Search NASA⌕ Search

SEARCH · Search NASA

Results for “classifier models”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 91 records · Page 5
All sourcesNASA NTRSDOE OSTI
DOE OSTI2023

Data-driven modeling of municipal water system responses to hydroclimate extremes

Sustainable western US municipal water system (MWS) management depends on quantifying the impacts of supply and demand dynamics on system infrastructure reliability and vulnerability. Systems modeling can replicate the interactions but extensive parameterization, high complexity, and long development cycles present barriers to widespread adoption. To address these challenges, we develop the Machine Learning Water Systems Model (ML-WSM) – a novel application of data-driven modeling for MWS management. We apply the ML-WSM framework to the Salt Lake City, Utah water system, where we benchmark prediction performance on the seasonal response of reservoir levels, groundwater withdrawal, and imported water requests to climate anomalies at a daily resolution against an existing systems model. The ML-WSM accurately predicts the seasonal dynamics of all components; especially during supply-limiting conditions (KGE > 0.88, PBias < ±3%). Extreme wet conditions challenged model skill but the ML-WSM communicated the appropriate seasonal trends and relationships to component thresholds (e.g., reservoir dead pool). The model correctly classified nearly all instances of vulnerability (83%) and peak severity (100%), encouraging its use as a guidance tool that complements systems models for evaluating the influences of climate on MWS performance.

29 ENERGY PLANNING, POLICY, AND ECONOMY↗
DOE OSTI2025

Applying Deep Learning for Wildfire Identification: Economical and Accessible Solutions Leveraging Small Datasets

Wildfires significantly impact human health, air quality, visibility, weather, and climate change and cause substantial economic losses. While state and county-operated air quality monitors provide critical insights during wildfires, they are not available in all regions. This highlights the need for affordable, accessible tools that allow the general public to assess air quality impacts. In this study, we apply machine learning with deep neural networks to diagnose air quality rapidly from sky images taken at the Pacific Northwest National Laboratory in Richland, WA, USA. Using a convolutional neural network (CNN) framework, we trained a deep learning model to classify air quality indices based on sky images. By leveraging transfer learning, our approach fine-tunes a pre-trained model on a small dataset of sky images, significantly reducing training time while maintaining high accuracy. Our results demonstrate the potential of deep learning to provide rapid air quality diagnostics during wildfire episodes, offering early warnings to the public and enabling timely mitigation strategies, particularly for vulnerable populations. Additionally, we show that lower respiratory infections pose the highest health risk during acute smoke exposures. Reactive oxygen species (ROS) from wildfire particles further exacerbate health risks by triggering inflammation and other adverse effects.

54 ENVIRONMENTAL SCIENCES↗
NASA NTRS1989

Markov reliability models for digital flight control systems

The reliability of digital flight control systems can often be accurately predicted using Markov chain models. The cost of numerical solution depends on a model's size and stiffness. Acyclic Markov models, a useful special case, are particularly amenable to efficient numerical solution. Even in the general case, instantaneous coverage approximation allows the reduction of some cyclic models to more readily solvable acyclic models. After considering the solution of single-phase models, the discussion is extended to phased-mission models. Phased-mission reliability models are classified based on the state restoration behavior that occurs between mission phases. As an economical approach for the solution of such models, the mean failure rate solution method is introduced. A numerical example is used to show the influence of fault-model parameters and interphase behavior on system unreliability.

