Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “interpretable models”

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 235 records · Page 13
All sourcesNASA NTRSDOE OSTI
DOE OSTI2022

Parameter Estimation for Electrode Degradation: Learning in the Face of Model-Experiment Discrepancies

Use of physics-based models to interpret battery degradation data over the course of cycling can provide deeper physical insight into the internal states of the system and how they evolve. We present a neural network trained on simulations generated by a previously published physics-based model for a lithium trivanadate (LVO) cathode to estimate parameters that evolve over the course of cycling. We focus on the robustness of the neural network through two case studies that probe different kinds of discrepancies between model and experiment: nonideal data and imperfect model. In the former, the experimental protocols do not meet the assumption made in the training data generated by the physics-based model, while in the latter, the physics-based model fails to describe all of the measured cathode behavior even under ideal conditions. When there is total model-experiment agreement, a neural network estimates parameters with improved accuracy compared to a maximum likelihood analysis using the same set of simulations. However, in both types of model-experiment discrepancy, the neural network returned biased parameter estimates. We introduce a data augmentation procedure into the neural network training to mitigate these effects and improve robustness, and employ it to estimate parameters for a cycling LVO cathode.

Mayilvahanan, Karthik S. (ORCID:0000000316282332)↗
DOE OSTI2020

High-throughput phase-field simulations and machine learning of resistive switching in resistive random-access memory

Metal oxide-based Resistive Random-Access Memory (RRAM) exhibits multiple resistance states, arising from the activation/deactivation of a conductive filament (CF) inside a switching layer. Understanding CF formation kinetics is critical to achieving optimal functionality of RRAM. Here a phase-field model is developed, based on materials properties determined by ab initio calculations, to investigate the role of electrical bias, heat transport and defect-induced Vegard strain in the resistive switching behavior, using MO 2- x systems such as HfO 2- x as a prototypical model system. It successfully captures the CF formation and resultant bipolar resistive switching characteristics. High-throughput simulations are performed for RRAMs with different material parameters to establish a dataset, based on which a compressed-sensing machine learning is conducted to derive interpretable analytical models for device performance (current on/off ratio and switching time) metrics in terms of key material parameters (electrical and thermal conductivities, Vegard strain coefficients). These analytical models reveal that optimal performance (i.e., high current on/off ratio and low switching time) can be achieved in materials with a low Lorenz number, a fundamental material constant. This work provides a fundamental understanding to the resistive switching in RRAM and demonstrates a computational data-driven methodology of materials selection for improved RRAM performance, which can also be applied to other electro-thermo-mechanical systems.

36 MATERIALS SCIENCE↗
DOE OSTI2023

Measurements and Model Improvement: Insight into NWP Model Error Using Doppler Lidar and Other WFIP2 Measurement Systems

Abstract Doppler-lidar wind-profile measurements at three sites were used to evaluate NWP model errors from two versions of NOAA’s 3-km-grid HRRR model, to see whether updates in the latest version 4 reduced errors when compared against the original version 1. Nested (750-m grid) versions of each were also tested to see how grid spacing affected forecast skill. The measurements were part of the field phase of the Second Wind Forecasting Improvement Project (WFIP2), an 18-month deployment into central Oregon–Washington, a major wind-energy-producing region. This study focuses on errors in simulating marine intrusions, a summertime, 600–800-m-deep, regional sea-breeze flow found to generate large errors. HRRR errors proved to be complex and site dependent. The most prominent error resulted from a premature drop in modeled marine-intrusion wind speeds after local midnight, when lidar-measured winds of greater than 8 m s −1 persisted through the next morning. These large negative errors were offset at low levels by positive errors due to excessive mixing, complicating the interpretation of model “improvement,” such that the updates to the full-scale versions produced mixed results, sometimes enhancing but sometimes degrading model skill. Nesting consistently improved model performance, with version 1’s nest producing the smallest errors overall. HRRR’s ability to represent the stages of sea-breeze forcing was evaluated using radiation budget, surface-energy balance, and near-surface temperature measurements available during WFIP2. The significant site-to-site differences in model error and the complex nature of these errors mean that field-measurement campaigns having dense arrays of profiling sensors are necessary to properly diagnose and characterize model errors, as part of a systematic approach to NWP model improvement. Significance Statement Dramatic increases in NWP model skill will be required over the coming decades. This paper describes the role of major deployments of accurate profiling sensors in achieving that goal and presents an example from the Second Wind Forecast Improvement Program (WFIP2). Wind-profile data from scanning Doppler lidars were used to evaluate two versions of HRRR, the original and an updated version, and nested versions of each. This study focuses on the ability of updated HRRR versions to improve upon predicting a regional sea-breeze flow, which was found to generate large errors by the original HRRR. Updates to the full-scale HRRR versions produced mixed results, but the finer-mesh versions consistently reduced model errors.

