SEARCH · Engineering Papers

Results for “training data quality”

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 OSTI2022

Deep-learning-guided high-resolution subsurface reflectivity imaging with application to ground-penetrating radar data

Subsurface reflectivity imaging is one of the most important geophysical characterization methods for revealing subsurface structures. In many cases, accurate subsurface reflectivity imaging is challenging because of, for example, random or coherent noise in the data and sparse source-receiver observation geometry. Here, we develop a deep-learning-guided iterative imaging method to improve subsurface structure imaging. Specifically, we train a supervised neural network to infer a noise-free, high-resolution image from a noisy, low-resolution image and use this estimated image as guidance to regularize least-squares imaging. We develop a systematic method to generate high-quality synthetic training data (data-label pairs) to train the guidance neural network. The trained neural network can provide high-fidelity predictions even for field-data images that are not in the training data. We validate our new imaging method using one synthetic and two field ground-penetrating radar data examples, and find that our method can produce clean, high-resolution subsurface reflectivity images where existing single-pass and least-squares imaging methods fail due to noise and insufficient data coverage.

58 GEOSCIENCES↗

DOE OSTI2025

Seismicity-constrained fault detection and characterization with a multitask machine learning model

Geological fault detection and characterization are crucial for understanding subsurface dynamics across scales. While methods for fault delineation based on either seismicity location analysis or seismic image reflector discontinuity are well-established, a systematic approach that integrates both data types remains absent. We develop a novel machine learning model that unifies seismic reflector images and seismicity location information to automatically identify geological faults and characterize their geometrical properties. The model encodes a seismic image and a seismicity location image separately, and fuses the encoded features with a spatial-channel attention fusion module to improve the learning of important features in both inputs. We design an automated strategy to generate high-quality synthetic training data and labels. To improve the realism of the seismicity location image, we include random seismicity noise and missing seismicity location associated with some of the faults. We validate the model’s efficacy and accuracy using synthetic data examples and two field data examples. Moreover, we show that fine-tuning the trained model with a small, domain-specific dataset enhances its fidelity for field data applications. The results demonstrate that integrating seismicity location and seismic images into a unified framework allows the end-to-end neural network to achieve higher fidelity and accuracy in delineating subsurface faults and their geometrical properties compared with image-only fault detection methods. Our approach offers an adaptive data-driven tool for geological fault characterization and seismic hazard mitigation, bridging the gap between seismicity location and image-based fault detection methods.

58 GEOSCIENCES↗

DOE OSTI2021

Active learning strategy for high fidelity short-term data-driven building energy forecasting

The quality of a data-driven model is heavily dependent on the quality of data. Data from building operation often have data bias problems, which means that the data sample is collected in a way that some members of the intended data population are less likely to be included than others. Data-driven energy forecasting models built on such data hence are biased and could lead to large forecasting errors. Active learning—an effective method to defying data bias—is rarely studied or applied in the area of data-driven building energy forecasting modeling. This paper attempts to fill this gap and explores the application of active learning in data-driven building energy forecasting. The developed strategy in this paper efficiently generate informative training data within a time budget and uses block design to passively consider weather disturbances. The developed active learning strategy is applied and evaluated in both virtual and real-building testbeds against traditional data-driven methods. Via these virtual and real-building evaluation cases, we have demonstrated that the data bias problem typically exists in building operation data is resolved by applying the developed active learning strategy. Furthermore, building energy forecasting models trained from data generated from the active learning strategy have shown improved performances in both model accuracy and model extendibility perspectives. The effectiveness of the block design module is also validated to effectively consider the impact of weather conditions on active learning design.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗

DOE OSTI2022

A review of computing-based automated fault detection and diagnosis of heating, ventilation and air conditioning systems

We report faults in Heating, Ventilation, and Air Conditioning (HVAC) systems of buildings result in significant energy waste in building operation. With fast-growing sensing data availability and advancement in computing, computational modeling has demonstrated strong capability to detect and diagnose HVAC system faults, hence, ensuring efficient building operation. This paper comprehensively reviews the state-of-the-art computing-based fault detection and diagnosis (FDD) for HVAC systems. Overall, the reviewed computing-based FDD methods are classified as two major approaches: knowledge-based and data-driven approaches. We then identify multiple important topics, including data availability, training data size, data quality, approach generality, capability, interpretability, and required modeling efforts, along with corresponding metrics to summarize the most updated FDD development. Generally, the knowledge-based approaches are further divided as physics-based modeling, Diagnostic Bayesian Network, and performance indicator-based methods while data-driven approaches include supervised learning, unsupervised learning, and regression and statistics-based methods. State-of-the-art FDD development, remaining challenges, and future research directions are further discussed to push forward FDD in practice. Availability of fault data, capability of existing methods to deal with complex fault situations (such as simultaneous faults), modeling interpretability for data-driven methods, and required engineering efforts for physics-based methods are identified as remaining challenges in FDD development. Improving modeling fidelity and reducing modeling efforts are essential for applying physics-based methods in real buildings. Meanwhile, addressing fault data availability, increasing algorithm adaptability, and handling multiple faults are essential to further enhance the applicability of data-driven FDD approaches.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗

