Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “AuC”

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.

143 records · Page 8
All sourcesNASA NTRSDOE OSTI
NASA NTRSDate not supplied

Mapping Wetland and Riparian Areas to Support Rio Grande Cutthroat Trout Habitat Restoration

The Rio Grande cutthroat trout (Oncorhynchus clarki virginalis; RGCT) population has declined significantly over the last century due to habitat loss, competition, and hybridization with non-native trout species. The species currently occupies roughly 11% of its historic habitat. Conservation efforts led by government and private actors have succeeded in increasing RGCT populations since the early 2000s. State, federal, and private partners began the largest native trout restoration initiative in North America. Since 2002, these efforts have included wetland and riparian area restoration and RGCT reintroduction. Current restoration efforts focus on restoring the Costilla Creek Watershed located in Colorado and New Mexico to provide cool water temperatures, improve water quality, and maintain suitable habitat for the trout species. To guide these restoration efforts, the team conducted a rapid assessment to locate and characterize wetland and riparian areas in the Costilla Creek watershed. The team utilized NASA data from the Landsat 8 Operational Land Imager (OLI), as well as the Sentinel-2 MultiSpectral Instrument (MSI), and the Sentinel-1 Synthetic Aperture Radar (SAR) for May 2016 to October 2019. To produce probability maps of wetland presence, the team used the Software for Assisted Habitat Modeling (SAHM) incorporating predictor variables generated from topographic indices, spectral indices, and radar. The top three models (General Wetland model, Stream and Wetland Connectivity model, and Inclusive Wetland model) showed a strong ability to detect wetlands. They all had AUC values greater than 0.9 and had high overlap with wetland areas during visual assessment over high-resolution imagery. The General Wetland model output was converted into a wetland polygon dataset and polygons were classified by wetland type. The resulting maps and datasets will support partners in determining the extent of possible RGCT habitat and identifying where habitat restoration efforts may be needed.

NASA DEVELOP↗
NASA NTRSDate not supplied

Algorithmic Detection of Elemental Biosignatures

Machine learning models that classify a sample as indicative or non-indicative of life could play an important role in life-detection missions. Their predictions result from agnostic algorithms and thereby add redundancy to judgements resulting from human expertise. Additionally, their important features can reveal the most informative measurements within the operational constraints of a life-detection mission. The Ladder of Life Detection (Neveu 2018) identifies the need for an understanding of how combinations of multiple biosignatures affect overall confidence. The present work provides a starting point to answer this need, and future work will expand the data types to obtain even more predictive combinations of features. Elemental abundance was chosen as a starting set of features due to its availability in diverse sample types, which are needed to train a generalizable model. A standardized dataset was collected, including 35 non-indicative, e.g., lunar rock, basalt; 19 indicative mixed, e.g., seawater, agricultural soil; 46 indicative non-alive, e.g., coal, chalk; and 10 indicative alive, e.g., biofilm, bacteria. This dataset could be valuable for complementary biosignature research. The samples were standardized to the same limit of detection of a simulated mission scenario. Four classification models were used: k-nearest neighbors (KNN), logistic regression (LR), linear support vector machines (SVM), and Gaussian naïve Bayes (GNB). To obtain feature importances, KNN was run on three principal components of the training data and LR and SVM were run with L1 and L2 regularization. The performances and feature importances of the six model variants on 40:60 train to validation ratios were assessed with Monte Carlo simulations. ROC AUC and mean accuracy scores ranged between 82% - 94%, with sensitivity greater than specificity. For indicative of life predictors, all models had C and Ca as strong and Cl as medium; a majority of models had N, K, and P as medium. For non-indicative of life predictors, all models had Si as strong, and a majority of models had Mg, Al, and Ti as medium. Varied elements were Fe (slightly non-indicative), H (slightly indicative), O (widely varied), Na, Mn, and S. These results serve as a proof of concept and suggest important elemental signals beyond merely the CHNOPS of Earth-based life.

