Search NASA⌕ Search

SEARCH · Search NASA

Results for “Dataset Curation”

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 73 records · Page 4
All sourcesNASA NTRSDOE OSTI
DOE OSTI2023

BigNeuron: a resource to benchmark and predict performance of algorithms for automated tracing of neurons in light microscopy datasets

BigNeuron is an open community bench-testing platform with the goal of setting open standards for accurate and fast automatic neuron tracing. We gathered a diverse set of image volumes across several species that is representative of the data obtained in many neuroscience laboratories interested in neuron tracing. Here, we report generated gold standard manual annotations for a subset of the available imaging datasets and quantified tracing quality for 35 automatic tracing algorithms. The goal of generating such a hand-curated diverse dataset is to advance the development of tracing algorithms and enable generalizable benchmarking. Together with image quality features, we pooled the data in an interactive web application that enables users and developers to perform principal component analysis, t-distributed stochastic neighbor embedding, correlation and clustering, visualization of imaging and tracing data, and benchmarking of automatic tracing algorithms in user-defined data subsets. The image quality metrics explain most of the variance in the data, followed by neuromorphological features related to neuron size. Furthermore, we observed that diverse algorithms can provide complementary information to obtain accurate results and developed a method to iteratively combine methods and generate consensus reconstructions. The consensus trees obtained provide estimates of the neuron structure ground truth that typically outperform single algorithms in noisy datasets. However, specific algorithms may outperform the consensus tree strategy in specific imaging conditions. Finally, to aid users in predicting the most accurate automatic tracing results without manual annotations for comparison, we used support vector machine regression to predict reconstruction quality given an image volume and a set of automatic tracings.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2026

Predicting the High-Temperature Oxidation Response of Nickel Superalloys Using CALPHAD-Enhanced Machine Learning

Structural materials such as Ni-based superalloys used in high-temperature power cycles are routinely exposed to toxic environments including high temperature and pressure, aqueous and gas corrosion, etc. Here, we present a physics-informed machine learning approach to predict the oxidation response of diverse Ni-superalloys. First, a high-fidelity experimental dataset is curated from typical oxidation mass-change experiments in air, covering 25+ elements and different physical behavior such as parabolic growth, non-parabolic growth, and oxide spallation. Second, the dataset is featurized using thermophysical, chemical, and mechanical properties obtained from high-throughput CALPHAD calculations. Third, several machine learning models are developed to identify key features related to mass-change characteristics and model the mass-change curve for various alloys. Finally, the model is deployed to rapidly screen over a new composition space and down-select candidate alloys with high oxidation resistance for experimental validation.

CALPHAD↗
DOE OSTI2022

A Neural Network Approach to Predict Gibbs Free Energy of Ternary Solid Solutions

Here, we present a data-centric deep learning (DL) approach using neural networks (NNs) to predict the thermodynamics of ternary solid solutions. We explore how NNs can be trained with a dataset of Gibbs free energies computed from a CALPHAD database to predict ternary systems as a function of composition and temperature. We have chosen the energetics of the FCC solid solution phase in 226 binaries consisting of 23 elements at 11 different temperatures to demonstrate the feasibility. The number of binary data points included in the present study is 102,000. We select six ternaries to augment the binary dataset to investigate their influence on the NN prediction accuracy. We examine the sensitivity of data sampling on the prediction accuracy of NNs over selected ternary systems. It is anticipated that the current DL workflow can be further elevated by integrating advanced descriptors beyond the elemental composition and more curated training datasets to improve prediction accuracy and applicability.

42 ENGINEERING↗
DOE OSTI2022

Scientific machine learning benchmarks

Deep learning has transformed the use of machine learning technologies for the analysis of large experimental datasets. In science, such datasets are typically generated by large-scale experimental facilities, and machine learning focuses on the identification of patterns, trends and anomalies to extract meaningful scientific insights from the data. In upcoming experimental facilities, such as the Extreme Photonics Application Centre (EPAC) in the UK or the international Square Kilometre Array (SKA), the rate of data generation and the scale of data volumes will increasingly require the use of more automated data analysis. Furthermore, at present, identifying the most appropriate machine learning algorithm for the analysis of any given scientific dataset is a challenge due to the potential applicability of many different machine learning frameworks, computer architectures and machine learning models. Historically, for modelling and simulation on high-performance computing systems, these issues have been addressed through benchmarking computer applications, algorithms and architectures. Extending such a benchmarking approach and identifying metrics for the application of machine learning methods to open, curated scientific datasets is a new challenge for both scientists and computer scientists. Here, we introduce the concept of machine learning benchmarks for science and review existing approaches. As an example, we describe the SciMLBench suite of scientific machine learning benchmarks.

