SEARCH · Engineering Papers

Results for “data quality metrics”

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 217 records · Page 12

All sources NASA NTRS DOE OSTI

DOE OSTI2021

Real-Time Health Monitoring for Gas Turbine Components Using Online Learning and High-Dimensional Data

Capital-intensive turbomachinery, such as gas turbines and combined cycle plants, are constantly being monitored for performance anomalies, faults, and physical degradation. Although these power-generating assets are equipped with hundreds of sensors, existing monitoring tools can only handle moderate-sized data. As a result, only a handful of aggregate metrics are used to monitor machine health. At the same time, developing advanced tools suitable for large datasets have been restricted by the lack of appropriate data. The objective of this proposal was to demonstrate a Big Data analytics framework for fault detection and diagnosis in gas turbine applications. We develop a predictive analytics framework methodology guided by these experimental data, industrial data from our collaborators, and physics-based models with engineering domain knowledge. Our analytics framework consists of four key components (1) a data curation process that addresses data storage, data quality assessments, and integrity checks, (2) a feature engineering component that utilizes statistical methods and transformation algorithms guided by physics-based models to extract high-fidelity fault features that can be leveraged for fault detection and classifying fault severities, (3) a Machine Learning-based fault detection and diagnostics algorithms for detecting operational and hardware faults in the combustion and the turbines section. We utilize two industry-class gas turbine component test rigs to generate first of its kind data for critical gas turbine faults with varying severity levels. Advanced gas turbine test facilities will be interrogated using state-of-the-art instrumentation techniques to build fault signatures and data trends for key combustor and turbine faults. Data generated from a combustor test rig (Georgia Tech) and a turbine test rig (Penn State) during both normal operation and with seeded faults serve as the basis for the Big Data sets. The test conditions in the two test facilities include common, critical events that occur in the operation. Utilizing the combustor test rig, we examine two common combustor faults: lean blowout and centerbody degradation. For the turbine section we develop analytic models for monitoring cooling faults in the gas turbine

03 NATURAL GAS↗

DOE OSTI2021

Real-Time Health Monitoring for Gas Turbine Components Using Online Learning and High-Dimensional Data (Final Report)

Capital-intensive turbomachinery, such as gas turbines and combined cycle plants, are constantly being monitored for performance anomalies, faults, and physical degradation. Although these power-generating assets are equipped with hundreds of sensors, existing monitoring tools can only handle moderate-sized data. As a result, only a handful of aggregate metrics are used to monitor machine health. At the same time, developing advanced tools suitable for large datasets have been restricted by the lack of appropriate data. The objective of this proposal was to demonstrate a Big Data analytics framework for fault detection and diagnosis in gas turbine applications. We develop a predictive analytics framework methodology guided by these experimental data, industrial data from our collaborators, and physics-based models with engineering domain knowledge. Our analytics framework consists of four key components: (1) a data curation process that addresses data storage, data quality assessments, and integrity checks, (2) a feature engineering component that utilizes statistical methods and transformation algorithms guided by physics-based models to extract high-fidelity fault features that can be leveraged for fault detection and classifying fault severities, (3) a Machine Learning-based fault detection and diagnostics algorithms for detecting operational and hardware faults in the combustion and the turbines section. We utilize two industry-class gas turbine component test rigs to generate first of its kind data for critical gas turbine faults with varying severity levels. Advanced gas turbine test facilities will be interrogated using state-of-the-art instrumentation techniques to build fault signatures and data trends for key combustor and turbine faults. Data generated from a combustor test rig (Georgia Tech) and a turbine test rig (Penn State) during both normal operation and with seeded faults serve as the basis for the Big Data sets. The test conditions in the two test facilities include common, critical events that occur in the operation. Utilizing the combustor test rig, we examine two common combustor faults: lean blowout and centerbody degradation. For the turbine section we develop analytic models for monitoring cooling faults in the gas turbine.

