Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “model interpretability”

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 505 records · Page 28

Dynamical Evolution of the Inner Heliosphere Approaching Solar Activity Maximum: Interpreting Ulysses Observations Using a Global MHD Model

In this study we describe a series of MHD simulations covering the time period from 12 January 1999 to 19 September 2001 (Carrington Rotation 1945 to 1980). This interval coincided with: (1) the Sun s approach toward solar maximum; and (2) Ulysses second descent to the southern polar regions, rapid latitude scan, and arrival into the northern polar regions. We focus on the evolution of several key parameters during this time, including the photospheric magnetic field, the computed coronal hole boundaries, the computed velocity profile near the Sun, and the plasma and magnetic field parameters at the location of Ulysses. The model results provide a global context for interpreting the often complex in situ measurements. We also present a heuristic explanation of stream dynamics to describe the morphology of interaction regions at solar maximum and contrast it with the picture that resulted from Ulysses first orbit, which occurred during more quiescent solar conditions. The simulation results described here are available at: http://sun.saic.com.

Riley, Pete↗

Medical Devices Assess, Treat Balance Disorders

You may have heard the phrase as difficult as walking and chewing gum as a joking way of referring to something that is not difficult at all. Just walking, however, is not all that simple physiologically speaking. Even standing upright is an undertaking requiring the complex cooperation of multiple motor and sensory systems including vision, the inner ear, somatosensation (sensation from the skin), and proprioception (the sense of the body s parts in relation to each other). The compromised performance of any of these elements can lead to a balance disorder, which in some form affects nearly half of Americans at least once in their lifetimes, from the elderly, to those with neurological or vestibular (inner ear) dysfunction, to athletes with musculoskeletal injuries, to astronauts returning from space. Readjusting to Earth s gravity has a significant impact on an astronaut s ability to balance, a result of the brain switching to a different "model" for interpreting sensory input in normal gravity versus weightlessness. While acclimating, astronauts can experience headaches, motion sickness, and problems with perception. To help ease the transition and study the effects of weightlessness on the body, NASA has conducted many investigations into post-flight balance control, realizing this research can help treat patients with balance disorders on Earth as well. In the 1960s, the NASA-sponsored Man Vehicle Laboratory at the Massachusetts Institute of Technology (MIT) studied the effects of prolonged space flight on astronauts. The lab s work intrigued MIT doctoral candidate Lewis Nashner, who began conducting NASA-funded research on human movement and balance under the supervision of Dr. Larry Young in the MIT Department of Aeronautics and Astronautics. In 1982, Nashner s work resulted in a noninvasive clinical technique for assessing the cooperative systems that allow the body to balance, commonly referred to as computerized dynamic posturography (CDP). CDP employs a series of dynamic protocols to isolate and assess balance function deficiencies. The technology was based on Nashner s novel, engineering-inspired concept of balance as an adaptable collaboration between multiple sensory and motor systems. CDP proved useful not only for examining astronauts, but for anyone suffering from balance problems. Today, CDP is the standard medical tool for objectively evaluating balance control.

Source record↗

Automated Detection of Oscillating Regions in the Solar Atmosphere

Recently observed oscillations in the solar atmosphere have been interpreted and modeled as magnetohydrodynamic wave modes. This has allowed for the estimation of parameters that are otherwise hard to derive, such as the coronal magnetic-field strength. This work crucially relies on the initial detection of the oscillations, which is commonly done manually. The volume of Solar Dynamics Observatory (SDO) data will make manual detection inefficient for detecting all of the oscillating regions. An algorithm is presented that automates the detection of areas of the solar atmosphere that support spatially extended oscillations. The algorithm identifies areas in the solar atmosphere whose oscillation content is described by a single, dominant oscillation within a user-defined frequency range. The method is based on Bayesian spectral analysis of time series and image filtering. A Bayesian approach sidesteps the need for an a-priori noise estimate to calculate rejection criteria for the observed signal, and it also provides estimates of oscillation frequency, amplitude, and noise, and the error in all of these quantities, in a self-consistent way. The algorithm also introduces the notion of quality measures to those regions for which a positive detection is claimed, allowing for simple post-detection discrimination by the user. The algorithm is demonstrated on two Transition Region and Coronal Explorer (TRACE) datasets, and comments regarding its suitability for oscillation detection in SDO are made.

