Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “physical feature”

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 37 records · Page 2
All sourcesNASA NTRSDOE OSTI
DOE OSTI2024

Cy-Phy ADS: Cyber Physical Anomaly Detection Framework for EV Charging Systems

Today’s large-scale Electric Vehicle (EV) infrastructures are heavily dependent on information communication technologies to maintain their operation and to support communication within sub-system components as well as the outside world. These technologies are vulnerable to various cyber and physical threats. Timely identification and mitigation of these threats are critical for improving human safety, avoiding economic losses, and preventing catastrophic system failures. By addressing this, our work presents a ResNet Autoencoder (AE) based Cyber-Physical Anomaly Detection System (Cy-Phy ADS) for detecting anomalies in EV Controller Area Network (CAN) protocol communication. It consists of four main components: Cyber-Physical Feature Extractor, ResNet AE-based Anomaly Detection Framework, Cyber-Physical Health Metric (CPHM), and Visualization Dashboard. The presented framework was trained and tested using CAN data collected from the EV charging system testbed at the Idaho National Laboratory. The presented Cy-Phy ADS compared against six widely used unsupervised anomaly detection algorithms: One Class Support Vector Machine (OCSVM), Variational Autoencoder (VAE), LSTM Autoencoder (LSTM AE), Isolation Forest (IForest), Principle Component Analysis (PCA) and Local Outlier Factor (LOF). Here the presented approach showed the highest accuracy among the compared methods. Further, the proposed approach showed comparable performance in terms of precision, F1, and False positive rate. It also showed the lowest training and inference time compared to the neural network-based baseline algorithms compared against with. Additionally, the Cy-Phy ADS has advantages such as unsupervised training, the ability to provide a holistic metric for system health characterization, and non-linear feature extraction.

99 GENERAL AND MISCELLANEOUS↗
DOE OSTI2023

DRiFT - Release 1.1.1: Organic Scintillators

DRiFT (a Detector Response Function Toolkit) is LANL-developed software that postprocesses output from the extensively validated radiation transport code, MCNP, and generates realistic nuclear instrumentation response. DRiFT is designed to be flexible, enabling users to specify detector type and many experimental settings, as well as accommodating the addition of their own desired features. Although DRiFT development has included scintillator, gas, and semiconductor features, the focus of this release is on organic scintillator and associated capabilities. Organic scintillators are widely used in the areas of nuclear safeguards and nuclear non-proliferation efforts. DRiFT has several diagnostic and detector physics features relevant to detailed scintillator simulations including: tracking source particle information, scintillation light production, the effects of PMT quantum efficiency and gain, and digitizer settings. Users can select responses from many scintillator and PMT types supported natively by DRiFT, or add their own by following the instructions in this document. We acknowledge that DRiFT is under active development, bug reports and general questions and comments should be directed to Madison Andrews, madison@lanl.gov. This manual is divided into four parts: I) An overview of DRiFT, including how to obtain and install the executable, II) A description of the detector physics related to scintillators available, III) a description of more general DRiFT features the user may find useful, and IV) a description of the test suite and examples made available with the code release.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
DOE OSTI2021

DRiFT - Release 1.0.0 Organic Scintillators

DRiFT (a Detector Response Function Toolkit) is LANL-developed software that postprocesses output from the extensively validated radiation transport code, MCNP [1], and generates realistic nuclear instrumentation response. DRiFT is designed to be flexible, enabling users to specify detector type and many experimental settings, as well as accommodating the addition of their own desired features. Although DRiFT development has included scintillator [2], gas [3], and semiconductor features [4], the focus of this release is on organic scintillator and associated capabilities. Organic scintillators are widely used in the areas of nuclear safeguards and nuclear non-proliferation efforts [5, 6]. DRiFT has several diagnostic and detector physics features relevant to detailed scintillator simulations including: tracking source particle information, scintillation light production, the effects of PMT quantum efficiency and gain, and digitizer settings. Users can select responses from many scintillator and PMT types supported natively by DRiFT, or add their own by following the instructions in this document. We acknowledge that DRiFT is under active development, bug reports and general questions and comments should be directed to Madison Andrews, madison@lanl.gov. This manual is divided into four parts: I) An overview of DRiFT, including how to obtain and install the executable, II) A description of the detector physics related to scintillators available, III) a description of more general DRiFT features the user may find useful, and IV) a description of the test suite and examples made available with the code release.

