SEARCH · Engineering Papers

Results for “validation dataset”

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.

SourceResearch connectionFrom yearThrough year

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

At least 37 records · Page 2

All sources NASA NTRS DOE OSTI

DOE OSTI2025

Using active learning to improve quasar identification for the DESI spectra processing pipeline

The Dark Energy Spectroscopic Instrument (DESI) survey uses an automatic spectral classification pipeline to classify spectra. QuasarNET is a convolutional neural network used as part of this pipeline originally trained using data from the Baryon Oscillation Spectroscopic Survey (BOSS). In this paper we implement an active learning algorithm to optimally select spectra to use for training a new version of the QuasarNET weights file using only DESI data, with the goal of improving classification accuracy. This active learning algorithm includes a novel outlier rejection step using a Self-Organizing Map to ensure we label spectra representative of the larger quasar sample observed in DESI. We perform two iterations of the active learning pipeline, assembling a final dataset of 5600 labeled spectra, a small subset of the approximately 1.3 million quasar targets in DESI's Data Release 1. When splitting the spectra into training and validation subsets we achieve similar performance to the previously trained weights file in completeness and purity calculated on the validation dataset but do so with less than one tenth of the amount of training data. The new weights also more consistently classify objects in the same way when used on unlabeled data compared to the old weights file. In the process of improving QuasarNET's classification accuracy we discovered a systemic error in QuasarNET's redshift estimation and used our findings to improve our understanding of QuasarNET's redshifts.

Machine learning↗

DOE OSTI2025

Developing predictive models for µ opioid receptor binding using machine learning and deep learning techniques

Opioids exert their analgesic effect by binding to the µ opioid receptor (MOR), which initiates a downstream signaling pathway, eventually inhibiting pain transmission in the spinal cord. However, current opioids are addictive, often leading to overdose contributing to the opioid crisis in the United States. Therefore, understanding the structure-activity relationship between MOR and its ligands is essential for predicting MOR binding of chemicals, which could assist in the development of non-addictive or less-addictive opioid analgesics. This study aimed to develop machine learning and deep learning models for predicting MOR binding activity of chemicals. Chemicals with MOR binding activity data were first curated from public databases and the literature. Molecular descriptors of the curated chemicals were calculated using software Mold2. The chemicals were then split into training and external validation datasets. Random forest, k-nearest neighbors, support vector machine, multi-layer perceptron, and long short-term memory models were developed and evaluated using 5-fold cross-validations and external validations, resulting in Matthews correlation coefficients of 0.528–0.654 and 0.408, respectively. Furthermore, prediction confidence and applicability domain analyses highlighted their importance to the models’ applicability. Our results suggest that the developed models could be useful for identifying MOR binders, potentially aiding in the development of non-addictive or less-addictive drugs targeting MOR.

Research & Experimental Medicine↗

DOE OSTI2021

Bias Characterization, Vertical Interpolation, and Horizontal Interpolation for Distributed Wind Siting Using Mesoscale Wind Resource Estimates

Much like their counterparts in utility-scale wind energy, developers of industrial, small-scale and distributed wind turbine deployments need to understand and accurately characterize the wind resource to properly assess the power generation and financial ramifications during siting and planning. National Renewable Energy Laboratory’s WIND (Wind Integration National Dataset) Toolkit (WTK) provides a best-in-class wind resource dataset generated using the Weather Research and Forecasting (WRF) model. This dataset includes parameters such as the wind speed, wind direction, and temperature at various heights, plus atmospheric stability near the surface. This data is available at 2-km spatial resolution and five-minute temporal resolution across 7 years, from 2007 to 2013 through a publicly accessible API interface. The Tools Assessing Performance (TAP) project seeks to extend this dataset to allow long term resource estimates and leverage it to better equip distributed wind equipment manufacturers, owner-operators, and installation professionals with better tools for practical siting applications. In this report, we present the results from our investigation within the TAP project focused on characterization of bias in WTK-based wind speed estimates and evaluation of vertical and horizontal interpolation techniques. We discuss the tradeoffs between different techniques and their combinations, as well as describe the lower bounds we determine for the studied validation errors. While the specific estimates we present are specific to WTK and the validation dataset we have chosen for this investigation (NREL's Wind Resource Meteorological Database), the overall analysis and the studied techniques are general enough to be applied to a broader set of wind datasets, both simulation-based and observational.

