# Inferring low-dimensional microstructure representations using convolutional neural networks

arXiv: https://arxiv.org/abs/1611.02764 · HTML: https://mlsanity.com/paper/1611.02764/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Nov 2016.

## Built on by (most cited first, 9 of 9)

- [Mesh-based graph convolutional neural networks for modeling materials with microstructure](https://mlsanity.com/paper/2107.00090/) (2021)
- [An efficient optimization based microstructure reconstruction approach with multiple loss functions](https://mlsanity.com/paper/2102.02407/) (2021)
- [Surrogate- and invariance-boosted contrastive learning for data-scarce applications in science](https://mlsanity.com/paper/2110.08406/) (2021)
- [Artificial intelligence approaches for materials-by-design of energetic materials: state-of-the-art, challenges, and future directions](https://mlsanity.com/paper/2211.08179/) (2022)
- [Predicting Peak Stresses In Microstructured Materials Using Convolutional Encoder-Decoder Learning](https://mlsanity.com/paper/2201.00722/) (2022)
- [qlty: handling large tensors in scientific imaging](https://mlsanity.com/paper/2407.04920/) (2024)
- [Towards Microstructural State Variables in Materials Systems](https://mlsanity.com/paper/2301.04261/) (2023)
- [Hybrid machine-learned homogenization: Bayesian data mining and convolutional neural networks](https://mlsanity.com/paper/2302.12545/) (2023)
- [A Framework for Supervised and Unsupervised Segmentation and Classification of Materials Microstructure Images](https://mlsanity.com/paper/2502.07107/) (2025)

## Abstract (arXiv)

We apply recent advances in machine learning and computer vision to a central problem in materials informatics: The statistical representation of microstructural images. We use activations in a pre-trained convolutional neural network to provide a high-dimensional characterization of a set of synthetic microstructural images. Next, we use manifold learning to obtain a low-dimensional embedding of this statistical characterization. We show that the low-dimensional embedding extracts the parameters used to generate the images. According to a variety of metrics, the convolutional neural network method yields dramatically better embeddings than the analogous method derived from two-point correlations alone.