61 RADIATION PROTECTION AND DOSIMETRY↗
DOE OSTI2024

Chapter 8: Searching for Life Beyond Earth

The search for life beyond Earth necessitates a rigorous and comprehensive examination of biosignatures, the types of observable imprints that life produces. These imprints and our ability to detect them with advanced instrumentation hold the key to our understanding of the presence and abundance of life in the universe. Biosignatures are the chemical or physical features associated with past or present life and may include the distribution of elements and molecules, alone or in combination, as well as changes in structural components or physical processes that would be distinct from an abiotic background. The scientific and technical strategies used to search for life on other planets include those that can be conducted in situ to planetary bodies and those that could be observed remotely. Here this chapter discusses numerous strategies that can be employed to look for biosignatures directly on other planetary bodies using robotic exploration including those that have been deployed to other planetary bodies, are currently being developed for flight, or will become a critical technology on future missions. Search strategies for remote observations using current and planned ground-based and space-based telescopes are also described. Evidence from spectral absorption, emission, or transmission features can be used to search for remote biosignatures and technosignatures. Improving our understanding of biosignatures, their production, transformation, and preservation on Earth can enhance our search efforts to detect life on other planets.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2024

Jet rotational metrics

Abstract Embedding symmetries in the architectures of deep neural networks can improve classification and network convergence in the context of jet substructure. These results hint at the existence of symmetries in jet energy depositions, such as rotational symmetry, arising from the physical features of the underlying processes. We introduce new jet observables, Jet Rotational Metrics (JRMs), which provide insights into the substructure of jets by comparing them to jets with perfect discrete rotational symmetry. We show that JRMs are formidable jet features, achieving good classification scores when used as inputs to deep neural networks. We also show that when used in combination with other jet observables, like N-subjettiness and EFPs, our features increase classification performance. The results suggest that JRMs may capture information not efficiently captured by the other observables, motivating the design of future jet observables for learning the underlying symmetries in the physical processes.

Physics↗
DOE OSTI2026

Identifying Anomalous DESI Galaxy Spectra with a Variational Autoencoder

The tens of millions of spectra being captured by the Dark Energy Spectroscopic Instrument (DESI) provide tremendous discovery potential. In this work we show how Machine Learning, in particular Variational Autoencoders (VAE), can detect anomalies in a sample of approximately 200,000 DESI spectra comprising galaxies, quasars and stars. We demonstrate that the VAE can compress the dimensionality of a spectrum by a factor of 100, while still retaining enough information to accurately reconstruct spectral features. We then detect anomalous spectra as those with high reconstruction error and those which are isolated in the VAE latent representation. The anomalies identified fall into two categories: spectra with artefacts and spectra with unique physical features. Awareness of the former can help to improve the DESI spectroscopic pipeline; whilst the latter can lead to the identification of new and unusual objects. To further curate the list of outliers, we use the Astronomaly package which employs Active Learning to provide personalised outlier recommendations for visual inspection. In this work we also explore the VAE latent space, finding that different object classes and subclasses are separated despite being unlabelled. We demonstrate the interpretability of this latent space by identifying tracks within it that correspond to various spectral characteristics. For example, we find tracks that correspond to increasing star formation and increase in broad emission lines along the Balmer series. In upcoming work we hope to apply the methods presented here to search for both systematics and astrophysically interesting objects in much larger datasets of DESI spectra.

Nicolaou, C. [University Coll. London] (ORCID:0000↗
DOE OSTI2023

Holographic thermal correlators: a tale of Fuchsian ODEs and integration contours

