Salvato in:
| Autori principali: | , , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2510.00776 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866914070205038592 |
|---|---|
| author | Li, Chengbo Wang, Ying Wang, Qianying Tan, Zhizhi Jia, Haiqing Liu, Yi Qian, Li Ran, Nian Liu, Jianjun Zhang, Zhixiong |
| author_facet | Li, Chengbo Wang, Ying Wang, Qianying Tan, Zhizhi Jia, Haiqing Liu, Yi Qian, Li Ran, Nian Liu, Jianjun Zhang, Zhixiong |
| contents | Two-dimensional (2D) materials have shown broad application prospects in fields such as energy, environment, and aerospace owing to their unique electrical, mechanical, thermal and other properties. With the development of artificial intelligence (AI), the discovery and design of novel 2D materials have been significantly accelerated. However, due to the lack of basic theories of material synthesis, identifying reliable synthesis processes for theoretically designed materials is a challenge. The emergence of large language model offers new approaches for the reliability prediction of material synthesis processes. However, its development is limited by the lack of publicly available datasets of material synthesis processes. To address this, we present the Material Synthesis 2025 (MatSyn25), a large-scale open dataset of 2D material synthesis processes. MatSyn25 contains 163,240 pieces of synthesis process information extracted from 85,160 high-quality research articles, each including basic material information and detailed synthesis process steps. Based on MatSyn25, we developed MatSyn AI which specializes in material synthesis, and provided an interactive web platform that enables multifaceted exploration of the dataset (https://matsynai.stpaper.cn/). MatSyn25 is publicly available, allowing the research community to build upon our work and further advance AI-assisted materials science. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_00776 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Material Synthesis 2025 (MatSyn25) Dataset for 2D Materials Li, Chengbo Wang, Ying Wang, Qianying Tan, Zhizhi Jia, Haiqing Liu, Yi Qian, Li Ran, Nian Liu, Jianjun Zhang, Zhixiong Materials Science Two-dimensional (2D) materials have shown broad application prospects in fields such as energy, environment, and aerospace owing to their unique electrical, mechanical, thermal and other properties. With the development of artificial intelligence (AI), the discovery and design of novel 2D materials have been significantly accelerated. However, due to the lack of basic theories of material synthesis, identifying reliable synthesis processes for theoretically designed materials is a challenge. The emergence of large language model offers new approaches for the reliability prediction of material synthesis processes. However, its development is limited by the lack of publicly available datasets of material synthesis processes. To address this, we present the Material Synthesis 2025 (MatSyn25), a large-scale open dataset of 2D material synthesis processes. MatSyn25 contains 163,240 pieces of synthesis process information extracted from 85,160 high-quality research articles, each including basic material information and detailed synthesis process steps. Based on MatSyn25, we developed MatSyn AI which specializes in material synthesis, and provided an interactive web platform that enables multifaceted exploration of the dataset (https://matsynai.stpaper.cn/). MatSyn25 is publicly available, allowing the research community to build upon our work and further advance AI-assisted materials science. |
| title | Material Synthesis 2025 (MatSyn25) Dataset for 2D Materials |
| topic | Materials Science |
| url | https://arxiv.org/abs/2510.00776 |