42 ENGINEERING↗
DOE OSTI2022

Data Curation for Machine Learning Applied to Geothermal Power Plant Operational Data for GOOML: Geothermal Operational Optimization with Machine Learning: Preprint

Geothermal Operational Optimization with Machine Learning (GOOML) is a transferable and extensible component-based geothermal asset modeling framework that considers complex steamfield relationships and identifies optimization prospects using a data-driven approach to physics-guided, data-centric machine learning. This framework has been used to develop digital twins that provide steamfield operators with operational environments to analyze and understand historical and forecasted power production, explore new steamfield configuration possibilities, and seek optimal asset management in real world applications. To create, test, and apply the GOOML framework, diverse time-series datasets spanning multiple years were sourced from various geothermal power plant components within several complex real-world geothermal operations. These operations are based in the United States and New Zealand and include a variety of technologies, end-uses and configurations, collectively covering nearly all relevant operating conditions for modern geothermal fields. Datasets were acquired from multiple sources to ensure that machine learning experiments generalized properly to various operating conditions. It was found that the data varied in quality, format, and completeness. To ensure consistency between the various datasets, a standardized data curation process was developed to reliably streamline data preparation. This paper will discuss best practices as learned from the GOOML data curation process which takes the following steps: 1) acquisition of large quantities of data from power plant operators, 2) digestion of data to gain an initial understanding of what is included, 3) data transformation, which includes converting the data into a standardized machine-readable format so that they can be visualized, quality checked, and cleaned, 4) quality assurance and quality control, involving identification of significant data gaps and apparent anomalies through mapping of data features to real world componentry via the GOOML historical model, followed by discussion with modelers and power plant operators to identify additional data needs and to resolve issues, 5) use in machine learning algorithms, and 6) repetition of steps one through five until all data needs are met and data are deemed suitable for producing trustworthy modeling results which may be disseminated, ideally along with the curated dataset. This iterative process is focused on improving the quality of the data rather than tuning machine learning model parameters and supports a shift towards data-centric AI as a means to improving real-world applicability of geothermal machine learning projects.

access↗
DOE OSTI2021

Data analytics approach to predict high-temperature cyclic oxidation kinetics of NiCr-based Alloys

Abstract Although of practical importance, there is no established modeling framework to accurately predict high-temperature cyclic oxidation kinetics of multi-component alloys due to the inherent complexity. We present a data analytics approach to predict the oxidation rate constant of NiCr-based alloys as a function of composition and temperature with a highly consistent and well-curated experimental dataset. Two characteristic oxidation models, i.e., a simple parabolic law and a statistical cyclic oxidation model, have been chosen to numerically represent the high-temperature oxidation kinetics of commercial and model NiCr-based alloys. We have successfully trained machine learning (ML) models using highly ranked key input features identified by correlation analysis to accurately predict experimental parabolic rate constants ( k p ). This study demonstrates the potential of ML approaches to predict oxidation kinetics of alloys over wide composition and temperature ranges. This approach can also serve as a basis for introducing more physically meaningful ML input features to predict the comprehensive cyclic oxidation behavior of multi-component high-temperature alloys with proper constraints based on the known underlying mechanisms.

36 MATERIALS SCIENCE↗
DOE OSTI2024

Aerial imagery dataset of lost oil wells

Orphaned wells are wells for which the operator is unknown or insolvent. The location of hundreds of thousands of these wells remain unknown in the United States alone. Cost-effective techniques are essential to locate orphaned wells to address environmental problems. In this paper, we present a dataset consisting of 120,948 aerial images of recently documented orphan wells. Each of these 512 × 512 images is paired with segmentation masks that indicate the presence or absence of such well. These images, sourced from the National Agriculture Imagery Program, cover the continental United States with spatial resolutions ranging from 30 centimeters to 1 meter. Additionally, we included negative examples by selecting locations uniformly across the United States. Accompanying metadata includes the IDs and spatial resolution of the original images, which are available for free through the United States Geological Survey, and the pixel coordinates of documented orphaned wells identified in these images. This dataset is intended to support the development of deep-learning models that can help locating undocumented orphan wells from such imagery, thereby blunting the environmental damage they do.

