proposed to provide insight into these models, but there is little research focused on supervised modeling with functional data inputs. We argue that, especially in applications of high consequence, it is important to explicitly model the functional dependence in a black-box analysis to not obscure or misrepresent patterns in explanations. As such, we propose the V ariable importance E xplainable E lastic S hape A nalysis (VEESA) pipeline for training supervised machine learning models with functional inputs. The pipeline is an analysis process that includes the data preprocessing, modeling, and post-hoc explanations. The preprocessing is done using elastic functional principal components analysis, which accounts for vertical and horizontal variability in functional data and, ultimately, allows for explanations in the original data space that identify the important functional variability without bias due to correlated variables. Here, we demonstrate the pipeline on two high-consequence applications: explosives classification for national security and inkjet printer identification in forensic science. The applications exhibit the VEESA pipeline’s ability to provide an understanding of the characteristics of the functional data useful for prediction. Code for implementing the pipeline is available in the veesa R package (and supplemental python code).

Elastic Shape Analysis↗
NASA NTRSDate not supplied

Developing Natural Language Processing and Supervised Learning Techniques to Classify Mars Tasks

As NASA's Human Research Program (HRP) prepares for long-duration Mars missions, understanding astronaut tasks is crucial. This study, conducted at NASA Glenn Research Center (GRC), employed Natural Language Processing (NLP) and machine learning techniques to analyze and classify Mars tasks. A list of 1,058 Mars tasks was provided by HRP experts including binary labeling of 18 Human System Task Categories (HSTCs). We developed an NLP model using Google's BERT language model to capture the semantic and syntactic nuances of these tasks. Supervised training was initially applied to a subset of the NLP-analyzed tasks to assess the model's effectiveness in classifying the remaining tasks. Incorporating HSTC descriptions significantly enhanced the classification accuracy for 9 out of the 18 HSTCs and reduced training time. To address the issue of severe class imbalance in the HSTC data, we introduced innovative weighting and sampling techniques for data augmentation. We then fine-tune BERT to implement a pairwise relatedness scoring method, allowing us to cluster tasks based on their relatedness and similarity, getting a step closer to labeling the tasks without supervision. In this presentation we guide you through data preprocessing, deciphering key syntax components using BERT, and performing supervised classification of the Mars tasks. This work showcases the potential use of advanced NLP techniques to analyze Mars missions to be incorporated into various crew health and performance analyses.

GenAI↗
NASA NTRSDate not supplied

Improving Sim-to-Real Transfer in Vision-Based Robot Navigation Via Instance-Level GAN-Based Data Augmentation

Achieving robust vision-based robotic tasks requires large amounts of data, which are often difficult to obtain in real-world scenarios. Simulators and synthetic data offer a cost-effective alternative, but the visual gap between simulation and reality hinders the performance of models when deployed in real-world environments. In this paper, we present a data augmentation pipeline that integrates a foundation model (Segment Anything Model) with an unsupervised image-to-image translation model (CycleGAN) for instance-level domain transfer from simulation to reality. This pipeline enables the generation of realistic labeled data from synthetic images for training supervised machine learning models in vision-based navigation tasks. We evaluate our approach on real-world data for ego-vehicle pose estimation, a critical autonomous navigation task involving the prediction of cross-track position and heading angle relative to road center line markings. The results of our tests show that our GAN-based data augmentation pipeline significantly outperforms models trained solely on simulation data or on data processed with standard image augmentation methods for sim-to-real transfer, enhancing model robustness and generalizability in real-world scenarios. Our method provides a scalable and flexible data augmentation tool for leveraging large synthetic datasets to enhance vision-based robotic navigation tasks.

artificial intelligence↗
DOE OSTI2025

Semi-supervised permutation invariant particle-level anomaly detection

The development of analysis methods to distinguish potential beyond the Standard Model phenomena in a model-agnostic way can significantly enhance the discovery reach in collider experiments. However, the typical machine learning (ML) algorithms employed for this task require fixed length and ordered inputs that break the natural permutation invariance in collision events. To address this, a semi-supervised anomaly detection tool is presented that takes a variable number of particle-level inputs and leverages a signal model to encode this information into a permutation invariant, event-level representation via supervised training with a Particle Flow Network (PFN). Data events are then encoded into this representation and given as input to an autoencoder for unsupervised ANomaly deTEction on particLe flOw latent sPacE (ANTELOPE), classifying anomalous events based on a low-level and permutation invariant input modeling. Performance of the ANTELOPE architecture is evaluated on simulated samples of hadronic processes in a high energy collider experiment, showing good capability to distinguish disparate models of new physics.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