Saved in:
Bibliographic Details
Main Authors: Wang, Hao, Zhong, Jiajun, Li, Yikun, Zhang, Junrong, Du, Rong
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2411.00803
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916641818804224
author Wang, Hao
Zhong, Jiajun
Li, Yikun
Zhang, Junrong
Du, Rong
author_facet Wang, Hao
Zhong, Jiajun
Li, Yikun
Zhang, Junrong
Du, Rong
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2411_00803
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Designing a Dataset for Convolutional Neural Networks to Predict Space Groups Consistent with Extinction Laws
Wang, Hao
Zhong, Jiajun
Li, Yikun
Zhang, Junrong
Du, Rong
Neural and Evolutionary Computing
Data Analysis, Statistics and Probability
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.
title Designing a Dataset for Convolutional Neural Networks to Predict Space Groups Consistent with Extinction Laws
topic Neural and Evolutionary Computing
Data Analysis, Statistics and Probability
url https://arxiv.org/abs/2411.00803