Meteorology & Atmospheric Sciences↗
DOE OSTI2023

A new method for predicting hurricane rapid intensification based on co-occurring environmental parameters

Abstract Tropical cyclones (TCs) that undergo Rapid Intensification (RI) can pose serious socioeconomic threats and can potentially result in major damaging impacts along coastal areas. Considering the complexity of various physical mechanisms that play a role in RI and its relatively low probability of occurrence, predicting RI remains a major operational challenge. In this study, we propose a simple deterministic binary classification model based on the co-occurrence of environmental parameters (MCE) to predict an RI event. More specifically, the model determines the possibility of RI based on a simple count of the number of environmental predictors deemed favorable and unfavorable. We compare our model results to logistic regression (LR) and decision tree (DT) models, well-trained using the same set of environmental predictors. Results reveal that at an RI threshold of 30 kt, the MCE exhibits a critical success index score of 0.233 which is 14% higher than DT and LR model performances. When tested at multiple RI thresholds, the MCE displays relatively higher skill scores across multiple metrics. By simultaneously evaluating the favorability of predictors, the MCE is able to comparatively reduce the number of false alarms predicted when certain predictors are unfavorable toward RI. Interpreting these model results to gain a physical understanding of how co-occurring environmental parameters can affect RI, we highlight future directions for using models based on the MCE approach to understand and predict TC RI as well as other meteorological extremes.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2020

Electron inelastic mean free path in water

Liquid phase transmission electron microscopy (LPTEM) is rapidly developing as a powerful tool for probing processes in liquid environments with close to atomic resolution. Knowledge of the water thickness is needed for reliable interpretation and modelling of analytical studies in LPTEM, and is particularly essential when using thin liquid layers, required for achieving the highest spatial resolutions. Furthermore, the log-ratio method in electron energy-loss spectroscopy (EELS) is often applied in TEM to quantify the sample thickness, which is measured relative to the inelastic mean free path ( λ IMFP ). However, λ IMFP itself is dependent on sample material, the electron energy, and the convergence and divergence angles of the microscope electronoptics. Here, we present a detailed quantitative analysis of the λ IMFP of water as functions of the EELS collection angle ( β ) at 120 keV and 300 keV in a novel nanochannel liquid cell. We observe good agreement with earlier studies conducted on ice, but find that the most widely used theoretical models significantly underestimate λ IMFP of water. We determine an adjusted average energy-loss term E m, water , and characteristic scattering angle θ E, water that improve the accuracy. The results provide a comprehensive knowledge of the λ IMFP of water (or ice) for reliable interpretation and quantification of observations in LPTEM and cryo-TEM studies.

77 NANOSCIENCE AND NANOTECHNOLOGY↗
DOE OSTI2025

SOHIP Abel Transform and Onion Peeling Model Module

This software provides tools for analyzing and modeling physical systems using mathematical transforms and layered models. It includes (1) functions for performing the Abel transform, which is used to relate measurements of bending angles to properties such as refractive index and radius in a medium. The code can compute bending angles from input profiles and also reconstruct these profiles from observed data; (2) the functions for modeling systems with multiple layers using an onion-peeling approach, allowing users to simulate and analyze the behavior of layered materials or structures. These capabilities are useful for researchers and engineers working in fields such as optics, atmospheric science, and materials analysis, enabling them to interpret and model data from experiments or simulations relates to refraction in spherical symmetric medium.

