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 OSTI2024

gcamfaostat: An R package to prepare, process, and synthesize FAOSTAT data for global agroeconomic and multisector dynamic modeling

The gcamfaostat R package is designed for the preparation, processing, and synthesis of the Food and Agriculture Organization (FAO) Statistics (FAOSTAT) agroeconomic data. The primary purpose is to facilitate FAOSTAT data use in global economic and multisector dynamic models while ensuring transparency, traceability, and reproducibility. Here, we provide an overview of the development of gcamfaostat (v1.0) and demonstrate its capabilities in generating and maintaining agroeconomic data required for the Global Change Analysis Model (GCAM). Our initiative seeks to enhance the quality and accessibility of data for the global agroeconomic modeling community, with the aim of fostering more robust and harmonized outcomes in a collaborative, efficient, and open-source framework. One of the important features of the package is the possibility to construct the FAO Food Balance Sheets at the disaggregated commodity level (with over 500 commodities), which provides a comprehensive and detailed data input for a variety of analytical and modeling applications. The processed data and visualizations offered by gcamfaostat can also be valuable to a broader audience interested in gaining insights into the intricacies of global agriculture.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2025

Failure Analysis–Informed Risk Assessment Framework for Geological Carbon Storage Using Numerical Simulation and Machine Learning

Geological carbon storage (GCS) is recognized as a critical technology for achieving large-scale reductions in anthropogenic carbon dioxide (CO 2 ) emissions. Ensuring long-term containment and safety requires robust risk assessment frameworks that account for geological uncertainty and identify potential failure scenarios. Among various indicators, the area of review (AoR) serves as a key metric for evaluating storage performance, regulatory compliance, and monitoring design, as it delineates the spatial extent impacted by pressure buildup and plume migration. However, conventional AoR-based risk assessments typically perturb parameters within narrow uncertainty bounds, potentially overlooking rare but high-impact events arising from extreme geological conditions. In this study, we present a failure analysis–informed risk assessment framework for large-scale GCS projects to improve site prescreening and monitoring design. A suite of 300 numerical simulations was generated using stochastic geological models that vary five key parameters: net-to-gross ratio, anisotropy azimuth, porosity multiplier, permeability multiplier, and vertical-to-horizontal permeability ratio. Among these, 200 realizations represent normal geological uncertainty, while 100 additional cases explore extreme yet plausible conditions for failure-case analysis. The AoR was simulated and computed from pressure and CO 2 saturation fields, where the baseline AoR boundary, representing the extent predicted under typical geological uncertainty, was defined as the union of 200 normal-range simulations, and failure was identified when extreme-range cases exceeded this baseline. Results show that incorporating broader parameter uncertainty produces significantly larger AoR extents, underscoring the potential underestimation of risk under conventional uncertainty ranges. Furthermore, spatial probability maps derived from failure-induced AoR exceedance identify regions requiring enhanced monitoring attention. Various machine learning (ML)–based classifiers were developed to predict failure occurrence from geological parameters, with the random forest model achieving the highest performance (F1-score of 0.986). Consistent findings from correlation coefficient, feature importance, and Sobol sensitivity analyses reveal that low net-to-gross ratios and permeability multipliers are the dominant risk drivers, reflecting reduced reservoir connectivity and limited pressure dissipation. Altogether, these results provide a novel framework for risk-informed site prescreening and monitoring design that explicitly considers rare but high-impact geological scenarios in GCS projects.

25 ENERGY STORAGE↗
DOE OSTI2022

Gluon saturation in proton and its contribution to single inclusive soft gluon production in high energy proton-nucleus collisions

The leading order single inclusive soft gluon production in high energy proton-nucleus (pA) collisions has been studied by various approaches for more than two decades. The first correction due to the gluon saturation in proton was analytically attempted recently through a diagrammatic approach in which only partial results were obtained. An important feature of the first saturation correction is that it includes both initial state and final state interactions. In this paper, we present the complete result derived from the Color Glass Condensate framework. Our approach is to analytically solve the classical Yang-Mills equations in the dilute-dense regime and then use the Lehmann-Symanzik-Zimmermann (LSZ) reduction formula to obtain gluon production from classical gluon fields.

