Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “dataset use case study”

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 325 records · Page 18
All sourcesNASA NTRSDOE OSTI
DOE OSTI2022

Detection of surface water temperature variations of Mongolian lakes benefiting from the spatially and temporally gap-filled MODIS data

Lakes provide critical water resources for human activities and ecosystems, particularly in the Mongolian Plateau (MP), which is characterized by a dry climate and a harsh environment. As a region that is sensitive to anthropogenic warming, tracking lake surface water temperature (LSWT) changes in Mongolian lakes is crucial for understanding the consequences of a warming climate on lake ecosystems. However, the long-term monitoring of LSWT is restricted by the spatiotemporal gaps in the raw imagery of remote sensing-based land surface temperature (LST), e.g., the commonly used Moderate Resolution Imaging Spectroradiometer (MODIS) LST products. This study applied an improved gap-filling method by utilizing the discrete cosine transform-based penalized least squares (DCT-PLS) strategy in the spatial domain combined with the linear interpolation (LI) algorithm in the temporal domain. The method was applied to fill gaps in the LSWT imagery of 12 representative lakes across MP. The randomly sampled high-quality MODIS LSWT values in the spatial and temporal domains were excavated as false data gaps and considered “virtual true” validation datasets. The spatial validation results showed that the estimated LSWT for all the lake cases were comparable with the “virtual true” LSWT values, with the average values of the coefficient of determination, mean absolute error, mean square error, and root mean square error being 0.98, 0.38 °C, 0.45 °C, and 0.59 °C, respectively. Meanwhile, the error of nighttime LSWT results was relatively lower than that of daytime LSWT. For temporal interpolation validation, the LI algorithm exhibited relatively better performance and could more objectively indicate the variation in LSWT. Benefiting from the spatially and temporally well-constrained data, we analyzed the interannual and intra-annual change characteristics of the LSWTs of the 12 lakes. The long-term variations of annual and seasonal mean LSWTs in the 12 selected lakes exhibited no evident trends in 2000–2020, while presented apparent interannual fluctuations. The slight changes in the average LSWTs of the 12 selected lakes were in excellent synchronization with the surrounding LST derived from the reanalysis datasets, confirming the widely reported phenomenon of “global warming hiatus” that occurred in the early 21st century. This study improves the understanding of the LSWT variations in Mongolian lakes in response to global climate change. It has the potential to provide an effective approach for monitoring LSWT changes in other large-scale studies.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2024

Uncertainty quantification in multivariable regression for material property prediction with Bayesian neural networks

With the increased use of data-driven approaches and machine learning-based methods in material science, the importance of reliable uncertainty quantification (UQ) of the predicted variables for informed decision-making cannot be overstated. UQ in material property prediction poses unique challenges, including multi-scale and multi-physics nature of materials, intricate interactions between numerous factors, limited availability of large curated datasets, etc. In this work, we introduce a physics-informed Bayesian Neural Networks (BNNs) approach for UQ, which integrates knowledge from governing laws in materials to guide the models toward physically consistent predictions. To evaluate the approach, we present case studies for predicting the creep rupture life of steel alloys. Experimental validation with three datasets of creep tests demonstrates that this method produces point predictions and uncertainty estimations that are competitive or exceed the performance of conventional UQ methods such as Gaussian Process Regression. Additionally, we evaluate the suitability of employing UQ in an active learning scenario and report competitive performance. The most promising framework for creep life prediction is BNNs based on Markov Chain Monte Carlo approximation of the posterior distribution of network parameters, as it provided more reliable results in comparison to BNNs based on variational inference approximation or related NNs with probabilistic outputs.

36 MATERIALS SCIENCE↗
DOE OSTI2021

Trigger-based Incremental Data Processing with Unified Sync and Async Model

In recent years, more and more applications in the cloud have needs to process large-scale on-line datasets, which evolve over time as new entries are added and existing entries are modified. Several programming frameworks, such as Percolator and Oolong, are proposed for such incremental data processing and can achieve efficient processing with an event-driven abstraction. However, these frameworks are inherently asynchronous, leaving the heavy burden of managing synchronization to applications' developers, which further significantly restricts their usabilities. In this study, we propose a trigger-based incremental computing framework in the cloud, called Domino, with both synchronous and asynchronous mechanisms to coordinate parallel triggers. With this new framework, both synchronous and asynchronous applications can be seamlessly developed. Use cases and extensive evaluation results confirm that it can deliver sufficient performance, and also is easy to use for incremental applications in large-scale distributed computing.