We analyze real-time thermal correlation functions of conserved currents in holographic field theories using the grSK geometry, which provides a contour prescription for their evaluation. We demonstrate its efficacy, arguing that there are situations involving components of conserved currents, or derivative interactions, where such a prescription is, in fact, essential. To this end, we first undertake a careful analysis of the linearized wave equations in AdS black hole backgrounds and identify the branch points of the solutions as a function of (complexified) frequency and momentum. All the equations we study are Fuchsian with only regular singular points that for the most part are associated with the geometric features of the background. Special features, e.g., the appearance of apparent singular points at the horizon, whence outgoing solutions end up being analytic, arise at higher codimension loci in parameter space. Using the grSK geometry, we demonstrate that these apparent singularities do not correspond to any interesting physical features in higher-point functions. We also argue that the Schwinger-Keldysh collapse and KMS conditions, implemented by the grSK geometry, continue to hold even in the presence of such singularities. For charged black holes above a critical charge, we furthermore demonstrate that the energy density operator does not possess an exponentially growing mode, associated with ‘pole-skipping’, from one such apparent singularity. Our analysis suggests that the connection between the scrambling physics of black holes and energy transport has, at best, a limited domain of validity.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗
DOE OSTI2022

A reaction–diffusion model for grayscale digital light processing 3D printing

We report that digital light processing (DLP) 3D printing is an additive manufacturing process that utilizes light patterns to photopolymerize a liquid resin into a solid. Due to the accuracy of modern digital micromirror devices (DMD) and recent advances in resin chemistry, it is now possible to create functionally graded structures using different light intensity values, also known as grayscale DLP (g-DLP). Different intensities of light lead to differences in the polymer crosslinking density after curing, which ultimately produces a part with gradients of material properties. However, g-DLP is a complicated process. First, the DLP printing is a highly coupled chemical and physical process that involves light propagation, chemical reactions, species diffusion, heat transfer, volume shrinkage, and changes in mechanical behaviors of the curing resin. Second, in g-DLP, light gradients create strong in plane gradients of chemical species concentrations in the curing liquid resin due to the strong dependence of light intensity on the rate of monomer crosslinking. Furthermore, light gradients through the depth create concentration gradients due to the degree of cure dependent light absorption and the use of photoabsorbers. These complex physical features of the printing process must be understood in order to properly control printing parameters such as light exposure time, printing speed, and grayscale variations to achieve accurate mechanical properties. In this paper, a photopolymerization reaction–diffusion model is developed and used in conjunction with experiments to investigate the coupled effects of light propagation, chemical reaction rates, and species diffusion during g-DLP 3D printing. The model is implemented numerically utilizing the finite difference method and simulation results are compared to experimental findings of simple printed structures. The agreement between experimental and model predictions of simple quantities of interest, such as geometric feature sizes, shows that the model can capture the overcure due to free-radical and other species diffusion during printing when grayscale patterns are employed. This model lays the groundwork for future extensions that can incorporate more complex coupled physics such as heat transfer, volume shrinkage, and material property evolution, which are critically important in utilizing g-DLP 3D printing for the fabrication of high-performance parts which excellent geometric and material property tolerances.

36 MATERIALS SCIENCE↗
DOE OSTI2024

Neural network denoising of x-ray images from high-energy-density experiments

Noise is a consistent problem for x-ray transmission images of High-Energy-Density (HED) experiments because it can significantly affect the accuracy of inferring quantitative physical properties from these images. We consider experiments that use x-ray area backlighting to image a thin layer of opaque material within a physics package to observe its hydrodynamic evolution. The spatial variance of the x-ray transmission across the system due to changing opacity serves as an analog for measuring density in this evolving layer. The noise in these images adds nonphysical variations in measured intensity, which can significantly reduce the accuracy of our inferred densities, particularly at small spatial scales. Denoising these images is thus necessary to improve our quantitative analysis, but any denoising method also affects the underlying information in the image. In this paper, we present a method for denoising HED x-ray images via a deep convolutional neural network model with a modified DenseNet architecture. In our denoising framework, we estimate the noise present in the real (data) images of interest and apply the inferred noise distribution to a set of natural images. These synthetic noisy images are then used to train a neural network model to recognize and remove noise of that character. We show that our trained denoiser network significantly reduces the noise in our experimental images while retaining important physical features.

