Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “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 235 records · Page 13
All sourcesNASA NTRSDOE OSTI
DOE OSTI2022

How to see hidden patterns in metamaterials with interpretable machine learning

Machine learning models can assist with metamaterials design by approximating computationally expensive simulators or solving inverse design problems. However, past work has usually relied on black box deep neural networks, whose reasoning processes are opaque and require enormous datasets that are expensive to obtain. Here, in this work, we develop two novel machine learning approaches to metamaterials discovery that have neither of these disadvantages. These approaches, called shape-frequency features and unit-cell templates, can discover 2D metamaterials with user-specified frequency band gaps. Our approaches provide logical rule-based conditions on metamaterial unit-cells that allow for interpretable reasoning processes, and generalize well across design spaces of different resolutions. The templates also provide design flexibility where users can almost freely design the fine resolution features of a unit-cell without affecting the user’s desired band gap.

36 MATERIALS SCIENCE↗
DOE OSTI2026

End-To-End Decentralized Transmission Line Protection in IBR-Dominated Weak Grids Using Interpretable Data-Driven Methods

Traditional transmission line protection relies on predictable synchronous-based fault signatures, which frequently fail under the non-standard, current-limited fault characteristics of Inverter-Based Resources (IBRs). This study investigates how to achieve secure, communication-free fault isolation in IBR-dominated weak grids without relying on opaque, computationally heavy "black-box" machine learning algorithms. To address this, we propose a novel, standalone, and inherently interpretable data-driven protection framework. Unlike centralized methods requiring multi-terminal communication, this decentralized approach relies solely on local measurements using a hierarchical linear-kernel Support Vector Machine (SVM). The methodology decomposes the protection task into four sequential stages that mimic traditional protection elements: fault detection and fault direction identification, fault type classification, zone classification, and location estimation. This multi-stage architecture allows for specialized feature engineering at each stage, combining high computational efficiency with logic traceability. The framework's end-to-end performance was validated via C-code and PSCAD/EMTDC co-simulation, utilizing a real-world utility network and an OEM black-box IBR model. The proposed relay achieves 97.2% overall accuracy and provides a reliable trip decision within a 2.5-cycle window. The results confirm 100% accuracy in fundamental fault detection, reliable zone selectivity across low to moderate fault resistances, and robust security against non-fault transients, proving its immediate viability for integration into commercial numerical relays.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2018

Above zone pressure interpretation for leaky well characterization and its identification from leaky caprock/fault

Pressure transient analysis has long been used for reservoir characterization. Above-zone (AZ) pressure has been recently investigated for inferring leakage pathway characteristics in leakage events from subsurface injection operations. The recorded pressure in the AZ should be purely related to leakage and therefore it can be safely inverted to deduce leakage characteristics. It is crucial to evaluate fluid leakage through abandoned wells to plan for further measurements of leakage prevention. However, the recorded AZ leakage signal may not be related to leaky well(s). Therefore, identification and spatial investigation of well leakage is required for leakage evaluation. Here in this paper, we propose a pressure interpretation method for early detection of leaky pathways, applying two observation points in the AZ. We distinguish leaky well, fault and caprock based on their corresponding flow regime identification. We show that the pressure difference of the two observation wells can be applied as a proxy for unknown leakage rate, which is crucial for leakage identification as well as characterization. Results show that the estimated location of the leaky well, leakage coefficient, and the leakage rate are in good agreement with the actual values. The estimated leakage coefficient of the leaky well can be used to evaluate well leakage in multiphase systems such as carbon dioxide leakage in deep saline aquifers.

02 PETROLEUM↗
DOE OSTI2019

Fast and interpretable classification of small X-ray diffraction datasets using data augmentation and deep neural networks

X-ray diffraction (XRD) data acquisition and analysis is among the most time-consuming steps in the development cycle of novel thin-film materials. We propose a machine-learning-enabled approach to predict crystallographic dimensionality and space group from a limited number of thin-film XRD patterns. We overcome the scarce-data problem intrinsic to novel materials development by coupling a supervised machine learning approach with a model-agnostic, physics-informed data augmentation strategy using simulated data from the Inorganic Crystal Structure Database (ICSD) and experimental data. As a test case, 115 thin-film metal-halides spanning 3 dimensionalities and 7 space-groups are synthesized and classified. After testing various algorithms, we develop and implement an all convolutional neural network, with cross-validated accuracies for dimensionality and space-group classification of 93% and 89%, respectively. We propose average class activation maps, computed from a global average pooling layer, to allow high model interpretability by human experimentalists, elucidating the root-causes of misclassification. Finally, we systematically evaluate the maximum XRD pattern step size (data acquisition rate) before loss of predictive accuracy occurs, and determine it to be 0.16° 2θ, which enables an XRD pattern to be obtained and classified in 5.5 minutes or less.

