NTR organizes and hosts scientific webinars on neural networks and invites speakers from all over the world to present their recent work.
On November 30 Olga Kononova, Roivant Sciences, New York, USA, presented a technical Zoom webinar on Teaching a Machine Synthesis by Automatically Reading Millions of Scientific Publications.
About the webinar:
The seminar follows the project I worked on during my postdoctoral training at the University of California, Berkeley.
We built an automated text mining pipeline that processes scientific publications and extracts information about materials synthesis from them.
By applying this pipeline to ~5M articles, we collected the dataset of ~70K synthesis reactions for multiple types of ceramics synthesis.
We used this dataset to explore synthesis conditions for common materials classes.
Materials:
- Kononova et al. «Opportunities and challenges of text mining in materials research», iScience 24, 2021, https://doi.org/10.1016/j.isci.2021.102155
- Kononova et al. «Text-mined dataset of inorganic materials synthesis recipes», Sci. Data 6, 2019, https://www.nature.com/articles/s41597-019-0224-1
- Webinar presentation
Moderator and contact: NTR CEO Nick Mikhailovsky: nickm@ntrlab.com.