Xu, Shuang [Lawrence Livermore National Laboratory↗
DOE OSTI2022

Stable carbon isotope values of syndepositional carbonate spherules and micrite record spatial and temporal changes in photosynthesis intensity

Marine and lacustrine carbonate minerals preserve carbon cycle information, and their stable carbon isotope values (δ 13 C) are frequently used to infer and reconstruct paleoenvironmental changes. However, multiple processes can influence the δ 13 C values of bulk carbonates, confounding the interpretation of these values in terms of conditions at the time of mineral precipitation. Co-existing carbonate forms may represent different environmental conditions, yet few studies have analyzed δ 13 C values of syndepositional carbonate grains of varying morphologies to investigate their origins. Here, we combine stable isotope analyses, metagenomics, and geochemical modeling to interpret δ 13 C values of syndepositional carbonate spherules (>500 μm) and fine-grained micrite (<63 μm) from a ~1600-year-long sediment record of a hypersaline lake located on the coral atoll of Kiritimati, Republic of Kiribati (1.9°N, 157.4°W). Petrographic, mineralogic, and stable isotope results suggest that both carbonate fractions precipitate in situ with minor diagenetic alterations. The δ 13 C values of spherules are high compared to the syndepositional micrite and cannot be explained by mineral differences or external perturbations, suggesting a role for local biological processes. We use geochemical modeling to test the hypothesis that the spherules form in the surface microbial mat during peak diurnal photosynthesis when the δ 13 C value of dissolved inorganic carbon is elevated. In contrast, we hypothesize that the micrite may precipitate more continuously in the water as well as in sub-surface, heterotrophic layers of the microbial mat. Both metagenome and geochemical model results support a critical role for photosynthesis in influencing carbonate δ 13 C values. The down-core spherule–micrite offset in δ 13 C values also aligns with total organic carbon values, suggesting that the difference in the δ13C values of spherules and micrite may be a more robust, inorganic indicator of variability in productivity and local biological processes through time than the δ 13 C values of individual carbonate forms.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2024

​Understanding a Stratigraphic Hydrothermal Resource – Geophysical Imaging at Steptoe Valley, Nevada

Sandia National Laboratories partnered with a multi-disciplinary group of subject matter experts to evaluate a stratigraphic geothermal resource in Steptoe Valley, Nevada using both established and novel geophysical imaging techniques. The stratigraphic reservoir in northern Steptoe Valley was previously discovered during oil and gas exploration. Subsequent studies, such as the Nevada Play Fairway Analysis, included data which further highlighted potential resource targets in the basin. Geophysical surveys, complemented with refined geologic mapping and geochemical sampling, were deployed to further characterize the resource. The resulting 3D geologic interpretation, conceptual model refinements, and reservoir simulations suggest that a >100MWe power-capable reservoir is likely economically accessible using conventional well placement and stimulation techniques in the Paleozoic carbonates of the deep/central basin of northern Steptoe Valley. Additional geophysical characterization and exploration drilling efforts are recommended to calibrate interpretation and determine where/how to potentially develop the northern Steptoe resource. The geophysical tools, interpretations, lessons learned, and public data generated by this study establish an exploration methodology to inform decisions for characterization and development of northern Steptoe Valley and other stratigraphic geothermal reservoirs in the western U.S.