36 MATERIALS SCIENCE↗
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↗
DOE OSTI2023

Interpretable Data-Driven Probabilistic Power System Load Margin Assessment with Uncertain Renewable Energy and Loads

The increasing uncertainties caused by the high-penetration of stochastic renewable generation resources poses a significant threat to the power system voltage stability. To address this issue, this paper proposes a probabilistic deep kernel learning enabled surrogate model to extract the hidden relationship between uncertain sources, i.e., wind power and loads, and load margin for probabilistic load margin assessment (PLMA). Unlike other deep learning approaches, a kernel SHAP provides the sensitivity analysis as well as interpretability of the inputs to outputs influences. This allows identifying the critical factors that affect load margin so that corrective control can be initiated for stability enhancement. Numerical results carried out on the IEEE 118-bus power system demonstrate the accuracy and efficiency of the proposed data-driven PLMA scheme.

deep kernel learning↗
DOE OSTI2023

RX-ADS: Interpretable Anomaly Detection Using Adversarial ML for Electric Vehicle CAN Data

Recent year has brought considerable advancements in Electric Vehicles (EVs) and associated infrastructures/ communications. Intrusion Detection Systems (IDS) are widely deployed for anomaly detection in such critical infrastructures. This paper presents an Interpretable Anomaly Detection System (RX-ADS) for intrusion detection in CAN protocol communication in EVs. Contributions include: 1) window based feature extraction method; 2) deep Autoencoder based anomaly detection method; and 3) adversarial machine learning based explanation generation methodology. The presented approach was tested on two benchmark CAN datasets: OTIDS and Car Hacking. The anomaly detection performance of RX-ADS was compared against the state-of-the-art approaches on these datasets: HIDS and GIDS. The RX-ADS approach presented performance comparable to the HIDS approach (OTIDS dataset) and has outperformed HIDS and GIDS approaches (Car Hacking dataset). Further, the proposed approach was able to generate explanations for detected abnormal behaviors arising from various intrusions. Furthermore, these explanations were later validated by information used by domain experts to detect anomalies. Other advantages of RX-ADS include: 1) the method can be trained on unlabeled data; 2) explanations help experts in understanding anomalies and root course analysis, and also help with AI model debugging and diagnostics, ultimately improving user trust in AI systems.

42 ENGINEERING↗
DOE OSTI2025

Geometric Interpretation of the Cluster Location Problem Part I: Theory

We present a new framing of the seismic location problem using principles drawn from differential geometry. Our interpretation relies upon the common assumption that travel times observed across a network are continuous, differentiable functions of source location. In consequence, travel‐time functions constitute a differentiable map between the source region and a Riemannian manifold. The manifold is said to be the image of the source region embedded in a generally high‐dimension travel‐time vector space. A cluster of events in the source region has an image of discrete points on the manifold, that, except in the simplest cases, cannot be viewed directly. However, it is possible to project the image of a cluster into a tangent space of the manifold for direct visualization. The projection operator can be computed directly from the data without a velocity model, but produces a distorted rendering of the cluster geometry. With a model we can predict the distortions and correct them to estimate cluster geometry. We develop these points with the simplest possible example, one for which direct visualization of the manifold is possible, using the example as an introduction to the relevant concepts from differential geometry in a familiar setting. The tangent space, a local linearization of the manifold, plays a key role. We develop a metric to estimate the limits of linearization, that is, to determine when the curvature of the manifold invalidates the linear assumption. We also examine the interplay of model error, inadequate network geometry, and pick error. We then generalize our results from the simple case to the general case of 3D source regions observed by general networks. Although we do suggest a new “project and correct” method for location, we do not develop it into a practical algorithm. In conclusion, our intention rather is to highlight new analytical methods grounded in differential geometry.