DOE OSTI2023

A large expert-curated cryo-EM image dataset for machine learning protein particle picking

Cryo-electron microscopy (cryo-EM) is a powerful technique for determining the structures of biological macromolecular complexes. Picking single-protein particles from cryo-EM micrographs is a crucial step in reconstructing protein structures. However, the widely used template-based particle picking process is labor-intensive and time-consuming. Though machine learning and artificial intelligence (AI) based particle picking can potentially automate the process, its development is hindered by lack of large, high-quality labelled training data. To address this bottleneck, we present CryoPPP, a large, diverse, expert-curated cryo-EM image dataset for protein particle picking and analysis. It consists of labelled cryo-EM micrographs (images) of 34 representative protein datasets selected from the Electron Microscopy Public Image Archive (EMPIAR). The dataset is 2.6 terabytes and includes 9,893 high-resolution micrographs with labelled protein particle coordinates. The labelling process was rigorously validated through 2D particle class validation and 3D density map validation with the gold standard. The dataset is expected to greatly facilitate the development of both AI and classical methods for automated cryo-EM protein particle picking.

42 ENGINEERING↗

DOE OSTI2024

Controlling radioisotope proportions when randomly sampling from Dirichlet distributions in PyRIID

As machine learning models for radioisotope quantification become more powerful, likewise the need for high-quality synthetic training data grows as well. For problem spaces that involve estimating the relative isotopic proportions of various sources in gamma spectra it is necessary to generate training data that accurately represents the variance of proportions encountered. In this report, we aim to provide guidance on how to target a desired variance of proportions which are randomly when using the PyRIID Seed Mixer, which samples from a Dirichlet distribution. We provide a method for properly parameterizing the Dirichlet distribution in order to maintain a constant variance across an arbitrary number of dimensions, where each dimension represents a distinct source template being mixed. We demonstrate that our method successfully parameterizes the Dirichlet distribution to target a specific variance of proportions, provided that several conditions are met. This allows us to follow a principled technique for controlling how random mixture proportions are generated which are then used downstream in the synthesis process to produce the final, noisy gamma spectra.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗

DOE OSTI2022

A Data Quality-Aware Framework to Reliably Forecast Photovoltaic Generation and Consumer Load for an Improved Resilience of Microgrids

Photovoltaic (PV) power and consumer load forecasting plays a critical role to ensure operational resilience of the electric grid. Most data-driven forecasting algorithms rely heavily on the continuous availability of good quality data for periodic training and validation. When deployed at the grid’s edge, prolonged disruptions to communications during extreme events degrade data quality. Factors such as missing observations, epistemic uncertainties, data drift, and concept drift are manifestations of data quality that impact the generalization of such field-deployed forecasting models. Currently, there exists no mechanism in the literature to dynamically switch between models under varying degrees of data quality as quantified by certain metrics for each factor highlighted above. This paper addresses this shortcoming by conceptually introducing a data qualityaware framework for reliable PV generation and consumer load forecasting. The framework’s design incorporates components of missing values, divergence tests, and continuous monitoring of generalization performance to detect changes in data quality caused by communications disruptions and trigger specific classes of forecasting models grouped under three use cases (UC1- UC3). As a first step towards validating this framework, real data collected from an actual field microgrid system is used to demonstrate the viability of the three use cases. Results show that the performance is the best in UC1 with an unadjusted R-square value of 0.954, followed by 0.939 for UC2 and 0.757 for UC3.

Sundararajan, Aditya↗

DOE OSTI2025

Online energy consumption forecast for battery electric buses using a learning-free algebraic method

Accurately predicting the energy consumption plays a vital role in battery electric buses (BEBs) route planning and deployment. Based on the algebraic derivative estimation, we present a novel method to forecast the energy consumption in real time. In contrast to the mainstream machine-learning-based methods, the proposed method does not require access to the historical energy consumption data. It eliminates the time-consuming and computationally expensive offline training. Consequently, its prediction performance is not constrained by the quantity and quality of the training data. Moreover, the method can swiftly adapt to new situations not included in the previous driving cycles, which makes it especially suitable for emerging transport modes, e.g., on-demand transit services. In addition, its online execution only involves algebraic calculations, yielding superior calculation efficiency. Using real-world data, we comprehensively compare the performance of the proposed learning-free algebraic method with multiple representative machine-learning-based methods. Finally, the advantages and limitations of the proposed method are discussed in detail.

