Accelerated Science
Revision as of 18:50, 31 August 2020 by Priya (talk | contribs) (Priya moved page Accelerated Materials Science Datasets to Accelerated Materials Science over a redirect without leaving a redirect: make page more general than datasets)
Machine learning can help accelerate materials science for climate change applications such as the design of solar fuels, battery conducting fluids, alternatives to cement, or better CO2 sorbents.[1] Some potentially relevant datasets are listed below.
Data
- The Materials Project: "[C]omputed information on known and predicted materials as well as powerful analysis tools to inspire and design novel materials."
- Inorganic Crystal Structure Database: "[T]he world's largest database for completely identified inorganic crystal structures."
- SciFinder: Chemical and materials science database (paid).
- "Concrete Compressive Strength" from the UCI Machine Learning Repository: Dataset of concrete compressive strength.
References
- ↑ "Tackling climate change in the EU". Climate Change and Law Collection.