SEARCH · Engineering Papers

Results for “Feature importance”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

SourceResearch connectionFrom yearThrough year

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 307 records · Page 17

All sources NASA NTRS DOE OSTI

DOE OSTI2023

Efficient QAOA Optimization using Directed Restarts and Graph Lookup

Variational Quantum Algorithms (VQA) aim to enhance the capabilities of Noisy Intermediate-Scale Quantum (NISQ) devices. These algorithms utilize parameterized circuits and classical optimizers to iteratively execute circuits with varying parameters. However, VQA faces computational overheads due to repeated iterations and random restarts. Prior work suggests using basic sub-graphs to transfer parameters for the input graph, reducing optimizer overheads but limiting applicability to structured regular graphs. In real-world applications, random irregular graphs are common, and existing methods are not scalable or practical for such graphs. This paper presents a framework that aims to improve random irregular graphs in VQA. The framework uses graph similarity and important features like total edge counts, average edge counts, and variance. It follows an iterative process to choose basis sub-graphs from a small database and adjust parameters accordingly. Classical optimizers then utilize these parameters to determine when to restart and perform gradient descent. This approach increases the chances of reaching global maximum points.

Wang, Meng↗

DOE OSTI2020

Neurotransmitter networks in mouse prefrontal cortex are reconfigured by isoflurane anesthesia

This study quantified eight, small molecule neurotransmitters collected simultaneously from prefrontal cortex of C57BL/6J mouse (n=23) during wakefulness and during isoflurane anesthesia (1.3%). Using isoflurane anesthesia as an independent variable enabled evaluation of the hypothesis that isoflurane anesthesia differentially alters concentrations of multiple neurotransmitters and their interactions. Machine learning was applied to reveal higher order interactions among neurotransmitters. Using a between-subjects design, microdialysis was performed during wakefulness and during anesthesia. Concentrations (nM) of acetylcholine, adenosine, dopamine, GABA, glutamate, histamine, norepinephrine, and serotonin in the dialysis samples are reported (mean ± SD). Relative to wakefulness, acetylcholine concentration was lower during isoflurane anesthesia (1.254 ± 1.118 versus 0.401 ± 0.134, P=0.009), and concentrations of adenosine (29.456 ± 29.756 versus 101.321 ± 38.603, P<0.001), dopamine (0.0578 ± 0.0384 versus 0.113 ± 0.084, P=0.036), and norepinephrine (0.126 ± 0.080 versus 0.219 ± 0.066, P=0.010) were higher during anesthesia. Isoflurane reconfigured neurotransmitter interactions in prefrontal cortex, and the state of isoflurane anesthesia was reliably predicted by prefrontal cortex concentrations of adenosine, norepinephrine, and acetylcholine. A novel finding to emerge from machine learning analyses is that neurotransmitter concentration profiles in mouse prefrontal cortex undergo functional reconfiguration during isoflurane anesthesia. Adenosine, norepinephrine, and acetylcholine showed high feature importance, supporting the interpretation that interactions among these three transmitters may play a key role in modulating levels of cortical and behavioral arousal.

60 APPLIED LIFE SCIENCES↗

DOE OSTI2022

Parametric dependencies of resonant layer responses across linear, two-fluid, drift-MHD regimes

Non-axisymmetric magnetic fields arising in a tokamak either by external or internal perturbations can induce complex non-ideal MHD responses in their resonant surfaces while remaining ideally evolved elsewhere. This layer response can be characterized in a linear regime by a single parameter called the inner-layer Delta, which enables outer-layer matching and the prediction of torque balance to non-linear island regimes. Here, we follow strictly one of the most comprehensive analytic treatments including two-fluid and drift MHD effects and keep the fidelity of the formulation by incorporating the numerical method based on the Riccati transformation when quantifying the inner-layer Delta. The proposed scheme reproduces not only the predicted responses in essentially all asymptotic regimes but also with continuous transitions as well as improved accuracies. In particular, the Delta variations across the inertial regimes with viscous or semi-collisional effects have been further resolved, in comparison with additional analytic solutions. The results imply greater shielding of the electromagnetic torque at the layer than what would be expected by earlier work when the viscous or semi-collisional effects can compete against the inertial effects, and also due to the intermediate regulation by kinetic Alfven wave resonances as rotation slows down. These are important features that can alter the nonaxisymmetric plasma responses including the field penetration by external fields or island seeding process in rotating tokamak plasmas.