33 ADVANCED PROPULSION SYSTEMS↗

DOE OSTI2025

Hydra: An AI-Based Framework for Interpretable and Portable Data Quality Monitoring

Hydra is an advanced framework designed for training and managing AI models for near real time data quality monitoring at Jefferson Lab. Deployed in all four experimental halls, Hydra has analyzed over 2 million images and has extended its capabilities to offline monitoring and validation. Hydra utilizes computer vision to continually analyze sets of images of monitoring plots generated 24/7 during experiments. Generally, these sets of images are produced at a rate and quantity that is exceedingly difficult for shift crews to effectively monitor. Significant effort has been devoted to enhancing Hydra’s user interface, to ensure that it provides clear, actionable insights for shift workers and other users. Gradient Weighted Class Activation Maps (GradCAM) provide added interpretability, allowing users to visualize important regions of the image for classification. Hydra has been containerized to enable the creation of portable demos and seamless integration with container-based technologies such as Kubernetes and Docker. With the user interface enhancements and containerization, Hydra can be rapidly deployed for new use cases and experiments. This talk will describe the Hydra framework, its user interface and experience, and the challenges inherent in its design and deployment.

Britton, Thomas [Thomas Jefferson National Acceler↗

DOE OSTI2025

A Practical Comparison of Data-Driven Prognostics Methods for Energy Systems

This study explores data-driven prognostics for nuclear power plant (NPP) condensers, focusing on tube fouling. We utilized the Asherah nuclear power plant simulator (ANS) to compare four methods: Random Forest (RF), Support Vector Regressor (SVR), Fully Connected Neural Network (FCNN), and Long Short-Term Memory Neural Network (LSTM). By simulating various fouling scenarios in the ANS, we generated data with different degradation rates under transient operations. The models were trained and tested on these data, with performance evaluated visually and numerically including uncertainty assessment. The LSTM model excelled, exhibiting minimal prediction noise and the most accurate remaining useful life estimates across all degradation levels. Its ability to capture long-term dependencies and produce cleaner outputs makes it a strong candidate, although accurate training data across the entire component lifespan are crucial. The RF model emerged as a robust alternative, providing reliable predictions with high confidence. The FCNN and SVR models, while less effective overall, showed potential under specific conditions. FCNN offers a less complex alternative to LSTM and might benefit from larger datasets. SVR excels in precision when the quality of the training data is high. Furthermore, this study highlights the operational benefits of advanced prognostics in the energy sector and emphasizes the need for further research in NPP condenser health management through real-life experiments.

21 SPECIFIC NUCLEAR REACTORS AND ASSOCIATED PLANTS↗

DOE OSTI2024

RECON Label Quality Report

The final quality of any AI/ML system is directly related to the quality of the input data used to train the system. In this case, we are trying to build a reliable image classifier that can correctly identify electrical components in x-ray images. The classification confidence is directly related to the quality of the labels in the training data, which are used in developing the AI/ML classifier. Incorrect or incomplete labels can substantially hinder the performance of the system during the training process, as it tries to compensate for variations that should not exist. Image labels are entered by subject matter experts, and in general can be assumed to be correct. However, this is not a guarantee, so developing ways to measure label quality and help identify or reject bad labels is important, especially as the database continues to grow. Given the current size of the database, a full manual review of each component is not feasible. This report will highlight the current state of the “RECON” x-ray image database and summarize several recent developments to try to help ensure high quality labeling both now and in the future. Questions that we hope to answer with this development include: 1) Are there any components with incorrect labels? 2) Can we suggest labels for components that are marked “Unknown”? 3) What kind of overall confidence do we have in the quality of the existing labels? 4) What systems or procedures can we put in place to maximize label quality?