Li, Ming↗
DOE OSTI2025

Closing the loop: model-predictive control for a closed-circuit reverse osmosis system

This article presents a model-predictive controller (MPC) for the maximization of the energy efficiency of a closed-circuit desalination reverse osmosis (CCRO) system. CCRO is a process for producing drinking water that is based on a cyclic operation with the following two phases: (a) filtration and (b) drain. In this article, we test model predictive control for optimal control of this process. The most important features of our approach are as follows: (a) the selection of a model structure that enables reliable forecasts of the filtration phase (up to 3 h), (b) an on-line model calibration strategy that ensures model forecast reliability, and (c) the satisfaction of equipment safety and operational constraints on the selected setpoints. We challenge this through deliberate introduction of changes in the unmeasured feed concentration and the applied constraints. Our results indicate that frequent model parameter updates are critical to maintain model reliability for MPC purposes. In addition, we illustrate that parameter identifiability is not guaranteed and that deliberate variation in flow rates is necessary even though the process never operates in steady state. Finally, MPC can compute flow rate setpoints that maximize the energy efficiency of the CCRO process while satisfying the applicable equipment and safety constraints.

closed-circuit reverse osmosis↗
DOE OSTI2020

Comoparison of Slit Trench and Engineered Trench 3D Vadose Zone Conceptual Models

In the next revision of the E-Area Low-Level Waste Facility (ELLWF) Performance Assessment (PA), radionuclide groundwater transport from slit (ST) and engineered trenches (ET) will be simulated using 3-dimensional PORFLOW models representing the vadose zone. In total, the conceptual framework will aim to model 29 total trenches with a degree of conservatism that provides a high level of confidence in meeting performance objectives. The implementation of generic conceptual models allows for a reasonable number of simulation scenarios, thereby reducing the chances of errors and enabling a better one-to-one comparison between the results, while still capturing the most important features of each trench. The current investigation seeks to understand if a generic trench model based on the general ET footprint can justifiably be used for representing both STs and ETs while maintaining a reasonable degree of conservatism. In this process, the groundwater transport of several key radionuclides was simulated for both ET and ST geometries and the flux-to-the-water-table profiles were compared. For all radionuclides simulated, the ET geometry is shown to be conservative (i.e., produces the highest peak flux to the water table).

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗
DOE OSTI2020

The future of the NPT: REVCON and beyond

The Treaty on the Nonproliferation of Nuclear Weapons (NPT), with its quinquennial review conferences (RevCons), has become the foundation of the international nonproliferation regime over the course of its 50-year history. With more states parties than any other arms control agreement (currently 191), the Treaty provides a legally binding framework for all states parties, constraining proliferation of nuclear weapons and committing the five recognized states who possess nuclear weapons to work toward disarmament. The NPT has enjoyed wide success in constraining the spread of nuclear weapons. Only one state party has left the agreement and gone on to acquire these weapons, and the overall track record of compliance with IAEA safeguards has been robust. However, for all its effectiveness in the area of nonproliferation, its achievements on the disarmament front have been relatively unimpressive. While the NWS – most notably the United States and the Soviet Union/Russia – have decreased the overall size of their nuclear arsenals significantly since 1970, these arsenals have remained an important feature of NWS security policies. The limited progress towards disarmament has created friction between the NNWS and NWS and has been the source of mounting tension within the NPT regime. The 2020 RevCon, the 50th anniversary of the NPT and 25th anniversary of its indefinite extension, faces a range of contentious challenges, old and new, which call into question the Treaty’s future viability.

29 ENERGY PLANNING, POLICY, AND ECONOMY↗
DOE OSTI2021

SAGE Intrusion Detection System: Sensitivity Analysis Guided Explainability for Machine Learning.