Mcgough, John↗
DOE OSTI2022

TULIP: An RNA-seq-based Primary Tumor Type Prediction Tool Using Convolutional Neural Networks

Background: With cancer as one of the leading causes of death worldwide, accurate primary tumor type prediction is critical in identifying genetic factors that can inhibit or slow tumor progression. There have been efforts to categorize primary tumor types with gene expression data using machine learning, and more recently with deep learning, in the last several years. Methods In this paper, we developed four 1-dimensional (1D) Convolutional Neural Network (CNN) models to classify RNA-seq count data as one of 17 highly represented primary tumor types or 32 primary tumor types regardless of imbalanced representation. Additionally, we adapted the models to take as input either all Ensembl genes (60,483) or protein coding genes only (19,758). Unlike previous work, we avoided selection bias by not filtering genes based on expression values. RNA-seq count data expressed as FPKM-UQ of 9,025 and 10,940 samples from The Cancer Genome Atlas (TCGA) were downloaded from the Genomic Data Commons (GDC) corresponding to 17 and 32 primary tumor types respectively for training and validating the models. Results: All 4 1D-CNN models had an overall accuracy of 94.7% to 97.6% on the test dataset. Further evaluation indicates that the models with protein coding genes only as features performed with better accuracy compared to the models with all Ensembl genes for both 17 and 32 primary tumor types. For all models, the accuracy by primary tumor type was above 80% for most primary tumor types. Conclusions: We packaged all 4 models as a Python-based deep learning classification tool called TULIP (TUmor CLassIfication Predictor) for performing quality control on primary tumor samples and characterizing cancer samples of unknown tumor type. Further optimization of the models is needed to improve the accuracy of certain primary tumor types.

Jones, Sara↗
DOE OSTI2022

SRF Cavity Fault Classification and Prediction at Jefferson Lab

Over the last few years several machine learning projects at Jefferson Lab have had a common focus to optimize operation of superconducting RF (SRF) cavities in the Continuous Electron Beam Accelerator Facility (CEBAF). In this talk we highlight work to identify and classify types of faults from C100-type cavities and then to extend those capabilities to provide real-time fault prediction. Early prediction may enable mitigation strategies to prevent some types of faults. In our approach we apply a two-step fault prediction pipeline. In the first step, a model distinguishes between faulty and normal signals. In the second step, signals flagged as faulty by the first model are classified into one of seven fault types based on learned signatures in the data. Initial results show that our model can successfully predict most fault types 200 ms before onset. In additional to model performance, we also highlight challenges in working with real-world data and challenges for deploying models.

Tennant, C.↗
DOE OSTI2020

Non-standard interactions in radiative neutrino mass models

Models of radiative Majorana neutrino masses require new scalars and/or fermions to induce lepton-number-violating interactions. We show that these new particles also generate observable neutrino non-standard interactions (NSI) with matter. We classify radiative models as type-I or II, with type-I models containing at least one Standard Model (SM) particle inside the loop diagram generating neutrino mass, and type-II models having no SM particle inside the loop. While type-II radiative models do not generate NSI at tree-level, popular models which fall under the type-I category are shown, somewhat surprisingly, to generate observable NSI at tree-level, while being consistent with direct and indirect constraints from colliders, electroweak precision data and charged-lepton flavor violation (cLFV). We survey such models where neutrino masses arise at one, two and three loops. In the prototypical Zee model which generates neutrino masses via one-loop diagrams involving charged scalars, we find that diagonal NSI can be as large as (8%, 3.8%, 9.3%) for (ε$_{ee}$, ε$_{μμ}$, ε$_{ττ}$), while off-diagonal NSI can be at most (10$^{–3}$%, 0.56%, 0.34%) for (ε$_{eμ}$, ε$_{eτ}$, ε$_{μτ}$). In one-loop neutrino mass models using leptoquarks (LQs), (ε$_{μμ}$, ε$_{ττ}$) can be as large as (21.6%, 51.7%), while ε$_{ee}$ and (ε$_{eμ}$, ε$_{eτ}$, ε$_{μτ}$) can at most be 0.6%. Other two- and three-loop LQ models are found to give NSI of similar strength. The most stringent constraints on the diagonal NSI are found to come from neutrino oscillation and scattering experiments, while the off-diagonal NSI are mostly constrained by low-energy processes, such as atomic parity violation and cLFV. We also comment on the future sensitivity of these radiative models in long-baseline neutrino experiments, such as DUNE. While our analysis is focused on radiative neutrino mass models, it essentially covers all NSI possibilities with heavy mediators.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2025