Ireland, J.↗

3D Propagation of Relativistic Solar Protons through Interplanetary Space

Context. Solar Energetic Particles (SEPs) with energy in the GeV range can propagate to Earth from their acceleration region near the Sun and produce Ground Level Enhancements (GLEs). The traditional approach to interpreting and modelling GLE observations assumes particle propagation only parallel to the magnetic field lines of interplanetary space, i.e. it is spatially 1D. Recent measurements by PAMELA have characterised SEP properties at 1 AU for the ~100 MeV-1 GeV range at high spectral resolution. Aims. We model the transport of GLE-energy solar protons using a 3D approach, to assess the effect of the Heliospheric Current Sheet (HCS) and drifts associated to the gradient and curvature of the Parker spiral. We derive 1 AU observables and compare the simulation results with data from PAMELA. Methods. We use a 3D test particle model including a HCS. Monoenergetic populations are studied first to obtain a qualitative picture of propagation patterns and numbers of crossings of the 1 AU sphere. Simulations for power law injection are used to derive intensity profiles and fluence spectra at 1 AU. A simulation for a specific event, GLE 71, is used to compare with PAMELA data. Results. Spatial patterns of 1 AU crossings and the average number of crossings are strongly influenced by 3D effects, with significant differences between periods of A+ and A- polarities. The decay time constant of 1 AU intensity profiles varies depending on the position of the observer and is not a simple function of the mean free path as in 1D models. Energy dependent leakage from the injection flux tube is particularly important for GLE energy particles, resulting in a rollover in the spectrum.

Solar energetic particles↗

3D propagation of relativistic solar protons through interplanetary space

Context.Solar energetic particles (SEPs) with energy in the GeV range can propagate to Earth from their acceleration region near the Sun and produce ground level enhancements (GLEs). The traditional approach to interpreting and modelling GLE observations assumes particle propagation which is only parallel to the magnetic field lines of interplanetary space, that is, spatially 1D propagation. Recent measurements by PAMELA have characterised SEP properties at 1 AU for the∼100 MeV–1 GeV range at high spectral resolution. Aims. We model the transport of GLE-energy solar protons using a 3D approach to assess the effect of the heliospheric current sheet(HCS) and drifts associated to the gradient and curvature of the Parker spiral. We derive 1 AU observables and compare the simulation results with data from PAMELA. Methods. We use a 3D test particle model including a HCS. Monoenergetic populations are studied first to obtain a qualitative picture of propagation patterns and numbers of crossings of the 1 AU sphere. Simulations for power law injection are used to derive intensity profiles and fluence spectra at 1 AU. A simulation for a specific event, GLE 71, is used for comparison purposes with PAMELA data. Results. Spatial patterns of 1 AU crossings and the average number of crossings per particle are strongly influenced by 3D effects, with significant differences between periods of A+ and A−polarities. The decay time constant of 1 AU intensity profiles varies depending on the position of the observer and it is not a simple function of the mean free path as in 1D models. Energy dependent leakage from the injection flux tube is particularly important for GLE energy particles, resulting in a rollover in the spectrum.

S. Dalla↗

Simulation of Radon-222 with the GEOS-Chem Global Model: Emissions, Seasonality, and Convective Transport