15 GEOTHERMAL ENERGY↗
DOE OSTI2025

AK112: Full Waveform Inversion Tomography of Alaska Improves Waveform Fits While Imaging Crustal, Mantle, and Slab Structure

We report a full waveform inversion tomography model of Alaska and the surrounding regions, inferring radially anisotropic shear and isotropic compressional wavespeeds by fitting complete waveforms from 120 regional earthquakes. Our multiscale approach inverted time–frequency phase misfits (maximum period of 100 s), starting with a minimum period of 40 s and ending at 20 s in 7 stages and 112 total iterations. The model (AK112) was evaluated by computing the misfits for 36 independent validation events. We find that misfit reductions were large and equal (∼55%) for both the inversion and validation data sets, providing confidence in the model. AK112 also provides much better waveform fits compared to other reported models for the region, including an isotropic version of itself, highlighting the importance of anisotropy. The model resolves known crustal, upper mantle, and slab structure to depths of 100 km with new detail: sedimentary basins in the Alaskan Shelf, Cook Inlet, and Colville basins, among others; discontinuous lithospheric structure across major terrane boundaries; and subducting slab geometry and back‐arc volcanic sources. In addition to tectonic interpretations, the model enables full waveform simulations for long‐period earthquake ground motions and source characterization (e.g., moment tensor and finite‐fault inversion).

Rodgers, Arthur [Lawrence Livermore National Labor↗
DOE OSTI2020

Building kinetic models for metabolic engineering

Kinetic formalisms of metabolism link metabolic fluxes to enzyme levels, metabolite concentrations and their allosteric regulatory interactions. Though they require the identification of physiologically relevant values for numerous parameters, kinetic formalisms uniquely establish a mechanistic link across heterogeneous omics datasets and provide an overarching vantage point to effectively inform metabolic engineering strategies. Advances in computational power, gene annotation coverage, and formalism standardization have led to significant progress over the past few years. However, careful interpretation of model predictions, limited metabolic flux datasets, and assessment of parameter sensitivity remain as challenges. In this study we highlight fundamental considerations which influence model quality and prediction, advances in methodologies, and success stories of deploying kinetic models to guide metabolic engineering.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2021

A Deep Gravity model for mobility flows generation

The movements of individuals within and among cities influence critical aspects of our society, such as well-being, the spreading of epidemics, and the quality of the environment. When information about mobility flows is not available for a particular region of interest, we must rely on mathematical models to generate them. In this work, we propose Deep Gravity, an effective model to generate flow probabilities that exploits many features (e.g., land use, road network, transport, food, health facilities) extracted from voluntary geographic data, and uses deep neural networks to discover non-linear relationships between those features and mobility flows. Our experiments, conducted on mobility flows in England, Italy, and New York State, show that Deep Gravity achieves a significant increase in performance, especially in densely populated regions of interest, with respect to the classic gravity model and models that do not use deep neural networks or geographic data. Deep Gravity has good generalization capability, generating realistic flows also for geographic areas for which there is no data availability for training. Finally, we show how flows generated by Deep Gravity may be explained in terms of the geographic features and highlight crucial differences among the three considered countries interpreting the model’s prediction with explainable AI techniques.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2023

Statistical Learning for Nonlinear Model Reduction from Local Simulations of Stochastic and Particle- and Agent-Based Systems

Stochastic physical systems across the sciences that have very high-dimensional state spaces, with a large number of fast degrees of freedom that force direct simulators to proceed by integration steps that are orders of magnitude smaller than events of interests (e.g., particle collisions). Examples range from molecular motion to dynamics of large populations of cells. A grand challenge in the simulation and understanding of such systems is the systematic construction of accurate, interpretable, reduced models, enabling faster simulations, revealing fundamental properties of the dynamics, and predicting phenomena of interest that the original simulator could not reached with sufficient accuracy or within a given computational budget. In this projected we developed novel statistical estimation/machine learning techniques for analyzing and building empirical reduced models for important families of high-dimensional stochastic systems, in particular: - we developed techniques for estimating interaction kernels in interacting particle- and agent-based systems, which are ubiquitous in Physics, Biology and many other sciences, given observed trajectories of the system; - we developed techniques for nonlinear model reduction for high-dimensional stochastic systems that have a small number of unknown, nonlinear slow variables, and a large number of fast modes, that are possibly of large magnitude, given observed short trajectories of the system in the form of bursts of trajectories from different initial conditions; - we developed novel techniques for estimating linear dynamical systems on graphs when both the dynamics and the underlying graph are unknown, and we have a sparse set of space-time observations; - we considered the problem of estimating an unknown nonlinear observation function of a standard process (e.g. Brownian motion), so that we can recognized if an observed dynamics is "just" a nonlinear version of a known dynamics; we also developed benchmarks for learning algorithms aimed at learning and classifying diffusion processes.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2023