Algorithmic↗
NASA NTRS2021

A Machine Learning Approach to Objective Identification of Dust in Satellite Imagery

Airborne dust has broad adverse effects on human activity, including aviation, human health, and agriculture. Remote sensing observations are used to detect dust and aerosols in the atmosphere using long established techniques. False color Red-Green-Blue (RGB) imagery using band differences sensitive to dust absorption (Dust RGB) is currently used operationally to assist forecasters and decision-makers in identifying dust at night, but there are still limitations, subjectivity, and nuances to image interpretation making night-time dust identification difficult even for experts. This study applies machine learning to the problem of night-time dust detection with a simple random forest (RF) model using Geostationary Operational Environmental Satellite-16 (GOES-16) Advanced Baseline Imager (ABI) infrared imagery, band differences sensitive to dust absorption, and Dust RGB color components as inputs to the model. The RF model achieves an Area-Under-Curve (AUC) of 0.97 with a standard deviation of 0.04 for dust cases. For images with dust present, the model correctly labels 85% of dust pixels and 99.96% of no-dust pixels for all dust images in the validation data set. The addition of a single null case to the training data set drastically reduces error in labeling no-dust pixels as dust from 45% to 14.5%. Application of the machine learning model to the April 13–14, 2019 dust event demonstrates the ability of the model to identify dust during night-time hours when visual dust detection is limited by the cooling ground surface characteristics.

dust↗
NASA NTRSDate not supplied

Algorithmic Classification of Raman Spectra Biosignatures: Improving Life Detection Confidence

“Agnostic” biosignatures – indicators of life (or the absence of life), independent of a particular biochemistry – are increasingly considered a high standard for life detection. The Ladder of Life Detection (2018) called for investigating how combinations of independent and different potential biosignatures affect confidence. To address this gap, statistical classification of elemental abundances, isotopic fractionation, and reflectance spectroscopy (VNIR) has been implemented. Raman spectroscopy, highly desirable due to its wide availability, has the potential to improve this predictive power. This work implemented biosignature classification algorithms on Raman data alone, in preparation for combination with the other data types. Raman spectroscopy data was collected from published databases and papers as part of a manually curated dataset of “indicative” and “non-indicative of life” samples. These currently include 61 non-indicative samples (meteorites, magnetite); 3 indicative living samples (bacteria); 20 indicative non-living samples (chalk, bone); and 12 indicative mixed (with non-indicative material) samples (soil, microbial mats). Laboratory work is ongoing to characterize additional samples, particularly a greater breadth of mixed systems. Spectra were interpolated, filtered with the Savitzsky-Golay filter, and de-noised. For a preliminary examination, agnostic features were manually extracted including mean intensity, number of peaks, and mean peak width. Different peak prominences and filtering polynomials were used to refine features. Classification algorithms were implemented: k-nearest neighbors (KNN), logistic regression (LR), linear support vector machines (SVM), random forest (RF), Gaussian naïve bayes (GNB). Lastly, Monte Carlo simulations on 1,000 50%-train-test-splits were used to validate classification performance and feature significance. The preliminary feature set achieved its highest AUC of 0.52 with LR, with no strongly discriminatory features. Work to improve feature extraction, such as through deep learning with back propagation, is planned. In future work, the Raman data will be combined with the other data types, and potentially new data types such as enantiomeric excess. This project was partially supported through the NASA Ames Project EXcellence (APEX) incubator program.

Astrobiology↗
NASA NTRS2022

Western Montana Ecological Forecasting II: Enhancing Habitat Suitability Modeling of Mustelid Species and Contaminant Monitoring in Northern Montana Using NASA Earth Observations

Environmental contaminants in aquatic ecosystems threaten both human and ecosystem health. Western Montana’s rivers possess great economic and ecological value, yet the status of contaminants in these systems can be unclear. Contaminants such as brominated flame-retardants, heavy metals, and pharmaceuticals negatively affect ecosystem health by traveling through the food chain and bioaccumulating in apex predators. Exposure to these contaminants can result in neurological, endocrine, and reproductive impairments in wildlife and humans. American mink (Neovison vison) and North American river otter (Lontra canadensis) have a predominantly aquatic diet and serve as reliable indicator species of environmental health. Working Dogs for Conservation (WD4C) uses detection dogs to locate scat samples of these species which are assessed for contaminants by the Virginia Institute of Marine Science (VIMS). With Software for Assisted Habitat Modeling (SAHM), the team generated current (2013-2020) and projected (2021-2040) habitat suitability models for mink and otter utilizing NASA Earth observations from Terra Moderate Resolution Imaging Spectroradiometer (MODIS), Global Precipitation Measurement Integrated Multi-Satellite Retrievals for GPM (GPM IMERG), Shuttle Radar Topography Mission (SRTM), and Soil Moisture Active Passive (SMAP). The habitat suitability maps’ study region encompassed Flathead National Forest and Blackfeet Indian Reservation. Additionally, the team created site accessibility and precipitation anomaly maps that display the viability of survey locations. The current habitat suitability models performed well (AUC-PR=0.88). The most important predictor variables for suitable habitat were distance to rivers, elevation, and land cover. These end products will further inform WD4C survey site selection and contaminant monitoring.

