arXiv subjects

Marat I. Latypov

Publications and source records attributed to Marat I. Latypov.

11 recordsLinked to original sources

arXiv2026

Neural electron backscatter diffraction

At the mesoscale, the state of a material is described by continuous fields. In polycrystals, crystallographic orientation and defect content vary continuously within grains, and grain boundaries trace continuous curves. Like other spatially resolved characterization methods, electron backscatter diffraction (EBSD) records this continuum on a discrete grid. Every subsequent analysis inherits the grid, whether it is classical Hough indexing or pattern-based machine learning. We introduce neural EBSD, which treats a scan as a continuous and differentiable field of Kikuchi diffraction intensity over specimen and detector coordinates. Two formulations are explored: a joint network over all four coordinates, and a factorized representation that combines continuous specimen-domain coefficient fields with learned detector-domain basis patterns. The factorized formulation exhibits higher accuracy: for recrystallized and additively manufactured Ni-base superalloys, it reconstructs 900,000 Kikuchi patterns per map with mean errors below 1% of the maximum intensity, while reducing data storage nearly 750-fold relative to the raw patterns. Since the learned field is continuous, patterns can be queried at any specimen position. Trained only on a quarter of the scan points, the model recovers withheld patterns whose indexed orientations fall within 4 deg. of reference at 97% of positions in the recrystallized alloy. Analytical spatial derivatives of the differentiable representation provide a diffraction gradient that localizes grain boundaries continuously, free of indexing, disorientation thresholds, and staircase artifacts. The gradient field also exposes intragranular heterogeneity, including dislocation-cell substructure in the as-built alloy.

cond-mat.mtrl-sci↗

arXiv2026

Lattice genome: representation and analysis of heterogeneous crystalline microstructures

Inspired by the concept of a generalized materials genome, we introduce the notions of lattice gene and lattice genome for crystalline materials. A lattice gene is a compact representation of the local crystalline structure obtained by encoding the Kikuchi diffraction patterns with a variational autoencoder. We show that this representation satisfies key criteria for a materials gene: compactness, experimental accessibility, existence of a distance metric reflecting structural similarity, and sufficient information content for reconstructing the original diffraction patterns. The lattice genome is the spatially resolved collection of lattice genes across a representative area mapped by electron backscatter diffraction (EBSD), which captures mesoscale heterogeneity that ultimately controls properties. We demonstrate three applications of the lattice genome: (i) latent component maps that visualize grain-scale and intra-grain heterogeneities, (ii) domain segmentation based on distance and angle metrics in the latent space, and (iii) kernel and domain latent vector spreads that quantify intragranular heterogeneity as high-dimensional analogs of kernel average misorientation and grain orientation spread. All three tools are validated on microstructures of additively manufactured and wrought Ni-base superalloys in as-built and recrystallized conditions.

cond-mat.mtrl-sci↗

arXiv2026

Thermodynamic assessment of the Ba-La-S and Ga-La-S systems

This paper presents the first thermodynamic assessment of binary and pseudo-binary phase diagrams in the Ba--La--S and Ga--La--S systems by means of the CALPHAD method. Experimental phase diagram equilibrium data and thermodynamic properties available from the literature were critically reviewed and assessed using thermodynamic models for the Gibbs energies of individual phases. The associated solution model was used to describe the short-range ordering behavior of the liquid phases. To supplement the limited experimental data reported in the literature, ab initio molecular dynamics calculations were employed to derive mixing enthalpies of the liquid phases in the binary subsystems. The resulting phase diagrams and calculated thermodynamic properties show good agreement with available literature within the investigated compositional ranges of binary and pseudo-binary systems.

cond-mat.mtrl-sci↗

arXiv2026

Eutectic and peritectic equilibria in coherent binary alloys

This work extends the Cahn--Larché thermodynamic framework to binary alloys in which two coherent solid phases coexist with an incoherent liquid and investigates how coherency strain energy modifies classical eutectic and peritectic equilibria. We derive equilibrium conditions for three-phase coexistence that include an elastic energy term dependent on the molar fractions of the solid phases and apply them to model binary eutectic and peritectic systems. We find that coherency stress transforms the eutectic point into a finite three-phase equilibrium field spanning a continuous range of compositions and temperatures. In contrast, coherency stress in peritectic systems progressively destabilizes the two-solid equilibrium without generating a stable three-phase field and can suppress the peritectic reaction entirely. This asymmetry is governed by the geometric relationship between the stress-free compositions of the phases: when the liquid composition lies between those of the two solids (eutectic configuration), the liquid serves as a thermodynamic buffer against the coherency penalty on the solid--solid pair; when it lies outside (peritectic configuration), no such mechanism is available. These results demonstrate that coherency stress can fundamentally alter three-phase equilibria involving a liquid and suggest that such effects may be significant in systems with large coherent misfits.

cond-mat.mtrl-sci↗

arXiv2026

Hearing the forest for the trees: machine learning and topological acoustics for remote sensing with seismic noise

Monitoring remote forests is a global challenge central to climate mitigation and biodiversity conservation, yet satellite observations are frequently limited by weather, dense canopies, and solar dependency. Here we show that passive seismic sensing offers a persistent, all-weather alternative for autonomous ecosystem monitoring by capturing characteristic learnable signatures of trees within the ambient wavefield. Using seismic data from Alaska, we demonstrate that cross-correlations between stations provide a physical basis for forest detection by approximating the empirical Green's function of the medium. Supervised machine learning models applied to these data achieve a classification accuracy of 86%, identifying key discriminating frequencies (35 to 60 Hz) consistent with known forest-wave interactions. A topological acoustics analysis of the geometric phase change independently confirms the physical origin of these data-driven classifications. Together, these results provide the first demonstration that subtle forest-wave interactions manifest in ambient seismic noise and can be harnessed as a scalable tool for continuous vegetation monitoring, offering a robust solution for tracking environmental change challenging regions.

