Brian DeCost
Papers
2
Total Citations
677
H-Index
2
About
Brian DeCost is a leading researcher at the intersection of materials science and artificial intelligence, with a primary focus on autonomous experimentation systems and data-driven materials discovery. His major contributions center on developing closed-loop frameworks that integrate machine learning, Bayesian active learning, and robotic experimentation to accelerate the identification of novel materials. DeCost’s work has been highly influential, with his most cited paper, “Autonomous experimentation systems for materials development: A community perspective,” garnering 352 citations and establishing a foundational vision for the field. Another key publication, “On-the-fly closed-loop materials discovery via Bayesian active learning,” with 325 citations, demonstrates how active learning—rooted in principles dating back to Laplace—can be modernized to guide real-time, autonomous decision-making in materials laboratories. These contributions have positioned DeCost as a pivotal figure in advancing self-driving labs, enabling faster, more efficient materials development. His research not only pushes the boundaries of automated science but also provides practical tools for researchers seeking to integrate AI with experimental workflows, making him a notable voice in the growing community of autonomous discovery.
Research Focus
Key Achievements
Top Papers
- 1
- 2