Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “decision trees”

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 397 records · Page 22

A Scalable HPC Insider Threat Monitoring System

Cyber Equations, Inc. is reporting on the results of its DOE SBIR Phase I project for the development of a Scalable HPC Insider Threat Monitoring System. This final report to the Department of Energy for Task DE-FOA-0001618 covers the period from 02/21/2017 to 02/20/2018 and summarizes the larger research accomplishments, which can be divided in theoretical and laboratory experiments. One of the many challenges for the U.S. Department of Energy (DOE) is the support of the high-performance computing (HPC) centers while providing quality information services, strategic vision, leadership, technical expertise, and capabilities necessary to enable the DOE to deliver effective, efficient, economical, and secure HPC services. In order to realize a secure DOE laboratory enterprise, DOE facilities operations must counter a wide range of cyber insider threats, from unsophisticated adversaries up to advanced, nation state sponsored actors. The DOE laboratories also presents an enormous insider attack surface of an ever-growing number of computers, networks, and devices all running a myriad of software. In addition, the DOE laboratories are connected to a variety of external organizations which multiplies the possibility of insider threat. During this SBIR project Cyber Equations developed a strategic combination of supervised and unsupervised machine learning techniques to control scale and classify whether entities, such as hosts, actors, or documents, are showing suspicious insider behavior. We conducted experiments using real cyber data to show that changes in observable behavior (e.g., changes in outbound traffic patterns) are indicative of attacks executing (e.g., insiders exfiltrating data, bots calling home, or an attack spreading). The features and methods we use, have been used in the anomaly detection research and development community for a significant amount of time and robust implementations are openly available. K-Means clustering, Decision Trees, and Support Vector Machine based classifiers are readily available through the R language and open source H20 machine learning framework. The Cyber Equations approach is novel in its use of these classifiers combined with Hadoop based parallel processing technology. The five stages of processing used by CyberInsider improve scalability and reduce the high number of false positives normally associated with network anomaly detection. In summary, the Cyber Equations has successfully accomplished all of its Phase I tasks and demonstrated the feasibility of the Insider Threat Monitoring System.

97 MATHEMATICS AND COMPUTING↗

Improving Physics Based Electron Neutrino Appearance Identication with a Long Short-Term Memory Network

The NOvA experiment is a long baseline neutrino oscillation experiment with the objective to measure the oscillation probability of muon type neutrinos ($\nu_{\mu}$) into electron type neutrinos ($\nu_e$). NOvA measures the interactions of neutrinos from the NuMI beam in two functionally identical liquid scintillator detectors. The far detector detects the appearance of electron neutrinos, leading to measurement of the oscillation parameters under study. Using an off -axis beam with an 810 km baseline length, NOvA is sensitive to measuring the neutrino mass hierarchy, the CP violating parameter, and the octant of the mixing angle, $\theta_{23}$. The data presented in this thesis has been collected from October 2013 until May 2018. The first NOvA $\nu_e$ charged current identifier utilized an artificial neural network with the physical features of the highest energy reconstructed shower as inputs. The $\nu_ e$ charged current identifier in this thesis utilizes a Long Short-Term Memory network with the physical features of every reconstructed shower in a particular interaction. In addition to the Long Short-Term Memory network, there are two Boosted Decision Trees to assist in event level selection. In the analysis of the data, 54 $\nu_e$ candidate events were detected with an expected background of 15 events. The results of this analysis prefer the normal mass hierarchy with maximal mixing and $\frac{\delta_{CP}}{\pi}=1.92_{-1.19}^{0.08}$. Results from this analysis differ from the published NOvA analysis, due to the differences of electron identification techniques.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

Application of artificial neural network to prompt gamma neutron activation analysis for chemical warfare agents identification

