Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Model interpretation”

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 649 records · Page 36
All sourcesNASA NTRSDOE OSTI
DOE OSTI2023

Multiscale graph neural network autoencoders for interpretable scientific machine learning

The goal of this work is to address two limitations in autoencoder-based models: latent space interpretability and compatibility with unstructured meshes. This is accomplished here with the development of a novel graph neural network (GNN) autoencoding architecture with demonstrations on complex fluid flow applications. To address the first goal of interpretability, the GNN autoencoder achieves reduction in the number nodes in the encoding stage through an adaptive graph reduction procedure. Further, this reduction procedure essentially amounts to flowfieldconditioned node sampling and sensor identification, and produces interpretable latent graph representations tailored to the flowfield reconstruction task in the form of so-called masked fields. These masked fields allow the user to (a) visualize where in physical space a given latent graph is active, and (b) interpret the time-evolution of the latent graph connectivity in accordance with the time-evolution of unsteady flow features (e.g. recirculation zones, shear layers) in the domain. To address the goal of unstructured mesh compatibility, the autoencoding architecture utilizes a series of multi-scale message passing (MMP) layers, each of which models information exchange among node neighborhoods at various lengthscales. The MMP layer, which augments standard single-scale message passing with learnable coarsening operations, allows the decoder to more efficiently reconstruct the flowfield from the identified regions in the masked fields. Analysis of latent graphs produced by the autoencoder for various model settings are conducted using unstructured snapshot data sourced from large-eddy simulations in a backward-facing step (BFS) flow configuration with an OpenFOAM-based flow solver at high Reynolds numbers.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2024

Integrating multi-modal remote sensing, deep learning, and attention mechanisms for yield prediction in plant breeding experiments

In both plant breeding and crop management, interpretability plays a crucial role in instilling trust in AI-driven approaches and enabling the provision of actionable insights. The primary objective of this research is to explore and evaluate the potential contributions of deep learning network architectures that employ stacked LSTM for end-of-season maize grain yield prediction. A secondary aim is to expand the capabilities of these networks by adapting them to better accommodate and leverage the multi-modality properties of remote sensing data. In this study, a multi-modal deep learning architecture that assimilates inputs from heterogeneous data streams, including high-resolution hyperspectral imagery, LiDAR point clouds, and environmental data, is proposed to forecast maize crop yields. The architecture includes attention mechanisms that assign varying levels of importance to different modalities and temporal features that, reflect the dynamics of plant growth and environmental interactions. The interpretability of the attention weights is investigated in multi-modal networks that seek to both improve predictions and attribute crop yield outcomes to genetic and environmental variables. This approach also contributes to increased interpretability of the model's predictions. The temporal attention weight distributions highlighted relevant factors and critical growth stages that contribute to the predictions. The results of this study affirm that the attention weights are consistent with recognized biological growth stages, thereby substantiating the network's capability to learn biologically interpretable features. Accuracies of the model's predictions of yield ranged from 0.82-0.93 R 2 ref in this genetics-focused study, further highlighting the potential of attention-based models. Further, this research facilitates understanding of how multi-modality remote sensing aligns with the physiological stages of maize. The proposed architecture shows promise in improving predictions and offering interpretable insights into the factors affecting maize crop yields, while demonstrating the impact of data collection by different modalities through the growing season. By identifying relevant factors and critical growth stages, the model's attention weights provide valuable information that can be used in both plant breeding and crop management. The consistency of attention weights with biological growth stages reinforces the potential of deep learning networks in agricultural applications, particularly in leveraging remote sensing data for yield prediction. To the best of our knowledge, this is the first study that investigates the use of hyperspectral and LiDAR UAV time series data for explaining/interpreting plant growth stages within deep learning networks and forecasting plot-level maize grain yield using late fusion modalities with attention mechanisms.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2017

Search for new phenomena with large jet multiplicities and missing transverse momentum using large-radius jets and flavour-tagging at ATLAS in 13 TeV pp collisions

A search is presented for particles that decay producing a large jet multiplicity and invisible particles. The event selection then applies a veto on the presence of isolated electrons or muons and additional requirements on the number of b-tagged jets and the scalar sum of masses of large-radius jets. In having explored the full ATLAS 2015-2016 dataset of LHC proton-proton collisions at √s=13 TeV, which corresponds to 36.1 fb -1 of integrated luminosity, no evidence is found for physics beyond the Standard Model. The results are interpreted in the context of simplified models inspired by R-parity-conserving and R-parity-violating supersymmetry, where gluinos are pair-produced. More generic models within the phenomenological minimal supersymmetric Standard Model are also considered.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2018