42 ENGINEERING↗

DOE OSTI2024

Data Generation for Machine Learning Interatomic Potentials and Beyond

The field of data-driven chemistry is undergoing an evolution, driven by innovations in machine learning models for predicting molecular properties and behavior. Recent strides in ML-based interatomic potentials have paved the way for accurate modeling of diverse chemical and structural properties at the atomic level. The key determinant defining MLIP reliability remains the quality of the training data. A paramount challenge lies in constructing training sets that capture specific domains in the vast chemical and structural space. This Review navigates the intricate landscape of essential components and integrity of training data that ensure the extensibility and transferability of the resulting models. We delve into the details of active learning, discussing its various facets and implementations. We outline different types of uncertainty quantification applied to atomistic data acquisition and the correlations between estimated uncertainty and true error. The role of atomistic data samplers in generating diverse and informative structures is highlighted. Furthermore, we discuss data acquisition via modified and surrogate potential energy surfaces as an innovative approach to diversify training data. The Review also provides a list of publicly available data sets that cover essential domains of chemical space.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

DOE OSTI2026

An information-matching approach to optimal experimental design and active learning

The efficacy of mathematical models heavily depends on the quality of the training data, yet collecting sufficient data is often expensive and challenging. Many modeling applications require inferring parameters only as a means to predict other quantities of interest (QoI). Because models often contain many unidentifiable (sloppy) parameters, QoIs often depend on a relatively small number of parameter combinations. Therefore, we introduce an information-matching criterion based on the Fisher information matrix to select the most informative training data from a candidate pool. This method ensures that the selected data contain sufficient information to learn only those parameters that are needed to constrain downstream QoIs. It is formulated as a convex optimization problem, making it scalable to large models and datasets. Here, we demonstrate the effectiveness of this approach across various modeling problems in diverse scientific fields, including power systems and underwater acoustics. Finally, we use information-matching as a query function within an active learning (AL) loop for materials science applications. In all these applications, we find that a relatively small set of optimal training data can provide the necessary information for achieving precise predictions. These results are encouraging for diverse future applications, particularly AL in large machine-learning models.

Materials science↗

DOE OSTI2021

Developing and testing capabilities for simulating cases with heterogeneous land/water surfaces in a novel atmospheric large eddy simulation code

Large eddy simulations (LES) are the primary computational tool used to simulate high Reynolds number three-dimensional turbulent flows. In the context of earth system sciences, particularly atmospheric science, LES are uniquely able to resolve the scales of atmospheric motion that are key for building process-level understanding of boundary layer turbulence, atmosphere-surface interaction, clouds, and cloud-aerosol-chemistry interaction, and are a core limited-area modeling capability. Increasing demands are being placed on LES code bases as growing high performance computing resources allow LES to address a wider range of scientific problems. In addition, LES are emerging as a source of high-quality machine learning training data. These demands necessitate an agile and extensible code base that allows the model to quickly adapt to emergent needs. However, LES have largely relied on legacy Fortran code bases that lack flexibility. A new, Python-based LES capability called Predicting INteractions of Aerosol and Clouds in Large Eddy Simulation (PINACLES) has been developed as part of the Department of Energy’s Earth System Model Development (ESMD) program area’s Enabling Aerosol-cloud interactions at Global convection-permitting scalES (EAGLES) project. PINACLES was developed from the ground up with a philosophy of maximizing scientific throughput, by attempting to optimize for both model throughput and software extensibility. The initial development of PINACLES delivered a state-of-the-art idealized LES capability solving the non-hydrostatic anelastic equations of motion with doubly periodic boundary conditions and idealized homogenous surface boundary conditions. Here we provide a final report on the outcomes of a fiscal year 2021 Seed Laboratory Directed Research Project that extended PINACLES in two key ways. First, PINACLES was coupled to a state-of-the-art land surface model enabling it to simulate spatially inhomogeneous land-atmosphere interactions that are known to control key atmospheric processes. Second, the dynamical core of PINACLES was modified to permit non-periodic boundary conditions. This model enhancement enables simulation of realistic cases with boundary conditions prescribed from atmospheric reanalysis and enables nested simulations conducted on a hierarchy of computational domains with increasing resolution. Together, these extensions to PINACLES make it a formidable modeling capability and expand its potential application to diverse components of DOE’s atmospheric science portfolio.

42 ENGINEERING↗

DOE OSTI2022

AI Data Quality Monitoring with Hydra

Hydra is an extensible framework for training and managing AI for near real time monitoring that aims to replace the tedious and repetitive data quality monitoring activities the shift crew and online monitoring coordinator typically perform. It continuously scans incoming data in the form of monitoring plots for signs of problems, flagging them for human review. A web app was developed such that experts can efficiently label images for training. Labels are stored in a database for use in training and model validation. Backed up by a comprehensive database, it utilizes an additional web based front-end for viewing the current monitoring status from anywhere in the world. The system has been in production use for the GlueX experiment at Jefferson Lab for more than 2 years with new features still under active development.