20 FOSSIL-FUELED POWER PLANTS↗

DOE OSTI2023

Interannual variability and trends of summertime PM2.5-based air quality in the Intermountain West

Abstract Summertime air quality is a growing public health concern in the populated region of Northern Utah. Whereas winter air pollution is highly linked with local atmospheric temperature inversions associated with upper atmospheric high-pressure and radiational cooling in valleys, the relationship between climate factors and the frequency of poor air quality during summer is still unknown. Analyzing the last 20 years of data, we demonstrated that summertime unhealthy days (as defined by PM2.5 air quality index level) in Northern Utah highly correlate with the number of dry-hot days, wildfire size, and an upper atmospheric ridge over the Northwestern United States. The persistent atmospheric ridge enhances lightning-caused fire burned areas in northwestern states and then transports the wildfire smoke toward Northern Utah. Similarly, climate model simulations confirm observational findings, such as an increasing trend of the upper atmospheric ridge and summertime dry days in the northwestern states. Such metrics developed in this study could be used to establish longer-term monitoring and seasonal forecasting for air quality and its compounding factors, which is currently limited to forecasting products for only several days.

54 ENVIRONMENTAL SCIENCES↗

DOE OSTI2025

Co-Firing Switchgrass and Waste Coal in A Power Plant: A Techno-Economic and Life Cycle Evaluation for The Ohio River Valley (SWITCH) (Final Technical Report for Ohio State/FE0032204)

Abandoned coal mine lands (AMLs) represent one of the most persistent environmental challenges in the United States. Prior to the enactment of the Surface Mining Control and Reclamation Act (SMCRA) in 1977, coal mining operations were not legally required to reclaim disturbed lands, leaving behind approximately 500,000 AML sites nationwide. These sites pose severe environmental and health risks, including acid mine drainage, soil and water contamination, and spontaneous combustion of waste coal piles. Millions of Americans live within one mile of these AMLs, underscoring the urgency of remediation. Traditional reclamation practices, such as planting cool-season grasses, often fail to fully restore ecological function or leverage the economic potential of these lands. This project addressed these challenges by developing integrated strategies for resource recovery, land reclamation, and sustainable energy production. This project evaluated an integrated strategy to convert this liability into an opportunity by recovering waste coal and co-firing it with switchgrass (Panicum virgatum L.) cultivated on reclaimed or marginal AML areas in existing coal-fired power plants. Switchgrass not only provides a renewable feedstock but also aids in land reclamation and carbon sequestration. 1) Remote Sensing and Machine Learning for Waste Coal Identification Using Sentinel-2 satellite imagery and supervised classification, we applied four machine learning models to detect historical waste coal piles. Random Forest achieved the highest accuracy (precision: 86%, recall: 77%). Time-series analysis revealed gradual vegetation recovery since 1986, indicating natural reclamation processes in historical sites, while active mining areas showed ongoing disturbance. This workflow enables scalable monitoring and prioritization of reclamation efforts. 2) UAS-Based Stockpile Volume Estimation To quantify recoverable waste coal, we evaluated Unmanned Aerial Systems (UAS) equipped with Light Detection and Ranging (LiDAR) and multispectral sensors. Structure-from-Motion (SfM) photogrammetry combined with interpolated Digital Terrain Models (DTMs) achieved strong agreement with LiDAR reference volumes (Root Mean Square Error (RMSE) ≈147 m 3 , Mean Absolute Percentage Error (MAPE) ≈2%). Sensitivity analysis confirmed that spatial resolution significantly influences accuracy, emphasizing the need for high-resolution data for precise volume estimation. This approach offers a scalable, cost-effective, and accurate alternative to conventional ground-based surveys. 3) Switchgrass Cultivation for Bioenergy and Water Quality Improvement We assessed the hydrological and water quality impacts of converting AMLs to switchgrass production areas using the Soil and Water Assessment Tool (SWAT). Results showed that converting 10% of the watershed area into the switchgrass production zone reduced streamflow by 3.1%, total suspended solids by 18.1%, total nitrogen by 7.6%, and total phosphorus by 6.2%, while achieving biomass yields of 8.6–9.2 metric tons per hectare. These findings highlight switchgrass as a dual-benefit strategy for land reclamation and bioenergy feedstock production. 4) Integrated Co-Firing and CCS for Carbon-Negative Power Generation We modeled co-firing scenarios using the Power Plant Flexible Model (PPFM) to evaluate plant efficiency, greenhouse gas (GHG) emissions, and levelized cost of electricity (LCOE). Without carbon capture and storage (CCS), increasing switchgrass co-firing ratios reduced LCOE from $\$$150/MWh at 0% biomass to $\$$110/MWh at full substitution. Under CCS, costs remained higher (~$\$$250/MWh at 0% biomass) but decreased to $\$$200/MWh at 100% biomass, while enabling net-zero or carbon-negative electricity due to switchgrass sequestration benefits. Although CCS introduced efficiency penalties, pairing it with biomass co-firing offset these impacts and maximized climate benefits. Overall, optimizing co-firing ratios between 60-100%, supported by reliable logistics and storage strategies, emerged as a practical pathway to balance affordability, sustainability, and net-zero or negative GHG emissions while promoting productive reuse of AMLs.

