Search NASA⌕ Search

SEARCH · Search NASA

Results for “feature engineering”

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 145 records · Page 8

Review of hydrodynamic instability experiments in inertially confined fusion implosions on National Ignition Facility

Hydrodynamic instabilities are a major factor in degradation of inertial confinement fusion (ICF) implosions. In the highest performing implosions on National Ignition Facility, yield amplification (YA) due to alpha particle heating approached ~3, while YA of ~15–30 is needed for ignition. Understanding and mitigation of the instabilities are critical to achieving ignition. This article reviews several experimental platforms that have been developed to directly measure these instabilities in all phases of ICF implosions. Measurements of ripple-shock propagation at OMEGA laser has provided results on initial seeds for the instabilities in three ablators—plastic (CH), beryllium, and high-density carbon. Additionally, at the ablation front, instability growth of pre-imposed modulations was measured in the linear regime using the hydrodynamic growth radiography platform. This platform was extended for modulation growth of 'native roughness' modulations and engineering features (fill tubes and capsule support membranes or 'tents'). Several new experimental platforms have or are being developed to measure instability growth at the ablator–ice interface. In the deceleration phase of implosions, complementary 'self-emission' and 'self-backlighting' platforms were developed to measure low-mode asymmetries and high-mode perturbations near peak compression.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗

Modeling and projecting implosion performance for the National Ignition Facility

Steady progress is being made in inertial confinement fusion experiments at the National Ignition Facility (NIF). Nonetheless, substantial further progress is still needed to reach the ultimate goal of fusion ignition. Closing the remaining gap will require either improving the quality of current implosions, increasing the implosion scale (and correspondingly the energy delivered by NIF), or some combination of the two. But how much of an improvement in implosion quality or energy scale is required to reach ignition? To reliably answer this question, an accurate understanding of current and past experiments is first required. Previous modeling efforts of NIF implosions have shown the need to resolve a wide range of scales (from microns to millimeters) as well as a faithful representation of the genuinely three-dimensional (3D) character of the stagnation process. Modeling NIF implosions is further complicated by the many perturbation sources that have been found to influence integrated implosion performance: flux asymmetries from the surrounding hohlraum, engineering features such as support tents and fill tubes, surface defects and contaminants, and more recently the radiation shadow cast by the fill tube on the capsule. A model including all of these effects, and with adequate resolution, challenges current computing capabilities but has recently become feasible on the largest computers. Here, we review the status of these multi-effect, 3D simulations of NIF implosions, their comparison to experimental data, and preliminary results on scaling these simulations to the threshold of ignition on NIF.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗

End-to-End Event Classification of High-Energy Physics Data

Feature extraction algorithms, such as convolutional neural networks, have introduced the possibility of using deep learning to train directly on raw data without the need for rule-based feature engineering. In the context of particle physics, such end-to-end approaches can be used for event classification to learn directly from detector-level data in a way that is completely independent of the high-level physics reconstruction. We demonstrate a technique for building such end-to-end event classifiers to distinguish simulated electromagnetic decays in a high-fidelity model of the CMS Electromagnetic Calorimeter.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

Photometric identification of compact galaxies, stars, and quasars using multiple neural networks

We present MargNet, a deep learning-based classifier for identifying stars, quasars, and compact galaxies using photometric parameters and images from the Sloan Digital Sky Survey Data Release 16 catalogue. MargNet consists of a combination of convolutional neural network and artificial neural network architectures. Using a carefully curated data set consisting of 240 000 compact objects and an additional 150 000 faint objects, the machine learns classification directly from the data, minimizing the need for human intervention. MargNet is the first classifier focusing exclusively on compact galaxies and performs better than other methods to classify compact galaxies from stars and quasars, even at fainter magnitudes. This model and feature engineering in such deep learning architectures will provide greater success in identifying objects in the ongoing and upcoming surveys, such as Dark Energy Survey and images from the Vera C. Rubin Observatory.