Climate-change mitigation↗
DOE OSTI2021

A machine learning aided interpretable model for rupture strength prediction in Fe-based martensitic and austenitic alloys

Abstract The class of 9–12% Cr ferritic-martensitic alloys (FMA) and austenitic stainless steels have received considerable attention due to their numerous applications in high temperature power generation industries. To design high strength steels with prolonged service life requires a thorough understanding of the long-term properties, e.g., creep rupture strength, rupture life, etc., as a function of the chemical composition and processing parameters that govern the microstructural characteristics. In this article, the creep rupture strength of both 9–12% Cr FMA and austenitic stainless steel has been parameterized using curated experimental datasets with a gradient boosting machine. The trained model has been cross validated against unseen test data and achieved high predictive performance in terms of correlation coefficient ( $$R^{2} > 0.98 $$ R 2 > 0.98 for 9–12% Cr FMA and $$R^{2} > 0.95 $$ R 2 > 0.95 for austenitic stainless steel) thus bypassing the need for additional comprehensive tensile test campaigns or physical theoretical calculations. Furthermore, the feature importance has been computed using the Shapley value analysis to understand the complex interplay of different features.

36 MATERIALS SCIENCE↗
DOE OSTI2024

Accelerating the design of lattice structures using machine learning

Lattices remain an attractive class of structures due to their design versatility; however, rapidly designing lattice structures with tailored or optimal mechanical properties remains a significant challenge. With each added design variable, the design space quickly becomes intractable. To address this challenge, research efforts have sought to combine computational approaches with machine learning (ML)-based approaches to reduce the computational cost of the design process and accelerate mechanical design. While these efforts have made substantial progress, significant challenges remain in (1) building and interpreting the ML-based surrogate models and (2) iteratively and efficiently curating training datasets for optimization tasks. Here, we address the first challenge by combining ML-based surrogate modeling and Shapley additive explanation (SHAP) analysis to interpret the impact of each design variable. We find that our ML-based surrogate models achieve excellent prediction capabilities (R 2 > 0.95) and SHAP values aid in uncovering design variables influencing performance. We address the second challenge by utilizing active learning-based methods, such as Bayesian optimization, to explore the design space and report a 5 × reduction in simulations relative to grid-based search. Collectively, these results underscore the value of building intelligent design systems that leverage ML-based methods for uncovering key design variables and accelerating design.

36 MATERIALS SCIENCE↗
DOE OSTI2026

Atomistic Simulation of Glasses and Amorphous Materials: Challenges and Opportunities for the Next Decade

Atomistic simulations have become indispensable tools for understanding glass structure, dynamics, and properties, yet persistent challenges limit their predictive power. This perspective examines three interconnected issues, namely glass formation procedures, interatomic potential development, and machine learning applications, which emerged from the 5th International Workshop on Challenges of Atomistic Simulations of Glasses and Amorphous Materials. We identify convergent community priorities for (i) standardized validation protocols, (ii) curated benchmark datasets with complete metadata, and (iii) open repositories for glasses. A systematic was forward is provided by a hierarchical validation framework for assessing the structural fidelity, property prediction, and behavioral realism of simulation techniques. Looking ahead, transformative advances are promised by the fusion of classical techniques with machine learning based approaches, for instance, by integrating swap Monte Carlo with machine-learning (ML) potentials, leveraging foundation models through transfer learning, and finetuning ML potentials with experimental data. Progress depends on the community committing to validated models, reproducible protocols, and sustained data sharing.