Chelsea Morton↗
NASA NTRSDate not supplied

Transcriptomics-based Machine Learning Analysis Predicts Space-Exposed Murine Livers

Limited sample sizes, high data dimensionality, and sensitivity to technical and biological variability of next generation sequencing (NGS), has typically limited machine learning (ML) in space studies and further study of radiation effects. However, pooling smaller studies while addressing intra- and inter-study variabilities allows for ML predictive modeling. Here, integration methods were applied to whole transcriptome shotgun sequencing (RNAseq) data from 6 mouse liver GeneLab datasets (GLDS) with a total of 113 spaceflight and ground-control samples to determine top features relevant to spaceflight including the effect of radiation exposure. Data was normalized within each study, then merged and scaled across all datasets. Data dimensionality was reduced using a minimum redundancy maximum relevance (MRMR) methodology. The top MRMR features were used to predict spaceflight vs. ground-control samples using a Random Forest (RF) classifier with 5-fold cross validation (CV). The ML-based gene sets were further compared against differential gene expression results from individual GLDS. CV training using the top 100 MRMR genes show averages of 86% accuracy and 0.95 AUC value on the validation set over 5 folds (Figure 1A). Baseline set analysis on differentially expressed genes (DEGs) identified using padj ≤ 0.05 show 811 or 68 DEGs overlapping between at least 2 or 3 studies, respectively (Figure 1B). Over-representation analysis showed overlapping biological processes related to fatty acid and lipid metabolism. Set analysis between the MRMR features and the DEGs showed 60 or 8 genes overlapping with at least 1 or 2 studies, respectively. MRMR feature selection and ensemble ML methods (e.g. RF) improve performance relative to a Naïve Bayes classifier when NGS data sets are analyzed. A challenge of applying ML methods across heterogeneous NGS data is accounting for signal:noise ratio. Here, signal validation across studies was shown by intersecting sets between top MRMR genes and DEGs from RNASeq analysis. Non-intersecting sets introduce opportunity to explore spaceflight relevant genes and implementing ML methods across existing NGS datasets may overcome sample size limitations. ML coupled with existing analytical methods enhances understanding of disease by revealing common underlying pathways across datasets.

Machine Learning↗
NASA NTRSDate not supplied

Transcriptomics-based Machine Learning Analysis Predicts Space-Exposed Murine Livers

Limited sample sizes, high data dimensionality, and sensitivity to technical and biological variability of next generation sequencing (NGS), typically limits machine learning (ML) approaches in spaceflight studies that include radiation effects. However, pooling smaller studies while addressing intra- and inter-study variabilities allows for ML predictive modeling. Here, integration methods were applied to whole transcriptome shotgun sequencing (RNA-seq) data from six mouse liver GeneLab datasets (GLDS) (n ranging from 6 to 39 samples) from with a total of 81 spaceflight and ground-control samples to determine top features (i.e. genes) relevant to spaceflight including the effect of radiation exposure. RNASeq counts were normalized for each study, then merged and scaled across all datasets. Data dimensionality was reduced using a minimum redundancy maximum relevance (MRMR) methodology. Redundancy and relevance were computed using the Pearson correlation and F-statistic, respectively. The top 100 MRMR features were used to predict spaceflight vs. ground-control samples using Random Forest (RF), Support Vector Machine (SVM), and Linear Discriminant Analysis (LDA) classifiers with 5-fold cross validation (CV). Principal component analysis (PCA) on the complete feature set versus the MRMR features shows separation between spaceflight samples and ground controls (Figure 1A). The ML-based gene sets were compared against differential gene expression results obtained with DESeq2 from individual GLDS. Using all features or randomly sampled subsets at matching set sizes with MRMR, a maximum classifier accuracy of 69% was shown on the test set over 5 folds. For all classifiers, CV training using at least the top 30 MRMR genes show minimum 89% accuracy and 0.95 AUC value on the test set over 5 folds (Figure 1B). Baseline set analysis on differentially expressed genes (DEGs) identified using padj ≤ 0.05 show 295 DEGs that overlap at least two studies and 13 DEGs that overlap three studies (Figure 1C). Set analysis between the top 100 MRMR features and the DEGs showed 47 genes that overlap at least one study and 24 genes that overlap two studies. Over-representation analysis showed overlapping biological processes related to fatty acid and lipid metabolism which may indicate these processes in the response to spaceflight stressors. MRMR feature selection for the selected ML methods improve performance relative to a classifier built on all features or randomly sampled subsets. Permutation feature importance within the decorrelated MRMR features showed concordance in feature ranking between ML methods. A challenge of applying ML methods across heterogeneous NGS data is accounting for signal:noise. Here, signal validation across studies was shown by intersecting sets between top MRMR genes and DEGs from DESeq2 analysis. Non-intersecting sets introduce opportunity to explore genes relevant to differentiating space flight exposed groups and implementing ML methods across existing NGS datasets may overcome sample size limitations.