Integrating GLL-Weibull Distribution Within a Bayesian Framework for Life Prediction of Shape Memory Alloy Spring Undergoing Thermo-mechanical Fatigue

The present paper tackles an important but unmapped problem of the reliability estimations of smart materials. First, an experimental setup is developed for accelerated life testing of the shape memory alloy (SMA) springs. Generalized log-linear Weibull (GLL-Weibull) distribution-based novel approach is then developed for SMA spring life estimation. Applied stimulus (voltage), elongation and cycles of operation are used as inputs for the life prediction model. The values of the parameter coefficients of the model provide better interpretability compared to artificial intelligence based life prediction approaches. In addition, the model also considers the effect of operating conditions, making it generic for a range of the operating conditions. Moreover, a Bayesian framework is used to continuously update the prediction with the actual degradation value of the springs, thereby reducing the uncertainty in the data and improving the prediction accuracy. In addition, the deterioration of material with number of cycles is also investigated using thermogravimetric analysis and scanning electron microscopy.

36 MATERIALS SCIENCE↗
DOE OSTI2018

In-situ neutron diffraction of a quasicrystal-containing Mg alloy interpreted using a new polycrystal plasticity model of hardening due to {10.2} tensile twinning

Due to the excellent balance of strength and ductility exhibited by some Mg-Zn-RE (Y subgroup rare earth element) alloys, which contain icosahedral quasicrystalline precipitates, it is of interest to examine their deformation mechanisms. Furthermore, the internal strain evolution Mg-3at%Zn-0.5 at%Y with 4 vol% i-phase was measured using in-situ neutron diffraction. The extruded samples exhibit an initially weak <10.0> || extrusion direction “rod texture,” distinct from the normally strong texture of extruded Mg alloys, but the grain size is unexceptional (16.7 ± 2.1 μm). The initially weak texture contributes to a nearly symmetric yielding response between tension and compression. The hardening responses are asymmetric, however, since {10.2} extension twinning is significantly more active during compressive straining, despite the initially weak texture. In-situ neutron diffraction tension and compression experiments parallel to the extrusion direction, together with elasto-plastic self-consistent (EPSC) crystal plasticity modeling, reveal the strength and hardening behavior of individual slip and twinning modes. A model that was previously published about twinning-detwinning (TDT) is implemented within the EPSC framework, and it is proven effective for describing the observed, mild tension-compression asymmetry. This is not possible with previous EPSC-based models of twinning. Finally, the description of hardening within the TDT model is modified, in order to accurately describe the evolution of internal strains within the twins.

36 MATERIALS SCIENCE↗
NASA NTRS1984

Diurnal variations of atmospheric nitric oxide - Ground-based infrared spectroscopic measurements and their interpretation with time-dependent photochemical model calculations

Total vertical column amounts of NO have been derived from infrared solar absorption spectra recorded near sunrise and sunset with the 0.01 per cm resolution Fourier transform interferometer at the national Solar Observatory on Kitt peak (elevation 2095 m, latitude 31.9 degrees N) on February 23, 1981. The results show an increase in NO concentration in the morning, late afternoon values about 40 percent higher than in the morning, and a decrease in NO concentration prior to sunset. The measured diurnal changes in the total vertical column amount are compared with values obtained from time-dependent photochemical calculations.

Rinsland, C. P.↗
NASA NTRS2000

Dusty Plasma Experiments Using an Electrodynamic Balance

Knowledge of the formation, distribution, physical, chemical and optical characteristics of interstellar, interplanetary, and planetary dust grains provide valuable information about many issues dealing with the origin and formation of the solar system bodies, interplanetary and interstellar environments as well as various industrial processes. Understanding the microphysics of individual grains and their interaction with the surrounding environment is key to properly model various conditions and interpret existing data. The theory and models of individual dust grains are well developed for environments that vary from dense planetary atmospheres to dusty plasmas to diffuse environments such is interplanetary space. However, experimental investigations of individual dust grains in equilibrium are less common, perhaps due to the difficult of these experiments. Laboratory measurements of dust grains have primarily measured ensemble properties or transient properties of single grains. A technique developed in the 1950's for ion spectroscopy, known as a quadrupole trap or 'Paul Trap', has recently been used to investigate single micron-sized dust grains. This scaled ion trap called an electrodynamic balance has been used for atmospheric aerosol research. A description of this technique is provided. Recent results from experiments to investigate the equilibrium potential of dust grains exposed to far ultraviolet light or to -,in electron or ion beam are presented. This laboratory technique ]ends itself to many applications that relate to planetary atmospheres, heliospheric environments, pre-stellar and pre-planetary conditions, and industrial settings. Several planned experimental approaches are presented. Potential experiments to investigate the interaction of multiple dust grains using an electrodynamic balance are proposed.

