Designing a Dataset for Convolutional Neural Networks to Predict Space Groups Consistent with Extinction Laws

TL;DR

This paper introduces a novel dataset creation strategy for training CNNs to predict space groups from diffraction patterns, resulting in more accurate and physically consistent predictions than traditional methods.

Contribution

The paper presents a new approach to generate diffraction pattern datasets based on Extinction Laws, improving CNN prediction accuracy and generalization for space group classification.

Findings

Model accuracy matches theoretical maximums based on Extinction Laws.

The new dataset strategy outperforms traditional database-based methods.

The trained model shows strong generalization to unseen data.

Abstract

In this paper, a dataset of one-dimensional powder diffraction patterns was designed with new strategy to train Convolutional Neural Networks for predicting space groups. The diffraction pattern was calculated based on lattice parameters and Extinction Laws, instead of the traditional approach of generating it from a crystallographic database. This paper demonstrates that the new strategy is more effective than the conventional method. As a result, the model trained on the cubic and tetragonal training set from the newly designed dataset achieves prediction accuracy that matches the theoretical maximums calculated based on Extinction Laws. These results demonstrate that machine learning-based prediction can be both physically reasonable and reliable. Additionally, the model trained on our newly designed dataset shows excellent generalization capability, much better than the one trained on a traditionally designed dataset.