79 ASTRONOMY AND ASTROPHYSICS↗

IL-Net: Using Expert Knowledge to Guide the Design of Furcated Neural Networks

Deep neural networks (DNN) excel at extracting patterns. Through representation learning and automated feature engineering on large datasets, such models have been highly successful in computer vision and natural language applications. Designing optimal network architectures from a principled or rational approach however has been less than successful, with the best successful approaches utilizing an additional machine learning algorithm to tune the network hyperparameters. However, in many technical fields, there exist established domain knowledge and understanding about the subject matter. In this work, we develop a novel furcated neural network architecture that utilizes domain knowledge as high-level design principles of the network. We demonstrate proof-of-concept by developing IL-Net, a furcated network for predicting the properties of ionic liquids, which is a class of complex multi-chemicals entities. Compared to existing state-of-the-art approaches, we show that furcated networks can improve model accuracy by approximately 20-35%, without using additional labeled data. Lastly, we distill two key design principles for furcated networks that can be adapted to other domains.

Sakloth, Khushmeen↗

Extensive Attention Mechanisms in Graph Neural Networks for Materials Discovery

We present our research where attention mechanism is extensively applied to various aspects of graph neural net- works for predicting materials properties. As a result, surrogate models can not only replace costly simulations for materials screening but also formulate hypotheses and insights to guide further design exploration. We predict formation energy of the Materials Project and gas adsorption of crystalline adsorbents, and demonstrate the superior performance of our graph neural networks. Moreover, attention reveals important substructures that the machine learning models deem important for a material to achieve desired target properties. Our model is based solely on standard structural input files containing atomistic descriptions of the adsorbent material candidates. We construct novel methodological extensions to match the prediction accuracy of state-of-the-art models some of which were built with hundreds of features at much higher computational cost. We show that sophisticated neural networks can obviate the need for elaborate feature engineering. Our approach can be more broadly applied to optimize gas capture processes at industrial scale.

Cong, Guojing↗

Falls Risk Classification of Older Adults Using Deep Neural Networks and Transfer Learning

Prior research in falls risk classification using inertial sensors has relied on the use of engineered features, which has concluded in a feature space containing hundreds of features that are likely redundant and possibly irrelevant. In this paper, we propose using fully convolutional neural networks (FCNNs) to classify older adults at low or high risk of falling using inertial sensor data collected from a smartphone. Due to the limited nature of older adult inertial gait data sets, we first pre-train the FCNN models using a publicly available data set for pedestrian activity recognition. Then via transfer learning, we train the network for falls risk classification. We reveal that via transfer learning, our falls risk classifier obtains an area under the receiver operating characteristic curve of 93.3%, which is 10.6% higher than the equivalent model trained without the use of transfer learning. Moreover, we show that our method outperforms other standard machine learning classifiers trained on features developed in prior research.

60 APPLIED LIFE SCIENCES↗

Deep Cellular Recurrent Network for Efficient Analysis of Time-Series Data With Spatial Information

Efficient processing of large-scale time series data is an intricate problem in machine learning. Conventional sensor signal processing pipelines with hand engineered feature extraction often involve huge computational cost with high dimensional data. Deep recurrent neural networks have shown promise in automated feature learning for improved time-series processing. However, generic deep recurrent models grow in scale and depth with increased complexity of the data. This is particularly challenging in presence of high dimensional data with temporal and spatial characteristics. Consequently, this work proposes a novel deep cellular recurrent neural network (DCRNN) architecture to efficiently process complex multi-dimensional time series data with spatial information. Here, the cellular recurrent architecture in the proposed model allows for location-aware synchronous processing of time series data from spatially distributed sensor signal sources. Extensive trainable parameter sharing due to cellularity in the proposed architecture ensures efficiency in the use of recurrent processing units with high-dimensional inputs. This study also investigates the versatility of the proposed DCRNN model for classification of multi-class time series data from different application domains. Consequently, the proposed DCRNN architecture is evaluated using two time-series datasets: a multichannel scalp EEG dataset for seizure detection, and a machine fault detection dataset obtained in-house. The results suggest that the proposed architecture achieves state-of-the-art performance while utilizing substantially less trainable parameters when compared to comparable methods in the literature.