01 COAL, LIGNITE, AND PEAT↗

DOE OSTI2023

Failure Modes and Effects Analysis of Biorefinery Pathways

This talk provides an overview of failure modes and effects analysis (FMEA) development and implementation as a systematic criticality and risk assessment tool for biorefinery pathways within the FCIC. This supports a quality by design (QbD) approach, and this talk provides a high-level overview of the results for the FMEA evaluation focused on the generation of pine residue materials for high-temperature pyrolysis conversion. the FMEA interviews included two approaches. The first approach was based around the entire system of unit operations giving a wholistic system level view. The second approach used detailed interviews from individual unit operation within the system allowing for specific failures for individual system components. These two approaches provide different resolutions of information about the reliability and risk. The FMEA results focused on failures associated with meeting critical quality attributes (CQAs) identified for the high temperature conversion of loblolly pine residues and were supplemented with experimental data supporting process upsets and reliability also collected within the consortium. Estimations of risk scores for meeting each given CQA specification, identification of the impacts for not meeting a CQA specification, capturing causes associated with material attributes and process parameters for each failure, identification of current detection methods, and speculation of potential mitigation strategies for decreasing a failure’s risk score were gathered through the FMEA interviews, and were combined to understand the overall process risk metrics and where technology, process, and knowledge improvements are needed in order to de-risk emerging biorefineries.

09 BIOMASS FUELS↗

DOE OSTI2019

Measuring Fundamental Improvements in Sustainable Urban Mobility: The Mobility-Energy Productivity Metric

Recent technological advancements in mobility are creating many options for connecting citizens with employment, goods, and services, particularly in urban areas where modes such as bike and car shares, electric scooters, ridesourcing, and ridesharing are proliferating at a rapid pace. Analysis and tools for overall transportation planning are dominated by urban regional travel demand models whose roots in highway operations poorly reflect the system dynamics in denser areas where parking costs, convenience, and availability - not to mention sustainability concerns and quality of life - are driving people to an ever-greater spectrum of mobility services. In this paper, we present a new paradigm for evaluating mobility options within an urban area. First developed for the U.S. Department of Energy's Energy Efficient Mobility System research program, this metric is termed the mobility-energy productivity (MEP) metric. At its heart, the MEP metric measures accessibility and appropriately weights it with travel time, cost, and energy of modes that provide access to opportunities in any given location. The proposed metric is versatile in that it can be computed from readily available data sources or derived from outputs of regional travel demand models. End times associated with parking, curb access, cost, and reliability and frequency of service need to be carefully considered to obtain an appropriate and accurate perspective when computing the metric. Ultimately, the MEP metric can be used to reflect the impacts of new mobility technologies (transportation network companies, electric scooters), business models (car shares and bike shares), and land-use practices (such as transit-oriented development) on sustainable urban mobility. This paper lays out the need, requirements, and framework for this new metric, and offers it, in collaboration with the American Society for Civil Engineers (ASCE), as a foundational metric for smart city assessment.