Explaining machine-learning models for gamma-ray detection and identification

As more complex predictive models are used for gamma-ray spectral analysis, methods are needed to probe and understand their predictions and behavior. Recent work has begun to bring the latest techniques from the field of Explainable Artificial Intelligence (XAI) into the applications of gamma-ray spectroscopy, including the introduction of gradient-based methods like saliency mapping and Gradient-weighted Class Activation Mapping (Grad-CAM), and black box methods like Local Interpretable Model-agnostic Explanations (LIME) and SHapley Additive exPlanations (SHAP). In addition, new sources of synthetic radiological data are becoming available, and these new data sets present opportunities to train models using more data than ever before. In this work, we use a neural network model trained on synthetic NaI(Tl) urban search data to compare some of these explanation methods and identify modifications that need to be applied to adapt the methods to gamma-ray spectral data. We find that the black box methods LIME and SHAP are especially accurate in their results, and recommend SHAP since it requires little hyperparameter tuning. We also propose and demonstrate a technique for generating counterfactual explanations using orthogonal projections of LIME and SHAP explanations.

73 NUCLEAR PHYSICS AND RADIATION PHYSICS↗
DOE OSTI2022

Identifying Critical Infrastructure in Imagery Data Using Explainable Convolutional Neural Networks

To date, no method utilizing satellite imagery exists for detailing the locations and functions of critical infrastructure across the United States, making response to natural disasters and other events challenging due to complex infrastructural interdependencies. This paper presents a repeatable, transferable, and explainable method for critical infrastructure analysis and implementation of a robust model for critical infrastructure detection in satellite imagery. This model consists of a DenseNet-161 convolutional neural network, pretrained with the ImageNet database. The model was provided additional training with a custom dataset, containing nine infrastructure classes. The resultant analysis achieved an overall accuracy of 90%, with the highest accuracy for airports (97%), hydroelectric dams (96%), solar farms (94%), substations (91%), potable water tanks (93%), and hospitals (93%). Critical infrastructure types with relatively low accuracy are likely influenced by data commonality between similar infrastructure components for petroleum terminals (86%), water treatment plants (78%), and natural gas generation (78%). Local interpretable model-agnostic explanations (LIME) was integrated into the overall modeling pipeline to establish trust for users in critical infrastructure applications. The results demonstrate the effectiveness of a convolutional neural network approach for critical infrastructure identification, with higher than 90% accuracy in identifying six of the critical infrastructure facility types.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2021

Fast ion transport by sawtooth instability in the presence of ICRF-NBI synergy in JET plasmas

JET experiments have shown that the three-ion scenarios using waves in the ion cyclotron range of frequencies (ICRF) is an efficient way to build fast ion population through beam ion acceleration by radio frequency (RF) waves. Here, such a heating scheme is applied to plasmas with at least two thermal ion species. Analysis of mixed discharges with complex heating schemes requires a workflow that allows to model thermal and fast ion transport consistently. This paper is dedicated to modelling of a mixed plasma discharge with significant fraction of fast ions and contributes to development of fast ion transport models. For interpretive analysis with the TRANSP code a JET hydrogen-deuterium (HD) plasma discharge with neutral beam injection (NBI) and ICRF heating has been chosen. The task is complicated by NBI-ICRF synergy and plasma magnetohydrodynamic activity, like sawtooth crashes. D beam ions accelerated by RF waves form a high energy tail in fast ion distribution. Significant difference between the neutron rate computed by TRANSP and measured one is observed if the same diffusivity for electrons and ions is assumed. Sensitivity studies show that uncertainties in input plasma parameters and thermal ion transport models are crucial for modelling mixed plasma discharges and increased D transport is required to reach the plasma composition consistent with diagnostic measurements at the plasma edge. Fast ion redistribution by a sawtooth instability is characterised by non-resonant transport due to reconnection of magnetic field lines and resonant transport caused by resonance interaction between the instability and fast ions. With ORBIT simulations it has been shown that resonant interaction strongly affects fast ions of high energies, like beam ions accelerated by RF waves and fusion products. For the considered case, fast ion profiles simulated by ORBIT remain peaked after the sawtooth crashes.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
DOE OSTI2024