47 OTHER INSTRUMENTATION↗
DOE OSTI2025

Interface diagnostics platform for thin-film solid-state batteries

Understanding the impedances of battery materials and their interfaces remains a major challenge, usually addressed by electrochemical impedance spectroscopy (EIS) where frequency-dependent complex impedance of full battery cells is measured and then modeled by a network of connected electrical elements. As conventionally applied, this approach produces ambiguity in that (1) multiple different network configurations may fit the data convincingly and (2) the method offers no direct association of the electrical elements with physical features of the battery. Here we present a new methodology that resolves both sources of ambiguity, enabled by expanding the experimental scope to directly inform the configuration of elements and their parameters in the network model. We demonstrate this methodology using thin film fabrication of solid state battery devices patterned by shadow masked sputter deposition, so that diagnostic devices corresponding to individual interface and material components can be fabricated simultaneously with full cell batteries. EIS models for the diagnostic devices can then be connected to form full cell networks whose topology matches the well-known physical configuration of the battery. When connected in this way, the full network model – made from connecting the diagnostic device EIS models – fits the full cell EIS data. For the case of a thin film solid state battery composed of amorphous silicon anode, lithium phosphorus oxynitride (LiPON) solid electrolyte, and lithium vanadium oxide (Li x V 2 O 5 ) cathode, we show that the approach allows us to identify ionic impedance/conductivity of the cathode/electrolyte as a limiting impedance and the anode/electrolyte interface cycling instability as a primary degradation factor.

25 ENERGY STORAGE↗
DOE OSTI2021

Nitrogen-doped graphene nanomaterials for electrochemical catalysis/reactions: A review on chemical structures and stability

The electronic structure of the carbon-based nanomaterials can be modulated by doping heteroatoms into them. When nitrogen is doped into the graphene structure with different bonding configurations, it changes the material's electronic properties in a variety of ways. Because of the tuned electronic properties, nitrogen-doped graphene (N-G) is applicable in electrochemical systems as catalyst. Despite having tremendous prospects, a holistic view of the structural and functional properties of N-G is still unclear. Moreover, to our knowledge, significant findings on the properties of N-G are not well documented yet, which creates an obstacle to the further improvement of this nanomaterial. Keeping our focus on the catalytic activities, in this paper, we presented an in-detailed review of the overall chemical structure and functional properties of N-G nanomaterials. Starting from the structural properties of major precursor materials for N-G synthesis, we reviewed the physical features and its dependence on the synthesis parameters. Also, a detailed study has been conducted on the key nitrogen functional groups' structural properties, favorable formation environment, influence on the electronic structure of N-G, and role in the catalytic activity. Finally, current progress on the stability of N-G nanocatalysts is reported with an insight into the degradation mechanism.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2023

Comparison of MHD stability properties between QH-mode and ELMy H-mode plasmas by considering plasma rotation and ion diamagnetic drift effects

Magnetohydrodynamic (MHD) stability at tokamak edge pedestal in a quiescent H-mode (QH-mode) and type-I ELMy H-mode plasmas in DIII-D experiment was analyzed by considering plasma rotation and ion diamagnetic drift effects. QH-mode plasma is marginally stable to kink/peeling mode (K/PM), but ELMy H-mode one is almost unstable to peeling-ballooning mode (PBM). It was identified that there are three physics features responsible for the difference in the MHD stability properties between QH-mode plasma and ELMy H-mode one. These are the distance of pedestal foot from the last closed flux surface (LCFS), the amount of the ion diamagnetic drift frequency at pedestal, and impact of coupled rotation and ion diamagnetic drift effects. These features were confirmed through the numerical experiments that the stability properties of the QH-mode plasma can be changed to that of the ELMy H-mode one by shifting the plasma profiles inward in the radial direction and halving the ion diamagnetic drift frequency. The reasons of the change in the stability properties are thought as that K/PM is stabilized due to the inward shift of the bootstrap current profile, and PBM is destabilized due to the reduction of the coupled rotation and ion diamagnetic drift stabilizing effect. Importance of these features was validated through numerical experiments with experimental data of other QH-mode plasmas in DIII-D. All the results show that MHD stability properties of QH-mode plasma can be obtained in case that pedestal foot is close to LCFS, ion diamagnetic drift frequency is large due to high ion temperature, and strong rotation shear exists near pedestal.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
DOE OSTI2022