Scientific Open-Source Software Is Less Likely to Become Abandoned Than One Might Think! Lessons from Curating a Catalog of Maintained Scientific Software

Scientific software is essential to scientific innovation and in many ways it is distinct from other types of software. Abandoned (or unmaintained), buggy, and hard to use software, a perception often associated with scientific software can hinder scientific progress, yet, in contrast to other types of software, its longevity is poorly understood. Existing data curation efforts are fragmented by science domain and/or are small in scale and lack key attributes. We use large language models to classify public software repositories in World of Code into distinct scientific domains and layers of the software stack, curating a large and diverse collection of over 18,000 scientific software projects. Using this data, we estimate survival models to understand how the domain, infrastructural layer, and other attributes of scientific software affect its longevity. We further obtain a matched sample of non-scientific software repositories and investigate the differences. We find that infrastructural layers, downstream dependencies, mentions of publications, and participants from government are associated with a longer lifespan, while newer projects with participants from academia had shorter lifespan. Against common expectations, scientific projects have a longer lifetime than matched non-scientific open-source software projects. We expect our curated attribute-rich collection to support future research on scientific software and provide insights that may help extend longevity of both scientific and other projects.

Malviya Thakur, Addi [ORNL] (ORCID:000000022681999↗
DOE OSTI2024

Assessing the evolution of research topics in a biological field using plant science as an example

Scientific advances due to conceptual or technological innovations can be revealed by examining how research topics have evolved. But such topical evolution is difficult to uncover and quantify because of the large body of literature and the need for expert knowledge in a wide range of areas in a field. Using plant biology as an example, we used machine learning and language models to classify plant science citations into topics representing interconnected, evolving subfields. The changes in prevalence of topical records over the last 50 years reflect shifts in major research trends and recent radiation of new topics, as well as turnover of model species and vastly different plant science research trajectories among countries. Our approaches readily summarize the topical diversity and evolution of a scientific field with hundreds of thousands of relevant papers, and they can be applied broadly to other fields.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2023

Automated classification of big X-ray diffraction data using deep learning models

Abstract In current in situ X-ray diffraction (XRD) techniques, data generation surpasses human analytical capabilities, potentially leading to the loss of insights. Automated techniques require human intervention, and lack the performance and adaptability required for material exploration. Given the critical need for high-throughput automated XRD pattern analysis, we present a generalized deep learning model to classify a diverse set of materials’ crystal systems and space groups. In our approach, we generate training data with a holistic representation of patterns that emerge from varying experimental conditions and crystal properties. We also employ an expedited learning technique to refine our model’s expertise to experimental conditions. In addition, we optimize model architecture to elicit classification based on Bragg’s Law and use evaluation data to interpret our model’s decision-making. We evaluate our models using experimental data, materials unseen in training, and altered cubic crystals, where we observe state-of-the-art performance and even greater advances in space group classification.

Chemistry↗
DOE OSTI2023

Making Corgis Important for Honeycomb Classification: Adversarial Attacks on Concept-based Explainability Tools

Methods for model explainability have become increasingly critical for testing the fairness and soundness of deep learning. Concept-based interpretability techniques, which use a small set of human-interpretable concept exemplars in order to measure the influence of a concept on a model's internal representation of input, are an important thread in this line of research. In this work we show that these explainability methods can suffer the same vulnerability to adversarial attacks as the models they are meant to analyze. We demonstrate this phenomenon on two well-known concept-based interpretability methods: TCAV and faceted feature visualization. We show that by leveraging the geometry of the problem and carefully perturbing the examples of the concept that is being investigated, we can radically change the output of the interpretability method. The attacks that we propose can either induce positive interpretations (polka dots are an important concept for a model when classifying zebras) or negative interpretations (stripes are not an important factor in identifying images of a zebra). Our work highlights the fact that in safety-critical applications, there is need for security around not only the machine learning pipeline but also the model interpretation process.