Machine Learning↗
NASA NTRSDate not supplied

Transcriptomics-based Machine Learning (ML) Analysis Predicts Space-Exposed Murine Livers

Limited sample sizes, high data dimensionality, and sensitivity to technical and biological variability of next generation sequencing (NGS), typically limits machine learning (ML) approaches in spaceflight studies that include radiation effects. However, pooling smaller studies while addressing intra- and inter-study variabilities allows for ML predictive modeling. Here, integration methods were applied to whole transcriptome shotgun sequencing (RNA-seq) data from six mouse liver GeneLab datasets (GLDS) (n ranging from 6 to 39 samples) from with a total of 81 spaceflight and ground-control samples to determine top features (i.e. genes) relevant to spaceflight including the effect of radiation exposure. RNASeq counts were normalized for each study, then merged and scaled across all datasets. Data dimensionality was reduced using a minimum redundancy maximum relevance (MRMR) methodology. Redundancy and relevance were computed using the Pearson correlation and F-statistic, respectively. The top 100 MRMR features were used to predict spaceflight vs. ground-control samples using Random Forest (RF), Support Vector Machine (SVM), and Linear Discriminant Analysis (LDA) classifiers with 5-fold cross validation (CV). Principal component analysis (PCA) on the complete feature set versus the MRMR features shows separation between spaceflight samples and ground controls (Figure 1A). The ML-based gene sets were compared against differential gene expression results obtained with DESeq2 from individual GLDS. Using all features or randomly sampled subsets at matching set sizes with MRMR, a maximum classifier accuracy of 69% on the test set over 5 folds. For all classifiers, CV training using at least the top 30 MRMR genes show minimum 89% accuracy and 0.95 AUC value on the test set over 5 folds (Figure 1B). Baseline set analysis on differentially expressed genes (DEGs) identified using padj ≤ 0.05 show 295 DEGs that overlap at least two studies and 13 DEGs that overlap three studies (Figure 1C). Set analysis between the top 100 MRMR features and the DEGs showed 47 genes that overlap at least one study and 24 genes that overlap two studies. Over-representation analysis showed overlapping biological processes related to fatty acid and lipid metabolism which may indicate these processes in the response to spaceflight stressors. MRMR feature selection for the selected ML methods improve performance relative to a classifier built on all features or randomly sampled subsets. Permutation feature importance within the decorrelated MRMR features showed concordance in feature ranking between ML methods. A challenge of applying ML methods across heterogeneous NGS data is accounting for signal:noise. Here, signal validation across studies was shown by intersecting sets between top MRMR genes and DEGs from DESeq2 analysis. Non-intersecting sets introduce opportunity to explore genes relevant to differentiating space flight exposed groups and implementing ML methods across existing NGS datasets may overcome sample size limitations.

