Search NASA⌕ Search

SEARCH · Search NASA

Results for “Traditional Machine Learning”

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 55 records · Page 3

Selective Information Extraction Strategies for Cancer Pathology Reports with Convolutional Neural Networks

To trust model predictions, it is important to ensure new data scored by the model comes from the same population used for model training. If the model is used to score new data different than the model’s training data, then predictions and model performance metrics cannot be trusted. Identifying and excluding these anomalous data points is an important task when using models in the real world. Traditional machine learning algorithms and classifiers don’t have the capability to abstain in this case. Here we propose a data-novelty detection algorithm for the Convolutional Neural Network classifier, yielding a rejection score for each new data point scored. It is a post-modeling procedure which examines the distribution of convolution filters to determine if the prediction should be trusted. We apply this algorithm to an information extraction model for a natural language text corpus. We evaluated the algorithm performance using a primary cancer site classification model applied to cancer pathology reports. Results demonstrate that the algorithm is an effective way to exclude cancer pathology reports from model scoring when they do not contain the expected information necessary to accurately classify the primary cancer type.

Yoon, Hong-Jun↗

Leveraging large language models to automate the identification of healthcare access barriers for veterans

Objective: To develop and evaluate an automated system for identifying healthcare barriers focusing on transportation issues in veterans’ clinical notes using large language models (LLMs) and to assess the impact of different prompting strategies on classification performance and explanation consistency. Methods: We developed a hybrid system combining pattern matching for templated notes with LLM analysis for free-text notes. Using 2000 manually annotated clinical notes, we compared four prompting strategies (dual-role short, dual-role long, analysis-first, analysis-only) across Mistral-7B and Llama-3.1 models. We evaluated classification performance using standard metrics and assessed explanation consistency through embedding similarity analysis. Results: The analysis-first strategy achieved superior performance, with Mistral-7B reaching an F1 score of 0.914, outperforming traditional machine learning approaches (GBM: 0.786, BERT: 0.811). LLMs demonstrated higher explanation consistency within models (mean cosine similarity 0.887–0.908) compared to cross-model similarities (0.767–0.872). Pattern matching successfully handled 6.7% of templated notes deterministically. Mistral-7B showed greater internal consistency but higher abstention rates compared to Llama-3.1. Conclusion: Requiring LLMs to analyze evidence before classification improves both accuracy and explanation consistency for identifying transportation barriers in clinical notes. This approach enables automated barrier detection at scale while providing clinically relevant explanations, supporting both population-level healthcare planning and individual patient care decisions.

Healthcare access barriers↗

A data-driven operational model for traffic at the Dallas Fort Worth International Airport

Airports are on the front line of significant innovations, allowing the movement of more people and goods faster, cheaper, and with greater convenience. As air travel continues to grow, airports will face challenges in responding to increasing passenger vehicle traffic, which leads to lower operational efficiency, poor air quality, and security concerns. This paper evaluates methods for traffic demand forecasting combined with traffic microsimulation, which will allow airport operations staff to accurately predict traffic and congestion. Using two years of detailed data describing individual vehicle arrivals and departures, aircraft movements, and weather at Dallas-Fort Worth (DFW) International Airport, we evaluate multiple prediction methods including the Auto Regressive Integrated Moving Average (ARIMA) family of models, traditional machine learning models, and DeepAR, a modern recurrent neural network (RNN). We find that these algorithms are able to capture the diurnal trends in the surface traffic, and all do very well when predicting the next 30 minutes of demand. Longer forecast horizons are moderately effective, demonstrating the challenge of this problem and highlighting promising techniques as well as potential areas for improvement. Traffic demand is not the only factor that contributes to terminal congestion, because temporary changes to the road network, such as a lane closure, can make benign traffic demand highly congested. Combining a demand forecast with a traffic microsimulation framework provides a complete picture of traffic and its consequences. The result is an operational intelligence platform for exploring policy changes, as well as infrastructure expansion and disruption scenarios. To demonstrate the value of this approach, we present results from a case study at DFW Airport assessing the impact of a policy change for vehicle routing in high demand scenarios. This framework can assist airports like DFW as they tackle daily operational challenges, as well as explore the integration of emerging technology and expansion of their services into long term plans.