Brown, Davis R.↗
NASA NTRS2025

Navigating Team Dynamics: Automated Detection of Micro-Behaviors Between Team Members Through Longitudinal Interaction Data

The success in future long term space exploration missions will depend on the cooperation, coordination, and mutual understanding among the crew members. Micro-behaviors are momentary, subtle linguistic and paralinguistic indicators of thinking and feeling toward another member of the team (Cortina et al., 2001; Smith & Griffiths, 2022) that can significantly impact team dynamics and influence the overall team performance (Paromita & Chaspari, 2024). Due to their interactive nature, micro-behaviors have a sender (i.e., the team member expressing the micro-behavior) and a target (the team member impacted by the micro-behavior). Detection of these behaviors can assist in avoiding possible conflict among crew members and promoting the overall team success. Our prior research focused on an initial proof of concept of machine learning (ML) models and natural language processing (NLP) techniques that were used for automatically detect micro-behaviors among crew members of the US National Aeronautics and Space Administration’s (NASA) Human Exploration Research Analog (HERA) Campaigns 4 and 5 missions (Paromita et al., 2023). Results underscored the importance of incorporating contextual information in the ML models in the form of sentiment analysis, type of task, and dyadic interaction among team members. Here, we expand the scope of our prior work in two ways. First, we assess ML/NLP methods on new behavioral annotations coded using an adapted version of Smith & Griffins (2022) theoretical framework in terms of Violation (i.e., presence of valenced behavior, uplifting/positive or discouraging/negative), Intensity (i.e., force of behavior in terms of how uplifting or discouraging is the behavior), and Intent (i.e., motive of the behavior in terms of whether it was deliberate or unintentional). Second, we expand the design of the ML model to preserve information about the role of each team member within the occurrence of the micro-behavior (in contrast to the previous model that only considered the sender and the target without determining the team member role). This allows to consider all team members' contributions in the conversation and model long-term dependencies in the dialogue. Our experiments for this study are conducted on data from 5 teams of the NASA HERA C4 (NASA grant NNX16AQ48G (PI: Bell)). Conversations were extracted from the 1.5 hour Team Interaction Battery (TIB) task that occurred 5 times in-mission per crew. This resulted in a total of 13,058 conversational turns (i.e., 17.8% uplifting, 3.3% discouraging, 75.76% neutral, 3.14% nulls). Our findings with the revised behavioral coding and ML/NLP models indicate a 43.66% macro F1-score (i.e., 38.29% precision (P), 50.8% recall (R)) for a dialog state-tracking model that includes information from the sender only, and a 40.9% F1-score (i.e., 38.7% P, 43.36% R) for the same model that includes information from both the sender and the target of the micro-behavior. These are significantly higher compared to simple random forest models that classify behaviors strictly based on speech content and do not consider iterative team dynamics, achieving a 36.07% F1-score (i.e., 39.04% R, 33.53% P). Our findings demonstrate potential ways to leverage large conversational datasets to better capture complex team dynamics. We will discuss future directions including proposed models that can incorporate additional mission days and tasks beyond the TIB for objectively quantifying team behavior at high temporal resolution in space exploration missions.

Projna Paromita↗
DOE OSTI2022

Monitoring Operational States of a Nuclear Reactor Using Seismoacoustic Signatures and Machine Learning

