Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “data enhancement”

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 307 records · Page 17
All sourcesNASA NTRSDOE OSTI
DOE OSTI2021

CASTELO: clustered atom subtypes aided lead optimization—a combined machine learning and molecular modeling method

Background: Drug discovery is a multi-stage process that comprises two costly major steps: pre-clinical research and clinical trials. Among its stages, lead optimization easily consumes more than half of the pre-clinical budget. We propose a combined machine learning and molecular modeling approach that partially automates lead optimization workflow in silico, providing suggestions for modification hot spots. Results: The initial data collection is achieved with physics-based molecular dynamics simulation. Contact matrices are calculated as the preliminary features extracted from the simulations. To take advantage of the temporal information from the simulations, we enhanced contact matrices data with temporal dynamism representation, which are then modeled with unsupervised convolutional variational autoencoder (CVAE). Finally, conventional and CVAE-based clustering methods are compared with metrics to rank the submolecular structures and propose potential candidates for lead optimization. Conclusion: With no need for extensive structure-activity data, our method provides new hints for drug modification hotspots which can be used to improve drug potency and reduce the lead optimization time. It can potentially become a valuable tool for medicinal chemists.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2025

Building partnerships for development of sustainable energy systems with atmospheric measurements

Atmospheric dynamics often play a critical role in the sustainability and reliability of diverse forms of energy production. This is especially true for the growing number of renewable energy deployments that harness aspects of the environment for power production. While the University of Memphis has a strong research background in energy systems, we have little experience working with the Earth and Environmental Systems Science Division (EESSD) and their associated User Facilities. Of particular interest to us is the Atmospheric Science Research and the Atmospheric Radiation Measurement (ARM) user facility to address surface-boundary layer interactions and physical phenomena. One of the major challenges for understanding and developing energy systems and management platforms is accurate modeling/forecasting of atmospheric conditions across disparate spatial and temporal scales. These conditions are often required to understand the lowest levels of the atmospheric boundary layer, but are also important to understand higher atmospheric conditions where aerosols affect cloud development. The objective of this work was to develop partnerships with national laboratories for collaboration on environmental science and its intersection with sustainable energy systems, as well as to leverage the ARM user facility data repositories to enhance our research capabilities in energy systems and their inter-dependence on environmental systems for future engagement with EESSD. Specifically, we accomplished these objectives by (1) developing collaborations with Oakridge National Laboratory ARM Data Science and Integration Group which resulted in student internships, (2) employed ARM data to develope modeling of the atmospheric boundary layer optical turbulence, and (3) optimally-sized large-scale renewable energy systems and their associated energy storage systems with ARM repository data.

29 ENERGY PLANNING, POLICY, AND ECONOMY↗
DOE OSTI2025

Uncovering hidden enhancers through unbiased in vivo testing

Chromatin signatures are widely used to identify tissue-specific in vivo enhancers, but their sensitivity and specificity remains unclear. Here we show that many developmental enhancers remain undetectable using currently available chromatin data. In an initial comparison of over 1200 developmental enhancers with tissue-matched chromatin data, 14% (n = 285) lacked canonical enhancer-associated chromatin signatures. To further assess the prevalence of enhancers missed by chromatin profiling approaches, we used a high-throughput transgenic enhancer assay to screen the regulatory landscapes of two key developmental genes at 5 kb resolution, spanning 1.3 Mb of mouse sequence in total. We observed that 23 of 88 (26%) in vivo enhancers discovered by this approach lacked enhancer-associated chromatin signatures in the respective tissue. Our findings suggest the existence of tens of thousands of enhancers that remain undiscovered by currently available chromatin data, underscoring the continued need for expanding resources for enhancer discovery.