The Portable Isotopic Neutron Spectroscopy (PINS) is a commercialized system developed by Idaho National Laboratory (INL) to examine chemical warfare agents (CWA) non-destructively, utilizing Prompt Gamma Neutron Activation Analysis (PGNAA) techniques. The PINS system takes advantage of a high-resolution gamma-ray spectrum from a mechanically-cooled high-purity germanium (HPGe) detector, and gamma-ray peak analysis provides input to its chemical identification logic with a probabilistic decision tree (PDT). The effectiveness of the chemical identification algorithm is determined by the availability of a wide range of data to train the algorithm to identify chemical-fills with accuracy. INL has a collection of gamma-ray spectra of various chemical-fills from the field-deployed PINS systems over the years, and it was envisaged to leverage such a database with the Artificial Neural Network (ANN) technique. Therefore, an ANN-based chemical identification algorithm was developed as an independent verification of the current algorithm. The ANN-based algorithm’s performance was evaluated against the U.S. Army blind test data, and results were presented and discussed in this study.

38 RADIATION CHEMISTRY, RADIOCHEMISTRY, AND NUCLEA↗

A Detailed Vehicle Simulation Process to Support CAFE and CO 2 Standards (MY 2021–2026 Final Rule Analysis)

In 1975, Congress passed the Energy Policy and Conservation Act (EPCA), requiring standards for corporate average fuel economy (CAFE), and charging the U.S. Department of Transportation (DOT) with the establishment and enforcement of these standards. The Secretary of Transportation has delegated these responsibilities to the National Highway Traffic Safety Administration (NHTSA). NHTSA has contracted the DOT Volpe National Transportation Systems Center (Volpe Center) to provide analytical support for NHTSA’s regulatory and analytical activities related to fuel economy standards. Unlike long-standing safety and criteria pollutant emissions standards, fuel economy standards apply to manufacturers’ overall fleets rather than to individual vehicle models. In developing the standards, NHTSA made use of the CAFE Compliance and Effects Modeling System (the “CAFE model”), which was developed by DOT’s Volpe Center for the 2005-2007 CAFE rulemaking and has been continually updated since. The model is the primary tool used by the agency to evaluate potential CAFE stringency levels by applying technologies incrementally to each manufacturer’s fleet until the requirements under consideration are met. The CAFE model relies on numerous technology-related and economic inputs such as market forecasts and technology cost and effectiveness estimates; these inputs are categorized by vehicle classification, technology synergies, phase-in rates, cost learning curve adjustments, and technology “decision trees.” The Volpe Center assists NHTSA in the development of the engineering and economic inputs to the CAFE model by analyzing the application of potential technologies to the current automotive industry vehicle fleet to determine the feasibility of future CAFE standards, the associated costs, and the benefits of the standards.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗

Optimizing Classifiers for Radionuclide Identification

Identifying threat nuclear materials is a critical for the prevention of acts of nuclear terrorism on the homeland. For this purpose, many radionuclide identification devices are deployed in the field. However, these will not necessarily be in the hands of non-experts, therefore these devices need to provide ready-made answers for the personnel in the field. This is where advanced algorithms are employed to both interpret the data and provide the identification of the nuclear material being interrogated. We took a machine learning approach to identification, by using training and validation data sets to create and optimize classifiers which determine which radionuclide is consistent with the data. The classifiers investigated were the Random Forest, Decision Tree, Support Vector Machine, and XG Boost and their performance was judged using the F1 Score for both hyperparameter tuning and comparison. In the end, we found out that the Random Forest Classifier worked the best based off the F1 Score they got which was 0.98.

45 MILITARY TECHNOLOGY, WEAPONRY, AND NATIONAL DEF↗

The Application of Machine Learning Techniques to Meteorological Forecasting

Fog and inland-penetrating sea-breezes occur often at SRS and have a strong impact on site operations. Site personnel therefore require accurate forecasts of these events, but both are difficult to forecast using traditional techniques. Our goal is to apply machine learning (ML) techniques to the problem of forecasting fog and the sea breeze at the Savannah River Site. We apply several such techniques - decision trees, regression, and a series of classification/regression techniques – and train them using the large datasets collected by our group at SRS and from external organizations that maintain databases of regional meteorological variables.