97 MATHEMATICS AND COMPUTING↗

Anomaly analysis and visualization for dynamic networks through spatiotemporal graph segmentations

With recent technology advance in Internet of Things (IoT) that involves human, sensors, and mobile devices, networks are not only growing much larger but more complex and dynamic in nature. The spatiotemporal dynamics of networks are represented by both topological changes and temporal shifts of attribute information associated with network components. Understanding the pattern and trend of dynamic networks is increasingly important. While data mining approaches are generally useful in analyzing the statistical properties of networks, there has been recent trend to consider bringing human into the loop, and to examine how feedback from visualizations of large-scale dynamic networks can further improve data mining and machine learning. Traditional visualization methods based on animation and sequences of snapshot graphs are also limited by human cognitive capability. Here, we present a dynamic network analysis and visualization (DNAV) tool which explores the spatiotemporal dimensions of graph components. In particular, nodes and edges are augmented with spatiotemporal segmentation based on both topological and attribute dynamics (e.g., time and locations of connectivity). To further facilitate analysis of large dynamic networks, DNAV includes statistical dynamic overviews alongside graph views, as well as data filtering modules for scalable analysis. Using case studies on public datasets, we demonstrate the effectiveness of DNAV in understanding and analyzing anomalies in dynamic networks such as computer communication networks.

97 MATHEMATICS AND COMPUTING↗

Sentiment analysis of the United States public support of nuclear power on social media using large language models

This study utilized large language models (LLMs) to analyze public sentiment in the United States (US) regarding nuclear power on social media, focusing on X/Twitter, considering climate change challenges and advancements in nuclear power technology. Approximately, 1.26 million nuclear tweets from 2008–2023 were examined to fine-tune LLMs for sentiment classification. We found the crucial role of accurate data labeling for model performance, with potential implications for a 15% improvement, achieved through high-confidence labels. LLMs demonstrated better performance compared to traditional machine learning classifiers, with reduced susceptibility to overfitting and up to 96% classification accuracy. LLMs are used to segment the US public tweets into policy and energy-related categories, revealing that 68% are politically themed. Policy tweets tended to convey negative sentiment, often reflecting opposing political perspectives and focusing on nuclear deals and international relations. Energy-related tweets covered diverse topics with predominantly neutral to positive sentiment, indicating broad support for nuclear power in 48 out of 50 US states. The US public positive sentiments toward nuclear power stemmed from its high power density, reliability regardless of weather conditions, environmental benefits, application versatility, and recent innovations and advancements in both fission and fusion technologies. Negative sentiments primarily focused on waste management, high capital costs, and safety concerns. The neutral campaign highlighted global nuclear facts and advancements, with varying tones leaning towards positivity or negativity. An interesting neutral theme was the advocacy for the combined use of renewable and nuclear energy to attain net-zero goals.

Energy & Fuels↗

Particle hit clustering and identification using point set transformers in liquid argon time projection chambers

Liquid argon time projection chambers are often used in neutrino physics and dark-matter searches because of their high spatial resolution. The images generated by these detectors are extremely sparse, as the energy values detected by most of the detector are equal to 0, meaning that despite their high resolution, most of the detector is unused in a particular interaction. Instead of representing all of the empty detections, the interaction is usually stored as a sparse matrix, a list of detection locations paired with their energy values. Traditional machine learning methods that have been applied to particle reconstruction such as convolutional neural networks (CNNs), however, cannot operate over data stored in this way and therefore must have the matrix fully instantiated as a dense matrix. Operating on dense matrices requires a lot of memory and computation time, in contrast to directly operating on the sparse matrix. We propose a machine learning model using a point set neural network that operates over a sparse matrix, greatly improving both processing speed and accuracy over methods that instantiate the dense matrix, as well as over other methods that operate over sparse matrices. Compared to competing state-of-the-art methods, our method improves classification performance by 14%, segmentation performance by more than 22%, while taking 80% less time and using 66% less memory. Compared to state-of-the-art CNN methods, our method improves classification performance by more than 86%, segmentation performance by more than 71%, while reducing runtime by 91% and reducing memory usage by 61%.

