4.6 Article

Catalyst Acquisition by Data Science (CADS): a web-based catalyst informatics platform for discovering catalysts

期刊

REACTION CHEMISTRY & ENGINEERING
卷 5, 期 5, 页码 903-911

出版社

ROYAL SOC CHEMISTRY
DOI: 10.1039/d0re00098a

关键词

-

资金

  1. Japan Science and Technology Agency (JST) CREST [JPMJCR17P2]
  2. JSPS KAKENHI [JP17K14803, JP19K11988]
  3. JST

向作者/读者索取更多资源

An innovative web-based integrated catalyst informatics platform, Catalyst Acquisition by Data Science (CADS), is developed for use towards the discovery and design of catalysts. The platform provides three main functionalities: a repository for data sharing and publishing, an analytic workspace for exploratory visual analysis, and catalyst property prediction tools with pretrained machine learning models. Access to such a platform helps decrease barriers to entry faced by researchers in catalytic chemistry when attempting to apply catalyst informatics towards data by providing analytical and visualization tools that can be simultaneously applied and easily accessed within a central space, thereby helping the advancement of catalyst informatics. The developed platform allows researchers to upload and collect data onto the platform and conduct data analysis using a system of linked workspaces consisting of interactive visualization tools and machine learning tools that simultaneously update according to the researchers' actions in real time. The platform also provides a space for collaboration where researchers can choose to publish their uploaded data and resulting analyses to the platform for collaborations with other users and groups. As an example, CADS is applied towards oxidative coupling of methane (OCM) data where use of the platform tools reveals underlying patterns and trends that are otherwise hidden within the original data. Thus, the proposed platform contributes towards the advancement of catalyst informatics for both specialists and non-specialists.

作者

我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。

评论

主要评分

4.6
评分不足

次要评分

新颖性
-
重要性
-
科学严谨性
-
评价这篇论文

推荐

暂无数据
暂无数据