MHD instability↗

DOE OSTI2022

Load Disaggregation (Modeling Individual Appliance Power Generation & Consumption in Real-Time)

We developed a machine learning-based load disaggregation method to estimate the real-time output of individual appliances from the whole-house measurements. We first learn the important features associated with each type of appliances using the ground truth consumption data of individual appliances potentially available for a small set of houses equipped with submeters. The learned features are then be used to estimate the power generation/consumption of the appliances from the whole-house consumption. This developed load disaggregation software includes two steps. The first step is to identify the on/off status of different appliances using a classification method, and the second step is to estimate the appliance output using a regression method.

Hao, Jun↗

DOE OSTI2022

Ring Pull Strain Analysis

Ring Pull Strain Analysis (RPSA) is a framework for analysis of Digital Image Correlation (DIC) data of gaugeless ring pull testing. It is meant for analysis of rings cut from tube cross sections and pulled in a displacement-controlled tensile test. This code takes load frame data, images take during testing, and csv files from the DIC analysis of those images and allows the user to analyze and plot data from the test. Some important features of the software include getting the strain values as a function of radial distance and angle, plotting of the strain around the ring, and stress-strain analysis of the load frame data.

Beck, Peter↗

DOE OSTI2024

Ring Pull Strain Analysis

Beck, Peter↗

DOE OSTI2023

VEESA R package

SAND2024-04584O R package for applying the VEESA pipeline method is a technique used for explainable machine learning with functional data. The VEESA pipeline makes use of the elastic-shape analysis framework for functional data. It also implements functional principal component analysis and permutation feature importance. Sandia National Laboratories is a multimission laboratory managed and operated by National Technology & Engineering Solutions of Sandia, LLC, a wholly owned subsidiary of Honeywell International Inc., for the U.S. Department of Energy's National Nuclear Security Administration under contract DE-NA0003525.

Tucker, James↗

DOE OSTI2024

Platform Of Optimal Experiment Management

The platform of optimal experiment management, POEM, powered with automated machine learning to accelerate the discovery of optimal solutions, and automatically guide the design of experiments to be evaluated. POEM currently supports 1) random model explorations for experiment design, 2) sparse grid model explorations with Gaussian Polynomial Chaos surrogate model to accelerate experiment design ,3) time-dependent model sensitivity and uncertainty analysis to identify the importance features for experiment design, 4) model calibrations via Bayesian inference to integrate experiments to improve model performance, and 5) Bayesian optimization for optimal experimental design. In addition, POEM aims to simplify the process of experimental design for users, enabling them to analyze the data with minimal human intervention, and improving the technological output from research activities.

Wang, Congjian [Idaho National Laboratory (INL), I↗

DOE OSTI2025

Machine learning methods for weather forecasting

SAND2025-14466O This repository contains code for developing, training, and evaluating machine learning models for weather and climate forecasting, including forecast skill assessment, feature importance analysis, and reproducible workflows for model comparison. Sandia National Laboratories is a multimission laboratory managed and operated by National Technology & Engineering Solutions of Sandia, LLC, a wholly owned subsidiary of Honeywell International Inc., for the U.S. Department of Energy’s National Nuclear Security Administration under contract DE-NA0003525.

Holthuijzen, Maike [Sandia National Lab. (SNL-CA),↗

DOE OSTI2026

ldrd_virus_work

This is a Python code base that takes openly-available genetic information on known viruses and performs supervised machine learning and feature importance analysis on the relationship of the viral genomes to the competence to infect humans or bind to a specific host cell receptor.

Reddy, Tyler [LANL]↗

DOE OSTI2020

Causal Interactions between Southern Ocean Polynyas and High-Latitude Atmosphere–Ocean Variability

Abstract Weddell Sea open-ocean polynyas have been observed to occasionally release heat from the deep ocean to the atmosphere, indicating that their sporadic appearances may be an important feature of high-latitude atmosphere–ocean variability. Yet, observations of the phenomenon are sparse and many standard-resolution models represent these features poorly, if at all. We use a fully coupled, synoptic-scale preindustrial control simulation of the Energy Exascale Earth System Model (E3SMv0-HR) to effectively simulate open-ocean polynyas and investigate their role in the climate system. Our approach employs statistical tests of Granger causality to diagnose local and remote drivers of, and responses to, polynya heat loss on interannual to decadal time scales. First, we find that polynya heat loss Granger causes a persistent increase in surface air temperature over the Weddell Sea, strengthening the local cyclonic wind circulation. Along with responding to polynyas, atmospheric conditions also facilitate their development. When the Southern Ocean experiences a rapid poleward shift in the circumpolar westerlies following a prolonged negative phase of the southern annular mode (SAM), Weddell Sea salinity increases, promoting density destratification and convection in the water column. Finally, we find that the reduction of surface heat fluxes during periods of full ice cover is not fully compensated by ocean heat transport into the high latitudes. This imbalance leads to a buildup of ocean heat content that supplies polynya heat loss. These results disentangle the complex, coupled climate processes that both enable the polynya’s existence and respond to it, providing insights to improve the representation of these highly episodic sea ice features in climate models.