TCR-H: explainable machine learning prediction of T-cell receptor epitope binding on unseen datasets

Artificial-intelligence and machine-learning (AI/ML) approaches to predicting T-cell receptor (TCR)-epitope specificity achieve high performance metrics on test datasets which include sequences that are also part of the training set but fail to generalize to test sets consisting of epitopes and TCRs that are absent from the training set, i.e., are ‘unseen’ during training of the ML model. We present TCR-H, a supervised classification Support Vector Machines model using physicochemical features trained on the largest dataset available to date using only experimentally validated non-binders as negative datapoints. TCR-H exhibits an area under the curve of the receiver-operator characteristic (AUC of ROC) of 0.87 for epitope ‘hard splitting’ (i.e., on test sets with all epitopes unseen during ML training), 0.92 for TCR hard splitting and 0.89 for ‘strict splitting’ in which neither the epitopes nor the TCRs in the test set are seen in the training data. Furthermore, we employ the SHAP (Shapley additive explanations) eXplainable AI (XAI) method for post hoc interrogation to interpret the models trained with different hard splits, shedding light on the key physiochemical features driving model predictions. TCR-H thus represents a significant step towards general applicability and explainability of epitope:TCR specificity prediction.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2021

Quantification of Cas9 binding and cleavage across diverse guide sequences maps landscapes of target engagement

The RNA-guided nuclease Cas9 has unlocked powerful methods for perturbing both the genome through targeted DNA cleavage and the regulome through targeted DNA binding, but limited biochemical data have hampered efforts to quantitatively model sequence perturbation of target binding and cleavage across diverse guide sequences. We present scalable, sequencing-based platforms for high-throughput filter binding and cleavage and then perform 62,444 quantitative binding and cleavage assays on 35,047 on- and off-target DNA sequences across 90 Cas9 ribonucleoproteins (RNPs) loaded with distinct guide RNAs. We observe that binding and cleavage efficacy, as well as specificity, vary substantially across RNPs; canonically studied guides often have atypically high specificity; sequence context surrounding the target modulates Cas9 on-rate; and Cas9 RNPs may sequester targets in nonproductive states that contribute to “proofreading” capability. Lastly, we distill our findings into an interpretable biophysical model that predicts changes in binding and cleavage for diverse target sequence perturbations.

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

Implementation of a 9-point stencil in SOLPS-ITER and implications for Alcator C-Mod divertor plasma simulations

The SOLPS-ITER code suite is used worldwide for plasma edge modeling, the interpretation of experiments, as well as for the design of the ITER divertor. The numerical scheme of the plasma solver of the code, B2.5, is based on the assumption of perfectly field-aligned grids, while in practice grids are often strongly distorted to match divertor target shapes. Neglecting these grid distortion leads to qualitatively and quantitatively incorrect results for fluid neutral simulations, and may affect results in cold (detached) divertors even when using kinetic neutral simulations. In this contribution, we present the first results of a newly implemented 9-point stencil in B2.5 to properly handle misaligned grids. The new scheme is then applied to fluid neutral simulations of a well-diagnosed and previously modeled Alcator C-Mod discharge. Results are compared with the original 5-point scheme neglecting grid distortion effects, as well as with simulations including a full kinetic neutral model. We conclude that the 9-point stencil is essential to correctly model the transport of fluid neutrals on distorted grids, and to capture the effects of divertor closure on the fluid neutral behavior.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