Search NASA⌕ Search

SEARCH · Search NASA

Results for “statistical learning”

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 631 records · Page 35

Matched-pair classification

Following an analogous distinction in statistical hypothesis testing, we investigate variants of machine learning where the training set comes in matched pairs. We demonstrate that even conventional classifiers can exhibit improved performance when the input data has a matched-pair structure. Online algorithms, in particular, converge quicker when the data is presented in pairs. In some scenarios (such as the weak signal detection problem), matched pairs can be generated from independent samples, with the effect not only doubling the nominal size of the training set, but of providing the structure that leads to better learning. A family of 'dipole' algorithms is introduced that explicitly takes advantage of matched-pair structure in the input data and leads to further performance gains. Finally, we illustrate the application of matched-pair learning to chemical plume detection in hyperspectral imagery.

97 MATHEMATICS AND COMPUTING↗

Enabling probabilistic learning on manifolds through double diffusion maps

Here, we present a generative learning framework for probabilistic sampling that extends Probabilistic Learning on Manifolds (PLoM), which is designed to generate statistically consistent realizations of a random vector in a finite-dimensional Euclidean space, informed by a (representative) set of observations. In its original form, PLoM constructs a reduced-order probabilistic model by combining three main components: (a) kernel density estimation to approximate the underlying probability measure, (b) Diffusion Maps to characterize the manifold of the data, and (c) a reduced-order Itô Stochastic Differential Equation (ISDE) to sample from the learned distribution. However, its sampling dynamics are posed in the ambient space and the retained number of reduced coordinates is chosen by projection-reconstruction error. In practice, this often (i) requires more coordinates than the data’s intrinsic dimension to achieve stable sampling and (ii) lacks a smooth, basis-independent lifting back to the data domain; moreover, standard Diffusion Maps emphasize harmonic eigenfunctions and can miss non-harmonic latent structure. We address these limitations by decoupling geometry learning from sampling: a first Diffusion Maps pass identifies non-harmonic coordinates on which we formulate a full-order ISDE directly in the latent space, while Double Diffusion Maps captures multiscale geometric features and Geometric Harmonics (GH) learns a smooth lifting map to the ambient variables that is independent of the particular diffusion basis. This hybrid design preserves the system’s dynamical richness with a compact geometric representation and enables principled out-of-sample inference. The effectiveness and robustness of the proposed method are illustrated through two numerical studies: one based on data generated from two-dimensional Hermite polynomial functions and another based on high-fidelity simulations of a detonation wave in a reactive flow.

Double diffusion maps↗

Stopping criteria for ending autonomous, single detector radiological source searches

While the localization of radiological sources has traditionally been handled with statistical algorithms, such a task can be augmented with advanced machine learning methodologies. The combination of deep and reinforcement learning has provided learning-based navigation to autonomous, single-detector, mobile systems. However, these approaches lacked the capacity to terminate a surveying/search task without outside influence of an operator or perfect knowledge of source location (defeating the purpose of such a system). Two stopping criteria are investigated in this work for a machine learning navigated system: one based upon Bayesian and maximum likelihood estimation (MLE) strategies commonly used in source localization, and a second providing the navigational machine learning network with a “stop search” action. A convolutional neural network was trained via reinforcement learning in a 10 m × 10 m simulated environment to navigate a randomly placed detector-agent to a randomly placed source of varied strength (stopping with perfect knowledge during training). The network agent could move in one of four directions (up, down, left, right) after taking a 1 s count measurement at the current location. During testing, the stopping criteria for this navigational algorithm was based upon a Bayesian likelihood estimation technique of source presence, updating this likelihood after each step, and terminating once the confidence of the source being in a single location exceeded 0.9. A second network was trained and tested with similar architecture as the previous but which contained a fifth action: for self-stopping. The accuracy and speed of localization with set detector and source initializations were compared over 50 trials of MLE-Bayesian approach and 1000 trials of the CNN with self-stopping. The statistical stopping condition yielded a median localization error of ~1.41 m and median localization speed of 12 steps. The machine learning stopping condition yielded a median localization error of 0 m and median localization speed of 17 steps. This work demonstrated two stopping criteria available to a machine learning guided, source localization system.