30 DIRECT ENERGY CONVERSION↗

DOE OSTI2019

Measuring Fundamental Improvements in Sustainable Urban Mobility: The Mobility-Energy Productivity Metric: Preprint

Recent technological advancements in mobility are creating many options for connecting citizens with employment, goods, and services, particularly in urban areas where modes such as bike and car shares, electric scooters, ridesourcing, and ridesharing are proliferating at a rapid pace. Analysis and tools for overall transportation planning are dominated by urban regional travel demand models whose roots in highway operations poorly reflect the system dynamics in denser areas where parking costs, convenience, and availability - not to mention sustainability concerns and quality of life - are driving people to an ever-greater spectrum of mobility services. In this paper, we present a new paradigm for evaluating mobility options within an urban area. First developed for the U.S. Department of Energy's Energy Efficient Mobility System research program, this metric is termed the Mobility-Energy Productivity (MEP) metric. At its heart, the MEP metric measures accessibility and appropriately weights it with travel time, cost, and energy of modes that provide access to opportunities in any given location. The proposed metric is versatile in that it can be computed from readily available data sources or derived from outputs of regional travel demand models. End times associated with parking, curb access, cost, and reliability and frequency of service need to be carefully considered to obtain an appropriate and accurate perspective when computing the metric. Ultimately, the MEP metric can be used to reflect the impacts of new mobility technologies (transportation network companies, electric scooters), business models (car shares and bike shares), and land-use practices (such as transit-oriented development) on sustainable urban mobility. This paper lays out the need, requirements, and framework for this new metric, and offers it, in collaboration with the American Society for Civil Engineers (ASCE), as a foundational metric for Smart City assessment.

30 DIRECT ENERGY CONVERSION↗

DOE OSTI2023

Role of social structure in establishment of an invasive large mammal after translocation

Abstract Background Data on the movement behavior of translocated wild pigs is needed to develop appropriate response strategies for containing and eliminating new source populations following translocation events. We conducted experimental trials to compare the home range establishment and space‐use metrics, including the number of days and distance traveled before becoming range residents, for wild pigs translocated with their social group and individually. Results We found wild pigs translocated with their social group made less extensive movements away from the release location and established a stable home range ~5 days faster than those translocated individually. We also examined how habitat quality impacted the home range sizes of translocated wild pigs and found wild pigs maintained larger ranges in areas with higher proportion of low‐quality habitat. Conclusion Collectively, our findings suggest translocations of invasive wild pigs have a greater probability of establishing a viable population near the release site when habitat quality is high and when released with members of their social unit compared to individuals moved independent of their social group or to low‐quality habitat. However, all wild pigs translocated in our study made extensive movements from their release location, highlighting the potential for single translocation events of either individuals or groups to have far‐reaching consequences within a much broader landscape beyond the location where they are released. These results highlight the challenges associated with containing populations in areas where illegal introduction of wild pigs occurs, and the need for rapid response once releases are identified. © 2023 The Authors. Pest Management Science published by John Wiley & Sons Ltd on behalf of Society of Chemical Industry.

Clontz, Lindsay M.↗

DOE OSTI2022

Generating Novel Aroma Phenotypes Using Commercial Wine Samples to Characterize an F1 Population

Due to their disease tolerance and cold hardy nature, interspecific hybrid grapes are widely grown in the Midwestern and Northeastern United States, with additional interest worldwide in the face of increased abiotic and biotic stresses from climate change. However, the aroma profile of these hybrids is unique and generally less popular in comparison with Vitis vinifera grapes. One of the challenges in any phenotyping project is first defining the traits of interest. As wine quality was our ultimate metric of interest, the aroma profile of commercial wines produced from the parents of a breeding population ( Vitis aestivalis derived ‘Norton’ x V. vinifera . ‘Cabernet Sauvignon’) was first assessed for traits of interest. We investigated 11 commercial wines each of Norton, a popular hybrid in Missouri and Cabernet Sauvignon (Cab) for their volatile profiles using the more inclusive metabolomics-based workflow. We then analyzed 21 Norton and 21 Cab grapes from different sites and vintages for the free and bound volatile compounds using HS-SPME-GCMS to validate the differences in wine. The GCMS data was processed using XCMS software to find features that were different between the two cultivars. The two cultivars were found to have differences in their volatile profiles, with 304 features different for wine volatiles, 418 features different for free volatiles, and 302 features different for bound volatiles at 0.05 significance level and with at least a 1.5-fold change between the two cultivars. Those features were used to identify several odor-active compounds in both grapes and wines, including β-damascenone, β-ionone, eugenol, 1,1,6-trimethyl-1,2-dihydronaphthalene (TDN), and methyl salicylate. Some of the identified compounds were higher in Norton than Cab; however, several features were higher in Cab. Using the identified aroma compounds as markers, we phenotyped an F1 population of Norton and Cab. The F1 population was found to be segregating for many aroma compounds with some genotypes demonstrating an even higher concentration of aroma volatiles than either of the parents. Ultimately, using commercially available samples paired with untargeted analysis proved to be an efficient way to determine phenotypes of interest for further analysis and may offer an easy way to choose potential parents with desired traits for breeding.

