Engineering Papers⌕ Search

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.

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 OSTI2020

X-ray photoelectron spectroscopy data from lightly Pd doped TiO 2 anatase nanoparticles

Here, two sets of XPS spectra from ≈13 nm slightly Pd-doped anatase TiO 2 particles are reported. Anatase is the most stable form of TiO 2 for small particles, and these spectra are the first spectra from nano-sized anatase to appear in Surface Science Spectra. The high resolution Ti 2p spectrum has an extended range showing important loss features not appearing in most of the earlier data records. The O 1s spectrum also has loss features often ignored, and in this case, the loss features are overlapped by some of the Ti 2s peak features that complicate quantitative analysis. The spectra reported here were used as example spectra in a guide to backgrounds in XPS, and the availability of these spectra in digital form allows LRH-analysts to compare their background selections and analysis approach to those discussed in the guide.

36 MATERIALS SCIENCE↗
DOE OSTI2025

Graph-based Reversible Evaluation and Tangents Library

GRETL is a C++ library for evaluation, re-evaluation and algorithmic differentiation of functional operations on an arbitrary computational graph with limited memory usage. Similar to popular machine learning frameworks in Python, like PyTorch and JAX, it tracks and stores both operations and output data as functions are evaluated. Once this composition of functions is built up, the entire chain of operations can be back propagated to compute sensitivities of the final result with respect to any number of inputs. In contrast to most machine learning applications, memory usage becomes the bottleneck for back propagation in many physics applications, especially for time-dependent PDEs. Dynamic check pointing becomes essential. An important distinguishing feature of GRETL is its ability to limit the maximum memory usage by automatically dynamic checkpointing the data output for each graph operation (see Wang, Moin, Iaccarino, 2009). During backpropagation, parts of the graph that are no longer in memory are automatically re-evaluated from upstream checkpointed states as needed for derivative sensitivity calculations (or more precisely, for vector-Jacobian products). GRETL is particularly beneficial for applications, such as coupled multi-physics, where deriving adjoint-based sensitivities and managing checkpoint memory across modules becomes onerous. Cases which can be readily handled by the GRETL library include: different time-integration algorithms per physics (e.g., coupled predictor-corrector algorithms, IMEX, etc.), sub-cycling, asynchronous integrators, state dependent timestep sizes, iterative solvers and coupling algorithms, controller algorithms, and more.

Tupek, MichaelR [Lawrence Livermore National Labor↗
DOE OSTI2024

Large-Scale Visualization of 3D Unstructured Groundwater Model Using Cave Automated Virtual Environment

The immersive three-dimensional (3D) virtual reality (VR) visualization of groundwater models allows us to deepen our understanding of aquifer systems and provide better solutions to present groundwater-related problems, such as groundwater recharge, water quality, and sustainability. Visualization assists in accurately developing groundwater models and revealing important subsurface features, including faulting, folding, and unconformity. However, assessing model accuracy poses challenges due to the complexity of geology and groundwater systems. This research demonstrates a workflow to visualize and analyze raw 3D unstructured groundwater model data using an immersive Cave Automated Virtual Environment (CAVE). To visualize the unstructured groundwater model data, the raw dataset is converted into interactive CAVE-compatible formats utilizing a set of tools: ParaView, Blender, and Unity. This enables researchers to immerse themselves in the data, identifying influential patterns and relationships. e resulting insights can inform the development of sophisticated machine-learning models for groundwater level prediction. The CAVE’s immersive capabilities allow intuitive exploration from various perspectives, providing a more holistic understanding of the factors affecting groundwater levels. These insights are crucial to improve predictive models. The CAVE results also facilitate collaborative analysis and have potential applications in training and education. is research demonstrates the value of immersive VR tools such as the CAVE for unraveling intricacies within high-dimensional scientific data to drive real-world forecasting and modeling applications.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2020

More exotic field theories in 3+1 dimensions

We continue the exploration of nonstandard continuum field theories related to fractons in 3+1 dimensions. Our theories exhibit exotic global and gauge symmetries, defects with restricted mobility, and interesting dualities. Depending on the model, the defects are the probe limits of either fractonic particles, strings, or strips. One of our models is the continuum limit of the plaquette Ising lattice model, which features an important role in the construction of the X-cube model.