Spann, J. F.↗
NASA NTRS2000

Electrodynamic Balance for Studies of Cosmic Dust Particles

Knowledge of the formation and distribution of interstellar, interplanetary, and planetary dust grains, and their physical, chemical and optical characteristics provide valuable information about many issues dealing with the origin and formation of the solar system bodies, interplanetary and interstellar environments as well as various industrial processes. Understanding the microphysics of individual grains and their interaction with the surrounding, environment is key to properly model various conditions and interpret existing data. The theory and models of individual dust grains are well developed for environments that vary from dense planetary atmospheres to dusty plasmas to diffuse environments such as interplanetary space. However, experimental investigations of individual dust grains in equilibrium are less common, perhaps due to the difficulty of these experiments. Laboratory measurements of dust grains have primarily measured ensemble properties or transient properties of single grains. A technique developed in the 1950's for ion spectroscopy, generally referred to as a quadrupole trap has recently been employed as an electrodynamic balance to investigate single micron-sized dust grains and for atmospheric aerosol research. A description of the theoretical basis and the experimental setup of the electrodynamic balance being developed in our laboratory are given. This laboratory technique lends itself to many applications that relate to planetary atmospheres, heliospheric environments, pre-stellar and pre-planetary conditions, and industrial settings. We present results from some recent experiments carried out to investigate the equilibrium potential of dust grains exposed to far ultraviolet light or to an electron beam. Some future experiments using an electrodynamic balance to investigate the optical characteristics, and condensation process involving dust grains in various astrophysical environments are discussed.

Spann, J. F.↗
DOE OSTI2025

VERITAS : A density-functional theory-based multiband kinetic model for understanding x-ray spectroscopy of dense plasmas

X-ray spectroscopy has long been a powerful diagnostic tool for hot, dilute plasmas, providing insights into plasma conditions by measuring line shifts and broadenings of atomic transitions. The technique critically depends on the accuracy of atomic physics models used to interpret spectroscopic measurements for inferring plasma properties such as free-electron density and temperature. Over the past decades, the atomic and plasma physics communities have developed robust atomic physics models to account for various processes in hot, dilute classical plasmas. While these models have been successful in that regime, their applicability becomes uncertain when interpreting x-ray spectroscopy experiments of above-solid-density plasmas. Given that finite-temperature density-functional theory (DFT) offers a more accurate description of dense plasma environments, we present the development of a DFT-based multi-band kinetic model, VERITAS, designed to improve the interpretation of x-ray spectroscopic measurements in high-density plasmas produced by laser-driven spherical implosions. This work details the VERITAS model and its application to both time-integrated and time-resolved x-ray spectra from implosion experiments on OMEGA. The advantages and limitations of the VERITAS model will also be discussed, along with potential directions for advancing x-ray spectroscopy of dense and superdense plasmas.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
DOE OSTI2022

Data-driven modeling of power generation for a coal power plant under cycling

Increased penetration of renewables for power generation has negatively impacted the dynamics of conventional fossil fuel-based power plants. The power plants operating on the base load are forced to cycle, to adjust to the fluctuating power demands. This results in an inefficient operation of the coal power plants, which leads up to higher operating losses. To overcome such operational challenge associated with cycling and to develop an optimal process control, this work analyzes a set of models for predicting power generation. Moreover, the power generation is intrinsically affected by the state of the power plant components, and therefore our model development also incorporates additional power plant process variables while forecasting the power generation. We present and compare multiple state-of-the-art forecasting data-driven methods for power generation to determine the most adequate and accurate model. We also develop an interpretable attention-based transformer model to explain the importance of process variables during training and forecasting. The trained deep neural network (DNN) LSTM model has good accuracy in predicting gross power generation under various prediction horizons with/without cycling events and outperforms the other models for long-term forecasting. The DNN memory-based models show significant superiority over other state-of-the-art machine learning models for short, medium and long range predictions. The transformer-based model with attention enhances the selection of historical data for multi-horizon forecasting, and also allows to interpret the significance of internal power plant components on the power generation. This newly gained insights can be used by operation engineers to anticipate and monitor the health of power plant equipment during high cycling periods.