Radon-222 (Rn-222) is a short-lived radioactive gas naturally emitted from land surfaces and has long been used to assess convective transport in atmospheric models. In this study, we simulate Rn-222 using the GEOS-Chem chemical transport model to improve our understanding of Rn-222 emissions and surface concentration seasonality and characterize convective transport associated with two Goddard Earth Observing System (GEOS) meteorological products, the Modern-Era Retrospective analysis for Research and Applications (MERRA) and GEOS Forward Processing (GEOS-FP). We evaluate four global Rn-222 emission scenarios by comparing model results with observations at 51 surface sites. The default emission scenario in GEOS-Chem yields a moderate agreement with surface observations globally (68.9 % of data within a factor of 2) and a large underestimate of winter surface Rn-222 concentrations at Northern Hemisphere midlatitudes and high latitudes due to an oversimplified formulation of Rn-222 emission fluxes (1 atom cm−2 s−1 over land with a reduction by a factor of 3 under freezing conditions). We compose a new global Rn-222 emission scenario based on Zhang et al. (2011) and demonstrate its potential to improve simulated surface Rn-222 concentrations and seasonality. The regional components of this scenario include spatially and temporally varying emission fluxes derived from previous measurements of soil radium content and soil exhalation models, which are key factors in determining Rn-222 emission flux rates. However, large model underestimates of surface Rn-222 concentrations still exist in Asia, suggesting unusually high regional Rn-222 emissions. We therefore propose a conservative upscaling factor of 1.2 for Rn-222 emission fluxes in China, which was also constrained by observed deposition fluxes of 210Pb (a progeny of Rn-222). With this modification, the model shows better agreement with observations in Europe and North America (> 80 % of data within a factor of 2) and reasonable agreement in Asia (close to 70 %). Further constraints on Rn-222 emissions would require additional concentration and emission flux observations in the central United States, Canada, Africa, and Asia. We also compare and assess convective transport in model simulations driven by MERRA and GEOS-FP using observed Rn-222 vertical profiles in northern midlatitude summer and from three short-term airborne campaigns. While simulations with both GEOS products are able to capture the observed vertical gradient of Rn-222 concentrations in the lower troposphere (0–4 km), neither correctly represents the level of convective detrainment, resulting in biases in the middle and upper troposphere. Compared with GEOS-FP, MERRA leads to stronger convective transport of Rn-222, which is partially compensated for by its weaker large-scale vertical advection, resulting in similar global vertical distributions of Rn-222 concentrations between the two simulations. This has important implications for using chemical transport models to interpret the transport of other trace species when these GEOS products are used as driving meteorology.

Bo Zhang↗

Mixed Integer Linear Programming in Planning

This project, Activity Planning with Resources for the Exploration of Space (APRES), uses a mixed-integer linear program (MILP) to solve planning problems. This work enables APRES to interpret a model file and output a solution with improved human readability. A plan model is optimized using a MILP solver and the best solution is taken. Once a plan is generated, it is parsed allowing it to retain only desired information and modified for swift human readability.

Christina Erwin↗

DOE Award No.: DE-FE0023919 Phase 4 Scientific/Technical Report

This is the Phase 4 Report for the ‘Deepwater Methane Hydrate Characterization and Scientific Assessment or Genesis of Methane Hydrates in the Gulf of Mexico (GOM2)’ research project (DOE Award No. DE-FE0023919). The report summarizes activities from October 1, 2019 to September 30, 2020. The project is led by the University of Texas at Austin (UT). The project objective is to gain insight into the nature, formation, occurrence and physical properties of methane hydrate-bearing sediments for the purpose of methane hydrate resource appraisal through the planning and execution of drilling, coring, logging, testing and analytical activities that assess the geologic occurrence, regional context, and characteristics of marine methane hydrate deposits in the Gulf of Mexico outer continental shelf (OCS). We published a dedicated American Association of Petroleum Geologists Bulletin volume describing initial results from the UT-GOM2-1 expedition in Sept. 2020. This is part 1 of a multi-volume commitment by AAPG to this project. We further confirmed that the natural gas in hydrate at GC-955 was formed by primary microbial processes (>76.1 %). The in-situ effective permeability hydrate-bearing sandy silts at the GC-955 reservoir ranges from 0.1 md (1.0×10-16 m2) to 2.4 md (2.4×10-15m2) in cores with 83% to 93% hydrate saturation. The intrinsic permeability (the single phase permeability) is estimated from reconstituted samples to be ~12 md (1.2×10-14 m2) to ~41 md (4.1×10-14 m2). We used observation and models to interpret that the core degradation that is found in pressure cores is due to dissociation of the methane hydrate in the outer circumference of the core and dissolution of that methane into the fresh pore water that the core is stored with. We are designing approaches to minimize this core loss in the future. We spent an enormous amount of effort to further improve the ability of the pressure coring tool (the PCTB) to pressure seal correctly. We completed upgrading the upper section of the PCTB to address poor pressure. We successful tested the modifications at Geotek’s test facility in Salt Lake City (Bench Test II). We completed a Land Test of the PCTB at the Schlumberger Cameron Test and Training Facility (CTTF). The tool did not seal in 6 out of 7 tests and we clearly demonstrated that cuttings were wedging in the ball valve assembly, keeping the ball valve from sealing. We reproduced the failure mechanism observed during the land test at Salt Lake City and confirmed the sensitivity of the ball valve assembly to grit. Geotek designed and tested 9 modifications to address this issue and the PCTB is now 100% successfully sealing in the presence of grit. Our science expedition is scheduled for spring 2022 and we are fully focused on preparing for this. UT and Ohio State completed a Shallow Hazard Assessment report for each proposed UT-GOM2-2 drilling location, pursuant to 30 CFR 250.214(f) and 250.244 (f). The Shallow Hazard Reports will accompany the UT-GOM2-2 Exploration Plan that is submitted to BOEM, and completes the geological and geophysical analysis for UT-GOM2-2 permitting efforts. We updated the UT-GOM2-2 Operations Plan (Version 1). We completed the UT-GOM2-2 Science and Sample Distribution Plan (Version 1). We evaluated the scope, budget, and schedule that would result from using a commercial vessel. We developed detailed drilling schedule, mud volume, and resource estimates. We developed a vessel specification document and a well plan, and sent these documents to prospective vessel contractors.