East Pacific Ocean Islands↗
DOE OSTI2026

FAIR Data and Interpretable AI Framework for Architectured Metamaterials

Our interdisciplinary effort successfully generated FAIR (Findable, Accessible, Interoperable, and Reusable) benchmark datasets for mechanical metamaterials while introducing a novel Artificial Intelligence (AI) framework known as Learning Refined Compositional Rules (LRCR). This framework was specifically designed to bridge the gap across varying computational length scales and extract the underlying physical mechanisms that connect a material's structural geometry to its bulk acoustic properties. Historically, the discovery of such structured materials relied heavily on human intuition or opaque, black-box optimization algorithms that were difficult to generalize. By combining interpretable machine learning techniques with rigorous experimental validation, this project established clear, generalizable design guidelines for tuning wave dispersion and controlling vibrations. Ultimately, the public availability of these structured datasets and algorithms will significantly reduce computational costs and accelerate the design of advanced multi-functional acoustic devices, offering broad societal impacts across fields like aerospace engineering, telecommunications, and biomedical implant design.

36 MATERIALS SCIENCE↗
DOE OSTI2015

Interpreting ~1 Hz magnetic compressional waves in Mercury's inner magnetosphere in terms of propagating ion‐Bernstein waves

Abstract We show that ~1 Hz magnetic compressional waves observed in Mercury's inner magnetosphere could be interpreted as ion‐Bernstein waves in a moderate proton beta ~0.1 plasma. An observation of a proton distribution with a large planetary loss cone is presented, and we show that this type of distribution is highly unstable to the generation of ion‐Bernstein waves with low magnetic compression. Ray tracing shows that as these waves propagate back and forth about the magnetic equator; they cycle between a state of low and high magnetic compression. The group velocity decreases during the high‐compression state leading to a pileup of compressional wave energy, which could explain the observed dominance of the highly compressional waves. This bimodal nature is due to the complexity of the index of refraction surface in a warm plasma whose upper branch has high growth rate with low compression, and its lower branch has low growth/damping rate with strong compression. Two different cycles are found: one where the compression maximum occurs at the magnetic equator and one where the compression maximum straddles the magnetic equator. The later cycle could explain observations where the maximum in compression straddles the equator. Ray tracing shows that this mode is confined within ±12° magnetic latitude which can account for the bulk of the observations. We show that the Doppler shift can account for the difference between the observed and model wave frequency, if the wave vector direction is in opposition to the plasma flow direction. We note that the Wentzel‐Kramers‐Brillouin approximation breaks down during the pileup of compressional energy and that a study involving full wave solutions is required.

Boardsen, S. A.↗
DOE OSTI2015

The response of ENSO flavors to mid‐Holocene climate: Implications for proxy interpretation

Abstract The response of El Niño–Southern Oscillation (ENSO) to mid‐Holocene boundary conditions remains an open question: paleoclimate proxies and climate model simulations do not agree in the magnitude of the reduction of ENSO variability, while recent proxy evidence from fossil corals from the central Pacific show that the reduction in mid‐Holocene ENSO variability compared to the end of the twentieth century is not different from the reduction during other Holocene time intervals. This is inconsistent with the interpretation of lake and ocean sediment records from the eastern Pacific, which show a significant reduction compared to all other Holocene periods. In order to reconcile the seemingly conflicting proxy evidence from the eastern and central Pacific, we hypothesize that ENSO remained active during the mid‐Holocene; however, there was a change in the spatial pattern of the sea surface temperature anomalies, also known as ENSO flavors. Using National Center for Atmospheric Research's Community Climate System Model version 4 forced with mid‐Holocene orbital conditions, we find that the frequency of occurrence of the strongest eastern Pacific (EP) events decreases in the mid‐Holocene and their variance is reduced by ∼30%, while the frequency of central Pacific (CP) events slightly increases and their variance does not change. We also find a shift in the seasonality of EP events, but not in that of CP events. Lastly, mid‐Holocene EP events develop more slowly and decay faster. The differential response of ENSO flavors to mid‐Holocene forcing is remotely forced by the West Pacific, where a weakening of the trade winds in early boreal spring in the mid‐Holocene initiates an anomalous downwelling annual Kelvin wave, which reaches the eastern Pacific during the ENSO development season, weakens the upper ocean stratification, and results in reduced ENSO upwelling feedback. The simulated reduction in the EP flavor versus the CP flavor in the mid‐Holocene is consistent with proxy evidence: The teleconnection patterns of the two flavors with temperature, precipitation, and salinity are distinct, and proxies from different regions of the Pacific might be recording variability associated with only one of the flavors, or some combination of their relative effects.