17 WIND ENERGY↗

DOE OSTI2023

MnEdgeNet for accurate decomposition of mixed oxidation states for Mn XAS and EELS L2,3 edges without reference and calibration

Accurate decomposition of the mixed Mn oxidation states is highly important for characterizing the electronic structures, charge transfer and redox centers for electronic, and electrocatalytic and energy storage materials that contain Mn. Electron energy loss spectroscopy (EELS) and soft X-ray absorption spectroscopy (XAS) measurements of the Mn L2,3 edges are widely used for this purpose. To date, although the measurements of the Mn L2,3 edges are straightforward given the sample is prepared properly, an accurate decomposition of the mix valence states of Mn remains non-trivial. For both EELS and XAS, 2+, 3+, and 4+ reference spectra need to be taken on the same instrument/beamline and preferably in the same experimental session because the instrumental resolution and the energy axis offset could vary from one session to another. To circumvent this hurdle, in this study, we adopted a deep learning approach and developed a calibration-free and reference-free method to decompose the oxidation state of Mn L2,3 edges for both EELS and XAS. A deep learning regression model is trained to accurately predict the composition of the mix valence state of Mn. To synthesize physics-informed and ground-truth labeled training datasets, we created a forward model that takes into account plural scattering, instrumentation broadening, noise, and energy axis offset. With that, we created a 1.2 million-spectrum database with 1-by-3 oxidation state composition ground truth vectors. The library includes a sufficient variety of data including both EELS and XAS spectra. By training on this large database, our convolutional neural network achieves 85% accuracy on the validation dataset. We tested the model and found it is robust against noise (down to PSNR of 10) and plural scattering (up to t/λ = 1). We further validated the model against spectral data that were not used in training. In particular, the model shows high accuracy and high sensitivity for the decomposition of Mn 3 O 4 , MnO, Mn 2 O 3 , and MnO 2 . The accurate decomposition of Mn 3 O 4 experimental data shows the model is quantitatively correct and can be deployed for real experimental data. Our model will not only be a valuable tool to researchers and material scientists but also can assist experienced electron microscopists and synchrotron scientists in the automated analysis of Mn L edge data.

25 ENERGY STORAGE↗

DOE OSTI2023

Moisture sources for precipitation variability over the Arabian Peninsula

Abstract We apply the Lagrangian-based moisture back trajectory method to two reanalysis datasets to determine the moisture sources for wet season precipitation over the Arabian Peninsula, defined as land on the Asian continent to the south of the Turkish border and west of Iran. To accomplish this, we make use of the evaporative source region between 65°W–120°E and 30°S–60°N, which is divided into twelve sub-regions. Our comparison of reanalyses and multiple observations allows us to validate datasets and highlight broad-scale similarities in characteristics, notwithstanding some inconsistencies in the southwest AP. The results indicate north-to-south spatiotemporal heterogeneity in the characteristics of dominant moisture sources. In the north, moisture for precipitation is mainly sourced from midlatitude land and water bodies, such as the Mediterranean and Caspian Seas. Areas further south are dependent on moisture transport from the Western Indian Ocean and parts of the African continent. The El Niño-Southern Oscillation (ENSO) exhibits an overall positive but sub-seasonally varying influence on the precipitation variability over the region, with noticeable moisture anomalies from all major source regions. A significant drying trend exists over parts of the Peninsula, which both reanalyses partially attribute to anomalies in the moisture advection from the Congo Basin and South Atlantic Ocean. However, considerable uncertainty in evaporation trends over the terrestrial evaporative sources in observations warrants additional modeling studies to further our understanding of key processes contributing to the negative trends.

54 ENVIRONMENTAL SCIENCES↗

DOE OSTI2022

What you get is not always what you see—pitfalls in solar array assessment using overhead imagery