LLNL Explosives Anisotropy Research

Lawrence Livermore National Laboratory scientists and engineers led a multi-institutional team in executing a series of high explosives tests that successfully demonstrated fundamental principles of anisotropy, a possible enabler for improved weapon and munition safety. Working under snowy and frigid conditions on Idaho’s Snake River Plain, a 13-member team from LLNL carried out 52 explosives shots over four days in mid-November at the Idaho National Laboratory’s (INL) National Security Test Range (NSTR) to complete the study. The broader anisotropy (ANISO) team included high explosives handlers and volunteers from INL, Los Alamos National Laboratory, Marine Raiders from the Marine Special Operations Command and members of the U.S. Special Operations Command. The purpose of the study was to explore theoretical methods of creating anisotropic explosives — explosives that perform differently depending on the direction the detonation wave moves through the explosive — by engineering certain physical features in the charges and obtaining basic data from testing. The work is part of an overall effort by the Lab to develop anisotropic explosives that could be used in munitions to reduce the severity and lethality of an unintended detonation without sacrificing performance. The data gathered from the study will be used to design and construct follow-on experiments at LLNL’s High Explosives Applications Facility (HEAF) and validate computer models for future anisotropic assemblies.

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

Topological descendants of a multicritical Dirac semimetal with magnetism and strain

The past decades have witnessed a transformation in characterizing condensed matter systems with topology. Aided by a refined understanding of topological band structures with crystalline symmetries that has emerged recently, many electronic phases have been identified, and a plethora of materials have been predicted to host properties and functionalities. A key underlying question, also with respect to future application, is to what extent the related physical features can be manipulated, especially in the context of magnetic order. Here, we describe a paradigmatic semimetal that simultaneously incorporates multiple and sometimes conflicting topology which guarantees gaplessness and leads to an exceptionally rich family of descendent phases on lowering symmetry. We predict that this multicritical phase is realized in EuTl 2 . Starting from the parent semimetallic state, which already separates two topological insulating regimes, the interplay of inherent magnetism and strain allows for an exceptionally rich phase diagram of topological descendant states.

75 CONDENSED MATTER PHYSICS, SUPERCONDUCTIVITY AND↗
DOE OSTI2021

Model fusion with physics-guided machine learning: Projection-based reduced-order modeling

The unprecedented amount of data generated from experiments, field observations, and large-scale numerical simulations at a wide range of spatiotemporal scales has enabled the rapid advancement of data-driven and especially deep learning models in the field of fluid mechanics. Although these methods are proven successful for many applications, there is a grand challenge of improving their generalizability. This is particularly essential when data-driven models are employed within outer-loop applications like optimization. In this work, we put forth a physics-guided machine learning (PGML) framework that leverages the interpretable physics-based model with a deep learning model. Leveraging a concatenated neural network design from multi-modal data sources, the PGML framework is capable of enhancing the generalizability of data-driven models and effectively protects against or inform about the inaccurate predictions resulting from extrapolation. We apply the PGML framework as a novel model fusion approach combining the physics-based Galerkin projection model and long- to short-term memory (LSTM) network for parametric model order reduction of fluid flows. We demonstrate the improved generalizability of the PGML framework against a purely data-driven approach through the injection of physics features into intermediate LSTM layers. Our quantitative analysis shows that the overall model uncertainty can be reduced through the PGML approach, especially for test data coming from a distribution different than the training data. Moreover, we demonstrate that our approach can be used as an inverse diagnostic tool providing a confidence score associated with models and observations. The proposed framework also allows for multi-fidelity computing by making use of low-fidelity models in the online deployment of quantified data-driven models.

42 ENGINEERING↗
DOE OSTI2023

Fast and accurate simulations of calorimeter showers with normalizing flows

In this study, we introduce caloflow, a fast detector simulation framework based on normalizing flows. For the first time, we demonstrate that normalizing flows can reproduce many-channel calorimeter showers with extremely high fidelity, providing a fresh alternative to computationally expensive geant4 simulations, as well as other state-of-the-art fast simulation frameworks based on generative adversarial networks (GANs) or variational autoencoders (VAEs). In addition to the usual histograms of physical features and images of calorimeter showers, we introduce a new metric for judging the quality of generative modeling: the performance of a classifier trained to differentiate real from generated images. We show that GAN-generated images can be identified by the classifier with nearly 100% accuracy, while images generated from caloflow are better able to fool the classifier. More broadly, normalizing flows offer several advantages compared to other state-of-the-art approaches (GANs and VAEs), including tractable likelihoods, stable and convergent training, and principled model selection. Normalizing flows also provide a bijective mapping between data and the latent space, which could have other applications beyond simulation, for example, to detector unfolding.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2022