Epigenomics↗
DOE OSTI2025

Boosting Noise2Inverse via enhanced model selection for denoising computed tomography data

Synchrotron-based x-ray tomographic imaging enables the examination of the internal structure of materials at high spatial and temporal resolution. Experimental constraints can impose dose and time limits on the measurements, introducing a higher level of noise and artifacts in the reconstructed images. Deep learning has emerged as a powerful tool to remove noise from reconstructed images. Recently, the Noise2Inverse method was designed specifically for denoising reconstructed images without requiring paired noisy and clean images. This method creates multiple statistically independent reconstructions used to pair the data in which training involves transforming one reconstruction into the other, and vice versa. Originally designed to be used after a fixed number of epochs, we see in practice that this approach may not produce the optimal model and may unnecessarily waste computational resources. Therefore, we propose an alternative method of identifying the best model during training that aligns with the Noise2Inverse method. During validation, we compare the model output of the multiple reconstructions among each other. We hypothesize that the best model is the one that produces images with the highest similarity, implying a convergence in the predicted material properties and absorption values. To compare model outputs, we consider the absolute error, square error, structural similarity index (SSIM), peak signal-to-noise ratio (PSNR), and cosine similarity. We evaluate our method on two simulated tomography datasets and two, real-world, low-contrast, high-energy x-ray tomography datasets. We show our approach is more effective at determining the best model, up to an increase of 12.50% and 12.53% in SSIM and PSNR, respectively, while only requiring a fifth of the training time compared to the original approach.

CT↗
DOE OSTI2025

Digital Filter Design for Point-on-Wave Sensors: Highlighting Frequency Response Limitations and Enhancing Grid Simulation Accuracy

Data is proving to be the backbone of today's and, more importantly, tomorrow's grid. As the system changes and introduces fast-acting devices like power electronics, overall observability tends to decrease from the utility point-of-view. This can be mitigated by adding more high-fidelity sensors onto the grid, although this incurs a cost. These sensors are never ideal, and each have unique frequency responses that may influence the data produced. This may, in turn, impact the protection and control of the power grid. This paper presents a methodology of representing these point-on-wave sensors digitally by estimating digital-filter representations of them, thereby introducing means of improving the sensor models used in electromagnetic-transient (EMT) simulations. This may help with identifying potential high-frequency, sensor-induced distortions, and system resonance compensation. Three commercial-grade medium-voltage point-on-wave sensors are utilized in a lab environment to obtain experimental frequency responses with a frequency sweep, and it is shown that both Infinite Impulse Response (IIR) and Finite Impulse Response (FIR) filter representations may approximate these responses with varying degrees of accuracy, though each has their own strengths and weaknesses. It is found that, in general, FIR estimation better approximates these sensors than IIR estimation does.

Wilson, Aaron [ORNL] (ORCID:0000000327331697)↗
DOE OSTI2025

Enhancing Cluster Identification in Atom Probe Tomography Data Using Transfer Learning

Atom probe tomography (APT) has enabled the direct visualization of solute clusters, providing valuable insights into material structures. This clustering is crucial for understanding the nanoscale composition and behavior of materials, which can significantly influence their mechanical and physical properties. However, the widely used clustering methods in the APT community face challenges such as subjective parametric selection and limited applicability, particularly in dealing with overlapping clusters, nested clusters, and artifacts across different scales, such as precipitates and dislocations. To address these challenges, we present a framework based on density-based cluster analysis that aims to be less dependent on user input, reproducible, and robust.

Density-based clustering↗
DOE OSTI2025

Enhancing Cluster Identification in Atom Probe Tomography Data Using Transfer Learning

Atom Probe Tomography (APT) is a powerful technique for visualizing the atomic-scale distribution of solutes in materials, but quantitative cluster analysis of APT datasets remains a challenge due to the need for subjective parameter selection in clustering algorithms. While distance-based and density-based methods such as HDBSCAN are widely used, their performance is highly sensitive to user-defined parameters, which undermines reproducibility and accuracy. This study proposes an image-based, deep learning-aided workflow for automating parameter selection and cluster detection in APT data analysis. By projecting 3D APT point clouds onto 2D planes, we leverage pretrained convolutional neural networks (ConvNeXt-Tiny and ResNet-50) through transfer learning to predict the number of clusters present in synthetic datasets. The output is used to guide K-means clustering and estimate HDBSCAN parameters, specifically minimum cluster size and minimum sample points. This approach reduces reliance on manual parameter tuning, improving consistency and scalability. The methodology demonstrates the feasibility of using image-based deep learning for interpreting complex spatial patterns in APT data, enabling faster and more objective analysis. The complete workflow and code are made publicly available to support reproducibility and future research.