Machine Learning↗
NASA NTRSDate not supplied

Transcriptomics-based Machine Learning Analysis Predicts Space-Exposed Murine Livers

Limited sample sizes, high data dimensionality, and sensitivity to technical and biological variability of next generation sequencing (NGS), typically limits machine learning (ML) approaches in spaceflight studies that include radiation effects. However, pooling smaller studies while addressing intra- and inter-study variabilities allows for ML predictive modeling. Here, integration methods were applied to whole transcriptome shotgun sequencing (RNA-seq) data from six mouse liver GeneLab datasets (GLDS) (n ranging from 6 to 39 samples) from with a total of 81 spaceflight and ground-control samples to determine top features (i.e. genes) relevant to spaceflight including the effect of radiation exposure. RNASeq counts were normalized for each study, then merged and scaled across all datasets. Data dimensionality was reduced using a minimum redundancy maximum relevance (MRMR) methodology. Redundancy and relevance were computed using the Pearson correlation and F-statistic, respectively. The top 100 MRMR features were used to predict spaceflight vs. ground-control samples using Random Forest (RF), Support Vector Machine (SVM), and Linear Discriminant Analysis (LDA) classifiers with 5-fold cross validation (CV). Principal component analysis (PCA) on the complete feature set versus the MRMR features shows separation between spaceflight samples and ground controls (Figure 1A). The ML-based gene sets were compared against differential gene expression results obtained with DESeq2 from individual GLDS. Using all features or randomly sampled subsets at matching set sizes with MRMR, a maximum classifier accuracy of 69% was shown on the test set over 5 folds. For all classifiers, CV training using at least the top 30 MRMR genes show minimum 89% accuracy and 0.95 AUC value on the test set over 5 folds (Figure 1B). Baseline set analysis on differentially expressed genes (DEGs) identified using padj ≤ 0.05 show 295 DEGs that overlap at least two studies and 13 DEGs that overlap three studies (Figure 1C). Set analysis between the top 100 MRMR features and the DEGs showed 47 genes that overlap at least one study and 24 genes that overlap two studies. Over-representation analysis showed overlapping biological processes related to fatty acid and lipid metabolism which may indicate these processes in the response to spaceflight stressors. MRMR feature selection for the selected ML methods improve performance relative to a classifier built on all features or randomly sampled subsets. Permutation feature importance within the decorrelated MRMR features showed concordance in feature ranking between ML methods. A challenge of applying ML methods across heterogeneous NGS data is accounting for signal:noise. Here, signal validation across studies was shown by intersecting sets between top MRMR genes and DEGs from DESeq2 analysis. Non-intersecting sets introduce opportunity to explore genes relevant to differentiating space flight exposed groups and implementing ML methods across existing NGS datasets may overcome sample size limitations.

Machine Learning↗
NASA NTRSDate not supplied

Transcriptomics-based Machine Learning (ML) Analysis Predicts Space-Exposed Murine Livers

NASA has employed high-throughput molecular assays to identify sub-cellular changes impacting human physiology during spaceflight. Machine learning (ML) methods hold the promise to improve our ability to identify important signals within highly dimensional molecular data. However, the inherent limitation of study subject numbers within a spaceflight mission minimizes the utility of ML approaches. To overcome the sample power limitations, data from multiple spaceflight missions must be aggregated while appropriately addressing intra- and inter-study variabilities. Here we describe an approach to log transform, scale and normalize data from six heterogeneous, mouse liver derived transcriptomics datasets (ntotal=137) which enabled ML-methods to perform well (AUC ≥ 0.87) in classifying spaceflown vs ground control animals rather than mission-of-origin. Concordance was found between liver-specific biological processes identified from harmonized ML-based analysis and study-by-study classical omics analysis. This work demonstrates the feasibility of applying ML methods on integrated, heterogeneous datasets of small sample size.

Machine Learning↗
NASA NTRS2021

Time series comparisons in Deep Space Network

The Deep Space Network (DSN) is NASA’s international array of antennas that support interplanetary spacecraft missions. DSN provides radar and radio astronomy observations that enhance our understanding of the solar system and the larger universe. A track is a block of continuous multi-dimensional time series from the beginning to end of DSN communication with the target spacecraft, containing 129 monitor data items lasting several hours at a frequency of 0.2-1Hz. Monitor data on each track reports on the performance of specific spacecraft operations and the DSN itself. DSN is receiving signals from 32 spacecraft across the solar system. DSN has pressure to reduce costs while maintaining the quality of support for DSN mission users. DSN operators need to simultaneously monitor multiple tracks and identify anomalies in real time. DSN has seen that as the number of missions increases, the data that needs to be processed increases over time. In this project, we look at the last 8 years of data for analysis. Any anomaly in the track indicates a problem with either the spacecraft, DSN equipment, or weather conditions. DSN operators typically write “discrepancy reports” for further analysis. It is recognized that it would be quite helpful to identify 10 similar historical tracks out of the huge database to quickly find/match anomalies. This tool has three functions: (1) identification of the top 10 similar historical tracks, (2) detection of anomalies compared to the reference normal track, and (3) comparison of statistical differences between two given tracks. The requirements for these features were confirmed by survey responses from 21 DSN operators and engineers. The preliminary machine learning model has shown promising performance (AUC=0.92). We plan to increase the number of data sets and perform additional testing to improve performance further before its planned integration into the Track Visualizer to assist DSN field operators and engineers.