97 MATHEMATICS AND COMPUTING↗
NASA NTRS2023

Machine Learning Framework for Hazard Extraction and Analysis of Trends (HEAT) in Wildfire Response

This research proposes a natural language processing enabled risk analysis framework, named Hazard Extraction andAnalysis of Trends (HEAT), and applies the framework to the ICS-209-PLUS data set of wildfire incident responseforms. The HEAT framework produces safety- and risk- relevant analyses, consisting of: (1) a set of hazards extractedfrom text data, (2) a primary analysis using hazard-relevant metrics, such as rate and severity, to form an FMEA-styletable and risk matrix, (3) a time series analysis of metric trends, and (4) a secondary analysis examining potentialpredictors for hazards. Results from HEAT provide quantitative risk-relevant information for high-level hazards doc-umented in existing-state operations. Because of the generalizability of the steps and limited data requirements, HEATcan be applied to any dataset containing narrative text, thus providing a framework for data-driven machine learning-enabled quantitative risk analysis across a variety of domains. To demonstrate HEAT in a case study, we apply theframework to the ICS-209-PLUS dataset of wildland fire incident response forms. Hazards identified in wildfire re-sponse arise from environmental conditions, the mission, and the wildland urban interface. The resulting risk matrixidentifies evacuations as high-risk hazards, while all other identified hazards are medium or serious risk.

natural language processing↗
DOE OSTI2022

High-Fidelity Simulation Study of the Unsteady Flow Effects on High-Pressure Turbine Blade Performance

Abstract Unsteadiness, in the form of both broadband background disturbances and discrete coherent wakes, can have a strong effect on the performance of turbomachinery blades. The influence of the incoming flow has received much interest as it inevitably affects the blade boundary layers and develops as it passes through the machine. In the present work, we investigate the effect of unsteady flow on high-pressure turbines (HPTs), using high-fidelity datasets produced by wall resolved large-eddy simulation of an HPT stage. The effects of incident wakes from an upstream stator, compounded by the presence of freestream turbulence, on the downstream rotor are investigated. Based on analyzing cases with different turbulence intensities and length scales prescribed at the inlet, we show that changing the freestream turbulence characteristics has a direct effect on the unsteady behavior of the stator wakes. As a result, the performance of the rotor is also significantly affected. By detailing the influence of the wake–turbulence interaction, we aim to distinguish driving forces on rotor performance, be it changes in the incident wakes or direct influence from the freestream turbulence. Furthermore, the aerothermal behaviors of the rotor blades have been extensively investigated, showing that the blade boundary layers on the suction and pressure sides respond differently to external disturbances. The insights gained can provide designers with guidelines in understanding the unsteady flow effects of a given flow state, and how the unsteadiness present, either broadband or deterministic, will affect the performance of downstream blades.

Engineering↗
DOE OSTI2024

Deep kernel methods learn better: from cards to process optimization

Abstract The ability of deep learning methods to perform classification and regression tasks relies heavily on their capacity to uncover manifolds in high-dimensional data spaces and project them into low-dimensional representation spaces. In this study, we investigate the structure and character of the manifolds generated by classical variational autoencoder (VAE) approaches and deep kernel learning (DKL). In the former case, the structure of the latent space is determined by the properties of the input data alone, while in the latter, the latent manifold forms as a result of an active learning process that balances the data distribution and target functionalities. We show that DKL with active learning can produce a more compact and smooth latent space which is more conducive to optimization compared to previously reported methods, such as the VAE. We demonstrate this behavior using a simple cards dataset and extend it to the optimization of domain-generated trajectories in physical systems. Our findings suggest that latent manifolds constructed through active learning have a more beneficial structure for optimization problems, especially in feature-rich target-poor scenarios that are common in domain sciences, such as materials synthesis, energy storage, and molecular discovery. The Jupyter Notebooks that encapsulate the complete analysis accompany the article.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2025