Monitoring nuclear reactors is an important safety and security task with growing requirements. We explore the possibility of using seismic and acoustic data for inferring the power level of an operating reactor. Continuous data recorded at a single seismoacoustic station that is located about 50 m away from a research reactor was visualized and analyzed. The data show a clear correlation between seismoacoustic features and reactor main operational states. We designed a workflow that includes two machine learning (ML) models to classify the reactor operational states (OFF, transition, and ON) and estimate reactor power levels (10%, 30%, 50%, 70%, and 90%). We applied and compared five ML algorithms for the reactor OFF-transition-ON and four approaches for the power level classification. We also compared the performance of ML models trained with seismic-only, acoustic-only, and both types of data. Five-fold cross validations were implemented to assure a thorough evaluation of the model performances. Additionally, the results show the extreme boosting gradient algorithm worked best for the first model, whereas random forests performed best for the second model. Combining seismic and acoustic data leads to better performance than using a single type of data. Seismic data contributed more than acoustic data for both models. We reached an accuracy of 0.98 for reactor OFF and ON. The accuracies for the transition state and power levels are less optimal with a minimum accuracy of 0.66. However, our results suggest seismic and acoustic data contain useful information about the transition state as well as power levels. Seismic and acoustic data could be integrated with other observations to improve monitoring performance.

21 SPECIFIC NUCLEAR REACTORS AND ASSOCIATED PLANTS↗
DOE OSTI2022

Expanded analysis of machine learning models for nuclear transient identification using TPOT

Industries around the world are becoming more and more data driven. The nuclear field is no exception with several different applications being proposed. One popular area of research is the use of machine learning in transient detection. This paper seeks to build upon a previous study which made use of the AutoML package TPOT to train traditional machine learning models to classify transient events occurring with a reactor. Synthetic data was once again collected using a GPWR reactor simulator. Data on 12 different events was collected using 15 different initial conditions. Here, a dataset consisting of over 100,000 data points was compiled and used to train 7 different machine learning models using a pre-defined TPOT dictionary with 12 different preprocessing techniques. Three of the trained models were able to produce validation results in the 90s with the expanded dataset. Once the models were trained, it was possible to look into where during the simulation, misclassifications occurred. Using these three models, analysis was done to determine if TPOT could be used to train models that were effective if important features were missing. The results from this were positive with the newly trained models scoring close to the original models. Finally, to conclude this study, the three high performing models were retrained using different random states to see if there was any major variation when different states were used.

42 ENGINEERING↗
NASA NTRS1993

Preliminary analysis of the JAPE ground vehicle test data with an artificial neural network classifier

Remotely sensing and classifying military vehicles in a battlefield environment have been the source of much research over the past 20 years. The ability to know where threat vehicles are located is an obvious advantage to military personnel. In the past active methods of ground vehicle detection such as radar have been used, but with the advancement of technology to locate these active sensors, passive sensors are preferred. Passive sensors detect acoustic emissions, seismic movement, electromagnetic radiation, etc., produced by the target and use this information to describe it. Deriving the mathematical models to classify vehicles in this manner has been, and is, quite complex and not always reliable. However, with the resurgence of artificial neural network (ANN) research in the past few years, developing models for this work may be a thing of the past. Preliminary results from an ANN analysis to the tank signatures recorded at the Joint Acoustic Propagation Experiment (JAPE) at the US Army White Sands Missile Range, NM, in July 1991, are presented.

Larsen, Nathan F.↗
DOE OSTI2020

Multimodal Data Representation with Deep Learning for Extracting Cancer Characteristics from Clinical Text

This paper presents a multimodal data representation to improve the performance of deep learning models for extracting cancer key characteristics from unstructured text in pathology reports. Specifically, in addition to using the text as the input to deep learning models, we use concept unique identifiers (CUIs) as another source of information to the models. We analyze the performance of different text and CUI data representations, including word embeddings and bag of embeddings (BOE), with a convolutional neural network (CNN) and a fully connected multilayer perceptron neural network (MLP-NN). The high level document embeddings from text and CUI inputs are combined by concatenating them and then applying a classifier. The model is used for extracting cancer subsite and histology from pathology reports. These two classification tasks have a large number of labels, i.e. 317 for subsite and 556 for histology, with extreme class imbalance. We compare the performance of the developed DL models across the two tasks based on micro- and macro-F1 scores. The evaluation shows that a multi-channel DL model that utilizes text represented by word embeddings and CUIs represented by BOE outperforms other DL models. Also, this approach significantly improves the model performance on low prevalence classes.