This report details the results of a three-fold investigation of sensitivity analysis (SA) for machine learning (ML) explainability (MLE): (1) the mathematical assessment of the fidelity of an explanation with respect to a learned ML model, (2) quantifying the trustworthiness of a prediction, and (3) the impact of MLE on the efficiency of end-users through multiple users studies. We focused on the cybersecurity domain as the data is inherently non-intuitive. As ML is being using in an increasing number of domains, including domains where being wrong can elicit high consequences, MLE has been proposed as a means of generating trust in a learned ML models by end users. However, little analysis has been performed to determine if the explanations accurately represent the target model and they themselves should be trusted beyond subjective inspection. Current state-of-the-art MLE techniques only provide a list of important features based on heuristic measures and/or make certain assumptions about the data and the model which are not representative of the real-world data and models. Further, most are designed without considering the usefulness by an end-user in a broader context. To address these issues, we present a notion of explanation fidelity based on Shapley values from cooperative game theory. We find that all of the investigated MLE explainability methods produce explanations that are incongruent with the ML model that is being explained. This is because they make critical assumptions about feature independence and linear feature interactions for computational reasons. We also find that in deployed, explanations are rarely used due to a variety of reason including that there are several other tools which are trusted more than the explanations and there is little incentive to use the explanations. In the cases when the explanations are used, we found that there is the danger that explanations persuade the end users to wrongly accept false positives and false negatives. However, ML model developers and maintainers find the explanations more useful to help ensure that the ML model does not have obvious biases. In light of these findings, we suggest a number of future directions including developing MLE methods that directly model non-linear model interactions and including design principles that take into account the usefulness of explanations to the end user. We also augment explanations with a set of trustworthiness measures that measure geometric aspects of the data to determine if the model output should be trusted.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2021

Design of double- and multi-bend achromat lattices with large dynamic aperture and approximate invariants

A numerical method to design nonlinear double- and multi-bend achromat (DBA and MBA) lattices with approximate invariants of motion is investigated. The search for such nonlinear lattices is motivated by Fermilab’s Integrable Optics Test Accelerator (IOTA), whose design is based on an integrable Hamiltonian system with two invariants of motion. While it may not be possible to design an achromatic lattice for a dedicated synchrotron light source storage ring with one or more exact invariants of motion, it is possible to tune the sextupoles and octupoles in existing DBA and MBA lattices to produce approximate invariants. In our procedure, the lattice is tuned while minimizing the turn-by-turn fluctuations of the Courant-Snyder actions J x and J y at several distinct amplitudes, while simultaneously minimizing diffusion of the on-energy betatron tunes. The resulting lattices share some important features with integrable ones, such as a large dynamic aperture, trajectories confined to invariant tori, robustness to resonances and errors, and a large amplitude-dependent tune-spread. Compared to the nominal NSLS-II lattice, the single- and multi-bunch instability thresholds are increased and the bunch-by-bunch feedback gain can be reduced.

43 PARTICLE ACCELERATORS↗
DOE OSTI2022

Understanding the Seismic Ground Motion Spatial Variability Using Network Analysis Community Detection

This project is to explore ground motion spatial distribution using a new approach graph-based network analysis. In this study, we combine a large-N seismic array and graph analytics to explore spatial variability and correlation at a local scale using small local and regional earthquakes. In this method, each seismic station is modeled as a node and the similarities of the waveforms that represent ground motions between two stations are modeled as edges. By analyzing this graph network using the similarity matrices and community detection algorithm, we can group the stations spatially with similar patterns. A random forest algorithm is used to reveal the important features that affect the spatial grouping. The result suggests site conditions, and how they interact with the incident seismic wavefield, strongly condition the spatial correlation of ground motion. Future progress in characterizing ground motion spatial variability will require dense wavefield measurements, either through nodal deployments, or perhaps distributed acoustic sensing measurements of seismic wavefields.

58 GEOSCIENCES↗
DOE OSTI2022

The Power of Priors: Improved Enrichment Safeguards

International safeguards currently rely on material accountancy to verify that declared nuclear material is present and unmodified. Although effective, material accountancy for large bulk facilities can be expensive to implement due to the high precision instrumentation required to meet regulatory targets. Process monitoring has long been considered to improve material accountancy. However, effective integration of process monitoring has been met with mixed results. Given the large successes in other domains, machine learning may present a solution for process monitoring integration. Past work has shown that unsupervised approaches struggle due to measurement error. Although not studied in depth for a safeguards context, supervised approaches often have poor generalization for unseen classes of data (e.g., unseen material loss patterns). This work shows that engineered datasets, when used for training, can improve the generalization of supervised approaches. Further, the underlying models needed to generate these datasets need only accurately model certain high importance features.