calibration and fitting methods↗

Application of convolutional neural networks for stellar spectral classification

ABSTRACT Due to the ever-expanding volume of observed spectroscopic data from surveys such as SDSS and LAMOST, it has become important to apply artificial intelligence (AI) techniques for analysing stellar spectra to solve spectral classification and regression problems like the determination of stellar atmospheric parameters Teff, $\rm {\log g}$, and [Fe/H]. We propose an automated approach for the classification of stellar spectra in the optical region using convolutional neural networks (CNNs). Traditional machine learning (ML) methods with ‘shallow’ architecture (usually up to two hidden layers) have been trained for these purposes in the past. However, deep learning methods with a larger number of hidden layers allow the use of finer details in the spectrum which results in improved accuracy and better generalization. Studying finer spectral signatures also enables us to determine accurate differential stellar parameters and find rare objects. We examine various machine and deep learning algorithms like artificial neural networks, Random Forest, and CNN to classify stellar spectra using the Jacoby Atlas, ELODIE, and MILES spectral libraries as training samples. We test the performance of the trained networks on the Indo-U.S. Library of Coudé Feed Stellar Spectra (CFLIB). We show that using CNNs, we are able to lower the error up to 1.23 spectral subclasses as compared to that of two subclasses achieved in the past studies with ML approach. We further apply the trained model to classify stellar spectra retrieved from the SDSS data base with SNR > 20.

Sharma, Kaushal↗

SIGHT: Stacked Integration of Geospatial Hierarchical Typologies for Inferring Building Characteristics

Building characteristics are often absent in building stock datasets, particularly in regions most vulnerable to climate change and requiring effective disaster management strategies. Traditional machine learning approaches, while widely used to predict building attributes, typically neglect the spatial context of the data, leading to less accurate and reliable outcomes. To address these challenges, this paper introduces a novel algorithm, the Stacked Integration of Geospatial Hierarchical Typologies. This algorithm adapts a meta-learning framework to incorporate geospatial context into the predictive modeling process. We demonstrate the utility of the algorithm through two primary use cases: building use type classification and building height prediction. The algorithm consistently achieved or exceeded a 0.94 macro average F1 score across five geographically distinct countries for building use type classification. For building height prediction, it accurately predicted heights with a root mean square error of 3.01 in a comprehensive study using roughly 3.6 million buildings in Japan. These results underscore the benefits of integrating spatial hierarchies into machine learning models, enhancing both predictive accuracy and reliability in geospatial modeling. This work introduces a new algorithm to address the pervasive data sparsity issue in existing building stock datasets.

Adams, Daniel [ORNL] (ORCID:0000000196950577)↗

A Comprehensive Informative Metric for Analyzing HPC System Status Using the LogSCAN Platform

Log processing by Spark and Cassandra-based ANalytics (LogSCAN) is a newly developed analytical platform that provides flexible and scalable data gathering, transformation and computation. One major challenge is to effectively summarize the status of a complex computer system, such as the Titan supercomputer at the Oak Ridge Leadership Computing Facility (OLCF). Although there is plenty of operational and maintenance information collected and stored in real time, which may yield insights about short- and long-term system status, it is difficult to present this information in a comprehensive form. In this work, we present system information entropy (SIE), a newly developed metric that leverages the powers of traditional machine learning techniques and information theory. By compressing the multivariant multi-dimensional event information recorded during the operation of the targeted system into a single time series of SIE, we demonstrate that the historical system status can be sensitively represented concisely and comprehensively. Given a sharp indicator as SIE, we argue that follow-up analytics based on SIE will reveal in-depth knowledge about system status using other sophisticated approaches, such as pattern recognition in the temporal domain or causality analysis incorporating extra independent metrics of the system.

