Microstructure reconstruction via artificial neural networks: A combination of causal and non-causal approach

TL;DR

This paper explores using artificial neural networks to reconstruct sponge-like microstructures by combining causal neighborhood prediction with non-causal smoothing, optimizing configurations for better spatial statistical accuracy.

Contribution

It introduces a hybrid causal and non-causal ANN approach for microstructure reconstruction and analyzes the impact of different network configurations on reconstruction quality.

Findings

Causal neighborhood prediction effectively captures microstructure features.

Non-causal smoothing improves the visual and statistical quality of reconstructions.

Optimal network configurations depend on neighborhood size and network depth.

Abstract

We investigate the applicability of artificial neural networks (ANNs) in reconstructing a sample image of a sponge-like microstructure. We propose to reconstruct the image by predicting the phase of the current pixel based on its causal neighbourhood, and subsequently, use a non-causal ANN model to smooth out the reconstructed image as a form of post-processing. We also consider the impacts of different configurations of the ANN model (e.g. number of densely connected layers, number of neurons in each layer, the size of both the causal and non-causal neighbourhood) on the models' predictive abilities quantified by the discrepancy between the spatial statistics of the reference and the reconstructed sample.