11 NUCLEAR FUEL CYCLE AND FUEL MATERIALS↗
DOE OSTI2022

Updates to Nek5000: RANS wall functions, NRC support, and documentation

As a key part of the U.S. Department of Energy’s Nuclear Energy Advanced Modeling and Simulation program (NEAMS), the next generation of tools for nuclear reactor design are being developed. A primary metric for success of this program is the adoption of those tools by industry stakeholders. To help meet this metric for Nek5000, development efforts this year have focused on the expansion of the available Reynolds-averaged Navier-Stokes (RANS) turbulence models to include wall function models, continued support of the U.S. Nuclear Regulatory Commission in simulating a hydrogen mitigation benchmark experiment, and expansion of the Nek5000 documentation to enhance the code’s usability. The implementation of wall functions is intended to significantly decrease time to-solution for a wide range of problems and it has been identified as an important feature by stakeholders across the nuclear community. The initial implementation of standard and pressure corrected wall functions has been tested in Nek5000 on the classical problems of channel flow and a backward facing step. It has also been tested on a 2D molten salt fast reactor core and a T-junction. The recommended formulation of choosing y + = 30 as a boundary value combined with a Neumann-Neumann formulation of the boundary condition for k and τ produces the most consistent results compared to a wall resolved approach. The collaboration with the NRC is a continuing exercise that has been ongoing for multiple years. This year we have concluded investigations into appropriate inlet conditions, showing that fully developed turbulent conditions are adequate for the full PANDA domain. We have also concluded simulations for an unobstructed jet and are now refocusing to the original obstructed jet case. The expansion of the code documentation has also been an ongoing effort over the past few years to address feedback from the various stakeholders. The documentation now more fully covers many of the available features and closes identified SQA gaps. Finally we report on three training sessions that were offered over the past year in an effort to expand the Nek5000 user base.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗
DOE OSTI2024

Optimal and robust reconstruction of BAO, redshift-space distortions and the Alcock-Paczynski effect

The goal of this project is to optimally reconstruct cosmological information that has been lost from large-scale clustering of galaxies due to cosmic structure growth. The outcome of our research will be used to improve dark energy and other cosmological constraints from the ongoing extended Baryon Oscillation Spectroscopic Survey (eBOSS) and the upcoming Dark Energy Spectroscopic Instrument (DESI). The large-scale galaxy clustering data contain two important features: the Baryon Acoustic Oscillations (BAO) and the overall shape from small to large scales.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2021

Feature Extraction: Improving Remote Sensor Classification of Non-Proliferation

This research focuses on developing algorithms for nuclear non-proliferation detection using remote sensor modeling. To improve the performance of classification models, we implemented a data pipeline with feature extraction. This pipeline takes raw data and transforms it into smaller data points called features that still describe the model. Improving this classification works towards the departments of energy’s missions of ensuring American’s security and prosperity by creating technology that addresses nuclear challenges. To conduct this analysis, we used the Python programming language and some key packages, including tsfresh and TSFEL. Originally tsfresh was selected because it has the most statistical features out of all the packages. Later TSFEL was incorporated due to the additional features it can extract from data, such as temporal and spectral. However, feature extraction becomes challenging in the presence of missing values. In this case, two additional Python packages were added to our workflow, NumPy and pandas, allowing for the feature extraction process to handle unknown values. Our data pipeline was tested on data collected from a simulation that describes the process state of a physical example. The results show the pipeline’s capability to consume and extract a total 17 features from tabular data. Future work includes producing classifications using decision tree-based models such as XGBoost and improving data collection by analyzing feature importance.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
DOE OSTI2024

