Argonne National Laboratory researcher Dr. Rajeev Assary described how AI and high-fidelity, first-principles simulations can help identify cost-efficient catalysts for deoxygenation chemistry.
Artificial intelligence (AI) has the potential to play a crucial role in accelerated catalyst design, discovery, and optimization of chemical processes for decarbonization. With the help of a range of AI tools—such as machine learning, deep learning, and large language models—researchers can uncover useful guidelines for designing new and improved catalysts for both low- and high-technology readiness level research activities.
In this webinar — hosted by the U.S. Department of Energy Bioenergy Technologies Office’s Chemical Catalysis for Bioenergy Consortium (ChemCatBio) — Argonne National Laboratory researcher Dr. Rajeev Assary discussed:
- How AI and high-fidelity, first-principles simulations can help identify cost-efficient catalysts for deoxygenation chemistry;
- Recent efforts on using machine learning to field billions of molecules to choose the best as liquid organic hydrogen carriers;
- Ongoing research directions for helping the catalysis community incorporate large language models in catalyst discovery.
Learn more about this webinar and download the presentation.