Density-based clustering↗
DOE OSTI2026

Advanced Semi-Supervised Learning with Uncertainty Estimation for Phase Identification in Distribution Systems

The integration of advanced metering infrastructure (AMI) into power distribution networks generates valuable data for tasks such as phase identification; however, the limited and unreliable availability of labeled data in the form of customer phase connectivity presents challenges. To address this issue, we propose a semi-supervised learning (SSL) framework that effectively leverages labeled and unlabeled data. Our approach incorporates self-training, label spreading, and Bayesian neural networks (BNNs) to enhance phase identification with AMI data. Our method uses an ensemble of multilayer perceptron classifiers in a self-training setup, iteratively adding high-confidence pseudo-labels to improve robustness. We also apply label spread to propagate labels based on data similarity, which enhances generalization across diverse distributions. In addition, we employ a BNNs with uncertainty estimation, boosting confidence in predictions and reducing phase identification errors. In our case study, we achieved approximately 98% +/- 0.08 accuracy with uncertainty using minimal and unreliable labeled data from a real U.S. utility, Duquesne Light Company. Our SSL approach, combined with uncertainty estimation, provides an efficient solution for phase identification in AMI data, ultimately improving the reliability of smart grid applications.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2026

Advanced Semi-Supervised Learning With Uncertainty Estimation for Phase Identification in Distribution Systems

The integration of advanced metering infrastructure (AMI) into power distribution networks generates valuable data for tasks such as phase identification; however, the limited and unreliable availability of labeled data in the form of customer phase connectivity presents challenges. To address this issue, we propose a semi-supervised learning (SSL) framework that effectively leverages labeled and unlabeled data. Our approach incorporates self-training, label spreading, and Bayesian neural networks (BNNs) to enhance phase identification with AMI data. Our method uses an ensemble of multilayer perceptron classifiers in a self-training setup, iteratively adding high-confidence pseudo-labels to improve robustness. We also apply label spread to propagate labels based on data similarity, which enhances generalization across diverse distributions. In addition, we employ a BNNs with uncertainty estimation, boosting confidence in predictions and reducing phase identification errors. In our case study, we achieved approximately 98% +/- 0.08 accuracy with uncertainty using minimal and unreliable labeled data from a real U.S. utility, Duquesne Light Company. Our SSL approach, combined with uncertainty estimation, provides an efficient solution for phase identification in AMI data, ultimately improving the reliability of smart grid applications.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2022

Lithium-Ion Mobility in Layered Oxide Li 2 (La 0.75 Li 0.25 )(Ta 1.5 Ti 0.5 )O 7 Containing Lithium on both Intra and Inter‐Stack Positions

With the aid of neutron diffraction and electrochemical impedance spectroscopy, we have demonstrated the effect of the increase in lithium concentration and distribution on Li-ion conductivity. This has been done through the synthesis of a layered oxide Li 2 (La 0.75 Li 0.25 )(Ta 1.5 Ti 0.5 )O 7 , with the so-called Ruddlesden-Popper type structure, where bilayer stacks of (Ta/Ti)O 6 octahedra are separated by lithium ions, located in inter-stack spaces. There are also intra-stack spaces that are occupied by a mixture of La and Li, as confirmed by neutron diffraction. The distribution of lithium over both inter- and intra-stack positions leads to the enhancement of Li-ion conductivity in Li 2 (La 0.75 Li 0.25 )(Ta 1.5 Ti 0.5 )O 7 compared to Li 2 La(TaTi)O 7 , which has a lower concentration of lithium ions, located only in inter-stack spaces. Furthermore, the analyses of real and imaginary components of electrochemical impedance data confirm the enhanced mobility of ions in Li 2 (La 0.75 Li 0.25 )(Ta 1.5 Ti 0.5 )O 7 . While the Li-ion conductivity needs further improvement for practical applications, the success of the strategy implemented in this work offers a useful methodology for the design of layered ionic conductors.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2021