The role of chromatin state in intron retention: A case study in leveraging large scale deep learning models

Complex deep learning models trained on very large datasets have become key enabling tools for current research in natural language processing and computer vision. By providing pre-trained models that can be fine-tuned for specific applications, they enable researchers to create accurate models with minimal effort and computational resources. Large scale genomics deep learning models come in two flavors: the first are large language models of DNA sequences trained in a self-supervised fashion, similar to the corresponding natural language models; the second are supervised learning models that leverage large scale genomics datasets from ENCODE and other sources. We argue that these models are the equivalent of foundation models in natural language processing in their utility, as they encode within them chromatin state in its different aspects, providing useful representations that allow quick deployment of accurate models of gene regulation. We demonstrate this premise by leveraging the recently created Sei model to develop simple, interpretable models of intron retention, and demonstrate their advantage over models based on the DNA language model DNABERT-2. Our work also demonstrates the impact of chromatin state on the regulation of intron retention. Using representations learned by Sei, our model is able to discover the involvement of transcription factors and chromatin marks in regulating intron retention, providing better accuracy than a recently published custom model developed for this purpose.

Biochemistry & Molecular Biology↗
DOE OSTI2026

Discovery of correlated electron molecular orbital materials using graph representations

Correlated electron molecular orbital (CEMO) materials host emergent electronic states built from molecular orbitals localized over clusters of transition metal ions yet have historically been discovered sporadically and generally been treated as isolated case studies. Here we establish CEMO materials as a systematically discoverable class and introduce a graph-based framework to identify, classify, and organize transition-metal cluster motifs in inorganic solids. Starting from crystal structures in the Materials Project, we construct transition metal connectivity graphs, extract cluster motifs using a bond-cutting algorithm, and determine cluster point groups, effective cluster sublattice dimensionality, and translational symmetry. Applying this approach in a high-throughput screen of 34,548 compounds yields 5,306 cluster-containing materials, including 2,627 stable or metastable compounds with isolated clusters and 984 materials featuring mixed-metal clusters. The resulting dataset reveals symmetry and element dependent trends in cluster formation. By integrating cluster classification with flat band lattice topology and battery-relevant information, we provide further relevant information to multiple scientific communities. The accompanying open dataset, Cluster Finder software, and interactive web platform enable systematic exploration of cluster driven electronic phenomena and establish a general pathway for discovering correlated quantum materials and functional materials with cluster-based or extended metal-metal bonding in inorganic solids.

Akhond, Md. Rajbanul [Department of Chemistry, 800↗
DOE OSTI2022

The Concept of a Quantum Edge Simulator: Edge Computing and Sensing in the Quantum Era

Sensors, enabling observations across vast spatial, spectral, and temporal scales, are major data generators for information technology (IT). Processing, storing, and communicating this ever-growing amount of data pose challenges for the current IT infrastructure. Edge computing—an emerging paradigm to overcome the shortcomings of cloud-based computing—could address these challenges. Furthermore, emerging technologies such as quantum computing, quantum sensing, and quantum communications have the potential to fill the performance gaps left by their classical counterparts. Here, we present the concept of an edge quantum computing (EQC) simulator—a platform for designing the next generation of edge computing applications. An EQC simulator is envisioned to integrate elements from both quantum technologies and edge computing to allow studies of quantum edge applications. The presented concept is motivated by the increasing demand for more sensitive and precise sensors that can operate faster at lower power consumption, generating both larger and denser datasets. These demands may be fulfilled with edge quantum sensor networks. Envisioning the EQC era, we present our view on how such a scenario may be amenable to quantification and design. Given the cost and complexity of quantum systems, constructing physical prototypes to explore design and optimization spaces is not sustainable, necessitating EQC infrastructure and component simulators to aid in co-design. We discuss what such a simulator may entail and possible use cases that invoke quantum computing at the edge integrated with new sensor infrastructures.