Effective integration planning for small, distributed solar photovoltaic (PV) arrays into electric power grids requires access to high quality data: the location and power capacity of individual solar PV arrays. Unfortunately, national databases of small-scale solar PV do not exist; those that do are limited in their spatial resolution, typically aggregated up to state or national levels. While several promising approaches for solar PV detection have been published, strategies for evaluating the performance of these models are often highly heterogeneous from study to study. The resulting comparison of these methods for practical applications for energy assessments becomes challenging and may imply that the reported performance evaluations overly optimistic. The heterogeneity comes in many forms, each of which we explore in this work: the degree of diversity of the locations and sensors (e.g. different satellites, aerial photography) from which the training and validation data originate, the validation of ground truth (manual annotation of imagery vs known solar PV locations), the level of spatial aggregation (e.g. array-level vs regional estimates), and inconsistencies in the training and validation datasets (e.g. different datasets are used for each study and those data are not always made accessible). For each, we discuss emerging practices from the literature to address them or suggest directions of future research. As part of our investigation, we evaluate solar PV identification performance in two large regions: the entire state of Connecticut and the city of San Diego, CA. In Connecticut, we also use 33,114 known parcel-level solar PV installations from Berkeley Lab’s Tracking the Sun dataset to evaluate parcel-level performance and evaluate capacity estimates using 169 municipalities. We also make our code (which we call SolarMapper), pre-trained models, training data, and predictions publicly available and provide a web portal for interactively inspecting each prediction that was made. Here our findings suggest that traditional performance evaluation of the automated identification of solar PV from satellite imagery may be optimistic due to common limitations in the validation process. The takeaways from this work are intended to inform and catalyze the large-scale practical application of automated solar PV assessment techniques by energy researchers and professionals.

14 SOLAR ENERGY↗

DOE OSTI2024

Event-Based Energy Impact Tracking and Forecasting with Limited Measurements for Rooftop Units

Packaged air conditioning units and heat pumps, also known as rooftop units (RTUs), are responsible for almost 133 billion kWh of electricity usage annually on site for space cooling U.S. commercial buildings. In addition, the use of heat pumps is a trend we expect to accelerate as buildings transition from fossil fuel-based heating to electricity as a key step for decarbonizing the U.S. commercial buildings sector. However, the operation conditions and energy use of RTUs and heat pumps are usually not well monitored as they are not commonly integrated with building automation systems and lack exposed sensing and control points. To fill this gap, this paper proposes a framework for tracking and forecasting energy impacts resulting from degradation of performance and improved performance for unit servicing using limited data. The proposed framework makes use of a constrained dataset, specifically measurements of the outdoor air temperature and the power demand of individual RTUs, to track and forecast changes in energy use associated with changes in performance over various temporal horizons ranging from days to weeks. Following the detection of an RTU fault, performance degradation, or performance improvement, the framework employs a prediction model to assess the cumulative energy impact. We demonstrate the effectiveness of the method with field-collected data for servicing and degradation examples and compare the predicting accuracy of Gradient Boosting Decision Tree (GBDT) Regression models to Support Vector Regression and Linear Regression models. The results show that GBDT achieved the best accuracy for time-series validation datasets for the servicing and degradation cases, and the prediction model was able to track the cumulative energy impacts of events. The proposed framework can inform building owners of the cumulative change in energy usage of RTUs associated with performance degradation, performance improvement, or a fault.

packaged air conditioners, packaged heat pumps, ro↗

DOE OSTI2022

Experimental measurements of gas-particle flows in large-scale strippers

Measurements of gas–solid particle flow in a large-scale stripper unit are reported. The experiments target industrial (pilot) scale measurements of gas-particle flow that can be used to validate numerical methods for modeling multiphase flows, such as computational fluid dynamics coupled to the discrete element method (CFD-DEM). Specifically, experiments were performed with Geldart Group B (533 µm) glass beads in a stripper unit. In general, previous CFD-DEM validation datasets were performed in benchtop experimental systems and limited to O(10 5 ) particles. Here, in this work, the number of particles in the isolated section of the stripper is O(10 7 ) for all tests. Measurements are reported for a ~2 m tall section of the ~1 m diameter stripper. Radial mass flux profiles measured at five axial positions and three axial pressure drop measurements are reported for six operating conditions.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

