Multi4D: an end-to-end neural network for structural determination at complex material interfaces

• URL: http://arxiv.org/abs/2609.14348v1
• Date: Sun, 13 Sep 2026 07:12:53 GMT
• Title: Multi4D: an end-to-end neural network for structural determination at complex material interfaces
• Abstract summary: We introduce Multi4D, a physics-informed neural network framework for automated multi-component crystallographic identification.<n>By combining a latent-space Transformer for physics-constrained style translation with a rotation-invariant convolutional neural network for orientation-agnostic classification, this approach translates diffraction datasets into deterministic crystallographic maps with 98.82% accuracy.<n>We apply Multi4D to generate high-fidelity structural maps of complex superconducting heterostructures, corroded alloy surfaces, and degraded solid-state battery interfaces down to single-nanometer spatial resolution.
• Score: 5.9461952475226445
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Heterogeneous interfaces dictate the performance and degradation of functional materials, making it essential to link local structural variations with macroscopic failure mechanisms to guide future materials design. Yet structural heterogeneity, phase overlap, and local disorder produce highly convoluted diffraction signatures, making extended transition regions difficult to interpret at atomic resolution across large fields of view. Here, we introduce Multi4D, a physics-informed neural network framework for automated multi-component crystallographic identification using four-dimensional scanning transmission electron microscopy (4D-STEM). By combining a latent-space Diffusion Transformer for physics-constrained style translation with a rotation-invariant convolutional neural network for orientation-agnostic classification, this approach translates multi-components diffraction datasets into deterministic crystallographic maps with 98.82% accuracy. In addition, we introduce Diffraction-Inferred Structural Complexity as an information-theoretic entropy metric derived from classifier predictive uncertainty that quantifies local structural ambiguity. We apply Multi4D to generate high-fidelity structural maps of complex superconducting heterostructures, corroded alloy surfaces, and degraded solid-state battery interfaces down to single-nanometer spatial resolution. This framework establishes a statistically robust analytical paradigm for automated microscopy, facilitating both industrial quality control and the data-driven discovery of interfacial design principles.

Related papers

• PathAR: Structure-First Autoregressive Synthesis of Multimodal Pathology Images [51.428093790826814]
  We propose pathology Autorgressive modeling (PathAR) to factorize structure and appearance for modality-label-conditioned pathology generation.<n>PathAR stabilizes morphology under heterogeneous modality-specific appearances and enables spatially aligned image-mask pair generation.
  arXiv  Detail & Related papers  (2026-06-01T01:43:48Z)
• Benchmarking Machine Learning Approaches for Polarization Mapping in Ferroelectrics Using 4D-STEM [0.5660019164402329]
  We benchmark multiple machine learning models to automate the detection of polarization directions from 4D-STEM diffraction patterns in ferroelectric potassium sodium niobate.<n>Our findings guide the development of robust, transferable machine learning tools for electron microscopy analysis.
  arXiv  Detail & Related papers  (2026-03-16T17:45:28Z)
• Layout-Guided Controllable Pathology Image Generation with In-Context Diffusion Transformers [57.54843029965778]
  Controllable pathology image synthesis requires reliable regulation of spatial layout, tissue morphology, and semantic detail.<n>We propose In-Context Diffusion Transformer (IC-DiT), a layout-aware generative model that incorporates spatial layouts, textual descriptions, and visual embeddings into a unified diffusion transformer.<n>IC-DiT achieves higher fidelity, stronger spatial controllability, and better diagnostic consistency than existing methods.
  arXiv  Detail & Related papers  (2026-03-11T06:14:11Z)
• Multimodal Machine Learning for Integrating Heterogeneous Analytical Systems [0.6734447582308918]
  We propose a machine learning framework that unifies heterogeneous analytical systems for end-to-end characterization.<n>We show how morphology descriptors are extracted from SEM images and captured curvature, orientation, intersection density, and void geometry.<n>Visualization using radar plots and UMAP reveals clear clustering of CNT films according to crystallinity and entanglements.
  arXiv  Detail & Related papers  (2026-01-31T08:12:43Z)
• Linearized Optimal Transport for Analysis of High-Dimensional Point-Cloud and Single-Cell Data [45.87606039212519]
  Single-cell technologies generate high-dimensional point clouds of cells.<n>Each patient is represented by an irregular point cloud rather than a simple vector.<n>We adapt the Linear Optimal Transport framework to embed irregular point clouds into a fixed-dimensional Euclidean space.
  arXiv  Detail & Related papers  (2025-10-24T21:33:12Z)
• Physics-Guided Dual Implicit Neural Representations for Source Separation [70.38762322922211]
  We develop a self-supervised machine-learning approach for source separation using a dual implicit neural representation framework.<n>Our method learns directly from the raw data by minimizing a reconstruction-based loss function.<n>Our method offers a versatile framework for addressing source separation problems across diverse domains.
  arXiv  Detail & Related papers  (2025-07-07T17:56:31Z)
• STEM Diffraction Pattern Analysis with Deep Learning Networks [0.0]
  This work presents a machine learning-based approach for predicting Euler angles directly from scanning transmission electron microscopy (STEM) diffraction patterns (DPs)<n>It enables the automated generation of high-resolution crystal orientation maps, facilitating the analysis of internal microstructures at the nanoscale.<n>Three deep learning architectures--convolutional neural networks (CNNs), Dense Convolutional Networks (DenseNets), and Shifted Windows (Swin) Transformers--are evaluated, using an experimentally acquired dataset labelled via a commercial TM algorithm.
  arXiv  Detail & Related papers  (2025-07-02T16:58:09Z)
• A Neural Network Transformer Model for Composite Microstructure Homogenization [1.2277343096128712]
  Homogenization methods, such as the Mori-Tanaka method, offer rapid homogenization for a wide range of constituent properties. This paper illustrates a transformer neural network architecture that captures the knowledge of various microstructures. The network predicts the history-dependent, non-linear, and homogenized stress-strain response.
  arXiv  Detail & Related papers  (2023-04-16T19:57:52Z)
• Disentangling multiple scattering with deep learning: application to strain mapping from electron diffraction patterns [48.53244254413104]
  We implement a deep neural network called FCU-Net to invert highly nonlinear electron diffraction patterns into quantitative structure factor images. We trained the FCU-Net using over 200,000 unique dynamical diffraction patterns which include many different combinations of crystal structures. Our simulated diffraction pattern library, implementation of FCU-Net, and trained model weights are freely available in open source repositories.
  arXiv  Detail & Related papers  (2022-02-01T03:53:39Z)
• A deep learning driven pseudospectral PCE based FFT homogenization algorithm for complex microstructures [68.8204255655161]
  It is shown that the proposed method is able to predict central moments of interest while being magnitudes faster to evaluate than traditional approaches. It is shown, that the proposed method is able to predict central moments of interest while being magnitudes faster to evaluate than traditional approaches.
  arXiv  Detail & Related papers  (2021-10-26T07:02:14Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.