Rebbapragada, Umaa↗
NASA NTRSDate not supplied

Development and Application of NASA SPoRT’s DustTracker-AI Model for Real-Time Identification and Tracking of Dust in Geostationary Satellite Imagery

The NASA Short-term Prediction Research and Transition (SPoRT) Center developed the DustTracker-AI model for identifying and tracking dust in NASA/NOAA Geostationary Operational Environmental Satellite (GOES) imagery in a real-time framework. A training dataset consisting of day and night dust cases was gathered over the southwestern consisting of 115 distinct images and over a million dust pixels and 256 million no dust pixels. The dataset was separated into training (60%), testing (20%), and validation (20%). A simple random forest machine learning model was developed originally to overcome the problem of night-time dust detection and has been expanded to a comprehensive day/night model for dust identification and tracking. This physically-based machine-learning approach uses NASA/NOAA GOES-16 Advanced Baseline Imager infrared imagery as inputs to the model. The model probability of dust output achieves an Area-Under-Curve (AUC) of 0.97 with a standard deviation of 0.04 for dust cases. For images with dust present, the model correctly labels 85% of dust pixels for all dust images in the validation data set. In conjunction with developing the machine-learning model, the NASA Short-term Prediction Research and Transition Center (SPoRT) partnered with NOAA National Weather Service forecast offices to evaluate the model for utility in weather forecasting operations during the 2021 and 2023 late winter-spring seasons. Preliminary evaluation has indicated the majority of forecasters described the DustTracker-AI probabilities as having added confidence to interpreting the Dust RGB and other satellite products to objectively assess the dust extent and trends and increased the amount of time the dust plume could be tracked into the night as compared to use of the Dust RGB. More recently, SPoRT tested small scale events associated with thunderstorm outflow and burn scars to determine the model’s ability to capture local events. This presentation highlights design of the model, validation/evaluation of model performance, and example cases collected during end user product assessments.

Connor H Welch↗
NASA NTRS2026

Proactive Wildfire Management: A Remote Sensing and Multimodal CNN-MLP Architecture for Ignition Risk Forecasting

As the frequency and intensity of wildfires increase, with fire seasons now starting earlier and ending later than they have over the past decades, current monitoring systems, such as lookout towers and satellites, are hindered by cloud cover, low-resolution imagery, and static data gaps that fail to track vegetation moisture levels fast enough to catch rapid pre-ignition changes. This report proposes a Machine Learning-enabled Wildfire Ignition Prediction framework that combines satellite monitoring with dynamic and high-resolution remote sensing from Unmanned Aerial Vehicle (UAV) swarms. The method would use multispectral and thermal data from the Landsat program to create a baseline for vegetation health, calculating a two-band Enhanced Vegetation Index (EVI2) and the moisture content of the vegetation. These inputs will later be fused with microscale UAV weather data, including thermal hotspots found through thick canopies, hyperspectral chemical signatures of pre-visual combustion, and local weather streams. The multispectral satellite, multispectral Light Detection and Ranging (LiDAR), and thermal data would then be processed through a Convolutional Neural Network (CNN), alongside a Multilayer Perceptron (MLP) for the micro-weather telemetry. The outputs of these networks would be fused into a single feature representation and passed through a final prediction network to generate real-time ignition risk scores and hotspot alerts. Model performance would be assessed using standard classification metrics, including a Receiver Operating Characteristic - Area Under the Curve (ROC AUC) and F1 score. This system would allow first responders to identify high-risk zones and intervene before ignition occurs, improving emergency response time compared to current approaches.

machine learning↗
DOE OSTI2025

Heterogeneous Point Set Transformers for Segmentation of Multiple View Particle Detectors

NOvA is a long-baseline neutrino oscillation experiment that detects neutrino particles from the NuMI beam at Fermilab. Before data from this experiment can be used in analyses, raw hits in the detector must be matched to their source particles, and the type of each particle must be identified. This task has commonly been done using a mix of traditional clustering approaches and convolutional neural networks (CNNs). Due to the construction of the detector, the data is presented as two sparse 2D images: an XZ and a YZ view of the detector, rather than a 3D representation. We propose a point set neural network that operates on the sparse matrices with an operation that mixes information from both views. Our model uses less than 10% of the memory required using previous methods while achieving a 96.8% AUC score, a higher score than obtained when both views are processed independently (85.4%).