60 APPLIED LIFE SCIENCES↗

Characterization and identification of HPC applications at leadership computing facility

High Performance Computing (HPC) is an important method for scientific discovery via large-scale simulation, data analysis, or artificial intelligence. Leadership-class supercomputers are expensive, but essential to run large HPC applications. The Petascale era of supercomputers began in 2008, with the first machines achieving performance in excess of one petaflops, and with the advent of new supercomputers in 2021 (e.g., Aurora, Frontier), the Exascale era will soon begin. However, the high theoretical computing capability (i.e., peak FLOPS) of a machine is not the only meaningful target when designing a supercomputer, as the resources demand of applications varies. A deep understanding of the characterization of applications that run on a leadership supercomputer is one of the most important ways for planning its design, development and operation. In order to improve our understanding of HPC applications, user demands and resource usage characteristics, we perform correlative analysis of various logs for different subsystems of a leadership supercomputer. This analysis reveals surprising, sometimes counter-intuitive patterns, which, in some cases, conflicts with existing assumptions, and have important implications for future system designs as well as supercomputer operations. For example, our analysis shows that while the applications spend significant time on MPI, most applications spend very little time on file I/O. Combined analysis of hardware event logs and task failure logs show that the probability of a hardware FATAL event causing task failure is low. Combined analysis of control system logs and file I/O logs reveals that pure POSIX I/O is used more widely than higher level parallel I/O. Based on holistic insights of the application gained through combined and co-analysis of multiple logs from different perspectives and general intuition, we engineer features to "fingerprint" HPC applications. We use t-SNE (a machine learning technique for dimensionality reduction) to validate the explainability of our features and finally train machine learning models to identify HPC applications or group those with similar characteristic. To the best of our knowledge, this is the first work that combines logs on file I/O, computing, and inter-node communication for insightful analysis of HPC applications in production.

Liu, Zhengchun↗

Tandem Predictions for HPC Jobs

At the core of the predictive analytics applied to High Performance Computing (HPC), the most prominent tasks are the prediction of job runtimes and the prediction of job queue times, both of which have the potential for informing HPC users during their every-day decision making. Accurate runtime predictions can help users better choose so-called wallclock times at job submission, decreasing the odds of their jobs waiting in queues longer than necessary. The accurate and timely queue time predictions offered for the available partitions can inform the favorable selection of partitions for running jobs. This potential is well understood as we see in the abundance of research studies that propose solutions for these tasks, including the work published in the last several years. These tasks are seemingly receptive to the Machine Learning (ML) solutions, considering that there is no shortage of training data where HPC centers over time run millions and millions of jobs. However, we study the existing research literature, as well as look for examples in the toolchains supported on the exemplar HPC facilities, and, surprisingly, do not find any practical solutions that are ready to be adopted. We interpret this as a manifestation of the shortage of UX/UI efforts that support HPC analytics and also as a sign that the research has not come to the consensus on solving these tasks. In this study, we aim to shed new light on the long-running task of job queue time prediction by exploring the utility of runtime predictions in improving prediction accuracy and, actually, predicting these two metrics together, in tandem. In other words, we show how runtime predictions become valuable input in the queue time modeling. We challenge the existing approaches to feature engineering for the queue time prediction and describe promising results we obtained for a large dataset of HPC jobs from a supercomputer at the National Renewable Energy Laboratory.

HPC↗

Avian Activity Classification Using Recurrent Networks to Fuse Videos with Metadata on Imbalanced Datasets

Activity classification plays a crucial role in various real-life scenarios involving both humans and animals. There is an increasing need for precise activity classification focused on avian-solar interactions, as the usage of solar energy facilities, such as photovoltaic array power stations, has been observed to impact bird species richness, behavior, and activity. However, there has been no work to develop an automated system to monitor and classify these avian-solar interactions. All current methods rely on human observers, which is time and human resources costly and subject to errors related to searcher efficiency. With the recent success of Deep Learning models in activity classification problems, this paper develops a recurrent neural network-based model to automatically classify six avian activities around solar energy facilities. Our proposed model integrates critical feature engineering metadata with video frame data, enabling improved learning and more accurate activity classification. Furthermore, we address the challenge of data imbalance during training and demonstrate the efficacy of our model in detecting and classifying different activities within video tracks. Additionally, we analyze the saliency/backpropagation map of the trained proposed model and validate its decision-making rationale.