DOE OSTI2022

Search for Lepton Flavor Violation in Two Body Muon and Pion Decay at Rest

The ability of the Mu2e experiment to probe, or discover beyond the Standard Model physics in direct Charged Lepton Flavor Violation $\mu^+$ and $\pi^+$ decay modes is estimated. These direct modes are searched for simultaneously with proposed Mu2e detector validation runs, and are complementary to the Mu2e main search goal, an indirect search for $\mu^- \to e^-$ conversion at the sensitivity level of $\sim 10^{-17}$. The $\mu^+$ validation run will operate at 50% nominal magnetic field and reduced proton beam intensity to less than 1/100th nominal, in order to observe the e+ spectrum from $\mu^+$ decay, at and below the Michel edge Ee . 53 MeV. The $\pi^+$ validation run, based on measuring the mono-energetic e+ emission in the decay $\pi^+ \to e+\nu$, at 76% of nominal magnetic field and reduced beam intensity less than 1/5th nominal. Both of these runs can be used to fix the momentum scale for the Mu2e conversion search. In addition the muon validation dataset can be used to correct for systematic errors in the detector response by mapping the well known to O(\u03B13) corrected theoretical Michel spectrum, to the observed spectrum. One direct search is for two-body Charged Lepton Flavor Violation $\mu^+ \to e^+X$ decay, where $X$ is a light new physics particle. This allows Mu2e to explore well motivated models including axion like particles with flavor violating couplings and massive $Z^0$ bosons with more sensitivity then present astrophysical and laboratory constraints. In two weeks of data-taking, Mu2e can achieve direct mode 90% confidence level branching ratio limits of $10^{-7}$ over the mass range $20 \le m_X \le 50$ MeV, improving the current experimental limit at $10^{-5}$ by two orders of magnitude. In the mass range $m_X \le 20$ MeV, assuming systematic error corrections can be made by correcting the Monte Carlo mapping, the achievable search sensitivity is found to be $2.3\times 10^{-7}$ for $m_X =0$, an order of magnitude improvement over the current best limit at $2.6\times 10^{-6}$, when assuming $V+A$ or isotropic coupling. The $\pi^+$ validation run, allows searching for $\pi^+ \to e^+N$ decay, where $N$ is a heavy neutral lepton such as a heavy sterile neutrino, in the mass region $20 \le m_N \le 65$ MeV. A branching ratio limit at 90% confidence level of $3\times 10^{-8}$ can be achieved in two weeks, an improvement of the current search sensitivity limit by an order of magnitude.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

DOE OSTI2022

O 2 based resonantly ionized photoemission thermometry analysis of supersonic flows

Characterization of the thermal gradients within supersonic and hypersonic flows is essential for understanding transition, turbulence, and aerodynamic heating. Developments in novel, impactful non-intrusive techniques are key for enabling flow characterizations of sufficient detail that provide experimental validation datasets for computational simulations. In this work, Resonantly Ionized Photoemission Thermometry (RIPT) signals are directly imaged using an ICCD camera to realize the techniques 1D measurement capability for the first time. The direct imaging scheme presented for oxygen-based RIPT (O 2 RIPT) uses the previously established calibration data to direct excite various resonant rotational peaks within the S-branch of the C 3 Π, ( v = 2) ← X 3 Σ( v ′ = 0) absorption band of O 2 . The efficient ionization of O 2 liberates electrons that induce electron avalanche ionization of local N 2 molecules generating N 2 + , which primarily deexcites via photoemissions of the first negative band of N 2 + ( B 2 Σ <#comment/> u + − <#comment/> X 2 Σ <#comment/> g + ) . When sufficient lasing energy is used, the ionization region and subsequent photoemission signal is achieved along a 1D line thus, if directly imaged can allow for gas temperature assignments along said line; demonstrated here of up to five centimeters in length. The temperature gradients present within the ensuing shock train of a supersonic under expanded free jet serves as a basis of characterization for this new RIPT imaging scheme. The O 2 RIPT results are extensively compared and validated against well-known and established techniques (i.e., CARS and CFD). The direct imaging capability fully realizes the technique’s fundamental potential and is expected to be the standard of implementation going forward. The direct imaging capability can play instrumental roles in future scientific studies that rely upon acute characterization of thermal gradients within a medium that cannot be easily resolved by a point. Furthermore, the removal of the spectrometer greatly reduces the cost, complexity, and optical alignment associated with prior RIPT measurements.

42 ENGINEERING↗

DOE OSTI2021

Protecting building occupants against the inhalation of outdoor-origin aerosols

During normal operations, buildings can protect their occupants from outdoor airborne particle hazards of all types, including airborne pollutants. A long-term international research effort has advanced our knowledge of building protection physics. Recently we have developed an operationally efficient, regional-scale methodology - Regional Shelter Analysis - to account for both building protection effects and the typical distribution of people in and among buildings. To provide input to this capability, we estimate here the degree of protection afforded by the currently existing US building stock. Here, we first assemble and summarize the published literature relevant to indoor particle losses including (a) deposition to indoor surfaces, (b) losses that occur when particles penetrate through the building envelope, and (c) heating, ventilation and air conditioning (HVAC) system filtration efficiencies as well as general building operating conditions. Building protection against inhaling particulate hazards varies strongly, by orders of magnitude, according to particle size, airborne particle loss rate, and to a lesser extent building use (occupancy). Protection increases modestly as particle size increases from 0.1 to 1 μm and significantly as particle size increases from 1 to 10 μm. Model results are placed in context with previously reported measurements. Suggestions for future work, including enhanced validation datasets are provided.

