Nature Search

Accurate prediction of synthesizability and precursors of 3D crystal structures via large language models

Predicting material synthesizability remains a major challenge in materials science. Here, the authors develop CSLLMs achieving 98.6% accuracy in predicting synthesizability while suggesting synthetic methods and precursors with >90% accuracy.

Zhilong Song
Shuaihua Lu
Jinlan Wang
ResearchOpen Access15 Jul 2025
Nature Communications

Volume: 16, P: 1-11
Author Correction: From bulk effective mass to 2D carrier mobility accurate prediction via adversarial transfer learning

Xinyu Chen
Shuaihua Lu
Jinlan Wang
Amendments and CorrectionsOpen Access31 Jul 2024
Nature Communications

Volume: 15, P: 1
Accelerated discovery of stable lead-free hybrid organic-inorganic perovskites via machine learning

Conventional trial-error method is inefficient in discovering new functional materials in vast chemical and structural space. Here Lu et al. use machine learning techniques to screen out the most promising lead-free organic-inorganic perovskites with proper bandgap and stability from thousands of them in a flash.

Shuaihua Lu
Qionghua Zhou
Jinlan Wang
ResearchOpen Access24 Aug 2018
Nature Communications

Volume: 9, P: 1-8
Inverse design of promising electrocatalysts for CO₂ reduction via generative models and bird swarm algorithm

Designing materials with optimal properties is a longstanding challenge, as current methods struggle to explore the vast chemical space effectively. Here, the authors combine generative model with optimization methods to design novel and highly active alloy electrocatalysts for CO₂ electroreduction.

Zhilong Song
Linfeng Fan
Jinlan Wang
ResearchOpen Access26 Jan 2025
Nature Communications

Volume: 16, P: 1-10
From bulk effective mass to 2D carrier mobility accurate prediction via adversarial transfer learning

Transfer learning strategies are useful to increase the accuracy of data-driven predictions in low-data regimes. Here the authors present a hybrid framework integrating transfer learning and expert knowledge to predict carrier mobility of 2D materials from bulk properties.

Xinyu Chen
Shuaihua Lu
Jinlan Wang
ResearchOpen Access25 Jun 2024
Nature Communications

Volume: 15, P: 1-9
Universal machine learning aided synthesis approach of two-dimensional perovskites in a typical laboratory

Chemical synthesis of advanced functional materials remains a complex and multidimensional challenge. Here, authors develop a data-driven framework to increase the success rate of the synthesis of two-dimensional perovskites.

Yilei Wu
Chang-Feng Wang
Jinlan Wang
ResearchOpen Access02 Jan 2024
Nature Communications

Volume: 15, P: 1-10
Three-dimensional stability of a fill slope reinforced by a frame beam anchor plate

Anping Huang
Yanpeng Zhu
Guangwen Fang
ResearchOpen Access24 Oct 2024
Scientific Reports

Volume: 14, P: 1-18

Search

Filter By:

Accurate prediction of synthesizability and precursors of 3D crystal structures via large language models

Author Correction: From bulk effective mass to 2D carrier mobility accurate prediction via adversarial transfer learning

Accelerated discovery of stable lead-free hybrid organic-inorganic perovskites via machine learning

Inverse design of promising electrocatalysts for CO2 reduction via generative models and bird swarm algorithm

From bulk effective mass to 2D carrier mobility accurate prediction via adversarial transfer learning

Universal machine learning aided synthesis approach of two-dimensional perovskites in a typical laboratory

Three-dimensional stability of a fill slope reinforced by a frame beam anchor plate

Search

Quick links

Inverse design of promising electrocatalysts for CO₂ reduction via generative models and bird swarm algorithm