38 RADIATION CHEMISTRY, RADIOCHEMISTRY, AND NUCLEA↗

A Comparative Study of Machine Learning Algorithms for Industry-Specific Freight Generation Model

According to Bureau of Transportation Statistics, the U.S. transportation system handled 14,329 million ton-miles of freight per day in 2020. Understanding the generation of these freight shipments is crucial for transportation researchers, planners, and policymakers to design and plan for a more efficient and connected freight transportation system. Traditionally, the freight generation modeling has been based on Ordinary Least Square (OLS) regression, although more advanced Machine Learning (ML) algorithms have been evaluated and proven to have excellent performance in various transportation applications in recent years. Furthermore, one modeling approach applied for one industry might not always be applicable for another as their freight generation logics can be quite different. The objective of this study is to apply and evaluate alternative ML algorithms in the estimation of freight generation for each of 45 industry types. Seven alternative ML algorithms, along with the base OLS regression, were evaluated and compared. In addition, the study considered different combinations of variables in both the original and logarithmic form as well as hyperparameters of those ML algorithms in the model selection for each industry type. The results showed statistically significant improvements in the root mean square error reduction by the alternative ML algorithms over the OLS for over 80% of cases. The study suggests utilizing the alternative ML algorithms can reduce the root mean square error by about 30%, depending on industry types.

97 MATHEMATICS AND COMPUTING↗

From Latent Dynamics to Meaningful Representations

While representation learning has been central to the rise of machine learning and artificial intelligence, a key problem remains in making the learnt representations meaningful. For this the typical approach is to regularize the learned representation through prior probability distributions. However such priors are usually unavailable or are ad hoc. To deal with this, recent efforts have shifted towards leveraging the insights from physical principles to guide the learning process. In this spirit, we propose a purely dynamics-constrained representation learning framework. Instead of relying on predefined probabilities, we restrict the latent representation to follow overdamped Langevin dynamics with a learnable transition density — a prior driven by statistical mechanics. We show this is a more natural constraint for representation learning in stochastic dynamical systems, with the crucial ability to uniquely identify the ground truth representation. We validate our framework for different systems including a real-world fluorescent DNA movie dataset. Here, we show that our algorithm can uniquely identify orthogonal, isometric and meaningful latent representations.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

Decoding {beta}-decay systematics: A global statistical model for {beta}{sup -} half-lives

Statistical modeling of nuclear data provides a novel approach to nuclear systematics complementary to established theoretical and phenomenological approaches based on quantum theory. Continuing previous studies in which global statistical modeling is pursued within the general framework of machine learning theory, we implement advances in training algorithms designed to improve generalization, in application to the problem of reproducing and predicting the half-lives of nuclear ground states that decay 100% by the {beta}{sup -} mode. More specifically, fully connected, multilayer feed-forward artificial neural network models are developed using the Levenberg-Marquardt optimization algorithm together with Bayesian regularization and cross-validation. The predictive performance of models emerging from extensive computer experiments is compared with that of traditional microscopic and phenomenological models as well as with the performance of other learning systems, including earlier neural network models as well as the support vector machines recently applied to the same problem. In discussing the results, emphasis is placed on predictions for nuclei that are far from the stability line, and especially those involved in r-process nucleosynthesis. It is found that the new statistical models can match or even surpass the predictive performance of conventional models for {beta}-decay systematics and accordingly should provide a valuable additional tool for exploring the expanding nuclear landscape.

73 NUCLEAR PHYSICS AND RADIATION PHYSICS↗

SPHINX: An SEP Model Validation Infrastructure developed through Community Challenges and the SEP Scoreboards