59 BASIC BIOLOGICAL SCIENCES↗

DOE OSTI2026

Employment access assessed using the mobility energy productivity (MEP) metric

Transit agencies, local governments, employers, and job-seekers have a shared interest in connecting residents with jobs in an affordable and time efficient manner, with public agencies also caring about energy efficiency and air quality. Employment hubs are an opportunity to solve the spatial mismatch between homes of job-seekers and the locations of desirable jobs. Such is the case in Columbus, Ohio, between Rickenbacker Industrial Park and the Linden neighborhood, which has experienced persistent poverty. Using the mobility energy productivity (MEP) metric to examine travel time, cost, and energy efficiency, we show current transit service is undesirable due to excessive travel time (70 min, MEP = 0), while driving alone (MEP = 0.20) may be less desirable than a hypothetical, fare-free microtransit service (MEP = 0.23). Updating MEP to use locally-derived input data can help identify parameters under which providing microtransit service in a specific place has compelling benefits in terms of vehicle energy efficiency as well as cost and travel time for riders.

29 ENERGY PLANNING, POLICY, AND ECONOMY↗

DOE OSTI2025

Automated Segmentation of Twin Boundaries in TRISO Silicon Carbide Using Deep Neural Networks

Coated particle fuels, such as the tristructural isotropic (TRISO) fuel particle, are essential for high-temperature gas reactor (HTGR) applications due to their efficiency and stability under normal and off-normal conditions. However, widespread commercialization and deployment of this technology for next-generation nuclear applications require robust quality assurance and quality control (QA/QC) methods linking fabrication, properties, and performance. Of the many important metrics for TRISO QA/QC, quantification of the silicon carbide (SiC) microstructure is critical because it correlates with fission product retention during irradiation. Previous work has shown extensive twinning of the SiC microstructure, which strongly affects microstructural metrics; however, twin grain boundaries are not expected play a significant role in fission product diffusion. This report summarizes the initial development, training, and testing of a machine learning image processing algorithm to detect twin grain boundaries in a backscattered electron image, which can be removed so that microstructural metrics can be recalculated for legacy data. Further development and deployment of this model will provide automated, scalable improvement of potential QA/QC methods for the SiC layer of TRISO particles.

11 NUCLEAR FUEL CYCLE AND FUEL MATERIALS↗

DOE OSTI2026

A User-Friendly GUI Tool for Automated Microstructural Analysis of Fiber-Reinforced Composites and Porous Structures

Understanding and quantifying microstructural features such as fiber orientation and porosity is critical for predicting the mechanical behavior and performance of fiber-reinforced polymer composites. Traditional manual analysis is time-consuming, subjective, and unsuitable for high-throughput datasets. We present a graphical user interface (GUI) application that automates the analysis of microscopy images to extract key microstructural metrics, including fiber orientation tensors, fiber orientation distribution, porosity and pore size distribution. The app integrates multiple image segmentation techniques including global and local thresholding, clustering, and region-based approaches, offering flexibility for different types of image qualities and features. Users can load microstructural images, select regions of interest and segmentation techniques tailored to their image dataset. It also addresses a critical challenge in fiber orientation analysis: the ambiguities caused by touching, overlapping, or partially cut fibers. It supports autorun examples for standardized workflows, enabling reproducible analysis and facilitating training and benchmarking. This tool significantly reduces manual intervention, enhances consistency, and accelerates data generation for structure–property modeling, process optimization, and digital materials research. The tool is intended for use by materials scientists, engineers, and researchers engaged in composite characterization, quality control, and machine learning-based microstructural studies.