SeismoGen: Seismic Waveform Synthesis Using GAN With Application to Seismic Data Augmentation

Abstract Detecting earthquake arrivals within seismic time series can be a challenging task. Visual, human detection has long been considered the gold standard but requires intensive manual labor that scales poorly to large data sets. In recent years, automatic detection methods based on machine learning have been developed to improve the accuracy and efficiency. However, the accuracy of those methods relies on access to a sufficient amount of high‐quality labeled training data, often tens of thousands of records or more. We aim to resolve this dilemma by answering two questions: (1) provided with a limited amount of reliable labeled data, can we use them to generate additional, realistic synthetic waveform data? and (2) can we use those synthetic data to further enrich the training set through data augmentation, thereby enhancing detection algorithms? To address these questions, we use a generative adversarial network (GAN), a type of machine learning model which has shown supreme capability in generating high‐quality synthetic samples in multiple domains. Once trained, our GAN model is capable of producing realistic seismic waveforms of multiple labels (noise and event classes). Applied to real Earth seismic data sets in Oklahoma, we show that data augmentation from our GAN‐generated synthetic waveforms can be used to improve earthquake detection algorithms in instances when only small amounts of labeled training data are available.

Wang, Tiantong↗
DOE OSTI2022

Using Splunk® Enterprise Search Commands for Advanced Analysis of Ivanti Connect Secure© Logs

Analyzing the logs of even the smallest Information Technology (IT) system can be a challenge considering they can generate millions of lines of log data in a very short time. Splunk® Enterprise is an industry leading tool that allows analysis of log data, which can enhance troubleshooting capabilities, improve system performance, and improve the security posture of an IT system. Ivanti Connect Secure© (ICS) is a market-leading platform powered by the Ivanti Secure Socket Layer Virtual Private Network (SSL VPN) appliance, providing an architecture for secure access to and protection of network resources. This paper describes an approach for using Splunk Enterprise search capabilities to perform advanced data analysis of ICS logs.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2026

QProR: An Efficient Framework for Quantity-of-Interest Based Progressive Retrieval with Guaranteed Error Control

Scientific applications generate an unprecedented volume of data, overwhelming the network and file systems’ bandwidth and posing challenges for efficient and scalable data retrieval and analysis. Progressive data compression offers a promising solution by enabling on-demand retrieval at reduced size. However, existing progressive methods either fail to bound the errors in essential quantities of interest (QoIs) derived from raw data or suffer from suboptimal retrieval efficiency. In this work, we propose QProR, an efficient QoI-based progressive framework that optimizes progressive retrieval for target QoIs. Our key contributions include: (1) a systematic framework that integrates error-controlled lossy compressors with bitplane encoding while decoupling the two processes for high flexibility and adaptability; (2) a novel weighted bitplane encoding method which incorperates QoI knowledge into data refactoring to enhance retrieval efficiency; (3) an optimized retrieval strategy that accounts for the varying impacts of different variables on multivariate QoIs; (4) comprehensive evaluations using six real-world datasets from multiple scientific applications and thorough comparisons against state of the arts. Experimental results demonstrate that QProR achieves up to 80.38% reduction in the retrieval size under the same requested QoI error tolerance, when compared with the best-performing existing methods. When transferring 384 GB of scientific data to remote sites, QProR delivers up to 1.68 × speedup in the end-to-end data transfer performance.