Avian activity classification; bidirectional LSTM;↗

ASP (Adaptive Splines for Prediction) [SWR-22-66]

This software package provides functionality to fit piecewise cubic splines to model the relationship between a univariate X (independent variable) and a univariate Y (dependent variable). The output is akin to linear regression but has higher "capacity" in that it can learn more complicated relationships despite leveraging only a single predictor. It thus can learn very reasonable relationships between X and Y with minimal effort. The canonical intended use case is for predicting electric demand (Y) from temperature (X). There can be complicated, non-linear relationships between these two variables, but these can be reasonably approximated by the sum of: 1) an "aggregate" relationship between daily average temperature and daily average demand, and 2) intra-day patterns represented as hourly offsets from the daily average load. The spline functionality is used for learning a robust "aggregate" relationship without the inconvenience of manual feature engineering while still ensuring robust results. The model fitting workhorse is R's built-in smooth.spline. This package provides a suite of options for controlling how smooth.spline fits a spline to the data. In particular, it is designed to return a model with a single critical point (i.e., a single location along the domain/support where the first derivative is zero). This is to ensure that predicted changes in electric demand are always positive as temperatures become more extreme. This helps to prevent overfitting, particularly when the input data has few observations or has significant uncertainty from other sources.

Murphy, Sinnott↗

Risk-informed Predictive Analytics To Achieve Cost-effective Condition-based Monitoring And Maintenance Strategy

The research involves developing risk-informed predictive analytic capabilities to achieve condition-based monitoring and maintenance strategies to reduce overall maintenance costs. The research utilizes data (real-time data, periodic data, and institutional knowledge) related to a particular plant asset from a specific nuclear plant site to develop risk-informed predictive analytic algorithms. The developed algorithms and codes are used to optimize the maintenance strategy and estimate/forecast generation costs based on the state of health of the plant asset. Developed codes specifically include 1. Parameter estimation code based on Bayesian inference 2. Statistical data analysis code 3. Feature engineering code 4. Health classifier code 5. Diagnosis code 6. Prognosis code 7. Hazard code 8. Generation risk code 9. Economic code

Agarwal, Vivek↗

Moltensaltpropnet

MoltenSaltPropnet is a physics-informed machine learning framework that aims to predict the thermophysical properties of molten fluoride and chloride salt mixtures, which are crucial for the design and safety of Generation IV molten salt reactors. The code processes data from the Molten-Salt Thermal Properties Database (MSTDB-TP) and the Janz compendium, converting critically evaluated correlations into fast, differentiable surrogate models for density, viscosity, thermal conductivity, and heat capacity across 448 distinct salt systems. The implementation consists of several key components: 1. Data Curation: The code parses and cleans the raw data, normalizing elemental mole fractions and extracting relevant regression coefficients for various thermophysical properties. 2. Feature Engineering: It generates fixed-length numerical descriptors that encapsulate the composition and temperature, incorporating polynomial interaction terms and dimensionality-reduction techniques to optimize model performance. 3. Coefficient Learning: Four different machine learning architectures are employed: a deep residual network (ResNet), a Kolmogorov–Arnold network (KAN), a sparsity-inducing neural network (SNN), and classical regression models. Each model learns to predict coefficients that define the temperature-dependent correlations for the thermophysical properties. 4. Property Reconstruction: The predicted coefficients are used to compute temperature-dependent property values, ensuring positivity and monotonic trends through a composite loss function that enforces physical constraints. 5. User Interface: An open-source web application enables users to filter the database, train task-specific models, and visualize the results, allowing for rapid exploration of candidate salt mixtures. MoltenSaltPropnet bridges the gap between limited experimental data and high-fidelity reactor simulations, providing a powerful tool for researchers in the field of molten salt reactors and advanced nuclear energy systems.