Gorantla, Pranay↗
DOE OSTI2024

A Principled Framework to Assess the Information-Theoretic Fitness of Brain Functional Sub-Circuits

In systems and network neuroscience, many common practices in brain connectomic analysis are often not properly scrutinized. One such practice is mapping a predetermined set of sub-circuits, like functional networks (FNs), onto subjects’ functional connectomes (FCs) without adequately assessing the information-theoretic appropriateness of the partition. Another practice that goes unchallenged is thresholding weighted FCs to remove spurious connections without justifying the chosen threshold. This paper leverages recent theoretical advances in Stochastic Block Models (SBMs) to formally define and quantify the information-theoretic fitness (e.g., prominence) of a predetermined set of FNs when mapped to individual FCs under different fMRI task conditions. Our framework allows for evaluating any combination of FC granularity, FN partition, and thresholding strategy, thereby optimizing these choices to preserve the important topological features of the human brain connectomes. By applying to the Human Connectome Project with Schaefer parcellations at multiple levels of granularity, the framework showed that the common thresholding value of 0.25 was indeed information-theoretically valid for group-average FCs, despite its previous lack of justification. Our results pave the way for the proper use of FNs and thresholding methods, and provide insights for future research in individualized parcellations.

Duong-Tran, Duy (ORCID:0009000944967575)↗
DOE OSTI2020

The impacts of biomass burning activities on convective systems over the Maritime Continent

Convective precipitation associated with Sumatra squall lines and diurnal rainfall over Borneo is an important weather feature of the Maritime Continent in Southeast Asia. Over the past few decades, biomass burning activities have been widespread during summertime over this region, producing massive fire aerosols. These additional aerosols, when brought into the atmosphere, besides influencing the local radiation budget through directly scattering and absorbing sunlight, can also act as cloud condensation nuclei or ice nuclei to alter convective clouds and precipitation over the Maritime Continent via so-called aerosol indirect effects. Based on 4-month simulations with or without biomass burning aerosols, conducted using theWeather Research and Forecasting model coupled with a chemistry module (WRFChem), we have investigated the aerosol–cloud interactions associated with biomass burning aerosols over the Maritime Continent. Results from selected cases of convective events have specifically shown the significant impact of fire aerosols on weak convections by their increasing of the quantities of hydrometeors and rainfall in both the Sumatra and Borneo regions. Statistical analysis over the fire season also suggests that fire aerosols have impacts on the nocturnal convections associated with the local anticyclonic circulation in western Borneo and weaken nocturnal rainfall intensity by about 9 %. Such an effect is likely to have come from the near-surface heating due to absorbing aerosols emitted from fires, which could weaken land breezes and thus the convergence of anticyclonic circulation.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2023

A comprehensive model of Drosophila epithelium reveals the role of embryo geometry and cell topology in mechanical responses

In order to understand morphogenesis, it is necessary to know the material properties or forces shaping the living tissue. In spite of this need, very few in vivo measurements are currently available. Here, using the early Drosophila embryo as a model, we describe a novel cantilever-based technique which allows for the simultaneous quantification of applied force and tissue displacement in a living embryo. By analyzing data from a series of experiments in which embryonic epithelium is subjected to developmentally relevant perturbations, we conclude that the response to applied force is adiabatic and is dominated by elastic forces and geometric constraints, or system size effects. Crucially, computational modeling of the experimental data indicated that the apical surface of the epithelium must be softer than the basal surface, a result which we confirmed experimentally. Further, we used the combination of experimental data and comprehensive computational model to estimate the elastic modulus of the apical surface and set a lower bound on the elastic modulus of the basal surface. More generally, our investigations revealed important general features that we believe should be more widely addressed when quantitatively modeling tissue mechanics in any system. Specifically, different compartments of the same cell can have very different mechanical properties; when they do, they can contribute differently to different mechanical stimuli and cannot be merely averaged together. Additionally, tissue geometry can play a substantial role in mechanical response, and cannot be neglected.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2023