Hui, Yawei↗

Optimal Proactive Vehicle Relocation for On-Demand Mobility Service with Deep Convolution-LSTM Network

This study develops an innovative model for inferring optimal proactive relocation strategy for empty vehicles of on-demand mobility service (OMS) directly from past observations of passenger demand. The output of our model is a row stochastic relocation matrix which gives the probability that an empty vehicle should be relocated from location i to location j at any given time. The matrix itself is high-dimensional and therefore challenging to obtain accurate estimation with traditional machine learning approach. Our model proposes the low-rank approximation of the relocation matrix, and introduces the deep convolution-LSTM network which extracts low-level spatial and temporal features from past demand observations for best restoration of the actual low rank approximation vector. The model is trained by deriving the optimal matching strategies from one year of real-world trip data. The results show that our model is able to predict the low-rank approximation of the relocation matrix with 4% of mean absolute error, may reduce the relocation cost by 20%-45% as compared to the real-world observations and is 50% optimal as compared to the global optimal matching with perfect information.

Lei, Zengxiang↗

Impedance-Aware Graph Convolutional Networks for Voltage Estimation in Active Distribution Networks

Voltage estimation plays a key role in ensuring the effective control and reliability of distribution networks. However, traditional machine learning methods often fail to capture the details of the distribution network’s topology. To overcome this challenge, graph convolutional networks (GCN) have emerged as an alternative. Graph convolutional networks inherently capture the topology of the grid, utilizing correlations to achieve precise voltage estimation. Other machine learning models and conventional GCNs fail to account for the distribution line characteristics found in the real world, limiting their effectiveness. This paper proposes an advanced variant of GCN called the Impedance-Aware Graph Convolutional Network (IA-GCN). The IA-GCN layer incorporates the magnitude of the impedance into the graph convolution mechanism, allowing it to capture topological nuances and provide valuable insights into node interrelationships by considering impedance as an intrinsic dimension. The performance of the IA-GCN layer is then compared with that of GCN and GraphSAGE layers through a surrogate model for voltage estimation. The performance analysis demonstrates that IA-GCN outperforms GCN by reducing the MAE by 87.55% and improving the R-squared value by 98%.

Ravi, Abhijith↗

Exploring Capability of Multimodal Foundation Model for Image-based Fault Detection of Photovoltaic Modules

Multimodal Foundation Model (MFM), like ChatGPT and Gemini, have emerged as powerful tools for their exceptional natural language processing capabilities and their emerging potential in image analysis. This paper investigates the application of MFMs for photovoltaic (PV) fault detection through image analysis, focusing on ChatGPT 4.0 and Gemini 1.5 Pro. Three types of PV images and the corresponding common PV faults are detected: bird droppings using visible images, cell cracks via electroluminescence (EL) images, and hotspots using infrared (IR) images. Among the two models, Gemini 1.5 Pro demonstrated superior performance, achieving near-perfect results with an average F1 score of 0.97, consistently outperforming ChatGPT 4.0 in accuracy and reliability. Unlike traditional machine learning (ML) models, MFMs can operate in a zero shot manner that does not require additional training by the user, and the input images are not limited by size, angle, scope, or PV technology. The strong adaptability and user-friendliness make MFM a promising tool for analyzing PV images and advancing health monitoring for PV modules.

Li, Baojie↗

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↗

Towards Architecture and OS-Independent Malware Detection via Memory Forensics

In this work, we take a fundamentally different approach to the problem of analyzing a device for compromises via malware; our approach is OS and instruction architecture independent and relies only on having the raw binary data extracted from the memory dump of a device. Our system leverages a multi-hundred TB dataset of both compromised host memory dumps extracted from the MalRec dataset [8] and the first known dataset of benign host memory dumps running normal, non-compromised software. After an average of 30 to 45 seconds of pre-processing on a single memory dump, our system leverages both traditional machine learning and deep learning algorithms to achieve an average of 98% accuracy of detecting a compromised host.

