GNoME
A graph neural network-based AI materials discovery model developed by DeepMind, capable of predicting hundreds of thousands of potentially stable material structures.
Core Facts
Timeline (last 90 days)
AI for Science is an interdisciplinary field that has emerged in recent years, referring to the use of artificial intelligence methods to accelerate scientific discovery, covering the entire process from hypothesis generation and experimental design to data analysis. Representative cases include DeepMind's AlphaFold (protein structure prediction), GNoME (new materials discovery), and Microsoft Research's work on molecular dynamics and quantum chemistry.
GNoME is a project published by Google DeepMind in Nature in 2023 that uses graph neural networks to predict the stability of inorganic crystal structures, producing about 2.2 million new crystal structures at once, of which about 380,000 were assessed as stable candidates.
GNoME (Graph Networks for Materials Exploration), released by DeepMind, predicts crystal structure stability through graph neural networks and screened out millions of potential new material candidates at once.
Of the 2.2 million crystal structures predicted by GNoME, approximately 380,000 are considered to have stability and may become candidate materials for next-generation batteries, semiconductors, or superconductors.
Google DeepMind's GNoME model predicted 2.2 million new crystal structures in 2023.
The GNoME project discovered 2.2 million new stable crystal structures in the field of materials science.
GNoME（Graph Networks for Materials Exploration）使用图神经网络（GNN）来预测晶体结构的稳定性，核心指标是材料在凸包上的分解能
GNoME项目采用主动学习策略，其38万种预测稳定的新材料中已有数百种被独立实验室合成验证
All Facts (10)
AlphaFold是DeepMind于2020年推出的蛋白质结构预测系统
90%VerifiedDeepMind's GNoME project predicted approximately 2.2 million potentially stable crystal structures, about an order of magnitude more than the stable materials previously known to humans.
65%UnverifiedAI for Science is an interdisciplinary field that has emerged in recent years, referring to the use of artificial intelligence methods to accelerate scientific discovery, covering the entire process from hypothesis generation and experimental design to data analysis. Representative cases include DeepMind's AlphaFold (protein structure prediction), GNoME (new materials discovery), and Microsoft Research's work on molecular dynamics and quantum chemistry.
50%UnverifiedGNoME is a project published by Google DeepMind in Nature in 2023 that uses graph neural networks to predict the stability of inorganic crystal structures, producing about 2.2 million new crystal structures at once, of which about 380,000 were assessed as stable candidates.
50%UnverifiedGNoME (Graph Networks for Materials Exploration), released by DeepMind, predicts crystal structure stability through graph neural networks and screened out millions of potential new material candidates at once.
50%UnverifiedOf the 2.2 million crystal structures predicted by GNoME, approximately 380,000 are considered to have stability and may become candidate materials for next-generation batteries, semiconductors, or superconductors.
50%UnverifiedGoogle DeepMind's GNoME model predicted 2.2 million new crystal structures in 2023.
50%UnverifiedThe GNoME project discovered 2.2 million new stable crystal structures in the field of materials science.
50%UnverifiedGNoME项目采用主动学习策略，其38万种预测稳定的新材料中已有数百种被独立实验室合成验证
50%UnverifiedGNoME（Graph Networks for Materials Exploration）使用图神经网络（GNN）来预测晶体结构的稳定性，核心指标是材料在凸包上的分解能
50%