Chawla, Komal [ORNL] (ORCID:0000000190327565)↗

DOE OSTI2019

Dark Energy Survey’s Observation Strategy, Tactics, and Exposure Scheduler

The Dark Energy Survey is a “stage III” dark energy experiment, performing an optical imaging survey to measure cosmological equation of state parameters using four independent methods. The scope and complexity of the survey, originally scheduled for 525 nights of observing spread over five years and combining a 5000 degree wide survey with a 10 field weekly time-domain survey, introduced complex strategic and tactical scheduling problems that needed to be addressed. We begin with an overview of the process used to develop DES strategy and tactics, from the inception of the project, to task forces that studied and developed strategy changes over the course of the survey, to the nightly pre-observing meeting in which immediate tactical issues were addressed. We then summarize the strategic choices made for each sub-survey, including metrics, scheduling considerations, choice of time domain fields and their sequences of exposures, and wide survey footprint and pointing layout choices. We go on to describe the detailed process that determined which specific exposures were taken at which specific times. We give a chronology of the strategic and tactical peculiarities of each year of observing, including the proposal and execution of a sixth year. We give an overview of obstac, the implementation of the DES scheduler used to simulate and evaluate strategic and tactical options, and automate exposure scheduling; and describe developments in obstac for use after DES. Appendices describe further details of data quality evaluation, t, and teff; airmass calculation; and modeling of the seeing and sky brightness. The significant corpus of DES data indicates that the simple scaling relations for seeing as a function of wavelength and airmass derived from the Kolmogorov turbulence model work adequately for exposure planning purposes: deviations from these relations are modest in comparison with short time-scale seeing variations.

79 ASTRONOMY AND ASTROPHYSICS↗

DOE OSTI2026

The Double-edged Sword of Data-driven Super-Resolution: Adversarial Super-resolution Models

Data-driven super-resolution (SR) methods are often integrated into imaging pipelines as preprocessing steps to improve downstream tasks such as classification and detection. However, these SR models introduce a previously unexplored attack surface into imaging pipelines. In this paper, we present AdvSR, a framework demonstrating that adversarial behavior can be embedded directly into SR model weights during training, requiring no access to inputs at inference time. Unlike prior attacks that perturb inputs or rely on backdoor triggers, AdvSR operates entirely at the model level. By jointly optimizing for reconstruction quality and targeted adversarial outcomes, AdvSR produces models that appear benign under standard image quality metrics while inducing downstream misclassification. We evaluate AdvSR on three SR architectures (SRCNN, EDSR, SwinIR) paired with a YOLOv11 classifier and demonstrate that AdvSR models can achieve high attack success rates with minimal quality degradation. These findings highlight a new model-level threat for imaging pipelines, with implications for how practitioners source and validate models in safety-critical applications.

Sullivan, Haley [ORNL] (ORCID:0000000274069217)↗

DOE OSTI2021

Evaluation of Time-Series Gap-Filling Methods for Solar Irradiance Applications

A complete solar resource data set is essential for any stage of a solar energy project - from feasibility studies to daily operations. But measured or modeled solar resource data are prone to data gaps and data quality issues. To mitigate these issues, a data imputation process should be implemented to obtain a complete and reliable temporal and spatial data series. This study focused on imputing temporal scales by applying random and artificial data gaps and then implementing eight imputation methods, including the Kalman filtering and smoothing and stine interpolations. These methods were implemented on 1-minute to half hourly irradiance data for 1 year using a few locations from the National Solar Radiation Database (NSRDB) and ground measurement data set. The results demonstrated that some of the simpler methods, such as the stine and linear interpolation methods, were the relatively best models based on the statistical metrics for imputing NSRDB and ground measurement data, respectively.