47 OTHER INSTRUMENTATION↗
NASA NTRS2014

Detecting Trend and Seasonal Changes in Bathymetry Derived from HICO Imagery: A Case Study of Shark Bay, Western Australia

The Hyperspectral Imager for the Coastal Ocean (HICO) aboard the International Space Station has offered for the first time a dedicated space-borne hyperspectral sensor specifically designed for remote sensing of the coastal environment. However, several processing steps are required to convert calibrated top-of-atmosphere radiances to the desired geophysical parameter(s). These steps add various amounts of uncertainty that can cumulatively render the geophysical parameter imprecise and potentially unusable if the objective is to analyze trends and/or seasonal variability. This research presented here has focused on: (1) atmospheric correction of HICO imagery; (2) retrieval of bathymetry using an improved implementation of a shallowwater inversion algorithm; (3) propagation of uncertainty due to environmental noise through the bathymetry retrieval process; (4) issues relating to consistent geo-location of HICO imagery necessary for time series analysis, and; (5) tide height corrections of the retrieved bathymetric dataset. The underlying question of whether a temporal change in depth is detectable above uncertainty is also addressed. To this end, nine HICO images spanning November 2011 to August 2012, over the Shark Bay World Heritage Area, Western Australia, were examined. The results presented indicate that precision of the bathymetric retrievals is dependent on the shallow water inversion algorithm used.Within this study, an average of 70% of pixels for the entire HICO-derived bathymetry dataset achieved a relative uncertainty of less than +/-20%. A per-pixel t-test analysis between derived bathymetry images at successive timestamps revealed observable changes in depth to as lowas 0.4 m. However, the present geolocation accuracy of HICO is relatively poor and needs further improvements before extensive time series analysis can be performed.

Geolocations accuracy↗
DOE OSTI2020

Deep anomaly detection for industrial systems: a case study

We explore the use of deep neural networks for anomaly detection of industrial systems where the data are multivariate time series measurements. We formulate the problem as a self-supervised learning where data under normal operation are used to train a deep neural network autoregressive model, i.e., use a window of time series data to predict future data values. The aim of such a model is to learn to represent the system dynamic behavior under normal conditions, while expect higher model vs. measurement discrepancies under faulty conditions. In real world applications, many control settings are discrete in nature. In this paper, vector embedding and joint losses are employed to deal with such situations. Both LSTM and CNN based deep neural network backbones are studied on the Secure Water Treatment (SWaT) testbed datasets. Also, Support Vector Data Description (SVDD) method is adapted to such anomaly detection settings with deep neural networks. Evaluation methods and results are discussed based on the SWaT dataset along with potential pitfalls.

anomaly detection, deep neural network↗
DOE OSTI2022

Long-term trends in urban NO 2 concentrations and associated paediatric asthma incidence: estimates from global datasets

Combustion-related nitrogen dioxide (NO 2 ) air pollution is associated with paediatric asthma incidence. We aimed to estimate global surface NO 2 concentrations consistent with the Global Burden of Disease study for 1990-2019 at a 1 km resolution, and the concentrations and attributable paediatric asthma incidence trends in 13 189 cities from 2000 to 2019. We scaled an existing annual average NO 2 concentration dataset for 2010-12 from a land use regression model (based on 5220 NO 2 monitors in 58 countries and land use variables) to other years using NO 2 column densities from satellite and reanalysis datasets. We applied these concentrations in an epidemiologically derived concentration-response function with population and baseline asthma rates to estimate NO 2 -attributable paediatric asthma incidence. We estimated that 1.85 million (95% uncertainty interval [UI] 0.93-2.80 million) new paediatric asthma cases were attributable to NO 2 globally in 2019, two thirds of which occurred in urban areas (1.22 million cases; 95% UI 0.60-1.8 million). The proportion of paediatric asthma incidence that is attributable to NO 2 in urban areas declined from 19.8% (1.22 million attributable cases of 6.14 million total cases) in 2000 to 16.0% (1.24 million attributable cases of 7.73 million total cases) in 2019. Urban attributable fractions dropped in high-income countries (-41%), Latin America and the Caribbean (-16%), central Europe, eastern Europe, and central Asia (-13%), and southeast Asia, east Asia, and Oceania (-6%), and rose in south Asia (+23%), sub-Saharan Africa (+11%), and north Africa and the Middle East (+5%). The contribution of NO 2 concentrations, paediatric population size, and asthma incidence rates to the change in NO 2 -attributable paediatric asthma incidence differed regionally. Despite improvements in some regions, combustion-related NO 2 pollution continues to be an important contributor to paediatric asthma incidence globally, particularly in cities. Mitigating air pollution should be a crucial element of public health strategies for children.