physics.geo-ph↗

arXiv2025

SR-CLD: Spatially Resolved Chord Length Distributions for Statistical Description and Visualization of Non-uniform Microstructures

This study introduces the calculation of spatially-resolved chord length distribution (SR-CLD) as an efficient approach for quantifying and visualizing non-uniform microstructures in heterogeneous materials. SR-CLD enables detailed analysis of spatial variation of microstructures in different directions that can be overlooked with traditional descriptions. We present the calculation of SR-CLD using efficient scan-line algorithm that counts pixels in constituents along pixel rows or columns of microstructure images for detailed, high-resolution SR-CLD maps. We demonstrate the application of SR-CLD in three case studies: on synthetic polycrystalline microstructures with known and intentionally created uniform and gradient spatial distributions of grain size; on non-uniform microstructures from welding simulations; and on experimental images of two-phase microstructures of additively manufactured Ti alloys with significant spatially non-uniform distributions of laths of one of the phases.

cond-mat.mtrl-sci↗

arXiv2025

Machine learning of microstructure--property relationships in materials leveraging microstructure representation from foundational vision transformers

Machine learning of microstructure--property relationships from data is an emerging approach in computational materials science. Most existing machine learning efforts focus on the development of task-specific models for each microstructure--property relationship. We propose utilizing pre-trained foundational vision transformers for the extraction of task-agnostic microstructure features and subsequent light-weight machine learning of a microstructure-dependent property. We demonstrate our approach with pre-trained state-of-the-art vision transformers (CLIP, DINOv2, SAM) in two case studies on machine-learning: (i) elastic modulus of two-phase microstructures based on simulations data; and (ii) Vicker's hardness of Ni-base and Co-base superalloys based on experimental data published in literature. Our results show the potential of foundational vision transformers for robust microstructure representation and efficient machine learning of microstructure--property relationships without the need for expensive task-specific training or fine-tuning of bespoke deep learning models.

cs.CV↗

arXiv2024

FIP-GNN: Graph neural networks for scalable prediction of grain-level fatigue indicator parameters

High-cycle fatigue is a critical performance metric of structural alloys for many applications. The high cost, time, and labor involved in experimental fatigue testing call for efficient and accurate computer models of fatigue life. We present FIP-GNN -- a graph neural network for polycrystals that (i) predicts fatigue indicator parameters as grain-level inelastic responses to cyclic loading quantifying the local driving force for crack initiation and (ii) generalizes these predictions to large microstructure volume elements with grain populations well beyond those used in training. These advances can make significant contributions to statistically rigorous and computationally efficient modeling of high-cycle fatigue -- a long-standing challenge in the field.

cond-mat.mtrl-sci↗

arXiv2024

AnisoGNN: graph neural networks generalizing to anisotropic properties of polycrystals

We present AnisoGNNs -- graph neural networks (GNNs) that generalize predictions of anisotropic properties of polycrystals in arbitrary testing directions without the need in excessive training data. To this end, we develop GNNs with a physics-inspired combination of node attributes and aggregation function. We demonstrate the excellent generalization capabilities of AnisoGNNs in predicting anisotropic elastic and inelastic properties of two alloys.

cond-mat.mtrl-sci↗

arXiv2023

Learning from 2D: machine learning of 3D effective properties of heterogeneous materials based on 2D microstructure sections

Microstructure--property relationships are key to effective design of structural materials for advanced applications. Advances in computational methods enabled modeling microstructure-sensitive properties using 3D models (e.g., finite elements) based on microstructure representative volumes. 3D microstructure data required as input to these models are typically obtained from either 3D characterization experiments or digital reconstruction based on statistics from 2D microstructure images. In this work, we present machine learning (ML) approaches to modeling effective properties of heterogeneous materials directly from 2D microstructure sections. To this end, we consider statistical learning models based on spatial correlations and convolutional neural networks as two distinct ML strategies. In both strategies, models are trained on a dataset of synthetically generated 3D microstructures and their properties obtained from micromechanical 3D simulations. Upon training, the models predict properties from 2D microstructure sections. The advantage of the presented models is that they only need 2D sections, whose experimental acquisition is more accessible compared to 3D characterization. Furthermore, the present models do not require digital reconstruction of 3D microstructures.

cond-mat.mtrl-sci↗

arXiv2018

Materials knowledge system for nonlinear composites

In this contribution, we present a new Materials Knowledge System framework for microstructure-sensitive predictions of effective stress--strain responses in composite materials. The model is developed for composites with a wide range of combinations of strain hardening laws and topologies of the constituents. The theoretical foundation of the model is inspired by statistical continuum theories, leveraged by mean-field approximation of self-consistent models, and calibrated to data obtained from micromechanical finite element simulations. The model also relies on newly formulated data-driven linkages between micromechanical responses (phase-average strain rates and effective strength) and microstructure as well as strength contrast of the constituents. The paper describes in detail the theoretical development of the model, its implementation into an efficient computational plasticity framework, calibration of the linkages, and demonstration of the model predictions on two-phase composites with isotropic constituents exhibiting linear and power-law strain hardening laws. It is shown that the model reproduces finite element results reasonably well with significant savings of the computational cost.

cond-mat.mtrl-sci↗