Karamperidou, Christina↗
DOE OSTI2018

A New Method for Interpreting Nonstationary Running Correlations and Its Application to the ENSO‐EAWM Relationship

Abstract We here propose a new statistical method to interpret nonstationary running correlations by decomposing them into a stationary part and a first‐order Taylor expansion approximation for the nonstationary part. Then, this method is applied to investigate the nonstationary behavior of the El Niño–Southern Oscillation (ENSO)‐East Asian winter monsoon (EAWM) relationship, which exhibits prominent multidecadal variations. It is demonstrated that the first‐order approximation of the nonstationary part can be expressed to a large extent by the impact of the nonlinear interaction between the Atlantic Multidecadal Oscillation (AMO) and ENSO (AMO*Niño3.4) on the EAWM. Therefore, the nonstationarity in the ENSO‐EAWM relationship comes predominantly from the impact of an AMO modulation on the ENSO‐EAWM teleconnection via this key nonlinear interaction. This general method can be applied to investigate nonstationary relationships that are often observed between various different climate phenomena.

Geng, Xin↗
DOE OSTI2024

Interpretable Machine Learning Models for Practical Antimonate Electrocatalyst Performance

Computationally predicting the performance of catalysts under reaction conditions is a challenging task due to the complexity of catalytic surfaces and their evolution in situ, different reaction paths, and the presence of solid-liquid interfaces in the case of electrochemistry. We demonstrate here how relatively simple machine learning models can be found that enable prediction of experimentally observed onset potentials. Inputs to our model are comprised of data from the oxygen reduction reaction on non-precious transition-metal antimony oxide nanoparticulate catalysts with a combination of experimental conditions and computationally affordable bulk atomic and electronic structural descriptors from density functional theory simulations. From human-interpretable genetic programming models, we identify key experimental descriptors and key supplemental bulk electronic and atomic structural descriptors that govern trends in onset potentials for these oxides and deduce how these descriptors should be tuned to increase onset potentials. Here, we finally validate these machine learning predictions by experimentally confirming that scandium as a dopant in nickel antimony oxide leads to a desired onset potential increase. Macroscopic experimental factors are found to be crucially important descriptors to be considered for models of catalytic performance, highlighting the important role machine learning can play here even in the presence of small datasets.

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

A multidimensional stability framework enhances interpretation and comparison of carbon cycling response to disturbance

Abstract The concept of stability is central to the study and sustainability of vital ecosystem goods and services as disturbances increase globally. While ecosystem ecologists, including carbon (C) cycling scientists, have long‐considered multiple dimensions of disturbance response, our discipline lacks an agreed‐upon analytical framework for characterizing multidimensional stability. Here, we advocate for the broader adoption of a standardized and normalized multidimensional stability framework for analyzing disturbance response. This framework includes four dimensions of stability: the degree of initial change in C fluxes (i.e., resistance ); rate (i.e., resilience ) and variability (i.e., temporal stability ) of return to pre‐disturbance C fluxes; and the extent of return to pre‐disturbance C fluxes (i.e., recovery ). Using this framework, we highlight findings not readily seen from analysis of absolute fluxes, including trade‐offs between initial and long‐term C flux responses to disturbance; different overall stability profiles among fluxes; and, using a pilot dataset, similar relative stability of net primary production following fire and insect disturbances. We conclude that ecosystem ecologists’ embrace of a unifying multidimensional stability framework as a complement to approaches focused on absolute C fluxes could advance global change research by aiding in the novel interpretation, comprehensive synthesis, and improved forecasting of ecosystems’ response to an increasing array of disturbances.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2017