60 APPLIED LIFE SCIENCES↗
NASA NTRS2007

Solar Occultation Satellite Data and Derived Meteorological Products: Sampling Issues and Comparisons with Aura MLS

Derived Meteorological Products (DMPs, including potential temperature (theta), potential vorticity, equivalent latitude (EqL), horizontal winds and tropopause locations) have been produced for the locations and times of measurements by several solar occultation (SO) instruments and the Aura Microwave Limb Sounder (MLS). DMPs are calculated from several meteorological analyses for the Atmospheric Chemistry Experiment-Fourier Transform Spectrometer, Stratospheric Aerosol and Gas Experiment II and III, Halogen Occultation Experiment, and Polar Ozone and Aerosol Measurement II and III SO instruments and MLS. Time-series comparisons of MLS version 1.5 and SO data using DMPs show good qualitative agreement in time evolution of O3, N2O, H20, CO, HNO3, HCl and temperature; quantitative agreement is good in most cases. EqL-coordinate comparisons of MLS version 2.2 and SO data show good quantitative agreement throughout the stratosphere for most of these species, with significant biases for a few species in localized regions. Comparisons in EqL coordinates of MLS and SO data, and of SO data with geographically coincident MLS data provide insight into where and how sampling effects are important in interpretation of the sparse SO data, thus assisting in fully utilizing the SO data in scientific studies and comparisons with other sparse datasets. The DMPs are valuable for scientific studies and to facilitate validation of non-coincident measurements.

Manney, Gloria↗
NASA NTRS2014

Detecting Trend and Seasonal Changes in Bathymetry Derived from HICO Imagery: A Case Study of Shark Bay, Western Australia

The Hyperspectral Imager for the Coastal Ocean (HICO) aboard the International Space Station has offered for the first time a dedicated space-borne hyperspectral sensor specifically designed for remote sensing of the coastal environment. However, several processing steps are required to convert calibrated top-of-atmosphere radiances to the desired geophysical parameter(s). These steps add various amounts of uncertainty that can cumulatively render the geophysical parameter imprecise and potentially unusable if the objective is to analyze trends and/or seasonal variability. This research presented here has focused on: (1) atmospheric correction of HICO imagery; (2) retrieval of bathymetry using an improved implementation of a shallow water inversion algorithm; (3) propagation of uncertainty due to environmental noise through the bathymetry retrieval process; (4) issues relating to consistent geo-location of HICO imagery necessary for time series analysis, and; (5) tide height corrections of the retrieved bathymetric dataset. The underlying question of whether a temporal change in depth is detectable above uncertainty is also addressed. To this end, nine HICO images spanning November 2011 to August 2012, over the Shark Bay World Heritage Area, Western Australia, were examined. The results presented indicate that precision of the bathymetric retrievals is dependent on the shallow water inversion algorithm used. Within this study, an average of 70% of pixels for the entire HICO-derived bathymetry dataset achieved a relative uncertainty of less than +/-20%. A per-pixel t-test analysis between derived bathymetry images at successive timestamps revealed observable changes in depth to as low as 0.4 m. However, the present geolocation accuracy of HICO is relatively poor and needs further improvements before extensive time series analysis can be performed.

coastal marine↗
DOE OSTI2022

Grey-box Fault Models and Applications for Low Carbon Emission CO2 Refrigeration System