Formation, cooling history and age of impact events on the IIE iron parent body: Evidence from the Miles meteorite

Most iron meteorites formed in planetary cores during differentiation, but the IIE iron meteorites have chemical and physical features that are inconsistent with this origin. By combining mineral chemistry, mineral modes and three-dimensional petrography, we reconstruct the bulk chemistry of the felsic silicate-bearing Miles IIE iron meteorite and demonstrate that the silicate inclusion compositions are similar to partial melts produced experimentally from an H chondrite composition. We use the reconstructed bulk composition, mineralogy and thermodynamic modelling to show that melting above ~ 1200°C under reducing conditions formed metal (Fe-Ni alloy) and felsic silicate partial melts. Upon cooling, the melts crystallized Mg-rich pyroxenes, Na- and K-rich feldspars, and tridymite. Importantly, this mechanism enriches cosmochemically volatile elements (i.e., those with a 50% condensation temperature of ~430–830°C, like Na and K) to the level found in the felsic silicate inclusions. The presence of crystallographically disordered srilankite (only stable above 1160°C) and an absence of Widmanstätten texture require both high peak temperatures and rapid cooling, which cannot be explained by core formation. Instead, they point to small melt volumes, a transient heat pulse, and small thermal mass, and imply efficient physical segregation of silicate and metallic melts through buoyancy separation followed by rapid cooling that arrested the separation of metal and silicate liquid phases. In situ 207 Pb/ 206 Pb age of 4542.3 ± 4.0 Ma in Zr-oxide and phosphate minerals dates the melting event that formed the silicate inclusions. This age aligns with the earliest ages found in other IIE iron meteorite silicates and requires a heating event ~25 million years after the solar system formed. We found 39 Ar/ 40 Ar ages of 3495 ± 52 Ma (low-T) and 4303 ± 7 Ma (high-T) in a K-feldspar grain, with the 3495 Ma age aligning with later thermal events recorded in other IIE iron meteorites. Dating reveals the complex petrogenetic and thermal history of Miles and the IIE iron meteorites. This is the first IIE iron meteorite found to record evidence of heating at 4.5 and 3.5 Ga likely from impact events. We propose that high-velocity impact(s) into an iron-rich, porous chondritic parent body at ~4.54 Ga produced immiscible metal and silicate melts that cooled rapidly and trapped low density silicate inclusions within high density metal. Other IIE irons that formed at lower peak temperatures (900–1000°C) contain chondritic silicate inclusions and relict chondrules, supporting this conceptual model. In conclusion, this petrogenesis is consistent with thermodynamic modelling, experimental data and the wide range of peak temperatures and cooling rates observed in the IIE iron meteorites.

58 GEOSCIENCES↗
DOE OSTI2022

Distilling physical origins of hardness in multi-principal element alloys directly from ensemble neural network models

Abstract Despite a plethora of data being generated on the mechanical behavior of multi-principal element alloys, a systematic assessment remains inaccessible via Edisonian approaches. We approach this challenge by considering the specific case of alloy hardness, and present a machine-learning framework that captures the essential physical features contributing to hardness and allows high-throughput exploration of multi-dimensional compositional space. The model, tested on diverse datasets, was used to explore and successfully predict hardness in Al x Ti y (CrFeNi) 1- x - y , Hf x Co y (CrFeNi) 1- x - y and Al x (TiZrHf) 1- x systems supported by data from density-functional theory predicted phase stability and ordering behavior. The experimental validation of hardness was done on TiZrHfAl x . The selected systems pose diverse challenges due to the presence of ordering and clustering pairs, as well as vacancy-stabilized novel structures. We also present a detailed model analysis that integrates local partial-dependencies with a compositional-stimulus and model-response study to derive material-specific insights from the decision-making process.

75 CONDENSED MATTER PHYSICS, SUPERCONDUCTIVITY AND↗