14 SOLAR ENERGY↗

DOE OSTI2026

Energy Systems Integration Facility Stewardship Summary: Fiscal Year 2025

A summary of NLR's stewardship of the nationally unique Energy Systems Integration Facility (ESIF) highlighting performance metrics, capability upgrades, and examples of R&D impact. 2025 brought a national focus on energy and ESIF is meeting the moment. All eyes are on data centers and domestic manufacturing and bringing the benefits of artificial intelligence to power system planning and operations. In step with national priorities, ESIF is building out capabilities that advance secure, reliable, and affordable power. ESIF hosted 190 multidisciplinary research projects, 855 high-performance computer users, and collaborated with 81 partners from industry, academia, research, and federal agencies. These research projects resulted in an AI method for detecting high-impedance faults with 90% accuracy, a grid controls demonstration in Connecticut, power quality validation of CorePower's flagship inductor, and a cybersecurity assessment of potential rogue capabilities in digitally connected energy devices. Facility infrastructure improvements enhanced the thermal research network, the SCADA system, the cyber range, power hardware-in-the-loop testing, and more. With support from the U.S Department of Energy (DOE), the ESIF laboratories continue to deliver leading solutions for secure, reliable, and affordable power.

24 POWER TRANSMISSION AND DISTRIBUTION↗

DOE OSTI2020

Neural networks for modeling and control of particle accelerators

Charged particle accelerators support a wide variety of scientific, industrial, and medical applications. They range in scale and complexity from systems with just a few components for beam acceleration and manipulation, to large scientific user facilities that span many kilometers and have hundreds-to-thousands of individually-controllable components. Specific operational requirements must be met by adjusting the many controllable variables of the accelerator. Meeting these requirements can be challenging, both in terms of the ability to achieve specific beam quality metrics in a reliable fashion and in terms of the time needed to set up and maintain the optimal operating conditions. One avenue toward addressing this challenge is to incorporate techniques from the fields of machine learning (ML) and artificial intelligence (AI) into the way particle accelerators are modeled and controlled. While many promising approaches within AI/ML could be used for particle accelerators, this dissertation focuses on approaches based on neural networks. Neural networks are particularly well-suited to modeling, control, and diagnostic analysis of nonlinear systems, as well as systems with large parameter spaces. They are also very appealing for their ability to process high-dimensional data types, such as images and time series (both of which are ubiquitous in particle accelerators). In this work, key studies that demonstrated the potential utility of modern neural network-based approaches to modeling and control of particle accelerators are presented. The context for this work is important: at the start of this work in 2012, there was little interest in AI/ML in the particle accelerator community, and many of the advances in neural networks and deep learning that enabled its present success had not yet been made at that time. As such, this work was both an exploration of possible application areas and a generator of proof-of-concept demonstrations in these areas.

43 PARTICLE ACCELERATORS↗

DOE OSTI2021

Optimal dimensionality selection for independent component analysis of transcriptomic data

Independent component analysis is an unsupervised machine learning algorithm that separates a set of mixed signals into a set of statistically independent source signals. Applied to high-quality gene expression datasets, independent component analysis effectively reveals both the source signals of the transcriptome as co-regulated gene sets, and the activity levels of the underlying regulators across diverse experimental conditions. Two major variables that affect the final gene sets are the diversity of the expression profiles contained in the underlying data, and the user-defined number of independent components, or dimensionality, to compute. Availability of high-quality transcriptomic datasets has grown exponentially as high-throughput technologies have advanced; however, optimal dimensionality selection remains an open question. We computed independent components across a range of dimensionalities for four gene expression datasets with varying dimensions (both in terms of number of genes and number of samples). We computed the correlation between independent components across different dimensionalities to understand how the overall structure evolves as the number of user-defined components increases. We then measured how well the resulting gene clusters reflected known regulatory mechanisms, and developed a set of metrics to assess the accuracy of the decomposition at a given dimension. We found that over-decomposition results in many independent components dominated by a single gene, whereas under-decomposition results in independent components that poorly capture the known regulatory structure. From these results, we developed a new method, called OptICA, for finding the optimal dimensionality that controls for both over- and under-decomposition. Specifically, OptICA selects the highest dimension that produces a low number of components that are dominated by a single gene. We show that OptICA outperforms two previously proposed methods for selecting the number of independent components across four transcriptomic databases of varying sizes. OptICA avoids both over-decomposition and under-decomposition of transcriptomic datasets resulting in the best representation of the organism’s underlying transcriptional regulatory network.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