63 RADIATION, THERMAL, AND OTHER ENVIRON. POLLUTAN↗

DOE OSTI2021

Recurrent neural network-based multiaxial plasticity model with regularization for physics-informed constraints

We report a recurrent neural network (RNN) based model is developed as a surrogate to predict nonlinear plastic response under multiaxial loading. The RNN-based model is trained and tested on stress versus strain curves generated using a numerical solution based on the classical radial return method. Besides simply learning the basic constitutive relationship, a novel approach is taken to enforce certain physical conditions. Specifically, regularization is employed to maintain non-negative plastic power density throughout the loading history thereby ensuring monotonically increasing plastic work and thermodynamic consistency. Enforcing physics in this manner permits coupling of the data-driven RNN approach with physics-based knowledge and laws. This has the effect of reducing the necessary amount of data and ensuring known physical laws are not violated. Since, once trained, the model need not perform the expensive task of solving nonlinear equations, its efficiency is orders of magnitude greater than its numerical counterpart. The RNN-based model has been trained on varied sets of data and the accuracy on test datasets validated. The developed model is general and robust and has widespread application such as in the simulation of metal forming, large scale plasticity, and part life prediction.

42 ENGINEERING↗

DOE OSTI2020

Data analytics for leak detection in a subcritical boiler

For decades, boiler leaks have been the leading cause of forced outages in the coal-fired unit. The leak occurrences are currently escalating since the existing plants must satisfy faster-ramping rates to support grid operation. Data analytics including Principal Component Analysis, Canonical Variate, and Fisher Discriminant Analysis were combined for detecting and characterizing the leak in a commercial 650 MW subcritical coal-fired power plant. The combined approach was shown to be highly effective in the fault investigation that would not have been easily achieved by an individual technique. The variability in both training and validation datasets was first evaluated using PCA. Then, the CV-FDA was employed to discriminate among faults, and to categorize the processed data into two main groups: no-leak (0) and leak (1), providing the timeframe and location of the leak occurrence. Furthermore, about 8,014 observations from 81 process variables were initially included in the calculation, while the variable count was reduced to 4 with less than 1% misclassification rate in total observations. Finally, the leak was isolated in the waterwall section. Thus, the outcome of this research may provide early detection and isolation of faulty operations in the coal-fired power plant that involves a considerable number of process variables.

20 FOSSIL-FUELED POWER PLANTS↗

DOE OSTI2021

The NIH Somatic Cell Genome Editing program

The move from reading to writing the human genome offers new opportunities to improve human health. The United States National Institutes of Health (NIH) Somatic Cell Genome Editing (SCGE) Consortium aims to accelerate the development of safer and more-effective methods to edit the genomes of disease-relevant somatic cells in patients, even in tissues that are difficult to reach. Here we discuss the consortium’s plans to develop and benchmark approaches to induce and measure genome modifications, and to define downstream functional consequences of genome editing within human cells. Central to this effort is a rigorous and innovative approach that requires validation of the technology through third-party testing in small and large animals. New genome editors, delivery technologies and methods for tracking edited cells in vivo, as well as newly developed animal models and human biological systems, will be assembled—along with validated datasets—into an SCGE Toolkit, which will be disseminated widely to the biomedical research community. We visualize this toolkit—and the knowledge generated by its applications—as a means to accelerate the clinical development of new therapies for a wide range of conditions.