Solar Energetic Particle (SEP) events are interesting from a scientific perspective as they are the product of a broad set of physical processes from the corona out through the extent of the heliosphere, and provide insight into processes of particle acceleration and transport that are widely applicable in astrophysics. From the operations perspective, SEP events pose a radiation hazard for aviation, electronics in space, and human space exploration, in particular for missions outside of the Earth’s protective magnetosphere including to the Moon and Mars (Whitman et al 2022). For these reasons, SEP modelers have developed a rich and diverse set of models with a wide variety of aims. Some models probe the basic physics at the heart of particle acceleration and transport. Others produce fast statistical forecasts or employ disruptive new techniques like Machine Learning with the goal to assist end users in making operational decisions. To enable a consistent and quantitative understanding of SEP model performance, a generalized, automated validation infrastructure, called SPHINX, is being developed at NASA SRAG in close collaboration with NASA CCMC, NASA M2M, NOAA SWPC, and BIRA-IASB. This infrastructure has been built up through a multi-year community challenge. Starting in 2018 at the SHINE workshop, an effort was launched through SHINE, ISWAT, and ESWW to encourage quantitative, comprehensive, and consistent validation of SEP models. This effort has defined a set of challenge SEP events with the aim of generating quantitative comparisons between forecasts and observations and a set of challenge “non-events” to assess false alarms. In 2023, these challenge lists have been extended to statistically significant numbers with a prescribed set of rules for producing forecasts and supported through the dedicated SEPVAL working meetings. The participation of the research community has allowed the infrastructure to validate all the types of outputs being produced by SEP models. In parallel, the SPHINX code is being applied to real time forecasts submitted to the SEP Scoreboards, ensuring that the validation infrastructure can interpret forecasts produced in an operational scenario and provide metrics meaningful for operations. Upon completion, SPHINX and its interactive user interface, SPHINX-Web, will be made available for public use.

space weather↗

ThickBrick: optimal event selection and categorization in high energy physics. Part I. Signal discovery

We provide a prescription called ThickBrick to train optimal machine-learning-based event selectors and categorizers that maximize the statistical significance of a potential signal excess in high energy physics (HEP) experiments, as quantified by any of six different performance measures. For analyses where the signal search is performed in the distribution of some event variables, our prescription ensures that only the information complementary to those event variables is used in event selection and categorization. This eliminates a major misalignment with the physics goals of the analysis (maximizing the significance of an excess) that exists in the training of typical ML-based event selectors and categorizers. In addition, this decorrelation of event selectors from the relevant event variables prevents the background distribution from becoming peaked in the signal region as a result of event selection, thereby ameliorating the challenges imposed on signal searches by systematic uncertainties. Our event selectors (categorizers) use the output of machine-learning-based classifiers as input and apply optimal selection cutoffs (categorization thresholds) that are functions of the event variables being analyzed, as opposed to flat cutoffs (thresholds). These optimal cutoffs and thresholds are learned iteratively, using a novel approach with connections to Lloyd’s k-means clustering algorithm. We provide a public, Python implementation of our prescription, also called ThickBrick, along with usage examples.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

Retrofit California: Better Buildings Program Overview

Energy efficiency retrofits (also called upgrades) are widely recognized as a critical component to achieving energy savings in the building sector to help lower greenhouse gas (GHG) emissions. To date, however, upgrades have accounted for only a small percentage of aggregate energy savings in building stock, both in California and nationally. Although the measures and technologies to retrofit a building to become energy efficient are readily deployed, establishing this model as a standard practice remains elusive. Retrofit California sought to develop and test new program models to increase participation in the energy upgrade market in California. The Program encompassed 24 pilot projects, conducted between 2010 and mid-2013 and funded through a $30 million American Recovery and Reinvestment Act (ARRA) grant from the U.S. Department of Energy’s (DOE) Better Buildings Neighborhood Program (BBNP). The broad scope of the Program can be seen in the involvement of the following regionally based Grant Partners: Los Angeles County (as prime grantee); Association of Bay Area Governments (ABAG), consisting of: StopWaste.org for Alameda County, Regional Climate Protection Authority (RCPA) for Sonoma County, SF Environment for the City and County of San Francisco, and City of San Jose; California Center for Sustainable Energy (CCSE) for the San Diego region; Sacramento Municipal Utilities District (SMUD). Within these jurisdictions, nine different types of pilots were tested with the common goal of identifying, informing, and educating the people most likely to undertake energy upgrades (both homeowners and contractors), and to provide them with incentives and resources to facilitate the process. Despite its limited duration, Retrofit California undoubtedly succeeded in increasing awareness and education among home and property owners, as well as contractors, realtors, and community leaders. However, program results indicate that a longer timeframe will be needed to transform the market and establish energy retrofits as the new paradigm. Innovations such as Flex Path, which came about because of barriers encountered during the Program, have already shown promise and are enabling increased participation. Together, the pilots represent an unprecedented effort to identify and address market barriers to energy efficiency upgrades and to provide lessons learned to shape future program planning and implementation. The statistics reflects the scope of the marketing and outreach campaigns, which tested a variety of approaches to increase understanding of the benefits of energy upgrades to drive participation in the Program. More traditional methods such as TV and radio advertisements were complimented by innovative community based social marketing campaigns that sought to leverage the trusted status of neighborhood organizations and leaders in order to motivate their constituents to undertake retrofits. The remainder of this report provides an overview of Retrofit California including brief summaries of the pilots’ main components and highlights, followed by the major findings or takeaway lessons from the approaches that were tested. Eleven of the pilots will be continued, with modifications, under the ratepayer-funded Regional Energy Networks. Involvement in the RENS by many of the Retrofit California partners will ensure that early lessons learned are carried forward to guide future programs for energy upgrades in California.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗

Machine Learning for Neutron Resonance Evaluations [Slides]

The performance of nuclear reactors and other nuclear systems depends on a precise understanding of the neutron interaction cross sections for materials used in these systems. These cross sections exhibit a resonance structure whose shape is determined in part by the angular momentum quantum numbers of the resonances. The correct assignment of the quantum numbers of neutron resonances is therefore of paramount importance. In this presentation, we describe the application of machine learning to automate the quantum number assignments. Scikit-learn classifiers were trained on simulated resonance data whose statistical properties were chosen to mimic real data. We explored the use of several physics (and random matrix theory)-motivated features for training the classifiers, including the nearest neighbor spacing distribution, cumulative level distribution, and channel width distributions. Initial results demonstrated that we can determine resonance spin groups somewhat reliably. We are now investigating the application of our approach to 52 Cr resonance data.

73 NUCLEAR PHYSICS AND RADIATION PHYSICS↗

AI-Batt (Autonomous Identification of Battery Life Models) [SWR 21-36]

Autonomous Identification of Battery Life Models (AI-Batt) AI-Batt is a MATLAB code base for developing lifetime models for batteries from accelerated aging data. The code base provides many functions for processing, visualizing, and modeling battery aging data, making the data processing, exploration, and modeling workflow substantially faster. These tools are tailored for working with battery aging data sets, which usually consist of many separate time-series for each cell, with many test conditions and possible replicates at each condition, which makes it difficult to simply process or visualize the data set. Complex modeling tasks, such as cross-validation, sensitivity analysis, and uncertainty quantification have been implemented to enable thorough statistical investigation of model predictions. Additionally, several machine-learning algorithms are implemented to autonomously identify suitable models via symbolic regression. Data processing functions automatically cast data from the struct data type, which is commonly used to store experimental data, but is not an acceptable input for most algorithms, to the table data type, which can be easily used as input to any optimization algorithm. Also, the data can be separated into time-invariant and time-variant data tables, which is helpful for exploring the data set as well as developing separate models for time-variant and time-invariant aging mechanisms. For example, in aging tests with constant temperature, temperature is a time-invariant experimental condition. Visualization tools enable plotting of data, model fits, and model simulations possible with single-line function calls, empowering data exploration of complex data sets with both time-varying and time-invariant trends. Plots can be automatically generated for the whole data set, or separated by data group (groups of test replicates) or individual data series. Data points or data series can be automatically colored by the value of a variable with a variety of color maps, and model predictions can also be colored by the value of a fit statistic. Comparisons between data sets and the predictions/simulations of different models on the same data set can be easily plotted as well. Distributions of parameter values from bootstrap resampling can be plotted to visualize the reliability of parameter estimation, or determine any correlations between parameters. Modeling tools handle the complex task of creating and parsing symbolic equations for modeling battery lifetime. Equations are parsed to grab relevant data variables, parameter values, or specified sub-models for input into optimization, evaluation, or simulation functions. Models can be optimized locally (one set of parameters for each data series), bi-level (some parameters shared across the data set), or globally (single set of parameters for all data). Functions implementing symbolic regression algorithms help users to discover effective model equations, even in poorly sampled, high-dimensional data.