Retamales, Mauricio Eduardo Tano [Idaho National L↗

Dataset: "Widespread Drought-driven Declines in Streamflows and Water quality in the Upper Colorado River Basin (1998-2022)"

This data package contains the associated data and scripts for Nagamoto, E., Ombadi, M., Ciulla, F. et al. Widespread drought-driven declines in streamflows and water quality in the Upper Colorado River Basin during 1998-2022. Commun Earth Environ 7, 734 (2026). https://doi.org/10.1038/s43247-026-03890-5. This purpose of this study was to investigate the impact of the 21st century drought on water quantity and quality at catchments throughout the Upper Colorado River Basin (UCRB). We used stream flow, water temperature, specific conductance, air temperature, precipitation, and catchment attribute data for over 200 sites in the UCRB, collected from the National Water Information System using Basin3D (Varadharajan, 2023), GAGESII (Falcone, 2010), and the Google Earth Engine. We identified years of severe drought between 1998 and 2022 using the Standardized Precipitation Evaporation Index (SPEI), then calculated the relative change percentage of the stream flow, water temperature, and specific conductance from drought versus non-drought years. We used the attribute information from GAGESII to investigate what physical traits of catchments are associated streamflow vulnerability (greater relative change) or resilience to drought. We used land cover data from the National Land Cover Database (USGS, 2024) to assess any changes to physical attributes that may not be represented in the static attributes information in GAGESII. To increase data availability, we modeled stream temperature using methods from Willard, 2023. While the study period is water years 1998 to 2022, the raw water quantity and quality data extends to 1950 and the meteorological data extends to 1980. The data and code can be downloaded via the UCRB_drought.zip. Within the zip, the files are organized as follows: - INPUTS: Contains all input data used in UCRB_Drought_Workflow.ipynb - OUTPUTS: Contains all intermediate data created from UCRB_Drought_Workflow.ipynb as well as final products including the calculated Standardized Evapotranspiration Index (SPEI) - climatic_variables: The code used to collect meteorologic data from Google Earth Engine - feature_importance: The code used for the catchment attributes analysis - preprocessing: Code used in UCRB_Drought_Workflow_Preprocessing.ipynb - pyeto: Code used in UCRB_Drought_Workflow_Preprocessing.ipynb - calculations: Code used in UCRB_Drought_Workflow_Impacts.ipynb - plotting: Code used in UCRB_Drought_Workflow_Impacts.ipynb - README.md - UCRB_Drought_Workflow_Preprocessing.ipynb: The code used to prep raw data for the analysis - UCRB_Drought_Workflow_Impact.ipynb: The code which uses the prepped raw data for analysis, and plots all figures - requirements_ucrb-drought_v2.yml: The requirements file to create a virtual environment and Jupyter Lab kernel to run the code The INPUTS folder is organized into the following major directories and sub-directories. The "RDC_WT_SC_RAW" folder contains raw data for streamflow, water temperature, and specific conductance in a ".h5" file. The "NLCD_RAW" folder contains ".csv" files with annual land cover percentages for counties within the UCRB. The "MET_RAW" folder contains a ".csv" file with monthly meteorological data (air temperature and precipitation) for the sites in the UCRB which was obtained from code in the climatic_variables folder. The "GAGESII" folder contains ".csv" files with physical catchment attribute variables for catchments across the country. The "WT_LSTM_data" folder contains ".csv" files with calculated WT (Willard, 2023) and the associated RMSEs. The "Upper_Colorado_River_Basin_Boundary" folder contains geographic data including a shapefile for plotting in the UCRB_Drought_Workflow.ipynb. The "RESERVOIRS_RAW" folder contains ".csv" files for each reservoir in the UCRB with daily reservoir storage. There are also two files in the INPUTS folder that have combined reservoir storage data and reservoir metadata. The OUTPUTS folder is organized into the following major directories and sub-directories. The "RDC_WT_SC_data" folder contains a folder "Water_year" with the associated cleaned data, metadata, and data availability information in ".csv" files, a folder "Median_Relchange" with the relative change comparing drought to non-drought years in ".csv" files, and a folder "Peak95_Min5_Relchange" that has ".csv" files for the relative change in peak (95th %) and minimum (5th %) variables. The "NLCD_data" folder contains the difference in land cover from the beginning to end of the study period and the percentage of the county that is within UCRB bounds can be found in Nagamoto et al (2025)). The "MET_data" folder contains separated monthly air temperature and precipitation data and the calculated PET in ".csv" files. The "SPEI_data" folder contains ".csv" files with calculated SPEI values (one restricted to the study period and the other with information from the entire MET data period). The "Paper_Tables" folder contains two ".csv" files containing site information and data availability and information about the GAGESII trait aggregated categories. The base directory includes the file “flmd.csv” for a list and description of all files and the file “dd.csv” for data dictionaries. Scripts for preprocessing, analysis, and figure generation are located in the associated GitHub repository found at [https://github.com/iNAIADS/drought-impacts/tree/develop/UCRB-drought]. UPDATE 1: Title and code file updated to match submitted manuscript 10-15-2025. UPDATE 2: Code and data files updated to match revised manuscript 3-4-2026. UPDATE 3: Code and data files updated to match revised manuscript 6-7-2026. ** NOTE: DD and FLMD have not been updated yet. UPDATE 4: Added associated Manuscript information and DD and FLMD have been updated. To cite this code, please use the following BibTeX: @misc{nagamoto2025drought, author = {Emily Nagamoto and Fabio Ciulla and Mohammad Ombadi and Jared Willard and Rosemary Carroll and Charuleka Varadharajan}, title = {Dataset: "Widespread Drought-driven Declines in Streamflows and Water quality in the Upper Colorado River Basin (1998-2022)"}, year = {2025}, doi = {10.15485/2551894}, publisher = {ESS-DIVE Repository}, url = {https://data.ess-dive.lbl.gov/datasets/doi:10.15485/2551894} }