59 BASIC BIOLOGICAL SCIENCES↗

DOE OSTI2021

Predicting distribution of malaria vector larval habitats in Ethiopia by integrating distributed hydrologic modeling with remotely sensed data

Abstract Larval source management has gained renewed interest as a malaria control strategy in Africa but the widespread and transient nature of larval breeding sites poses a challenge to its implementation. To address this problem, we propose combining an integrated high resolution (50 m) distributed hydrological model and remotely sensed data to simulate potential malaria vector aquatic habitats. The novelty of our approach lies in its consideration of irrigation practices and its ability to resolve complex ponding processes that contribute to potential larval habitats. The simulation was performed for the year of 2018 using ParFlow-Common Land Model (CLM) in a sugarcane plantation in the Oromia region, Ethiopia to examine the effects of rainfall and irrigation. The model was calibrated using field observations of larval habitats to successfully predict ponding at all surveyed locations from the validation dataset. Results show that without irrigation, at least half of the area inside the farms had a 40% probability of potential larval habitat occurrence. With irrigation, the probability increased to 56%. Irrigation dampened the seasonality of the potential larval habitats such that the peak larval habitat occurrence window during the rainy season was extended into the dry season. Furthermore, the stability of the habitats was prolonged, with a significant shift from semi-permanent to permanent habitats. Our study provides a hydrological perspective on the impact of environmental modification on malaria vector ecology, which can potentially inform malaria control strategies through better water management.

59 BASIC BIOLOGICAL SCIENCES↗

DOE OSTI2025

Network Anomaly Detection in Distributed Edge Computing Infrastructure

As networks continue to grow in complexity and scale, detecting anomalies has become increasingly challenging, particularly in diverse and geographically dispersed environments. Traditional approaches often struggle with managing the computational burden associated with analyzing large-scale network traffic to identify anomalies. This paper introduces a distributed edge computing framework that integrates federated learning with Apache Spark and Kubernetes to address these challenges. We hypothesize that our approach, which enables collaborative model training across distributed nodes, significantly enhances the detection accuracy of network anomalies across different network types. We show that by leveraging distributed computing and containerization technologies, our framework not only improves scalability and fault tolerance but also achieves superior detection performance compared to state-of-the-art methods. Extensive experiments on the UNSW-NB15 and ROAD datasets validate the effectiveness of our approach, demonstrating statistically significant improvements in detection accuracy and training efficiency over baseline models, as confirmed by MannWhitney U and Kolmogorov-Smirnov tests (p<0.05).

Marfo, William [University of Texas at El Paso,Dep↗

DOE OSTI2024

Entropy-Infused Deep Learning Loss Function for Capturing Extreme Values in Wind Power Forecasting

Extreme scenarios in wind power generation occur with higher frequency and larger magnitude in the recent years due to the ever-increasing extreme meteorological factors. Accurate forecasting of the occurrence of extreme values in wind power generation is of great concern to ensure reliable power system operation. Recently, deep learning models have surged in popularity for wind power forecasting, with the mean squared error (MSE) loss function being commonly used. However, the MSE loss function, being sensitive to extreme values, disproportionately penalizes larger errors, cannot adequately capture the extreme values present in wind energy data, and novel loss functions have seldom been tailored for wind power forecasting. To this end, in this paper, we introduce a novel loss function specifically crafted to capture extreme values in wind power forecasting. The experimental results with four fundamental deep learning methods on open source wind power dataset validate that the new loss function is efficient and superior in all cases compared to MSE in capturing extreme values while maintaining forecasting performance.

17 WIND ENERGY↗

DOE OSTI2025

Detecting Masquerade Attacks in Controller Area Networks Using Graph Machine Learning

Modern vehicles rely on a myriad of electronic control units (ECUs) interconnected via controller area networks (CANs) for critical operations. Despite their ubiquitous use and reliability, CANs are susceptible to sophisticated cyberattacks, particularly masquerade attacks, which inject false data that mimic legitimate messages at the expected frequency. These attacks pose severe risks such as unintended acceleration, brake deactivation, and rogue steering. Traditional intrusion detection systems (IDS) often struggle to detect these subtle intrusions due to their seamless integration into normal traffic. This paper introduces a novel framework for detecting masquerade attacks in the CAN bus using graph machine learning (ML). We hypothesize that the integration of shallow graph embeddings with time series features derived from CAN frames enhances the detection of masquerade attacks. We show that by representing CAN bus frames as message sequence graphs (MSGs) and enriching each node with contextual statistical attributes from time series, we can enhance detection capabilities across various attack patterns compared to using graph-based features only. Our method ensures a comprehensive and dynamic analysis of CAN frame interactions, improving robustness and efficiency. Extensive experiments on the ROAD dataset validate the effectiveness of our approach, demonstrating statistically significant improvements in the detection rates of masquerade attacks compared to a baseline that uses graph-based features only as confirmed by Mann-Whitney U and Kolmogorov-Smirnov tests (p < 0.05) .

Marfo, William [Univ. of Texas, El Paso, TX (Unite↗