MatterGen: a generative model for inorganic materials design

生成语法 生成设计 生成模型 计算机科学 财产(哲学) 微调 材料科学 人工智能 物理 量子力学 认识论 哲学 复合材料 相容性(地球化学)
作者
Claudio Zeni,Robert Pinsler,Daniel Zügner,Andrew T. Fowler,Matthew K. Horton,Xiang Fu,Sasha Shysheya,Jonathan Crabbé,Lixin Sun,Jake A. Smith,Nguyen, Bichlien,Schulz, Hannes,Lewis, Sarah,Chin-Wei Huang,Ziheng Lu,Zhou, Yichi,Yang, Han,Hao, Hongxia,Li, Jielan,Tomioka, Ryota
出处
期刊:Cornell University - arXiv [Cornell University]
被引量:66
标识
DOI:10.48550/arxiv.2312.03687
摘要

The design of functional materials with desired properties is essential in driving technological advances in areas like energy storage, catalysis, and carbon capture. Generative models provide a new paradigm for materials design by directly generating entirely novel materials given desired property constraints. Despite recent progress, current generative models have low success rate in proposing stable crystals, or can only satisfy a very limited set of property constraints. Here, we present MatterGen, a model that generates stable, diverse inorganic materials across the periodic table and can further be fine-tuned to steer the generation towards a broad range of property constraints. To enable this, we introduce a new diffusion-based generative process that produces crystalline structures by gradually refining atom types, coordinates, and the periodic lattice. We further introduce adapter modules to enable fine-tuning towards any given property constraints with a labeled dataset. Compared to prior generative models, structures produced by MatterGen are more than twice as likely to be novel and stable, and more than 15 times closer to the local energy minimum. After fine-tuning, MatterGen successfully generates stable, novel materials with desired chemistry, symmetry, as well as mechanical, electronic and magnetic properties. Finally, we demonstrate multi-property materials design capabilities by proposing structures that have both high magnetic density and a chemical composition with low supply-chain risk. We believe that the quality of generated materials and the breadth of MatterGen's capabilities represent a major advancement towards creating a universal generative model for materials design.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
迷途发布了新的文献求助10
刚刚
刚刚
噜噜噜的应助被勤奋一一采纳,获得10
刚刚
1秒前
byemaxf发布了新的文献求助10
1秒前
小困包发布了新的文献求助10
2秒前
理查德完成签到,获得积分10
2秒前
2秒前
XA完成签到,获得积分10
2秒前
吴新月完成签到,获得积分20
3秒前
3秒前
3秒前
所所的应助被科研通管家采纳,获得10
4秒前
十七发布了新的文献求助100
4秒前
搞怪冷之完成签到,获得积分10
4秒前
充电宝的应助被科研通管家采纳,获得10
4秒前
阿浩发布了新的文献求助10
4秒前
4秒前
NexusExplorer的应助被科研通管家采纳,获得10
4秒前
DSPOHO完成签到 ,获得积分10
4秒前
大模型的应助被科研通管家采纳,获得10
4秒前
4秒前
4秒前
4秒前
搜集达人的应助被科研通管家采纳,获得10
4秒前
魏哥哥的应助被lay采纳,获得30
4秒前
4秒前
5秒前
鱼鱼鱼完成签到,获得积分10
5秒前
liu完成签到,获得积分10
5秒前
5秒前
5秒前
6秒前
吴新月发布了新的文献求助10
6秒前
7秒前
8秒前
8秒前
2Y_DADA完成签到,获得积分10
8秒前
S1Mon发布了新的文献求助10
9秒前
缓慢耳机发布了新的文献求助10
9秒前
高分求助中
(应助此贴封号)【重要!!请各用户(尤其是新用户)详细阅读】【科研通的精品贴汇总】 10000
拉伸高分子熔体中缠结行为的模拟和小角中子散射研究 1700
The World Atlas of Wine 9th edition 1000
奈特基础组织学:配套组织病理学(第4版)(Netter's Essential Histology With Correlated Histopathology) 800
John McDowells Bildungstheorie 800
Markov Decision Processes and Reinforcement Learning 700
八旗制度の研究 600
热门求助领域 (近24小时)
化学 材料科学 医学 生物 纳米技术 计算机科学 工程类 有机化学 化学工程 生物化学 物理 复合材料 内科学 催化作用 光电子学 人工智能 细胞生物学 无机化学 物理化学 数学
热门帖子
关注 科研通微信公众号,转发送积分 8171069
求助须知:如何正确求助?哪些是违规求助? 9563791
关于积分的说明 21772202
捐赠科研通 7762628
什么是DOI,文献DOI怎么找? 3430786
关于科研通互助平台的介绍 2554696
邀请新用户注册赠送积分活动 2475672