A geospatial risk analysis graphical user interface for identifying hazardous chemical emission sources

Background: Performing back trajectory and forward trajectory using the Hybrid Single-Particle Lagrangian Integrated Trajectory Model (HYSPLIT) is a reliable approach for assessing particle transport after release among mid-field atmospheric models. HYSPLIT has an externally facing online interface that allows non-expert users to run the model trajectories without requiring extensive training or programming. However, the existing HYSPLIT interface is limited if simulations have a large amount of meteorological data and timesteps that are not coincident. The objective of this study is to design and develop a more robust tool to rapidly evaluate hazard transport conditions and to perform risk analysis, while still maintaining an intuitive and user-friendly interface. Methods: HYSPLIT calculates forward and backward trajectories of particles based on wind speed, wind direction, and the corresponding location, timestamp, and Pasquill stability classes of the regions of the atmosphere in terms of the wind speed, the amount of solar radiation, and the fractional cloud cover. The computed particle transport trajectories, combined with the online Proton Transfer Reaction-Mass Spectrometry (PTR-MS) data (https://figshare.com/articles/dataset/ARL_Data_from_PROS_station_at_Hanford_site/19993964), can be used to identify and quantify the sources and affected area of the hazardous chemicals’ emission using the potential source distribution function (PSDF). PSDF is an improved statistical function based on the well-known potential source contribution function (PSCF) in establishing the air pollutant source and receptor relationship. Performing this analysis requires a range of meteorological and pollutant concentration measurements to be statistically meaningful. The existing HYSPLIT graphical user interface (GUI) does not easily permit computations of trajectories of a dataset of meteorological data in high temporal frequency. To improve the performance of HYSPLIT computations from a large dataset and enhance risk analysis of the accidental release of material at risk, a geospatial risk analysis tool (GRAT-GUI) is created to allow large data sets to be processed instantaneously and to provide ease of visualization. Results: The GRAT-GUI is a native desktop-based application and can be run in any Windows 10 system without any internet access requirements, thus providing a secure way to process large meteorological datasets even on a standalone computer. GRAT-GUI has features to import, integrate, and convert meteorological data with various formats for hazardous chemical emission source identification and risk analysis as a self-explanatory user interface. The tool is available at https://figshare.com/articles/software/GRAT/19426742.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2022

NRAP-Open-IAM: Open-Source Integrated Assessment Model

NRAP Open IAM is the latest evolution in a series of quantitative models developed under the U.S. Department of Energy’s National Risk Assessment Partnership (NRAP) to address risk assessment, risk management and containment assurance questions of geological carbon storage (GCS). NRAP Open IAM allows a user to define a site specific GCS scenario, characterize important site features, events, and processes (considering uncertainty), couple together reduced order models of various system components to rapidly forecast response to CO 2 injection, and perform stochastic analysis to quantify containment effectiveness, leakage risk, and impact to receptors of concern.

