图神经网络指导新型深紫外大双折射晶体材料的设计
Graph neural network guided design of novel deep-ultraviolet optical materials with high birefringence
克鲁格洛夫伊万 1柳德米拉别列兹尼科娃 2谢聪伟 3储冬冬 3李珂 3吉洪诺夫叶夫格尼 3阿布都卡地吐地 3阿尔斯兰马齐托夫 2张敏 3潘世烈 3杨志华3
作者信息
- 1. Research Center for Crystal Materials,State Key Laboratory of Functional Materials and Devices for Special Environmental Conditions,Xinjiang Key Laboratory of Functional Crystal Materials,Xinjiang Technical Institute of Physics and Chemistry,Chinese Academy of Sciences,Urumqi 830011,China;Moscow Institute of Physics and Technology,9 Institutsky Lane,Dolgoprudny 141700,Russia
- 2. Moscow Institute of Physics and Technology,9 Institutsky Lane,Dolgoprudny 141700,Russia;Emerging Technologies Research Center,XPANCEO,Internet City,Emmay Tower,Dubai,United Arab Emirates
- 3. Research Center for Crystal Materials,State Key Laboratory of Functional Materials and Devices for Special Environmental Conditions,Xinjiang Key Laboratory of Functional Crystal Materials,Xinjiang Technical Institute of Physics and Chemistry,Chinese Academy of Sciences,Urumqi 830011,China
- 折叠
摘要
寻找具有大双折射率(Δn)的晶体材料,尤其是深紫外大双折射晶体材料,对于制备光纤传感器等偏振器件非常重要.具有大双折射率的晶体材料通常需借助实验技术发现.然而,大量耗时的实验并不利于高效寻找具有大双折射率的晶体材料.在本文中,我们收集了一个包含数千晶体结构及其光学性质的数据集,并采用原子线图神经网络(ALIGNN)训练了可用于快速预测晶体材料双折射率的机器学习模型.我们采用D-optimality准则评估所构建机器学习模型的预测可信度.基于该双折射率机器学习模型,我们从Materials Project数据库中搜索了具有大双折射率的晶体材料,发现了两种新型深紫外大双折射候选材料NaYCO3F2和SC1O2F,它们的双折射率分别为0.202和0.101@1064 nm.进一步分析表明,具有强各向异性的多阴离子基团和π共轭平面基团有利于产生大的双折射率.
Abstract
Finding crystals with high birefringence(Δn),especially in deep-ultraviolet(DUV)regions,is important for developing polarization devices such as optical fiber sensors.Such materials are usually discovered using experimental techniques,which are costly and inefficient for a large-scale screening.Herein,we collected a database of crystal structures and their optical properties and trained atomistic line graph neural network to predict their Δn.To estimate the level of confidence of the trained model on new data,D-optimality criterion was implemented.Using trained graph neural net-work,we searched for novel materials with high Δn in the Materials Project database and discovered two new DUV bi-refringent candidates:NaYCO3F2 and SC1O2F,with high Δn values of 0.202 and 0.101 at 1064 nm,respectively.Further analysis reveals that strongly anisotropic units with various anions and π-conjugated planar groups are beneficial for highΔn.
关键词
machine learning/birefringence/optical materials/D-optimalityKey words
machine learning/birefringence/optical materials/D-optimality引用本文复制引用
出版年
2024
NETL
NSTL
万方数据