Duncan R. Sutherland

National Institute of Standards and Technology

Papers

Total Citations

H-Index

About

Duncan R. Sutherland is a materials scientist and computational researcher whose work sits at the dynamic intersection of artificial intelligence, automation, and materials discovery. His research focuses on leveraging machine learning and autonomous experimentation to dramatically accelerate the characterization, synthesis, and development of novel materials — a challenge that has historically demanded enormous time and resources from the scientific community. Sutherland's most influential contribution, "Automation and Machine Learning for Accelerated Polymer Characterization and Development" (2024), has already garnered 30 citations since its publication, reflecting the timeliness and significance of his vision for integrating accessible machine learning tools into polymer science workflows. His earlier work on autonomous synthesis of metastable materials (2021) further demonstrates his commitment to AI-driven experimental paradigms, exploring how non-equilibrium materials — notoriously difficult to synthesize — can be discovered more efficiently through intelligent, self-directing systems. Across his research, Sutherland consistently champions the idea that the convergence of automation and data-driven methods can not only speed up discovery but deepen scientific understanding of the fundamental physics and chemistry governing material formation. His work is increasingly essential reading for researchers navigating the future of materials science.