03 NATURAL GAS↗

A Review on the State of the Art of Machine Learning and Satellite Imaging: Detecting Scene Changes in Selected Nuclear Fuel Cycle Datasets

The timely detection of clandestine nuclear facilities is one of the greatest challenges faced by the International Atomic Energy Agency’s (IAEA). Idaho National Laboratory is currently applying machine learning (ML) to existing satellite imagery (SI) datasets to find facilities within the nuclear fuel life cycle, with primary focus placed on identifying critical predecessor (i.e., fuel fabrication and fuel enrichment) and successor (i.e., nuclear power plants) facilities. This could provide a satellite image methodology that the IAEA could leverage to discover clandestine facilities. The work presented in this paper describes the evolution of a workflow developed by this team for object detection related to critical infrastructure by expanding that workflow for the purpose of identifying nuclear fuel cycle components and automating dependency assessments. This will be done using two methods housed within a single pipeline. The first method involves implementing a DenseNet161 convolutional neural network to classify the images and explain the results using Local Interpretable Model-Agnostic Explanations (LIME). The second method implements You Only Look Once version 5 (YoloV5), to detect objects within images, provide a probability for the detection, and provide a bounding box that corresponds to the object of interest. The results of this work are anticipated to provide a clear picture of this portion of the nuclear fuel cycle and perform as a stand-alone tool for image assessment that can be expanded to additional fuel cycle components and implemented in international safeguards and national security domains. This capability addresses the IAEA’s need to detect undeclared nuclear materials and activities within a state while encompassing the entire nuclear fuel cycle.

97 MATHEMATICS AND COMPUTING↗

Leak Detection and Sensor Importance Within a Solvent Extraction Process Abstract

In anticipation of the Special Nuclear Material test bed (Beartooth), Idaho National Laboratory has developed a smaller, multi-sensor system for analyzing the solvent extraction process. These systems will allow for research into nuclear fuel processing operations. The multi-sensor system consists of a row of centrifugal contactors and allows for measurement sources that are not traditionally used in the solvent extraction process to be explored including temperature, vibration, acoustics, pH, color, flow, and motor current. Currently, the solvent extraction process is very labor intensive and requires vigilant operators to identify the occurrence of leaks, which can be common during startup or after any change to the system. This study aims to locate leaks using non-traditional measurement sources then to identify which signals were of greatest importance in making this classification using Local Interpretable Model-agnostic Explanations. These results can be used to help solvent extraction process operators detect leaks and to inform future test beds designers to which sensors contain relevant, actionable information in this scenario.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗

Modelling asteroid brightness variations. II - The interpretability of light curves and phase curves

