TexFlow: learning crystallographic texture on SO(3) manifold via normalizing flows
Abstract
Crystallographic texture is an important microstructural feature that statistically describes the orientations of grains in polycrystalline materials. Conventional texture analysis relies on the orientation distribution functions and pole figures, which are essential for interpreting the texture of a given material specimen but do not, by themselves, provide a direct framework for predictive modeling of process-structure-property linkages. Data- and machine learning-based approaches offer a means to address this gap; however, a key challenge lies in developing representations and learning frameworks that account for the manifold structure of rotations. In particular, many existing machine learning techniques are designed for Euclidean data and therefore are not readily applicable to rotations in the non-Euclidean group SO(3). Here we introduce TexFlow, a conditional normalizing flow framework for texture modeling that learns a probability distribution over rotations in SO(3) by construction. Rotations are encoded in a six-dimensional Gram-Schmidt orthogonalization representation which is then mapped back to valid rotations R∈SO(3). The framework supports conditional probabilistic modeling of texture p(R|c), where c may represent processing parameters like temperature or deformation state. To complement conventional texture-analysis visualizations, such as pole figures and sections of the orientation distribution function, we further introduce Hopf-fibration visualizations as a compact global representation of texture. TexFlow is validated on both unconditional and conditional experimental and simulated texture datasets spanning diverse material systems. We show that TexFlow can accurately capture multimodal textures and their conditional evolution, providing a data-driven framework for establishing process-texture linkages.
Related
- Evolution of microstructure and crystallographic texture in a novel Zr-4Nb-2Al alloy during hot rotary swaging
- Physics-based prediction, uncertainty quantification and decision-making for IN718 crystallographic texture intensity across LPBF defocus regimes
- SIMANF: Sample Free Learning of Unnormalized Distributions via Simulated Annealing in Normalizing Flows
- Decoding Crystallographic Surface Chirality from Real Space and Momentum Space Images by Machine Learning
- Leakage-Safe Machine Learning for Hydrogen Embrittlement Detection in 316L Stainless Steel: A Region-Held-Out Evaluation of Texture and Deep Features in SEM Micrographs
BibTeX
@misc{haribabu2026texflow,
title = {{TexFlow: learning crystallographic texture on SO(3) manifold via normalizing flows}},
author = {Gowtham Nimmal Haribabu and Tarakram Ramgopal and Divakar Vetriveeran and Siddhant Kumar},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.28363},
eprint = {2610.28363},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.28363},
}
RIS
TY - UNPB
TI - TexFlow: learning crystallographic texture on SO(3) manifold via normalizing flows
AU - Gowtham Nimmal Haribabu
AU - Tarakram Ramgopal
AU - Divakar Vetriveeran
AU - Siddhant Kumar
PY - 2026
DA - 2026/10/20
PB - arXiv
DO - 10.48550/arxiv.2610.28363
UR - https://arxiv.org/abs/2610.28363
AB - Crystallographic texture is an important microstructural feature that statistically describes the orientations of grains in polycrystalline materials. Conventional texture analysis relies on the orientation distribution functions and pole figures, which are essential for interpreting the texture of a given material specimen but do not, by themselves, provide a direct framework for predictive modeling of process-structure-property linkages. Data- and machine learning-based approaches offer a means to address this gap; however, a key challenge lies in developing representations and learning frameworks that account for the manifold structure of rotations. In particular, many existing machine learning techniques are designed for Euclidean data and therefore are not readily applicable to rotations in the non-Euclidean group SO(3). Here we introduce TexFlow, a conditional normalizing flow framework for texture modeling that learns a probability distribution over rotations in SO(3) by construction. Rotations are encoded in a six-dimensional Gram-Schmidt orthogonalization representation which is then mapped back to valid rotations R∈SO(3). The framework supports conditional probabilistic modeling of texture p(R|c), where c may represent processing parameters like temperature or deformation state. To complement conventional texture-analysis visualizations, such as pole figures and sections of the orientation distribution function, we further introduce Hopf-fibration visualizations as a compact global representation of texture. TexFlow is validated on both unconditional and conditional experimental and simulated texture datasets spanning diverse material systems. We show that TexFlow can accurately capture multimodal textures and their conditional evolution, providing a data-driven framework for establishing process-texture linkages.
ER -