Vasylkivska, Veronika S.↗
DOE OSTI2024

Modeling for a Digital Twin-Based Remote Operation System Framework

New reactor designs and technologies are being developed to grow and advance the nuclear industry. Microreactors are one of the many new concepts for advancing the industry. Microreactors are very small reactors generally designed to have an operating power of 20 MWth or less. They are ideal for many applications in which it would not be feasible to have a large-scale reactor, such as powering remote communities, military bases, and mining sites. Many of these applications currently rely on diesel generators for power, and replacing those generators with the carbon-free energy of a microreactor is a major driving factor for microreactor development. However, most of the use cases for microreactors are in isolated locations where construction and labor costs are much higher. Microreactors will need to be comparable to other energy production methods for their deployment to be successful. Remotely operating the microreactor has a great potential to benefit the economics and make it more cost competitive. With remote operations, the operation facility location could be strategically chosen based on factors such as construction costs, workforce size, etc. The benefits of remote operations could be leveraged even more if the remote operation system is semi-autonomous. If the remote operation system is semi-autonomous, more microreactors could be operated and monitored from one remote operation facility. Additionally, with the system handling some tasks for the human operator, it could reduce the number of operating staff necessary for the microreactor. Digital twins can be used to introduce a level of automation to the remote operation system. Digital twins are capable of component monitoring, system operation and control, and predictive performance [1]. All of those features are important for a successful semi-autonomous remote operation system.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗
DOE OSTI2024

DETERMINATION OF STRUT QUALITY FACTORS IN ADDITIVELY MANUFACTURED LATTICES USING IN-SITU COMPRESSION TESTING µ-CT

In response to the need for an automated, commercial method to qualify additively manufactured (AM) lattice components, an experiment was conducted to evaluate the effects of defective lattice struts on the structural compression strength. Lattice samples with known defective or missing struts were compressed using a Deben CT5000RT and imaged using xray µ-CT. The compressive force and x-ray computed tomography results were compared to defect free standards to evaluate the impact of each defect type on the overall structure’s compressive strength. This analysis will allow for simplifications to Finite Element Analysis (FEA) on AM parts without sacrificing model fidelity. Understanding the contribution of each defect type and severity will also better inform non-destructive evaluation (NDE) personnel of the inspection parameters necessary to detect the smallest feature of importance.

Dinova, Vincent A.↗
DOE OSTI2020

Arctic Tipping Points Triggering Global Change (LDRD Final Report)

The Arctic is warming and feedbacks in the coupled Earth system may be driving the Arctic to tipping events that could have critical downstream impacts for the rest of the globe. In this project we have focused on analyzing sea ice variability and loss in the coupled Earth system Summer sea ice loss is happening rapidly and although the loss may be smooth and reversible, it has significant consequences for other Arctic systems as well as geopolitical and economic implications. Accurate seasonal predictions of sea ice minimum extent and long-term estimates of timing for a seasonally ice-free Arctic depend on a better understanding of the factors influencing sea ice dynamics and variation in this strongly coupled system. Under this project we have investigated the most influential factors in accurate predictions of September Arctic sea ice extent using machine learning models trained separately on observational data and on simulation data from five E3SM historical ensembles. Monthly averaged data from June, July, and August for a selection of ice, ocean, and atmosphere variables were used to train a random forest regression model. Gini importance measures were computed for each input feature with the testing data. We found that sea ice volume is most important earlier in the season (June) and sea ice extent became a more important predictor closer to September. Results from this study provide insight into how feature importance changes with forecast length and illustrates differences between observational data and simulated Earth system data. We have additionally performed a global sensitivity analysis (GSA) using a fully coupled ultra- low resolution configuration E3SM. To our knowledge, this is the first global sensitivity analysis involving the fully-coupled E3SM Earth system model. We have found that parameter variations show significant impact on the Arctic climate state and atmospheric parameters related to cloud parameterizations are the most significant. We also find significant interactions between parameters from different components of E3SM. The results of this study provide invaluable insight into the relative importance of various parameters from the sea ice, atmosphere and ocean components of the E3SM (including cross-component parameter interactions) on various Arctic-focused quantities of interest (QOIs).