Smith, Kandler↗

FutureTense

Protective vaccines and reliable diagnostics are essential tools for controlling viral diseases. However, the efficacy of these tools can be diminished by mutations in viral genomes. The delay between the emergence of new viral strains and the redesign of vaccines and diagnostics allows for continued viral transmission. Is it possible to address this challenge by computationally predicting viral genome sequence evolution? Can we “future-proof” vaccines and diagnostics by targeting both current and anticipated future sequence variants? While predicting viral evolution is still an unsolved, “grand challenge” problem in biology, the large, and rapidly growing, number of SARS-CoV-2 genome sequences provide an opportunity to quantify the ability of machine learning to predict viral genome sequence evolution. Towards this end, we have developed a simple computational model for predicting viral evolution at the level of individual nucleotides. The key metric for quantifying the per-base, prediction accuracy for viral evolution is the Mann-Whitney U statistic (or, equivalently, the area under the receiver operator curve). Since the Mann-Whitney U statistic is not a differentiable function, existing deep leaning packages (like Pytorch and Keras/TensorFlow) are not useful, as they require that the accuracy metric/objective function be analytically differentiable with respect to the model parameters. To overcome this challenge, we have implemented custom software, “FutureTense”, that can train a machine learning model by maximizing the non-differentiable Mann-Whitney U statistic. This software trains a machine learning model by exploring along the direction of the discrete gradient of the Mann-Whitney U statistic in the model parameter space. Parallel computing and genome sequence-specific optimizations are used to accelerate model training. The resulting machine learning model learns the observed high C->U mutation rates in the SARS-CoV-2 genome (which are potentially induced by host defenses) and provides prediction accuracies that are significantly better than one would expect from random chance. While predicting viral evolution is still quite far from a solved problem, the surprising performance of this simple model gives hope that the accuracy of predicting viral genome evolution can be further increased by more sophisticated approaches.

Gans, Jason↗

Machine learning-based multidomain processing for texture-based image segmentation and analysis

Atomic and molecular resolved atomic force microscopy (AFM) images offer unique insights into materials' properties such as local ordering, molecular orientation, and topological defects, which can be used to pinpoint physical and chemical interactions occurring at the surface. Utilizing machine learning for extracting underlying physical parameters increases the throughput of AFM data processing and eliminates inconsistencies intrinsic to manual image analysis, thus enabling the creation of reliable frameworks for qualitative and quantitative evaluation of experimental data. Here, we present a robust and scalable approach to the segmentation of AFM images based on flexible pre-selected classification criteria. The usage of supervised learning and feature extraction allows us to retain the consideration of specific problem-dependent features (such as types of periodical structures observed in the images and the associated numerical parameters: spacing, orientation, etc.). We highlight the applicability of this approach for the segmentation of molecular resolved AFM images based on the crystal orientation of the observed domains, automated selection of boundaries, and collection of relevant statistics. Finally, we outline a general strategy for machine learning-enabled analysis of nanoscale systems exhibiting periodic order that could be applied to any analytical imaging technique

36 MATERIALS SCIENCE↗

AUTOMATIC LIMIT SURFACE SEARCH FOR PWR TRANSIENTS BY RELAP5-3D/RAVEN CODES

Deterministic safety analysis of nuclear power plants can be improved by applying modern algorithms and codes exploiting machine learning and parallel computing. In this paper we show the application of some of these advanced methodologies for the determination of limit surfaces. A limit surface is an n-dimensional surface describing the plant status, e.g. identifying, as function of selected plant parameters, the boundaries between failed and safe conditions for the core fuel. Using the RELAP5-3D system thermal-hydraulic code coupled to the RAVEN statistical-analysis code, we show how to apply machine-learning algorithms (near-neighbor, support-vector machine, etc.) for determining relevant limit surfaces for PWR station-blackout and loss of offsite power. As a first step, a set of training simulations is run to sample the nuclear power plant responses. Those calculations are used to train a Reduced-Order-Model (ROM), which RAVEN then uses for determining an approximated limit surface. Verification of the guessed limit surface is then automatically performed and calculation is terminated depending by the chosen convergence criteria. The combination of High Performance Computing (HPC) and ROMs allow a remarkable reduction of the time required for the surface determination. RAVEN performs also the automatic data collection of the output of the numerous runs, thus easing the workload of the safety analyst. Finally, using RAVEN “Ensamble Forward” sampling technique, we show how to inform the limit surface calculations with some of the code and input uncertainties.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗

