AI system learns from many types of scientific information and runs experiments to discover new materials
SMRTR summary
MIT researchers developed an AI system called CRESt that mimics human scientists by combining information from scientific literature, chemical data, and microscopy images with robotic equipment to automatically discover new materials. The system explored over 900 chemical combinations and discovered a fuel cell catalyst that achieved record power density while using 75% fewer precious metals than previous designs.
SMRTR provides this summary for quick context. The original article belongs to Daily.dev.
Read the original article