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2021

Eject, crash, or survive: Using machine learning to predict orbital instability of exoplanetary systems

Astronomers throughout history, including titans like Kepler and Newton, have tackled planetary dynamics and orbital instability. Despite strides taken in research, understanding the evolution of planetary orbits remains an intricate, computationally expensive, and analytically unsolved problem. I apply machine learning classification methods to numerical simulations of planetary systems in order to predict the long-term fate of the planet - whether the planet remains in a stable orbit or not. My method uses the first 41.1 years (≤ 500 orbits) of data from a planet’s simulation to calculate 17 dynamically-motivated metrics; I trained my classifier on these features to predict a planet’s stability after 107 years. At 84.33%, my classifier was comparable in accuracy to pre-existing literature, despite using significantly less computational power than most other methods. In my research, I found that the standard deviation of eccentricity, mass ratios for neighboring planets, and semi-major axis ratio with the outer planet neighbor to be the most predictive features of instability. I propose reasons for the importance of these features, their role in planetary dynamics, as well as possible explanations for why some planets were misclassified. By understanding the important metrics of instability and reasons for misclassification, we can begin to understand more about system architectures, orbital motion and dynamics, and the formation and evolution of the exoplanetary systems. This is applicable in our own Solar System, and with exoplanet discovery missions such as TESS, this research becomes especially relevant in understanding the new exoplanetary systems we discover.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2021

Eject, crash, or survive: Using machine learning to predict orbital instability of exoplanetary systems

Astronomers throughout history, including titans like Kepler and Newton, have tackled planetary dynamics and orbital instability. Despite strides taken in research, understanding the evolution of planetary orbits remains an intricate, computationally expensive, and analytically unsolved problem. I apply machine learning classification methods to numerical simulations of planetary systems in order to predict the long-term fate of the planet - whether the planet remains in a stable orbit or not. My method uses the first 41.1 years (≤ 500 orbits) of data from a planet’s simulation to calculate 17 dynamically-motivated metrics; I trained my classifier on these features to predict a planet’s stability after 107 years. At 84.33%, my classifier was comparable in accuracy to pre-existing literature, despite using significantly less computational power than most other methods. In my research, I found that the standard deviation of eccentricity, mass ratios for neighboring planets, and semi-major axis ratio with the outer planet neighbor to be the most predictive features of instability. I propose reasons for the importance of these features, their role in planetary dynamics, as well as possible explanations for why some planets were misclassified. By understanding the important metrics of instability and reasons for misclassification, we can begin to understand more about system architectures, orbital motion and dynamics, and the formation and evolution of the exoplanetary systems. This is applicable in our own Solar System, and with exoplanet discovery missions such as TESS, this research becomes especially relevant in understanding the new exoplanetary systems we discover.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2024

Detecting Important Drivers of Gridded Population Modeling With Machine Learning

High-resolution population datasets have been lever-aged across a broad swath of domains, such as climate change, public policy, humanitarian aid, and rescue operations, among others. Machine learning methods were adopted to generate high-resolution or gridded population estimates by using various geospatial input features such as buildings, roads, and nighttime lights. In this study, we evaluate the importance of population features using Random Forest models across three levels of analysis, utilizing permutation measures. Our research aims to address key questions to enhance our understanding of high-resolution population modeling, such as: Are certain features globally (10 countries collectively) more important than others? Do optimal features vary by country? Within each country, do feature importance differ across administrative units? What similarities exist in feature importance at the global, country, and administrative unit levels? To answer these questions, we leverage the Kneedle algorithm to automate the selection of optimum features. We find that there are patterns displayed by features across spatial boundaries, evidenced by the same feature being the most important indicator of population across 7 of the 10 countries modeled. Our findings indicate that while important features may vary across geographies, certain features consistently hold greater importance than others agnostic of geography.