Kaufman, Zachary S.↗

DOE OSTI2024

Taking the MPI standard and the open MPI library to exascale

The Open MPI for Exascale (OMPI-X) project was one of two in the Exascale Computing Project (ECP) focused on advancing the MPI ecosystem. The OMPI-X team worked with other MPI Forum members to champion several important features for inclusion in the MPI 4.0, 4.1, and upcoming 5.0 MPI standard versions, in support of the needs of exascale applications and systems. The team also worked with the larger Open MPI community to bring implementations of these new features and other enhancements into Open MPI, one of the leading open-source implementations of the MPI interface. Here, this paper describes the motivation for the work of the OMPI-X project in the context of exascale computing needs, the nature of the resulting new capabilities in the MPI standard, and how they were implemented in the Open MPI library. Features include improved support for “MPI + X” programming models through partitioned communications and support for user-level threading, sessions, fault tolerance through the user-level fault mitigation (ULFM) and Reinit models, and other features. We also discuss enhancements to Open MPI providing improved performance and scalability for existing features, such as collective operations, one-sided operations, support for the Slingshot-11 interconnect of the initial exascale systems, and how the OMPI-X team worked to improve quality assurance for the Open MPI library, particularly on platforms of interest to the Department of Energy community.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2020

Performance and community structure dynamics of microbial electrolysis cells operated on multiple complex feedstocks

Microbial electrolysis is a promising technology for converting aqueous wastes into hydrogen. However, substrate adaptability is an important feature, seldom documented in microbial electrolysis cells (MECs). In addition, the correlation between substrate composition and community structure has not been well established. This study used an MEC capable of producing over 10 L/L-day of hydrogen from a switchgrass-derived bio-oil aqueous phase and investigated four additional substrates, tested in sequence on a mature biofilm. The additional substrates included a red oak-derived bio-oil aqueous phase, a corn stover fermentation product, a mixture of phenol and acetate, and acetate alone. The MECs fed with the corn stover fermentation product resulted in the highest performance among the complex feedstocks, producing an average current density of 7.3 ± 0.51 A/m 2 , although the acetate fed MECs outperformed complex substrates, producing 12.3 ± 0.01 A/m 2 . 16S rRNA gene sequencing showed that community structure and community diversity were not predictive of performance, and replicate community structures diverged despite identical inoculum and enrichment procedure. The trends in each replicate, however, were indicative of the influence of the substrates. Geobacter was the most dominant genus across most of the samples tested, but its abundance did not correlate strongly to current density. High-performance liquid chromatography (HPLC) showed that acetic acid accumulated during open circuit conditions when MECs were fed with complex feedstocks and was quickly degraded once closed circuit conditions were applied. The largest net acetic acid removal rate occurred when MECs were fed with red oak bio-oil aqueous phase, consuming 2.93 ± 0.00 g/L-day. Principal component analysis found that MEC performance metrics such as current density, hydrogen productivity, and chemical oxygen demand removal were closely correlated. Net acetic acid removal was also found to correlate with performance. However, no bacterial genus appeared to correlated to these performance metrics strongly, and the analysis suggested that less than 70% of the variance was accounted for by the two components. This study demonstrates the robustness of microbial communities to adapt to a range of feedstocks and conditions without relying on specific species, delivering high hydrogen productivities despite differences in community structure. The results indicate that functional adaptation may play a larger role in performance than community composition. Further investigation of the roles each microbe plays in these communities will help MECs to become integral in the 21st-century bioeconomy to produce zero-emission fuels.

