Establishing baselines for generative discovery of inorganic crystals

生成语法 材料科学 纳米技术 计算机科学 人工智能
作者
Nathan J. Szymanski,Christopher J. Bartel
出处
期刊:Materials horizons [Royal Society of Chemistry]
卷期号:12 (19): 8000-8011 被引量:22
标识
DOI:10.1039/d5mh00010f
摘要

Generative artificial intelligence offers a promising avenue for materials discovery, yet its advantages over traditional methods remain unclear. In this work, we introduce and benchmark two baseline approaches - random enumeration of charge-balanced prototypes and data-driven ion exchange of known compounds - against four generative techniques based on diffusion models, variational autoencoders, and large language models. Our results show that established methods such as ion exchange are better at generating novel materials that are stable, although many of these closely resemble known compounds. In contrast, generative models excel at proposing novel structural frameworks and, when sufficient training data is available, can more effectively target properties such as electronic band gap and bulk modulus. To enhance the performance of both the baseline and generative approaches, we implement a post-generation screening step in which all proposed structures are passed through stability and property filters from pre-trained machine learning models including universal interatomic potentials. This low-cost filtering step leads to substantial improvement in the success rates of all methods, remains computationally efficient, and ultimately provides a practical pathway toward more effective generative strategies for materials discovery. By establishing baselines for comparison, this work highlights opportunities for continued advancement of generative models, especially for the targeted generation of novel materials that are thermodynamically stable.
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
思念需要什么完成签到,获得积分10
1秒前
2秒前
秋风的应助被美小美采纳,获得10
2秒前
哈哈姐发布了新的文献求助10
2秒前
CYB完成签到,获得积分10
2秒前
热情煎饼发布了新的文献求助10
2秒前
3秒前
英姑的应助被plaaf采纳,获得10
3秒前
3秒前
从容松弛完成签到 ,获得积分10
3秒前
李伟发布了新的文献求助20
3秒前
3秒前
3秒前
茶茶完成签到,获得积分10
3秒前
Jun的应助被CHI采纳,获得20
4秒前
轻松翰完成签到,获得积分10
4秒前
我是老大的应助被Rowlet采纳,获得10
4秒前
Enna完成签到,获得积分10
4秒前
4秒前
5秒前
坚强飞兰完成签到 ,获得积分10
5秒前
初初初啊发布了新的文献求助10
5秒前
5秒前
5秒前
5秒前
5秒前
Maestro_S的应助被Tan采纳,获得10
5秒前
华仔的应助被EllenLawliet采纳,获得10
6秒前
lucky关注了科研通微信公众号
6秒前
6秒前
黑犬发布了新的文献求助10
7秒前
mer发布了新的文献求助10
7秒前
funkii完成签到,获得积分10
7秒前
8秒前
8秒前
8秒前
LHP12580发布了新的文献求助10
8秒前
Donghaol发布了新的文献求助10
9秒前
5k全完成签到,获得积分10
9秒前
Maestro_S的应助被含糊的代丝采纳,获得30
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 8170142
求助须知:如何正确求助?哪些是违规求助? 9563136
关于积分的说明 21768635
捐赠科研通 7761603
什么是DOI,文献DOI怎么找? 3430600
关于科研通互助平台的介绍 2554420
邀请新用户注册赠送积分活动 2475330