54 ENVIRONMENTAL SCIENCES↗

Low-Cost Aero Technology Demonstrations

The main focus of this work was to demonstrate the use of polymeric additive manufacturing (AM) to create tooling for both preforming and consolidation. Polymeric tooling was utilized where both modest and higher pressures are used for part consolidation. The key focus for the AM tooling development was for fabrication of complex structures such as ducting, C-channel stiffened skins, and airfoils where conventional male tooling would typically be trapped in the cured part. The AM tooling was evaluated for use as a tool master used to fabricate and re-shape deformable/re-formable mandrels based on SpinTech’s shape memory composite technology known as Smart Tooling. The AM tooling was also evaluated for use as a mold for composite infusion and consolidation. Key performance parameters were tracked for project schedule completion with each step comprising of “art to part” cycle time, cost, and model fidelity for dimensions, performance, and cost. The primary focus of this demonstration was to determine if a 50% cost reduction was achievable, for each AM tooling-set, as compared to conventional processes. UDRI leveraged project partner SpinTech, who manufactures tools and parts in these categories and thus provided a baseline regarding current best practices and provided valuable feedback during the entirety of this demonstration. This demonstration primarily focused on the use of AM tooling for fabrication of three composite component structures which are typically utilized in aircraft and comprise salient geometric features of broad interest. These components are often tooling intensive and have features requiring extraction of male tools which are usually trapped by the geometry. The three structures selected by the team included: 1) A one-piece airfoil shell comprised of compound contours where male tooling would be trapped unless the part were manufactured in two halves as is typically the case. 2) A one-piece duct used for air handling, comprised of compound contours where male tooling would be trapped unless the part were manufactured in two halves, or a washout mandrel were to be used. 3) A co-cured C-channel stiffened skin where typically C-channels would be individually manufactured and then bonded to a cured skin. The demonstration was comprised of three main tasks: • Task 1: AM Tool Feasibility Study – ensure the AM tooling meets the performance requirements as specified by SpinTech to match baseline performance. • Task 2: Complex Tool Demonstration – Fabricate tooling, preforms, and parts representative of an airfoil and duct. • Task 3: Large Aerostructure Fabrication Demonstration – Fabricate tooling, preforms, and part representative of a C-channel stiffened skin. With the conclusion of this project, a decision tree was developed to determine the key considerations necessary to determine if use of AM tooling for the three selected structures was able to attain the same quality as historically achieved on metallic tooling, while providing a significant cost reduction.

36 MATERIALS SCIENCE↗

Data Science and Machine Learning for Genome Security

This report describes research conducted to use data science and machine learning methods to distinguish targeted genome editing versus natural mutation and sequencer machine noise. Genome editing capabilities have been around for more than 20 years, and the efficiencies of these techniques has improved dramatically in the last 5+ years, notably with the rise of CRISPR-Cas technology. Whether or not a specific genome has been the target of an edit is concern for U.S. national security. The research detailed in this report provides first steps to address this concern. A large amount of data is necessary in our research, thus we invested considerable time collecting and processing it. We use an ensemble of decision tree and deep neural network machine learning methods as well as anomaly detection to detect genome edits given either whole exome or genome DNA reads. The edit detection results we obtained with our algorithms tested against samples held out during training of our methods are significantly better than random guessing, achieving high F1 and recall scores as well as with precision overall.

59 BASIC BIOLOGICAL SCIENCES↗

Improving Solar and Solar+Storage Screening Techniques to Reduce Utility Interconnection Time and Costs (Final Technical Report)

Residential PV installations have increased rapidly over the last decade, and the increased application volume has caused permitting delays and lower overall adoption rates. In this project, we developed and evaluated whether data-driven secondary modeling and screening techniques can help utilities assess customer applications more accurately than traditional screening shortcuts. Secondary topologies are predicted using decision trees and commonly available information, such as service transformer, customer, and street locations. Conductors were predicted using a logistic regression method based on real world object (RWO) types, service transformer ratings, conductor length, and distance to transformer. After developing the combined primary and secondary distribution network model, hosting capacity results were used to train a random forest model to predict the pass/fail likelihood of a customer application. Powerflow based models with predicted secondaries and data-driven methods both increased the screening success rate, relative to common utility heuristics, by as much as 55 percentage points. Data-driven screening techniques were described by one utility as a "right-sized" approach for residential customers given the low-risk of small errors and the high-cost of accurate modeling.