Multiscale Modeling of Reconstructed Tricalcium Silicate using NASA Multiscale Analysis Tool

To study microstructure characteristics of cementitious materials hydrated in space; previously, cement binder formations were processed under microgravity conditions and was further compared against ground-based experiments. For accurate estimation of process-structure-property linkage, particularly on samples hydrated in the microgravity environment, it is desired to have a high-fidelity volumetric representation of the microstructure. However, owing to small sample size and high porosity of the space-returned samples, conventional experimental characterization techniques are not viable. Hence, a deep learning-based reconstruction algorithm was employed to obtain high fidelity 3D volumes from sparse high resolution 2D Scanning Electron Microscopy (SEM) images, as inputs to micromechanics-based modeling. This machine learning-based reconstruction methodology validated against low-order statistical descriptors, captured the microstructural topology of both sample types (ground, 1g and microgravity, μg). Due to the lack of gravity, hydration products of the samples processed in space differed from those processed-on ground. Such AI-generated virtual samples were analyzed in a multiscale recursive micromechanics approach using the NASA Multiscale Analysis Tool (NASMAT). Here, we present a methodology to rapidly integrate and evaluate these AI-generated volumes in NASMAT. The synthesized microstructural volumes are directly employed as Representative Volume Elements (RVEs) to preserve the fidelity (1 pixel = 0.54 m). Invariably, analysis of such largescale problems (5123 voxels) requires huge amount of computational resources. By taking advantage of the NASMAT architecture, we also focused on systematic multiscale integration of these AI-reconstructed virtual volumes to reduce the computational demands. In this work, this methodology is demonstrated on the ground-based, 1g samples. The estimated stiffness value of 15.90 GPa is comparable to experimentally obtained modulus of hydrated tricalcium silicate sample. The workflow presented here paves the way for utilizing the NASMAT tool to perform multiscale analyses of other multi-phase material systems using either 3D virtual datasets synthesized using AI or obtained via micro-CT.

Machine Learning↗

Parallel Integration and Chromosomal Expansion of Metabolic Pathways

Robust fermentation of biomass-derived sugars into bioproducts demands the reliable microbial expression of metabolic pathways. Plasmid-based expression systems may suffer from instability and result in highly variable titers, rates, and yields. An established mitigation approach, Chemical Induced Chromosomal Expansion (CIChE), expands a singly integrated pathway to plasmid-like copy numbers, while maintaining stability in the absence of antibiotic selection pressure. Here, we report Parallel Integration and Chromosomal Expansion (PIACE), extensions to CIChE that enable independent expansions of pathway components across multiple loci, use suicide vectors to achieve high-efficiency site-specific integration of sequence-validated multi-gene components, and introduce a heat-curable plasmid to obviate recA deletion post pathway expansion. We applied PIACE to stabilize an isopentenol pathway across three loci in E. coli DH1, and to then generate libraries of pathway component copy-number variants to screen for improved titers. Furthermore, polynomial regressor statistical modeling of the production screening data suggests that increasing copy numbers of all isopentenol pathway components would further improve titers.

09 BIOMASS FUELS↗

Sampling lattices in semi-grand canonical ensemble with autoregressive machine learning

Calculating thermodynamic potentials and observables efficiently and accurately is key for the application of statistical mechanics simulations to materials science. However, naive Monte Carlo approaches, on which such calculations are often dependent, struggle to scale to complex materials in many state-of-the-art disciplines such as the design of high entropy alloys or multi-component catalysts. To address this issue, we adapt sampling tools built upon machine learning-based generative modeling to the materials space by transforming them into the semi-grand canonical ensemble. Furthermore, we show that the resulting models are transferable across wide ranges of thermodynamic conditions and can be implemented with any internal energy model U, allowing integration into many existing materials workflows. We demonstrate the applicability of this approach to the simulation of benchmark systems (AgPd, CuAu) that exhibit diverse thermodynamic behavior in their phase diagrams. Finally, we discuss remaining challenges in model development and promising research directions for future improvements.

36 MATERIALS SCIENCE↗