Masato Sumita

National Institute for Materials Science, The University of Tokyo

Papers

Total Citations

150

H-Index

About

Masato Sumita is a leading researcher at the intersection of artificial intelligence, chemistry, and materials science, pioneering automated discovery through black-box optimization. His most cited work, "Black-Box Optimization for Automated Discovery" (2021, 132 citations), redefines how researchers design chemical compounds and materials by framing the entire trial-and-error process as a computational optimization problem, drastically reducing human effort. Sumita’s 2018 proof-of-concept study, "Hunting for Organic Molecules with Artificial Intelligence," demonstrated a groundbreaking AI-driven molecule generator integrated with density functional theory (DFT), synthesis, and measurement—achieving molecules with desired excitation energies and bridging computational prediction with experimental validation. In 2022, he further advanced automation with "Automatic Rietveld refinement by robotic process automation with RIETAN-FP," introducing robotic process automation (RPA) to eliminate manual parameter tuning in crystallographic analysis. With over 150 cumulative citations, Sumita’s work is instrumental in accelerating materials discovery, making complex chemical optimization accessible to non-experts. His contributions are pivotal for students and researchers seeking to harness AI for autonomous scientific exploration, reducing human costs while enhancing reproducibility and efficiency in chemistry and materials science.