Britton, Thomas↗

DOE OSTI2022

Photovoltaic System Health-State Architecture for Data-Driven Failure Detection

The timely detection of photovoltaic (PV) system failures is important for maintaining optimal performance and lifetime reliability. A main challenge remains the lack of a unified health-state architecture for the uninterrupted monitoring and predictive performance of PV systems. To this end, existing failure detection models are strongly dependent on the availability and quality of site-specific historic data. The scope of this work is to address these fundamental challenges by presenting a health-state architecture for advanced PV system monitoring. The proposed architecture comprises of a machine learning model for PV performance modeling and accurate failure diagnosis. The predictive model is optimally trained on low amounts of on-site data using minimal features and coupled to functional routines for data quality verification, whereas the classifier is trained under an enhanced supervised learning regime. The results demonstrated high accuracies for the implemented predictive model, exhibiting normalized root mean square errors lower than 3.40% even when trained with low data shares. The classification results provided evidence that fault conditions can be detected with a sensitivity of 83.91% for synthetic power-loss events (power reduction of 5%) and of 97.99% for field-emulated failures in the test-bench PV system. Finally, this work provides insights on how to construct an accurate PV system with predictive and classification models for the timely detection of faults and uninterrupted monitoring of PV systems, regardless of historic data availability and quality. Such guidelines and insights on the development of accurate health-state architectures for PV plants can have positive implications in operation and maintenance and monitoring strategies, thus improving the system’s performance.

photovoltaics↗

DOE OSTI2025

Multi-fidelity learning for interatomic potentials: low-level forces and high-level energies are all you need

The promise of machine learning interatomic potentials (MLIPs) has led to an abundance of public quantum mechanical (QM) training datasets. The quality of an MLIP is directly limited by the accuracy of the energies and atomic forces in the training dataset. Unfortunately, most of these datasets are computed with relatively low-accuracy QM methods, e.g. density functional theory with a moderate basis set. Due to the increased computational cost of more accurate QM methods, e.g. coupled-cluster theory with a complete basis set (CBS) extrapolation, most high-accuracy datasets are much smaller and often do not contain atomic forces. The lack of high-accuracy atomic forces is quite troubling, as training with force data greatly improves the stability and quality of the MLIP compared to training to energy alone. Because most datasets are computed with a unique level of theory, traditional single-fidelity (SF) learning is not capable of leveraging the vast amounts of published QM data. In this study, we apply multi-fidelity learning (MFL) to train an MLIP to multiple QM datasets of different levels of accuracy, i.e. levels of fidelity. Specifically, we perform three test cases to demonstrate that MFL with both low-level forces and high-level energies yields an extremely accurate MLIP—far more accurate than a SF MLIP trained solely to high-level energies and almost as accurate as a SF MLIP trained directly to high-level energies and forces. Therefore, MFL greatly alleviates the need for generating large and expensive datasets containing high-accuracy atomic forces and allows for more effective training to existing high-accuracy energy-only datasets. Indeed, low-accuracy atomic forces and high-accuracy energies are all that are needed to achieve a high-accuracy MLIP with MFL.

36 MATERIALS SCIENCE↗

DOE OSTI2023

Improving and Assessing the Quality of Uncertainty Quantification in Deep Learning

Deep learning (DL) models have enjoyed increased attention in recent years because of their powerful predictive capabilities. While many successes have been achieved, standard deep learning methods suffer from a lack of uncertainty quantification (UQ). While the development of methods for producing UQ from DL models is an active area of current research, little attention has been given to the quality of the UQ produced by such methods. In order to deploy DL models to high-consequence applications, high-quality UQ is necessary. This report details the research and development conducted as part of a Laboratory Directed Research and Development (LDRD) project at Sandia National Laboratories. The focus of this project is to develop a framework of methods and metrics for the principled assessment of UQ quality in DL models. This report presents an overview of UQ quality assessment in traditional statistical modeling and describes why this approach is difficult to apply in DL contexts. An assessment on relatively simple simulated data is presented to demonstrate that UQ quality can differ greatly between DL models trained on the same data. A method for simulating image data that can then be used for UQ quality assessment is described. A general method for simulating realistic data for the purpose of assessing a model’s UQ quality is also presented. A Bayesian uncertainty framework for understanding uncertainty and existing metrics is described. Research that came out of collaborations with two university partners are discussed along with a software toolkit that is currently being developed to implement the UQ quality assessment framework as well as serve as a general guide to incorporating UQ into DL applications.

97 MATHEMATICS AND COMPUTING↗