Li, Wenbo [University of Kentucky]↗
DOE OSTI2025

The Natural Products Magnetic Resonance Database (NP-MRD) for 2025

The Natural Products Magnetic Resonance Database or NP-MRD (https://np-mrd.org) is a comprehensive, freely accessible, web-based resource for the deposition, distribution, extraction and retrieval of nuclear magnetic resonance (NMR) data on natural products. The NP-MRD was initially established to support compound de-replication and data dissemination for the natural products community. However, that community has now grown to include many users from the metabolomics, microbiomics, foodomics and nutrition science fields. Indeed, since its launch in 2021, the NP-MRD has expanded enormously in size, scope and popularity. The current version of NP-MRD now contains nearly 7X more compounds (281,859 vs. 40,908) and 7X more NMR spectra (5.1 million vs. 817,000) than the first release. More specifically, an additional 4.6 million predicted spectra and another 11,000 spectra simulated from experimental chemical shifts were deposited into the database. Likewise, the number of NMR raw spectral data depositions has grown from a 165 spectra per year to more than 10,000 per year. As a result of this expansion, the number of monthly webpage views has grown from 55 to 20,000 and the number of monthly visitors has increased from 7 to 2500. To address this growth and to better support the expanding needs of its diverse community of users, many additional improvements to the NP-MRD have been made. These include significant enhancements to the data submission process, important improvements to the visualization and display of NMR spectra, notable updates to the database’s spectral search utilities and useful additions to support better NMR spectral analysis/prediction. Significant efforts have also been undertaken to remediate and update many of NP-MRD’s database entries. This manuscript describes these database improvements and expansion efforts, along with how they have been implemented and what future upgrades to the NP-MRD are planned.

Artifical Intelligence↗
DOE OSTI2025

Fostering Geothermal Machine Learning Success: Elevating Big Data Accessibility and Automated Data Standardization in the Geothermal Data Repository

The Department of Energy's (DOE's) Geothermal Data Repository (GDR) has implemented improvements to both its data lakes and its data standards and automated data pipelines. The GDR data lakes have reduced storage and compute-related barriers to using large geothermal datasets, enabling these large datasets to be accessed by anyone with a modern computer and internet access. More recently, the GDR has been working to further reduce barriers through streamlining the data intake process, educating users on the process and requirements, and helping users access data from the data lakes. These improvements have augmented the quantity of datasets the GDR is able to accept into its data lakes and have enabled users who are new to cloud tools to access these datasets more easily, overall increasing the accessibility of big geothermal data for use in machine learning and other projects. In addition, the GDR now has built-in data standards and pipelines for drilling data, geospatial data, and distributed acoustic sensing (DAS) data. These standardization efforts aim to enhance the real-world applicability of geothermal machine learning outcomes by improving the quality of training data. Specifically, through standardizing high-value datasets, the GDR is reducing project-specific data curation requirements, thus allowing more time for actual research. By automating this process, the burden of standardization is lifted from the user, ultimately increasing the availability of standardized data. This paper provides an update on recent improvements made to the GDR's data lakes and automated data pipelines, including: (1) streamlining the data lake intake process, (2) better educating users on the process and requirements through a new data lakes page, (3) adding data lake direct access links to GDR data lake submission pages, (4) implementing a DAS data pipeline to convert DAS data uploaded in SEG-Y format to a standardized hierarchical data format v5 (HDF5), (5) extending this pipeline to encompass data in the GDR data lake, (6) adding metadata requirements for geospatial data, (7) making user interface/user experience (UX) enhancements to the data pipelines' documentation pages, and (8) improving the GDR's data standards and pipelines pages to better guide users in ensuring that their data is standardized by the GDR's automated data pipelines. 2024 Geothermal Resources Council. All rights reserved.

accessibility↗
DOE OSTI2025

Assimilating partial observation to enhance feedback control of stochastic dynamical systems

Here, in this paper, we present a novel methodology to tackle feedback optimal control problems in scenarios where the exact state of the controlled process is unknown. It integrates data assimilation techniques and optimal control solvers to manage partial observation of the state process, a common occurrence in practical scenarios. Traditional stochastic optimal control methods assume full state observation, which is often not feasible in real-world fluid dynamics control problems. Our approach underscores the significance of utilizing observational data to inform control policy design. Specifically, we introduce a kernel learning backward stochastic differential equation (SDE) filter to enhance data assimilation efficiency and propose a sample-wise stochastic optimization method within the stochastic maximum principle framework. We demonstrate the efficacy and accuracy of our method in the control of advection-diffusion-reaction flow problem and the Dubins airplane maneuvering problem with model uncertainty.

data driven↗