14 SOLAR ENERGY↗

Automated System-wide Event Detection and Classification Using Machine Learning on Synchrophasor Data

As the number of phasor measurement units (PMUs) deployed in a power system increases, and their data volume streamed to the control canter intensifies, operators are facing challenges related to the analysis of such data, which need to be observed and responded to as the measurements are displayed in the Control Room. Humans are generally unable to process such large amount of data efficiently and rapidly. There is an apparent need for automated ways to analyze the data, extract actionable information about occurrence of specific events, and characterize the events quickly and cost effectively. This paper discusses the use of machine learning (ML) to facilitate such tasks by providing automated, highly computationally efficient, and cost-effective ways of extracting actionable information from synchrophasor big data in real-time. We developed Big Data Smart (BDSmart) ML-based prototype tool for the Control Room use that automatically analyses data properties from synchrophasor system measurements taken across the three grid Interconnections in the USA (Western, Eastern and ERCOT). The data collected from several hundreds of PMUs located across the Interconnections over a period of two years have been made available for our extensive study. As a result, we were able to identify a number of big data properties that influence how ML methodology is applied to select, develop, train and test the data models that can eventually be used for the tool implementation. The resulting set of candidate algorithms spans unsupervised, supervised, semi-supervised and transfer-learning approaches. Many ML techniques, such as decision trees, multinomial logistic regression, feed-forward neural networks, K-nearest neighbor, multiclass support vector machine, and single and multi-channel convolutional neural networks, are implemented, and their performance is examined. We offer the results from testing the data models. The novelty of our study is in the approaches for bad data detection and mitigation, selection of a simplified feature for event detection, and data label improvements. As a result, we came up with a list of recommendations for the utilities on how to improve the PMU recording practices to cater to the future ML applications aimed at automating the analysis of synchrophasor data.

Synchrophasors, Machine Learning, System-wide Even↗

Turbulence Modeling with Nek5000/RS, SOD2D and Alya

We present Validation and Verification (V & V) study of two high-order spectral element method (SEM) based Computational Fluid Dyanimcs (CFD) codes that we will utilize for work on turbulence modeling: Nek5000 and SOD2D. While the former solves the incompressible form of Navier-Stokes equation, the latter works with compressible set of equations and uses an entropy-viscosity formulation to account for the discontinuities for high Mach number flows. We demonstrate the accuracy of these codes for two benchmark sub-sonic turbulent flows: periodic channel and pipe flow, by carrying out first and second order statistical analysis, grid convergence and turbulent structure analysis using wall-resolved large eddy simulations (WRLES). Later, we report on the implementation and testing of various wall-modeling strategies for large eddy simulation of turbulent flows in Nek5000. These include both classical log-law based and decision-tree based machine-learning models. Accuracy of these closure strategies are analyzed and necessary future work is outlined.

97 MATHEMATICS AND COMPUTING↗

SULI Peer Review

Daniel Xing is a SULI intern whose project was titled: “An Improved Boosted Decision Tree Framework for Event Classification MicroBooNE” This is a physical subject that helps us understand how we can better model neutrinos. I do not study neutrinos, so listening to this talk was very formal.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

Track vs Shower Discrimination in the Event Reconstruction of the ICARUS Experiment

The ICARUS collaboration has employed the 760-ton T600 liquid argon TPC detector in a successful three-year physics run at the underground LNGS laboratory, performing a sensitive search for LSND-like anomalous appearance in the CERN Neutrino to Gran Sasso beam, which contributed to the constraints on the allowed neutrino oscillation parameters to a narrow region around 1 eV. After a significant overhaul at CERN, the T600 detector has been installed at Fermilab. The detector commissioning phase lasted until June 2022, then ICARUS moved to data taking for neutrino oscillation physics collecting events from the Booster Neutrino Beam (BNB) and the Neutrinos at the Main Injector (NuMI) beam off-axis. The initial experiment goals are to either confirm or refute the claim by Neutrino-4 short-baseline reactor experiment, perform measurements of neutrino cross sections with the NuMI beam and several Beyond Standard Model searches. Then, ICARUS will jointly search for evidence of sterile neutrinos with the Short-Baseline Near Detector (SBND). In this contribution, we discuss recent changes to the standard TPC event reconstruction that uses Pandora, a pattern recognition software common to liquid argon-based detectors. In particular, we performed a new training of the Boosted Decision Tree (BDT) employed to separate track-like and shower-like reconstructed particles using Monte Carlo simulations of neutrino events from BNB in ICARUS. We compare the discrimination capabilities of the old and new BDT training and discuss further improvements of this algorithm.