Alawad, Mohammed↗
DOE OSTI2021

Superconducting Radio-frequency Cavity Fault Classification Using Machine Learning at Jefferson Laboratory

We report on the development of machine learning models for classifying C100 superconducting radiofrequency (SRF) cavity faults in the Continuous Electron Beam Accelerator Facility (CEBAF) at Jefferson Lab. Of the 418 SRF cavities in CEBAF, 96 are designed with a digital low-level RF system configured such that a cavity fault triggers recordings of RF signals for each of eight cavities in the cryomodule. Subject matter experts analyze the collected time-series data and identify which of the eight cavities faulted first and classify the type of fault. This information is used to find trends and strategically deploy mitigations to problematic cryomodules. However, manually labeling the data is laborious and time-consuming. By leveraging machine learning, near real-time - rather than postmortem - identification of the offending cavity and classification of the fault type has been implemented. We discuss the performance of the machine learning models during a recent physics run. We also discuss efforts for further insights into fault types through unsupervised learning techniques and present preliminary work on cavity and fault prediction using data collected prior to a failure event.

Tennant, C. D.↗
DOE OSTI2020

Machine Learning Based Cavity Fault Classification and Prediction

We report on the development of machine learning models for classifying C100 superconducting radio frequency (SRF) cavity faults in the Continuous Electron Beam Accelerator Facility (CEBAF) at Jefferson Lab. CEBAF is a continuous-wave recirculating linac utilizing 418 SRF cavities to accelerate electrons up to 12 GeV through 5-passes. Of these, 96 cavities (12 cryomodules) are designed with a digital low-level RF system configured such that a cavity fault triggers waveform recordings of 17 RF signals for each of the eight cavities in the cryomodule. Subject matter experts (SME) can analyze the collected time-series data, identify which of the eight cavities faulted first, and classify the type of fault. This information is used to find trends and strategically deploy mitigations to problematic cryomodules. However, manually labeling the data is laborious and time-consuming. By leveraging machine learning, near real-time – rather than post-mortem – identification of the offending cavity and classification of the fault type has been implemented. We discuss the performance of the ML models during a recent physics run.

43 PARTICLE ACCELERATORS↗
DOE OSTI2022

A deep learning approach to real-time HIV outbreak detection using genetic data

Pathogen genomic sequence data are increasingly made available for epidemiological monitoring. A main interest is to identify and assess the potential of infectious disease outbreaks. While popular methods to analyze sequence data often involve phylogenetic tree inference, they are vulnerable to errors from recombination and impose a high computational cost, making it difficult to obtain real-time results when the number of sequences is in or above the thousands. Here, we propose an alternative strategy to outbreak detection using genomic data based on deep learning methods developed for image classification. The key idea is to use a pairwise genetic distance matrix calculated from viral sequences as an image, and develop convolutional neutral network (CNN) models to classify areas of the images that show signatures of active outbreak, leading to identification of subsets of sequences taken from an active outbreak. We showed that our method is efficient in finding HIV-1 outbreaks with R0 ≥ 2.5, and overall a specificity exceeding 98% and sensitivity better than 92%. We validated our approach using data from HIV-1 CRF01 in Europe, containing both endemic sequences and a well-known dual outbreak in intravenous drug users. Our model accurately identified known outbreak sequences in the background of slower spreading HIV. Importantly, we detected both outbreaks early on, before they were over, implying that had this method been applied in real-time as data became available, one would have been able to intervene and possibly prevent the extent of these outbreaks. This approach is scalable to processing hundreds of thousands of sequences, making it useful for current and future real-time epidemiological investigations, including public health monitoring using large databases and especially for rapid outbreak identification.

59 BASIC BIOLOGICAL SCIENCES↗