Robles, Edgar E. [UC, Irvine (main)]↗
DOE OSTI2026

Towards Secure Autonomous Vehicles: An Integrated Edge and Multi-Modal Machine Learning Framework for Intrusion Detection

Autonomous vehicles (AVs) are vulnerable to cyberattacks targeting both internal communication networks and external perception sensors. While edge-based intrusion de- tection for Controller Area Network (CAN) buses offers real-time protection, it cannot detect cross-modal threats. Conversely, multi-modal fusion approaches improve coverage but often lack efficiency for in-vehicle deployment. This thesis integrates two complemen- tary solutions: (1) a lightweight, edge-deployable machine learning framework for CAN bus intrusion detection, and (2) a late-fusion system combining CAN FD and LiDAR data. Together, they form a hierarchical defense capable of handling single-modality and coordi- nated attacks. Simulations show that CAN-only models reach 93% accuracy on simulated DoS, spoofing, replay, and fuzzy attacks, while the fusion system achieves 0.87 AUC and 0.82 F1-score at 2 ms latency. This unified framework establishes a scalable, explainable, and field-ready strategy for AV cybersecurity.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2026

Automated Membership Inference Attacks: Discovering MIA Signal Computations using LLM Agents

Membership inference attacks (MIAs), which enable adversaries to determine whether specific data points were part of a model's training dataset, have emerged as an important framework to understand, assess, and quantify the potential information leakage associated with machine learning systems. Designing effective MIAs is a challenging task that usually requires extensive manual exploration of model behaviors to identify potential vulnerabilities. In this paper, we introduce AutoMIA -- a novel framework that leverages large language model (LLM) agents to automate the design and implementation of new MIA signal computations. By utilizing LLM agents, we can systematically explore a vast space of potential attack strategies, enabling the discovery of novel strategies. Our experiments demonstrate AutoMIA can successfully discover new MIAs that are specifically tailored to user-configured target model and dataset, resulting in improvements of up to 0.18 in absolute AUC over existing MIAs. This work provides the first demonstration that LLM agents can serve as an effective and scalable paradigm for designing and implementing MIAs with SOTA performance, opening up new avenues for future exploration.

Tran, Toan Viet [Emory University]↗
DOE OSTI2025

Using Boosted Decision Trees to Select High Quality Measurements in the Mu2e Experiment at Fermilab

This thesis presents the implementation and evaluation of a Boosted Decision Tree (BDT) model to improve the selection of high-quality track measurements in the Mu2e experiment at Fermilab. The Mu2e experiment is a high-energy physics experiments seeking to observe a rare theoretical physics process known as Charged Lepton Flavor Violation. A significant challenge faced by the Mu2e experiment are so-called background events, which are events whose data mimics that of the rare physics process the experiment seeks to observe. Without a mechanism to reduce background, it would be impossible to know whether Charged Lepton Flavor Violation occurred or not. To this end, high-quality track measurements must be distinguished from low-quality track measurements. A track can be conceived of as the reconstructed path of a particle that traveled through the Mu2e detector. In addition to other data, data about such tracks is stored using a C++-based framework, specific to the domain of high-energy physics, known as ROOT. A boosted decision tree model was trained using ROOT’s Toolkit For Multivariate Analysis by leveraging variables ancillary to track quality. In evaluation, the BDT achieves a ROC-AUC of 0.927 in discriminating good-quality tracks from poor-quality tracks. Such a score is indicative of both strong discrimination and strong generalization. Subsequently, it is shown that applying a BDT-based quality cut to the distribution of particle momenta significantly enhances the signal-to-background distinction for signal electrons, paving the way for improved sensitivity to Charged Lepton Flavor Violation.

Mullany, Brendan T. [Drew U.] (ORCID:0009000818888↗