54 ENVIRONMENTAL SCIENCES↗

Phase Picking Beyond Local Distances: Where Waveform Filtering Still Matters for Deep Learning Models

Waveform filtering is a standard step in traditional seismic phase picking but often receives little attention in deep learning workflows, where models are typically trained on raw or minimally processed waveforms. Although this strategy performs well for local events, we show that performance can degrade substantially at regional distances. To address this limitation, we introduce two ways to incorporate multiband-filtered waveforms into deep learning phase pickers. The stacking approach concatenates filtered inputs along the channel dimension, while the branching approach processes each frequency band through a dedicated network branch before feature fusion. Both approaches can substantially improve performance across epicentral distances of 0° to 20°, but their effectiveness depends strongly on the selected frequency bands. Tests with multiple filter banks show that filter-bank design should be treated as part of model optimization rather than as a fixed preprocessing choice. Grad-CAM analysis of the branching model indicates that band importance varies among waveform samples and across training realizations, with only a weak overall preference for the 0.25 to 0.5 Hz band. These results show that no single filter band is consistently optimal and demonstrate that explicit feature engineering remains valuable for robust deep learning-based seismic phase picking.

58 GEOSCIENCES↗

Bioscience at Los Alamos National Laboratory [Slides]

Highlights: >350 peer-reviewed articles in structural biology since 1997. Institutional h-index 53, cites ~ 17,000; 29 de novo protein structures & 26 protein-ligand complex structures made in the last 5 years; Protein Crystallography Station has 28 published neutron structures, more than half the total produced world wide; Geoff Waldo/GFP-based methods for protein engineering featured at Nobel Symposium 2008

09 BIOMASS FUELS↗

High Gradient Accelerator Research

The goal of the MIT program of research on high gradient acceleration is the development of advanced acceleration concepts that lead to a practical and affordable next generation linear collider at the TeV energy level. Other applications, which are more near-term, include accelerators for materials processing; medicine; defense; mining; security; and inspection. The specific goals of the MIT program are: • Pioneering theoretical research on advanced structures for high gradient acceleration, including photonic structures and metamaterial structures; evaluation of the wakefields in these advanced structures • Experimental research to demonstrate the properties of advanced structures both in low-power microwave cold test and high-power, high-gradient test at megawatt power levels • Experimental research on microwave breakdown at high gradient including studies of breakdown phenomena induced by RF electric fields and RF magnetic fields; development of new diagnostics of the breakdown process • Theoretical research on the physics and engineering features of RF vacuum breakdown • Maintaining and improving the Haimson / MIT 17 GHz accelerator, the highest frequency operational accelerator in the world, a unique facility for accelerator research • Providing the Haimson / MIT 17 GHz accelerator facility as a facility for outside users • Active participation in the US DOE program of High Gradient Collaboration, including joint work with SLAC and with Los Alamos National Laboratory; participation of MIT students in research at the national laboratories • Training the next generation of Ph. D. students in the field of accelerator physics.

43 PARTICLE ACCELERATORS↗