43 PARTICLE ACCELERATORS↗

Progress Toward the First Search for Bound Neutron Oscillation into Antineutron in a Liquid Argon TPC

This note presents current progress for a neutron-antineutron oscillation ($n–\overline{n}$) search in MicroBooNE paving the way for the first search analysis of such process in a Liquid Argon Time Projection Chamber (LArTPC). Convolutional Neural Network (CNN) and Boosted Decision Tree (BDT) algorithms were used to select signal $n–\overline{n}$ events over cosmogenic backgrounds. The CNN-only, BDT-only, and the combined (CNN+BDT) methods were demonstrated on the Monte-Carlo signal and background events. Validation of the CNNonly and the BDT-only methods was carried out on a small dataset of MicroBooNE Run1 off-beam data, setting the starting point toward further improvement of the analysis.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

Sensitivity of the MicroBooNE experiment to dark trident interactions

This note describes an ongoing search for dark tridents in the MicroBooNE detector. The dark trident interaction is a proposed interaction of sub-GeV dark matter with ordinary matter that would allow an exploration of a hidden dark sector composed of a dark scalar or fermion χ and a dark photon A'. This dark matter candidate can be produced at fixed-target neutrino beams such as the NuMI beam and travel uninterrupted to the MicroBooNE liquid argon detector. The interaction with the liquid argon occurs through the process χ + Ar → χ + Ar + A' where the dark photon promptly decays inside the detector through: A' → e + + e - . Two event selection strategies are explored, one using boosted decision trees and the other one applying a convolutional neural network. For both analyses a projected sensitivity in MicroBooNE after 2 × 10 21 protons on target is presented.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

Logical Approach to Tritium Vacuum Pump Selection

Introduction Vacuum pumps are essential to the operation of tritium purification and recovery processes. However, not all vacuum pumps sold meet the requirements for tritium service. Manufacturers routinely do not fully appreciate the hazards associated with tritium, or the complex materials interactions. Therefore, a decision tree was established detailing which pump types, and certain manufacturers, are either fully compatible, limited use, or to avoid at all costs to establish a more structured and uniform approach to tritium vacuum pumps.

ANGELETTE, LUCAS↗

Geometric Measures of Trustworthiness for Machine Learning Predictions

his report details the findings from the research and investigation of Geometric Measures of Trustworthiness for Machine Learning Predictions. We explored the trustworthiness of machine learning (ML) models’ predictions using geometric measures to quantify the similarity of a query point with the training data. Predictive uncertainty in ML can originate from at least three sources: (1) Model uncertainty, which represents the uncertainty in model form (e.g. decision tree, vs neural network) and estimating the model parameters from the training data, (2) Data uncertainty, which represents the natural complexities of the data such as class overlap and inherent noise, and (3) Distributional uncertainty, which represents the mismatch between the training and operational distributions. The proposed measures focus on measuring and explaining the data and distributional uncertainties by measuring the relationships of operational data with the training data.

97 MATHEMATICS AND COMPUTING↗

Operational Forecasting of Induced Seismicity (CRADA Final Report)

This was a collaborative effort between Lawrence Livermore National Security, LLC ("LLNS"), as manager and operator of Lawrence Livermore National Laboratory ("LLNL"), The Regents of the University of California, as manager and operator of Lawrence Berkeley National Laboratory (Collectively, Contractors) and Nanometrics, Inc. ("Participant"), to develop a toolkit called "Operational Forecasting of Induced Seismicity (ORION)" that includes a decision tree method for operational forecasting of induced seismicity rates related to fluid disposal operations.

58 GEOSCIENCES↗