Lebakula, Viswadeep [ORNL] (ORCID:0000000152935914↗
DOE OSTI2022

Nonnegative canonical tensor decomposition with linear constraints: nnCANDELINC

Abstract There is an emerging interest for tensor factorization applications in big‐data analytics and machine learning. To speed up the factorization of extra‐large datasets, organized in multidimensional arrays (also known as tensors), easy to compute compression‐based tensor representations, such as, Tucker and tensor train formats, are used to approximate the initial large‐tensor. Further, tensor factorization is used to extract latent features that can facilitate discoveries of new mechanisms and signatures hidden in the data, where the explainability of the latent features is of principal importance. Nonnegative tensor factorization extracts latent features that are naturally sparse and parts of the data, which makes them easily interpretable. However, to take into account available domain knowledge and subject matter expertise, often additional constraints need to be imposed, which lead us to canonical decomposition with linear constraints (CANDELINC), a canonical polyadic decomposition with rank deficient factors. In CANDELINC, Tucker compression is used as a preprocessing step, which lead to a larger residual error but to more explainable latent features. Here, we propose a nonnegative CANDELINC (nnCANDELINC) accomplished via a specific nonnegative Tucker decomposition; we refer to as minimal or canonical nonnegative Tucker. We derive several results required to understand the specificity of nnCANDELINC, focusing on the difficulties of preserving the nonnegative rank of a tensor to its Tucker core and comparing the real valued to nonnegative case. Finally, we demonstrate nnCANDELINC performance on synthetic and real‐world examples.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2026

Teleseismic Network Association with GENIE

In this report we investigate adapting the Graph Neural Interpretation Engine (GENIE), an associator developed for three-component dense monitoring networks, to regional to teleseismic association using a sparse network of array stations. We expand GENIE’s input features to include first-P detection time, azimuth, and slowness estimates. Additionally, we include a probability of detection (PDET) term which measures a station’s likelihood of detecting an event. To assess each feature’s relative importance, we train four models, each using an increasing set of node features and find that the PDET models perform the best. We define two measures of event complexity which demonstrate that all GENIE model versions perform better than the standard backprojection stack.

47 OTHER INSTRUMENTATION↗
DOE OSTI2025

Enhancing Unknown Waveform Detection by Learning Intra and Inter-domain Dependencies with Advanced Attention Fusion Mechanisms

Detection of unknown waveforms in mission-critical communications is a crucial area of interest for the Department of Energy (DoE). Traditional methods and recent deep learning-based approaches often assume that the training set includes all possible classes, which is impractical for detecting new waveforms. This limitation gives rise to the problem of open-set recognition (OSR), which involves correctly identifying known classes while detecting and rejecting unknown or unseen classes. To address this limitation, we propose a novel dual-domain complex-valued neural architecture that jointly processes time-domain and frequency-domain signal representations using transformer mechanisms. A transformer model is a deep learning architecture that uses self-attention mechanisms to process and learn relationships in sequential data. Our model employs a cosine similarity loss to extract domain-specific features and incorporates a transformer architecture in the latent space to weigh the importance of different features from the time and frequency domains. The transformer layer includes stacked self-attention and cross-attention modules to learn intra-domain and inter-domain dependencies, creating a more holistic signal representation. An attention-based fusion module intelligently combines the time and frequency-domain features using multi-head attention, enabling the network to learn the optimal feature for each domain in each input signal. Quantitative results demonstrate the impact of these architectural choices on overall performance, showing significant improvement after incorporating self and cross-attention modules and using complex attention fusion over simple weighted fusion. Our ongoing work will focus on addressing the limitations of threshold-based OSR methods by developing a novel generative framework that integrates a conditional diffusion probabilistic model (DPM). DPM is a generative framework that learns to synthesize complex data by reversing a gradual noising process using a neural network trained to denoise step-by-step. Our goal is to leverage the inherent strengths of DPMs for identifying unknown signals more robustly. One primary advantage of using a DPM is its ability to provide a more reliable anomaly score based on the model's reconstruction error, rather than relying solely on classifier confidence. Additionally, the iterative denoising process of DPMs makes this approach naturally resilient to low Signal-to-Noise Ratio (SNR) conditions, where traditional methods often fail. By implementing this generative framework, we aim to enhance the model's capability to accurately detect unknown waveforms and maintain performance in challenging environments.

99 - GENERAL AND MISCELLANEOUS↗