09 BIOMASS FUELS↗

DOE OSTI2023

Top-Down Proteomics of Mouse Islets With Beta Cell CPE Deletion Reveals Molecular Details in Prohormone Processing

Altered prohormone processing, such as with proinsulin and pro-islet amyloid polypeptide (proIAPP), has been reported as an important feature of prediabetes and diabetes. Proinsulin processing includes removal of several C-terminal basic amino acids and is performed principally by the exopeptidase carboxypeptidase E (CPE), and mutations in CPE or other prohormone convertase enzymes (PC1/3 and PC2) result in hyperproinsulinemia. A comprehensive characterization of the forms and quantities of improperly processed insulin and other hormone products following Cpe deletion in pancreatic islets has yet to be attempted. In the present study we applied top-down proteomics to globally evaluate the numerous proteoforms of hormone processing intermediates in a β-cell-specific Cpe knockout mouse model. Increases in dibasic residue–containing proinsulin and other novel proteoforms of improperly processed proinsulin were found, and we could classify several processed proteoforms as novel substrates of CPE. Interestingly, some other known substrates of CPE remained unaffected despite its deletion, implying that paralogous processing enzymes such as carboxypeptidase D (CPD) can compensate for CPE loss and maintain near normal levels of hormone processing. In summary, our quantitative results from top-down proteomics of islets provide unique insights into the complexity of hormone processing products and the regulatory mechanisms.

59 BASIC BIOLOGICAL SCIENCES↗

DOE OSTI2024

Data for "Design of Diverse, Functional Mitochondrial Targeting Sequences Across Eukaryotic Organisms Using Variational Autoencoder"

Mitochondria play a key role in energy production and metabolism, making them a promising target for metabolic engineering and disease treatment. However, despite the known influence of passenger proteins on localization efficiency, only a few protein-localization tags have been characterized for mitochondrial targeting. To address this limitation, we leverage a Variational Autoencoder to design novel mitochondrial targeting sequences. In silico analysis reveals that a high fraction of the generated peptides (90.14%) are functional and possess features important for mitochondrial targeting. We characterize artificial peptides in four eukaryotic organisms and, as a proof-of-concept, demonstrate their utility in increasing 3-hydroxypropionic acid titers through pathway compartmentalization and improving 5-aminolevulinate synthase delivery by 1.62-fold and 4.76-fold, respectively. Moreover, we employ latent space interpolation to shed light on the evolutionary origins of dual-targeting sequences. Overall, our work demonstrates the potential of generative artificial intelligence for both fundamental research and practical applications in mitochondrial biology.

AI/ML↗

DOE OSTI2025

Longitudinal shaping of plasma waveguides using diffractive axicons for laser wakefield acceleration

New techniques for the optical generation of plasma waveguides—optical fibers for ultra-intense light pulses—have become vital to the advancement of multi-GeV laser wakefield acceleration. Here, we demonstrate the fabrication and characterization of a transmissive 8-level logarithmic diffractive axicon (LDA) for the generation of meter-scale plasma waveguides. These LDAs enable the formation of a Bessel-like beam with controllable start and end locations of the focal line and near-constant intensity on axis. We present measurements of the Bessel-like focal profile produced by the LDA and of the leading end of the plasma column generated by it. One important feature is the formation of a funnel-mouthed plasma channel entrance that can act as waveguide coupler. We also compare the diffraction efficiency of our 8-level LDA to 4-level and binary versions, with measurements comparing well to theory.

Tripathi, N.↗

DOE OSTI2022

Unstructured clinical notes within the 24 hours since admission predict short, mid & long-term mortality in adult ICU patients

Mortality prediction for intensive care unit (ICU) patients is crucial for improving outcomes and efficient utilization of resources. Accessibility of electronic health records (EHR) has enabled data-driven predictive modeling using machine learning. However, very few studies rely solely on unstructured clinical notes from the EHR for mortality prediction. In this work, we propose a framework to predict short, mid, and long-term mortality in adult ICU patients using unstructured clinical notes from the MIMIC III database, natural language processing (NLP), and machine learning (ML) models. Depending on the statistical description of the patients’ length of stay, we define the short-term as 48-hour and 4-day period, the mid-term as 7-day and 10-day period, and the long-term as 15-day and 30-day period after admission. We found that by only using clinical notes within the 24 hours of admission, our framework can achieve a high area under the receiver operating characteristics (AU-ROC) score for short, mid and long-term mortality prediction tasks. The test AU-ROC scores are 0.87, 0.83, 0.83, 0.82, 0.82, and 0.82 for 48-hour, 4-day, 7-day, 10-day, 15-day, and 30-day period mortality prediction, respectively. We also provide a comparative study among three types of feature extraction techniques from NLP: frequency-based technique, fixed embedding-based technique, and dynamic embedding-based technique. Lastly, we provide an interpretation of the NLP-based predictive models using feature-importance scores.

60 APPLIED LIFE SCIENCES↗

DOE OSTI2025

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↗