Krishnan, N. M. Anoop↗
DOE OSTI2020

OSTI Semantic Thesaurus v1

The OSTI Semantic Thesaurus is a reference for scientific and technical terms and relationships. The term data is used to implement keyword-to-concept mapping in OSTI.GOV searches, where searched term(s) will be mapped to related scientific concepts, allowing the end user to retrieve results related to their search terms and also explore narrower and similar concepts. The OSTI Semantic Thesaurus originally inherited data and structure from the INIS/ETDE Thesaurus (https://www.etde.org/edb/IAEA-INIS-ETDE-01-2013-08.pdf), which was a controlled terminology for indexing information within the subject scopes of the International Nuclear Information System (INIS) and the Energy Technology Data Exchange (ETDE). The data has been expanded upon since that time with the inclusion of scientific concepts from sources like Wikidata, and through manual curation. This dataset is an export from the OSTI Semantic Thesaurus in RDF/SKOS format, which is specifically suited for representation of controlled vocabularies like thesauri. While the full thesaurus includes additional relation types which may be included in future revisions, this export is limited to broader, narrower, and related term relations. Definitions and scope notes are included where available.

96 KNOWLEDGE MANAGEMENT AND PRESERVATION↗
DOE OSTI2023

Exploring model complexity in machine learned potentials for simulated properties

Abstract Machine learning (ML) enables the development of interatomic potentials with the accuracy of first principles methods while retaining the speed and parallel efficiency of empirical potentials. While ML potentials traditionally use atom-centered descriptors as inputs, different models such as linear regression and neural networks map descriptors to atomic energies and forces. This begs the question: what is the improvement in accuracy due to model complexity irrespective of descriptors? We curate three datasets to investigate this question in terms of ab initio energy and force errors: (1) solid and liquid silicon, (2) gallium nitride, and (3) the superionic conductor Li $$_{10}$$ 10 Ge(PS $$_{6}$$ 6 ) $$_{2}$$ 2 (LGPS). We further investigate how these errors affect simulated properties and verify if the improvement in fitting errors corresponds to measurable improvement in property prediction. By assessing different models, we observe correlations between fitting quantity (e.g. atomic force) error and simulated property error with respect to ab initio values. Graphical abstract

Rohskopf, A. (ORCID:0000000227128296)↗
DOE OSTI2021

Smart Semi-Supervised Accumulation of Large Repositories for Industrial Control Systems Device Information

Industrial Control Systems device manufacturers frequently add new features to improve their product performance. Oftentimes, these changes are mainly vendor-driven initiatives, and customers may not be aware of the full impact of these new capabilities on their cybersecurity posture. In the energy sector, this can lead to considerable dissonance between vendor-provided cybersecurity claims and a customer’s responsibility for Operation Technology cybersecurity compliance. Thus, the resulting dynamic verification burden is shifted towards the customer and may pose a significant cybersecurity risk to the energy sector landscape. We found that there is very limited research into cybersecurity auditing for Operational Technology. However, a solution is needed for vetting the vendor-supplied feature claims and their adherence to cybersecurity requirements and standards. We are presently engaged in an effort to develop such a system. This paper demonstrates one vital aspect of this effort in proposing an end-to-end framework to accumulate a large repository of ICS device information for this vetting system, curate the dataset, and conduct extensive processing. This framework is designed to use web scraping, data analytics and Natural Language Processing (NLP) techniques to identify vendor websites, automate the collection of website-accessible documents and automatically derive metadata from them for identification of product documents relevant to the repository. We have found that this automated approach to vendor identification, document extraction into a product repository, and NLP pre-processing is unique and has not been previously presented in the literature. The preliminary work shows that this is feasible and can produce reliable results with minimum supervision. Future work will be built upon this foundation in order to achieve semi-supervised vetting of device technical information – a vital capability for ensuring that vendor-claimed device cybersecurity capabilities match industry requirements.

Ameri, Kimia↗
DOE OSTI2026

Enhancing Operational Safety via Agentic Dialogue Hazard Identification Analysis

Operational safety in high-stakes domains such as industrial process control, autonomous, and safety-critical systems demand reliable hazard identification. While large language models (LLMs) have shown promise in automating safety analysis tasks, single-turn, monolithic inference is brittle: it lacks the self-correction, deliberation, and contextual refinement that safety engineers apply iteratively. In this paper, we introduce HAZDIAL, a framework that investigates whether structured agentic dialogue (multi-agent, multi-turn interactions) improves the quality of NLP-based hazard identification over single-pass baselines. We systematically compare two dialogue modalities: adversarial debate and constructive discussion, and propose an genetic algorithm-based agentic interaction optimization. We evaluate all configurations against a curated golden dataset using standard classification metrics (accuracy, precision, recall, F1) and a novel dialogue metrics. This work advances the intersection of dialogue systems, multi-agent reasoning, and AI safety, providing empirical evidence for dialogue-driven hazard analysis.