Temperature-Time Modeling of Spent Fuel Cladding in Dry Storage Casks

This report uses thermal and decay heat modeling to investigate spent fuel performance and the potential for cladding to anneal in dry storage conditions. Annealing is an important feature to investigate in SNF cladding because it has a direct relationship to cladding response in storage, transportation and disposal conditions. Annealed cladding may have lower strength than unannealed cladding, however its increased ductility would provide better protection against rupture in high strain rate situations such as severe accidents. These consequences are the driver for this work however are outside of the scope of this report. The modeling focused on three representative storage systems, the TN-32B, MAGNASTOR with TSC-37 canister, and NUHOMS AHSM with a 32PTH2 canister. This covers the vertical dual-purpose, vertical ventilated and horizontal ventilated casks respectively. Decay heat modeling using high and low enrichment assemblies was used to bound the decay heat curves that might be expected in dry storage. To bound the temperature relationship, the storage casks were modeled starting at the design basis heat loads with heat decaying through time. Although the results are bounding there is not an attempt to maximize conservatism, rather the intent to form a reasonable upper limit on temperature that will be broadly applicable to the U.S. cask fleet. This will allow materials testing to focus on relevant conditions for annealing that may affect the U.S. spent fuel inventory. The results show a clear dependence on heat load pattern in time in Figure S-1 and Figure S-2. This dependence is due to the different assembly decay heat curves for different assemblies in preferentially loaded casks. It shows the need for careful decay heat modeling when examining in service fuel temperatures that are less than the cask design basis heat load. The body of the report shows percent cladding cutoffs of 300°C and 350 °C as well. These results can be used to inform testing and conclusions about cladding performance through time and the potential for cladding annealing during dry storage.

11 NUCLEAR FUEL CYCLE AND FUEL MATERIALS↗
DOE OSTI2021

Gate Set Tomography

Gate set tomography (GST) is a protocol for detailed, predictive characterization of logic operations (gates) on quantum computing processors. Early versions of GST emerged around 2012-13, and since then it has been refined, demonstrated, and used in a large number of experiments. This paper presents the foundations of GST in comprehensive detail. The most important feature of GST, compared to older state and process tomography protocols, is that it is calibration-free . GST does not rely on pre-calibrated state preparations and measurements. Instead, it characterizes all the operations in a gate set simultaneously and self-consistently, relative to each other. Long sequence GST can estimate gates with very high precision and efficiency, achieving Heisenberg scaling in regimes of practical interest. In this paper, we cover GST's intellectual history, the techniques and experiments used to achieve its intended purpose, data analysis, gauge freedom and fixing, error bars, and the interpretation of gauge-fixed estimates of gate sets. Our focus is fundamental mathematical aspects of GST, rather than implementation details, but we touch on some of the foundational algorithmic tricks used in the pyGSTi implementation.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2022

Unitary Selective Coupled-Cluster Method

Simulating molecules using the Variational Quantum Eigensolver method is one of the promising applications for NISQ-era quantum computers. Designing an efficient ansatz to represent the electronic wave function is crucial in such simulations. Standard unitary coupled-cluster with singles and doubles (UCCSD) ansatz tends to have a large number of insignificant terms that do not lower the energy of the system. In this work, we present a unitary selective coupled-cluster method, a way to construct a unitary coupled-cluster ansatz iteratively using a selection procedure with excitations up to fourth order. This approach uses the electronic Hamiltonian matrix elements and the amplitudes for excitations already present in the ansatz to find the important excitations of higher order and to add them to the ansatz. The important feature of the method is that it systematically reduces the energy error with increasing ansatz size for a set of test molecules. {The main advantage of the proposed method is that the effort to increase the ansatz does not require any additional measurements on a quantum computer.}

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗
DOE OSTI2021

Localized Defect Detection from Spatially Mapped, In-Situ Process Data With Machine Learning

In powder bed fusion additive manufacturing, machines are often equipped with in-situ sensors to monitor the build environment as well as machine actuators and subsystems. The data from these sensors offer rich information about the consistency of the fabrication process within a build and across builds. This information may be used for process monitoring and defect detection; however, little has been done to leverage this data from the machines for more than just coarse-grained process monitoring. In this work we demonstrate how these inherently temporal data may be mapped spatially by leveraging scan path information. We then train a XGBoost machine learning model to predict localized defects—specifically soot–using only the mapped process data of builds from a laser powder bed fusion process as input features. The XGBoost model offers a feature importance metric that will help to elucidate possible relationships between the process data and observed defects. Finally, we analyze the model performance spatially and rationalize areas of greater and lesser performance.

3D printing↗