Light curves and phase curves have been computed for various asteroid models using the Lumme-Bowell (1981) scattering law. The effects of the scattering parameters on light curves were found to be almost negligible for homogeneous surfaces. The effects on phase curves were more distinct, but changing any of the scattering parameters affects the phase curves in a very similar way, making it impossible to find a unique set of parameter values corresponding to a given phase curve. Light curve amplitudes, on the other hand, depend very strongly on body shape. At least in the case of a triaxial ellipsoid it is possible to determine the axial ratios. Some observed irregularities of light curves can also be modelled easily, but the uniqueness of such models is far from obvious.

Karttunen, H.↗

Interpretable and flexible non-intrusive reduced-order models using reproducing kernel Hilbert spaces

This paper develops an interpretable, non-intrusive reduced-order modeling technique using regularized kernel interpolation. Existing non-intrusive approaches approximate the dynamics of a reduced-order model (ROM) by solving a data-driven least-squares regression problem for low-dimensional matrix operators. Our approach instead leverages regularized kernel interpolation, which yields an optimal approximation of the ROM dynamics from a user-defined reproducing kernel Hilbert space. We show that our kernel-based approach can produce interpretable ROMs whose structure mirrors full-order model structure by embedding judiciously chosen feature maps into the kernel. The approach is flexible and allows a combination of informed structure through feature maps and closure terms via more general nonlinear terms in the kernel. We also derive a computable a posteriori error bound that combines standard error estimates for intrusive projection-based ROMs and kernel interpolants. In conclusion, the approach is demonstrated in several numerical experiments that include comparisons to operator inference using both proper orthogonal decomposition and quadratic manifold dimension reduction.

Data-driven model reduction↗

Interpretable Convolutional Learning Classifier System (C-LCS) for Higher Dimensional Datasets

The purpose of this paper is to devise an interpretable hybrid classification model for Convolutional Neural Networks (CNN) and a Learning Classifier System (LCS). The presented hybrid system integrates the fundamental attributes from both types of these classifiers. In the proposed hybrid model CNN works as an automatic feature extractor, and LCS works to provide interpretable rule-based classification results. Although LCS has limitations working on higher dimensional datasets, we resolve this limitation by using CNN as a feature extractor. The other concept of the non-interpretability of CNN is addressed by using the LCS rule. Furthermore, our experiment with higher dimensional datasets like CIFAR-10 and Fashion-MNIST shows that extended LCS provides comparable performance to the standard neural network model while also providing interpretable results. We named this extended LCS method Convolutional Learning Classifier Cystem (C-LCS).

Jelani Owens↗

An Investigation of LES Wall Modeling for Rayleigh–Bénard Convection via Interpretable and Physics-Aware Feedforward Neural Networks with DNS

Abstract The traditional approach of using the Monin–Obukhov similarity theory (MOST) to model near-surface processes in large-eddy simulations (LESs) can lead to significant errors in natural convection. In this study, we propose an alternative approach based on feedforward neural networks (FNNs) trained on output from direct numerical simulation (DNS). To evaluate the performance, we conduct both a priori and a posteriori tests. In the a priori (offline) tests, we compare the statistics of the surface shear stress and heat flux, computed from filtered DNS input variables, to the stress and flux obtained from the filtered DNS. Additionally, we investigate the importance of various input features using the Shapley additive explanations value and the conditional average of the filter grid cells. In the a posteriori (online) tests, we implement the trained models in the System for Atmospheric Modeling (SAM) LES and compare the LES-generated surface shear stress and heat flux with those in the DNS. Our findings reveal that vertical velocity, a traditionally overlooked flow quantity, is one of the most important input features for determining the wall fluxes. Increasing the number of input features improves the a priori test results but does not always improve the model performance in the a posteriori tests because of the differences in input variables between the LES and DNS. Last, we show that physics-aware FNN models trained with logarithmic and scaled parameters can well extrapolate to more intense convection scenarios than in the training dataset, whereas those trained with primitive flow quantities cannot. Significance Statement The traditional near-surface turbulence model, based on a shear-dominated boundary layer flow, does not represent near-surface turbulence in natural convection. Using a feedforward neural network (FNN), we can construct a more accurate model that better represents the near-surface turbulence in various flows and reveals previously overlooked controlling factors and process interactions. Our study shows that the FNN-generated models outperform the traditional model and highlight the importance of the near-surface vertical velocity. Furthermore, the physics-aware FNN models exhibit the potential to extrapolate to convective flows of various intensities beyond the range of the training dataset, suggesting their broader applicability for more accurate modeling of near-surface turbulence.