Petrik, Rachel L.↗

Codon2Vec v1.0

Background: Codon2Vec is an embedding neural network that predicts 'high' or 'low' gene expression directly from the protein-coding sequences. Embedding neural networks are commonly used for natural language processing (NLP) applications. Analogous to how an English sentence is a string of words, a gene can be thought of as a string of codons. Similar to how NLP neural networks model English sentences as a non-random sequence of words, we considered a coding sequence as a non-random non-overlapping array of codons (k-mers of length = 3). Value Proposition: - Codon2Vec achieved a high median AUC-ROC score of 83.8% when trained and applied to transcriptomic data from 300 fungal species - Unlike Codo2Vec, conventional methods predicting for expression based on codon usage rely on a priori knowledge of optimal codons or a set of reference genes. - Unlike Codon2vec, these methods do not account for the effect of codon order on gene expression. - Codon2Vec neural network bypasses the need for artisanal feature selection step that is necessary for traditional machine learning models.

Wint, Rhondene↗

Methods for Causal Discovery

SAND2025-11742O Methods for Causal Discovery is a software tool that is used for causal discovery from data, including predicting and visualizing directed acyclic graphs from data using traditional machine learning techniques. Sandia National Laboratories is a multimission laboratory managed and operated by National Technology & Engineering Solutions of Sandia, LLC, a wholly owned subsidiary of Honeywell International Inc., for the U.S. Department of Energy’s National Nuclear Security Administration under contract DE-NA0003525.

SciDAC↗

Defect Detection Model Development for Large Scale Thermoplastic Printing

Large-format additive manufacturing (LFAM) offers several advantages, including high throughput, cost-effective pellet-fed extrusion, and the capability to produce large-scale structures. The main pain points of LFAM include start and stops during the printing process, warpage, long layer times that lead to bead freezing, and bead separation due to shrinkage. These issues can lead to overfill, underfill and buildup of material in different sections of a print. This can lead to hidden defects embedded within the printed layers, or even ultimate failure of the printed structure. This ensures these defects can only be identified through nondestructive testing (NDT) inspection methods after printing, which can be timely and costly. Aligned Vision work specializes in 2D projectors with visual inspection systems and machine learning. Traditionally system is used for composite layup and layup inspections. In this work we used the LFAM system at Oak Ridge National Laboratory to create defect rich samples. The Aligned Vision inspection system then performed in-situ monitoring of the print process after each part was printed. This in-situ vision inspection system was used to develop a layer-by-layer inspection model that looks for overfill, underfill, and the buildup of defects using only a camera-based vision system. This leads to the assurance of high-quality production components.

36 MATERIALS SCIENCE↗

Satellite Embedding-Based Population Imputation for Areas with Missing Building Footprint Data: A Computer Vision-Based Approach

High-resolution population modeling is important for supporting effective decision-making across diverse sectors. LandScan Mosaic generates population estimates at the level of individual buildings and aggregates them to 3 arc-second grids, and this approach performs well in regions where building footprint data are comprehensive and reliable. However, large portions of the globe still suffer from incomplete, sparse, or entirely missing building stock datasets, creating a structural limitation for strictly building-based population models. To address this research gap, this study proposes a computer vision-based framework that employs Google Earth Engine satellite embeddings and UNet, which allows us to directly impute grid-level population estimates in building-data-deficient areas. Applied to Taiwan as a case study, the framework achieved strong predictive performance with R$^{2}$ of 0.89, RMSE of 18.70, and MAE of 8.41, outperforming traditional machine learning approaches. Notably, the proposed framework effectively addressed building false-positive errors inherent in Global Human Settlement Layer (GHSL) data, correctly identifying uninhabited areas that were erroneously classified as populated. The framework also offers significant advantages for global population mapping, particularly in terms of scalability and temporal consistency, thereby extending the coverage and accuracy of high-resolution population products in data-scarce regions worldwide. Urban planners, decision makers, and related stakeholders can obtain granular population distributions to support more accurate and targeted infrastructure investment, service delivery, resource allocation, and risk assessment decisions.

97 MATHEMATICS AND COMPUTING↗