Das, Sanjay [ORNL] (ORCID:0009000542591915)↗
DOE OSTI2026

Curation and Dissemination of Complex Multi-Modal Datasets for Radiation Detection, Localization, and Tracking

The PANDAWN sensor network in Chicago, IL, is a state-of-the-art testbed for networked, multi-modal sensing. It integrates AI/data science methods into its operation, from data acquisition to automated data labeling and curation workflows. The curation and dissemination of diverse multi-modal datasets will enable the development of new radiological/nuclear (R/N) detection, localization, and tracking algorithms and methods relevant across the nonproliferation mission space. This article first introduces the PANDAWN sensor network and the features that make it stand out from previous multi-modal data acquisition efforts. We then review the various data streams acquired on the PANDAWN nodes and present the implementation of an automated data curation pipeline that includes the labeling of radiation and contextual data streams. Here, we finally provide a short overview of different studies that leveraged the curated datasets.

Data curation↗
DOE OSTI2020

Curation of Ground-Truth Validated Benchmarking Datasets for Fault Detection & Diagnostics Tools

Fault detection and diagnostics (FDD) analytical tools for heating, ventilation and air conditioning (HVAC) systems represent one of the most active areas of smart building technology development. A diversity of techniques is used for FDD analytics, spanning physical models, black box, and rule-based approaches, and researchers continuously strive to develop improved algorithms. With FDD algorithm numbers now in the hundreds, there is a need for performance evaluation of these algorithms in order to assess improvements, improve costeffectiveness, and to prioritize investment in the further development of these technologies. A persistent challenge of FDD advance has been the lack of common datasets to benchmark the performance accuracy of FDD algorithms. This paper summarizes the successful curation of HVAC operational data, paired with validated ground-truth information regarding the presence and absence of faults. The current dataset, consisting of both simulation and experimental data, will evolve to include a larger set of HVAC systems with the objective of creating the largest publicly available dataset to be used by FDD developers, users, and researchers to compare and contrast performance accuracy across FDD algorithms, helping to drive improvements that will spur greater market adoption of FDD tools. Furthermore, in order to avoid previously observed issues with contributed datasets and ensure high quality and consistency of future submissions, the development of data validation and ground-truth assessment protocol is detailed in this study.

Casillas, Armando↗
DOE OSTI2025

2024 Buildings Technology Baseline: Dataset Documentation

The Buildings Technology Baseline is a curated and regularly updated dataset of current and projected performance, retail, and installed price data for all major building energy technologies needed to enable cost/benefit analyses. Building technology analyses require an up-to-date understanding of installation costs and cost-effectiveness of key building energy efficiency technologies. The dataset was assembled by Guidehouse during fiscal year 2024. Data was gathered from the 2024 National Residential Efficiency Measures Database (NREMDB), the 2023 Energy Information Administration Updated Buildings Sector Appliance and Equipment Costs and Efficiencies ("EIA Building Data Report"), DOE Lighting Market Model, the 2023 RSMeans database, and the 2020 Grid-Interactive Efficient Building Technology Cost, Performance, and Lifetime Characteristics ("GEB Data Report"), Lawrence Berkeley National Laboratory, various literature, as well as new data from online retailers, stakeholder interviews, and contractor databases in 2023 and 2024. The dataset has been reviewed by subject matter experts at NREL and DOE. The 2024 dataset release is intended to be a starting point for interested users to provide feedback. This database is not intended to provide specific cost estimates for a specific project. The cost estimates do not include any rebates or tax incentives that may be available for the measures. Rather, it is meant to help determine which measures may be more cost-effective. The National Renewable Energy Laboratory (NREL) makes every effort to ensure accuracy of the data; however, NREL does not assume any legal liability or responsibility for the accuracy or completeness of the information.

29 ENERGY PLANNING, POLICY, AND ECONOMY↗