54 ENVIRONMENTAL SCIENCES↗

Experimental Observations of the Topology of Convolutional Neural Network Activations

Topological data analysis (TDA) is a branch of computational mathematics, bridging algebraic topology and data science, that provides compact, noise-robust representations of complex structures. Deep neural networks (DNNs) learn millions of parameters associated with a series of transformations defined by the model architecture resulting in high-dimensional, difficult to interpret internal representations of input data. As DNNs become more ubiquitous across multiple sectors of our society, there is increasing recognition that mathematical methods are needed to aid analysts, researchers, and practitioners in understanding and interpreting how these models' internal representations relate to the final classification. In this paper we apply cutting edge techniques from TDA with the goal of gaining insight towards interpretability of convolutional neural networks used for image classification. We use two common TDA approaches to explore several methods for modeling hidden layer activations as high-dimensional point clouds, and provide experimental evidence that these point clouds capture valuable structural information about the model's process. First, we demonstrate that a distance metric based on persistent homology can be used to quantify meaningful differences between layers and discuss these distances in the broader context of existing representational similarity metrics for neural network interpretability. Second, we show that a mapper graph can provide semantic insight as to how these models organize hierarchical class knowledge at each layer. These observations demonstrate that TDA is a useful tool to help deep learning practitioners unlock the hidden structures of their models.

topological data analysis, deep learning↗

Interpretation of TOMS Observations of Tropical Tropospheric Ozone with a Global Model and In Situ Observations

We interpret the distribution of tropical tropospheric ozone columns (TTOCs) from the Total Ozone Mapping Spectrometer (TOMS) by using a global three-dimensional model of tropospheric chemistry (GEOS-CHEM) and additional information from in situ observations. The GEOS-CHEM TTOCs capture 44% of the variance of monthly mean TOMS TTOCs from the convective cloud differential method (CCD) with no global bias. Major discrepancies are found over northern Africa and south Asia where the TOMS TTOCs do not capture the seasonal enhancements from biomass burning found in the model and in aircraft observations. A characteristic feature of these northern topical enhancements, in contrast to southern tropical enhancements, is that they are driven by the lower troposphere where the sensitivity of TOMS is poor due to Rayleigh scattering. We develop an efficiency correction to the TOMS retrieval algorithm that accounts for the variability of ozone in the lower troposphere. This efficiency correction increases TTOC's over biomass burning regions by 3-5 Dobson units (DU) and decreases them by 2-5 DU over oceanic regions, improving the agreement between CCD TTOCs and in situ observations. Applying the correction to CCD TTOCs reduces by approximately DU the magnitude of the "tropical Atlantic paradox" [Thompson et al, 2000], i.e. the presence of a TTOC enhancement over the southern tropical Atlantic during the northern African biomass burning season in December-February. We reproduce the remainder of the paradox in the model and explain it by the combination of upper tropospheric ozone production from lightning NOx, peristent subsidence over the southern tropical Atlantic as part of the Walker circulation, and cross-equatorial transport of upper tropospheric ozone from northern midlatitudes in the African "westerly duct." These processes in the model can also account for the observed 13-17 DU persistent wave-1 pattern in TTOCs with a maximum above the tropical Atlantic and a minimum over the tropical Pacific during all seasons. The photochemical effects of mineral dust have only a minor role on the modeled distribution of TTOCs, including over northern Africa, due to multiple competing effects. The photochemical effects of mineral dust globally decease annual mean OH concentrations by 9%. A global lightning NOx source of 6 Tg N yr(sup -1) in the model produces a simulation that is most consistent with TOMS and in situ observations.

Martin, Randall V.↗