01 COAL, LIGNITE, AND PEAT↗
DOE OSTI2018

Modeling the effects of oxidation-induced porosity on the elastic moduli of nuclear graphites

Oxidation of nuclear graphites produces microstructural changes that affect the elastic moduli of these materials. It is widely accepted that the primary effect of oxidation is to increase porosity, but the related effect on the moduli cannot be explained satisfactorily by simply noting changes to porosity. In this work, models describing the elastic moduli of porous, polycrystalline graphite materials are developed to interpret experimental determinations of Young's modulus and shear modulus in two grades of nuclear graphite – IG-110 and NBG-18 – that were oxidized to produce varying levels of porosity. Experimental measurements were carried out using laser-based ultrasonic methods and were interpreted successfully using models that take into account the effects of preferential oxidation of different elements of the graphite microstructure. The results indicate the importance of the processes that lead to increased porosity since these can heavily influence the nature of the resulting structure-property relationships.

36 MATERIALS SCIENCE↗
NASA NTRS1991

The formal verification of generic interpreters

The task assignment 3 of the design and validation of digital flight control systems suitable for fly-by-wire applications is studied. Task 3 is associated with formal verification of embedded systems. In particular, results are presented that provide a methodological approach to microprocessor verification. A hierarchical decomposition strategy for specifying microprocessors is also presented. A theory of generic interpreters is presented that can be used to model microprocessor behavior. The generic interpreter theory abstracts away the details of instruction functionality, leaving a general model of what an interpreter does.

Windley, P.↗
DOE OSTI2023

End-to-end AI framework for interpretable prediction of molecular and crystal properties

We introduce an end-to-end computational framework that allows for hyperparameter optimization using the DeepHyper library, accelerated model training, and interpretable AI inference. The framework is based on state-of-the-art AI models including CGCNN, PhysNet, SchNet, MPNN, MPNN-transformer, and TorchMD-NET. We employ these AI models along with the benchmark QM9, hMOF, and MD17 datasets to showcase how the models can predict user-specified material properties within modern computing environments. We demonstrate transferable applications in the modeling of small molecules, inorganic crystals and nanoporous metal organic frameworks with a unified, standalone framework. We have deployed and tested this framework in the ThetaGPU supercomputer at the Argonne Leadership Computing Facility, and in the Delta supercomputer at the National Center for Supercomputing Applications to provide researchers with modern tools to conduct accelerated AI-driven discovery in leadership-class computing environments. We release these digital assets as open source scientific software in GitLab, and ready-to-use Jupyter notebooks in Google Colab.

36 MATERIALS SCIENCE↗
NASA NTRS1979

Calculational investigation of impact cratering dynamics - Early time material motions

Early time two-dimensional finite difference calculations of laboratory-scale hypervelocity (6 km/sec) impact of 0.3 g spherical 2024 aluminum projectiles into homogeneous plasticene clay targets were performed and the resulting material motions analyzed. Results show that the initial jetting of vaporized target material is qualitatively similar to experimental observation. The velocity flow field developed within the target is shown to have features quite similar to those found in calculations of near-surface explosion cratering. Specific application of Maxwell's analytic Z-Model (developed to interpret the flow fields of near-surface explosion cratering calculations), shows that this model can be used to describe the flow fields resulting from the impact cratering calculations, provided that the flow field center is located beneath the target surface, and that application of the model is made late enough in time that most of the projectile momentum has been dissipated.

Thomsen, J. M.↗
NASA NTRS1990

Interpretation of satellite-measured bidirectional reflectance from Cirrus cloudy atmospheres

The interpretation of the observed bidirectional reflectance from cirrus cloudy atmospheres is presented. A theoretical model was developed for the computation of the transfer of solar radiation in an anisotropic medium with particular applications to oriented ice crystals in cirrus clouds. In this model, the adding principle for radiative transfer was used with modifications to account for the anisotropy of scattering particles and the associated scattering phase matrix. The single-scattering properties, including the phase function, single-scattering albedo, and extinction cross sections, were used for randomly and horizontally oriented hexagonal ice crystals in radiative transfer computations. The radiative transfer model developed for the cirrus clouds was modified to account for the scattering contributions from the atmosphere and the surface. In order to test the relevance and significance of the ice crystal model for the interpretation of observed bidirectional reflectance from satellites, visible radiances collected on the half hour by the GOES series were selected. The data are calibrated and corrected with the proper filter functions, then navigated to match selected landmark data. A number of clear and cloudy cases during the cirrus IFO of the Fire experiment were chosen for theoretical analyses. The cloud particle shape and size distributions that were taken during satellite overpasses are used in radiative transfer calculations. The sensitivities of the shape, orientation, and size distribution of ice crystals on the reflected intensities at the top of the atmosphere are investigated. Finally, the relative importance of these cloud microphysical properties in the interpretation of satellite bidirectional reflectance are assessed and presented.

Takano, Y.↗