CO2 refrigeration systems have attracted more attentions in recent years because of their zero-carbon emission advantages compared with traditional refrigerants. These systems are widely used in certain commercial buildings such as supermarkets. However, very limited energy studies have been done for such refrigeration systems under faults. Furthermore, this study investigated five common faults for supermarket transcritical CO2 refrigeration systems with display cases. The following major tasks were implemented for this study. (1) Five fault models (gray-box format) regarding the power consumption and supply air temperature were proposed for low- and high-temperature display cases, respectively. The models cover: ice accumulation on evaporator coil, evaporator fan partial failure, expansion valve failure, display door open, and condenser blockage. (2) These fault models were calibrated with field tests, and the modeling accuracies were in good agreement with measurement datasets. (3) The proposed fault models demonstrated more than 90% of fault detection for Fault Detection and Diagnostics (FDD) purposes for both field measurement and simulated data.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗
DOE OSTI2022

A Convolutional Neural Network Model for Battery Capacity Fade Curve Prediction using Early Life Data

Herein, early prediction of battery performance degradation trends can facilitate research of new materials and cell designs, rapid deployment of batteries in real-world applications, timely replacement of batteries in critical applications, and even the secondary use market. In this study, we design a convolutional neural network model to predict the entire battery capacity fade curve - a critical indicator of battery performance degradation - using first 100 cycles of data (~ three weeks of testing). We use the discharge voltage-capacity curves as input to the model and automate the feature extraction process through the convolutional layers of the network. Our approach can predict the per cycle capacity fade rate and rollover cycle (knee point) in the capacity fade curve, which indicate the onset of rapid capacity decay. On the publicly available graphite/LiFePO 4 battery dataset, optimized networks predict the capacity fade curves, rollover cycle, and end of life with 3.7% (worst-case), 19%, and 17% mean absolute percentage errors, respectively.

25 ENERGY STORAGE↗
DOE OSTI2024

Digital twins and deep learning segmentation of defects in monolayer MX 2 phases

Developing methods to understand and control defect formation in nanomaterials offers a promising route for materials discovery. Monolayer MX 2 phases represent a particularly compelling case for defect engineering of nanomaterials due to the large variability in their physical properties as different defects are introduced into their structure. However, effective identification and quantification of defects remain a challenge even as high-throughput scanning transmission electron microscopy methods improve. This study highlights the benefits of employing first principles calculations to produce digital twins for training deep learning segmentation models for defect identification in monolayer MX 2 phases. Around 600 defect structures were obtained using density functional theory calculations, with each monolayer MX 2 structure being subjected to multislice simulations for the purpose of generating the digital twins. Several deep learning segmentation architectures were trained on this dataset, and their performances evaluated under a variety of conditions such as recognizing defects in the presence of unidentified impurities, beam damage, grain boundaries, and with reduced image quality from low electron doses. Further, this digital twin approach allows benchmarking different deep learning architectures on a theory dataset, which enables the study of defect classification under a broad array of finely controlled conditions. It thus opens the door to resolving the underpinning physical reasons for model shortcomings and potentially chart paths forward for automated discovery of materials defect phases in experiments.

36 MATERIALS SCIENCE↗
DOE OSTI2024

Optimization-Based Model Reduction Scheme for Renewable Energy Power Plants Using Standardized Testing Scenarios

This paper presents an optimization-based model reduction scheme for renewable energy (RE) power plants consisting of inverter-based resources (IBRs) operating in grid-following (GFL) or grid-forming (GFM) modes. More importantly, the datasets feeding the optimization-based model reduction scheme are generated and re-used through the standardized grid-interactive testing scenarios. Particularly, the proposed scheme makes use of the power plant point of common coupling (PCC) measurements of various quantities specified by standardized tests (e.g., voltage and frequency ride through) as per IEEE 2800, to estimate the parameters of the reduced-order model such that its dynamic performance aligns with the original detailed power plant model. The proposed model reduction approach does not require the parameters of individual IBRs and using standardized test data as input to the formulated optimization problem simplifies the reduced-order modelling scheme. Extensive case studies following standardized test scenarios verified the remarkable accuracy of the proposed approach.

Yallamilli, Ram S. [Purdue University]↗