Statistical interpretation of the Amerithrax “morph” assay results

In the Amerithrax investigation PCR–based “morph assays” were used to link the anthrax letters with the RMR–1029 flask at USAMRIID. Quantitative data reported for several of these assays are not consistent with Poisson sampling statistics, but instead exhibit “Taylor's Law” behavior where the variance greatly exceeds the mean. A plausible statistical model for this behavior can explain the large number of observed negative and “inconclusive” findings, and implies a high likelihood that a repository sample could contain a “morph” mutant at concentrations well above the nominal detection limit but nonetheless give a negative or inconclusive test result. A Bayesian framework relates the assay results to the probability that a sample actually contains all four morph mutants, even though it tested negative for at least one. The analysis implies that the observed false negative rate actually does not significantly weaken the conclusion that the morph assays correctly excluded all but the stocks derived from RMR–1029 as possible sources of the letter powders, at least when the test results were unambiguous. In conclusion, these findings expand upon and resolve some of the issues cited in recent reviews, and indicate the importance of developing a rigorous statistical framework for interpreting “morph” assay data.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2014

Factors influencing the development and implementation of advanced radiographer practice in Australia – a qualitative study using an interpretative phenomenological approach

The purpose of this study was to explore the factors influencing the implementation or the lack of implementation of advanced practitioner role in Australia. This study uses an interpretative phenomenological approach to explore the in-depth real life issues, which surround the advanced practitioner as a solution to radiologist workforce shortages in Australia. Research participants are radiographers, radiation therapists and health managers registered with the Australian Institute of Radiography (AIR) and holding senior professional and AIR Board positions with knowledge of current advanced practice. In total, seven interviews were conducted revealing education, governance, technical, people issues, change management, government, costs and timing as critical factors influencing advanced practice in Australia. Seven participants in this study perceived an advanced practice role might have major benefits and a positive impact on the immediate and long-term management of patients. Another finding is the greater respect and appreciation of each other's roles and expertise within the multidisciplinary healthcare team. Engagement is required of the critical stakeholders that have been identified as ‘blockers’ (radiologists, health departments) as well as identified allies (e.g. emergency clinicians, supportive radiologists, patient advocacy groups). The research supports that the AIR has a role to play for the professional identity of radiographers and shaping the advanced practice role in Australia.

42 ENGINEERING↗
DOE OSTI2026

A Step-by-Step Protocol from METASPACE to Biological Interpretation

Mass spectrometry imaging (MSI) represents an exceptional tool for exploring complex biological systems spatially at the molecular level. However, due to its multidimensional nature and large-scale data output, it presents considerable challenges when it comes to extracting meaningful biological insights. Recent advancements, such as the METASPACE platform, have enabled researchers to efficiently process, annotate, and interpret MSI datasets by leveraging machine learning and cloud-based infrastructure. In this tutorial, we present a detailed and user-friendly R-pipeline designed to help METASPACE users navigate untargeted metabolomic annotations and transform them into practical insights about their biological systems. By combining METASPACE annotations with rapid R-based screening, this workflow not only streamlined the analytical process but also enhanced the understanding of spatial molecular distribution, especially for complex systems. Here, this easy-to-follow approach has the potential for applications in diagnostics, drug discovery, environmental and ecological processes, and more. We envision this pipeline to be particularly useful for newcomers to the field of MSI and

Moreno Pedraza, Abigail↗
DOE OSTI2019

Interpreting Experimental Results from Shock Impacts on Single Crystal PETN in the Context of Continuum Models

Here we interpret previous experimental measurements of impacts on single crystal PETN in the context of a simple continuum model. Hugoniot calculations using the simple model framework under various limiting assumptions envelope measured Hugoniot states reasonably well and suggest that non-negligible deviatoric elastic strains may exist in the shock compressed state for weak impacts. An accompanying simple kinematic model for lattice deformation was used to estimate the expected shifts in X-ray diffraction peaks for the (211) plane under impacts normal to (110) planes. The results suggest that negligible relaxation of the deviatoric lattice deformation occurs on the short (10–20 ns) time and wave propagation (40–80 m) scales of laser-driven shock experiments, and that the corresponding elastic strains may be large. Because of the potentially large deviatoric elastic strains, the specific finite deformation strain measure used within thermomechanical single crystal models is of significant consequence, which is explored numerically by the comparison of isothermal purely elastic responses under uniaxial and simple shear deformations.

36 MATERIALS SCIENCE↗