Cormac Toher

About

Cormac Toher is a leading figure in computational materials science, whose research centers on the intersection of machine learning, high-throughput screening, and materials discovery. His most impactful work, "On-the-fly closed-loop materials discovery via Bayesian active learning" (325 citations), revolutionizes how new materials are identified by integrating active learning algorithms with autonomous experimentation. This approach dramatically accelerates the discovery process, enabling researchers to navigate vast chemical spaces with unprecedented efficiency. Toher’s contributions have established a framework for self-driving laboratories, where machine learning models iteratively guide experiments in real time, reducing human bias and resource waste. Beyond this landmark paper, his broader portfolio includes developing robust descriptors for thermoelectric and mechanical properties, as well as advancing uncertainty quantification in computational predictions. His work has been instrumental in bridging the gap between theory and experiment, earning him recognition as a pioneer in closed-loop discovery systems. For students and researchers, Toher’s research exemplifies how Bayesian optimization and active learning can transform materials design, offering a blueprint for accelerating innovation in energy, electronics, and beyond.

Research Focus

Key Achievements

Top Papers

1. 1
   On-the-fly closed-loop materials discovery via Bayesian active learning

   325 citations

Key Collaborators

Contact & Links