AI System Builds Nanoparticles by Specifying Their Atomic Structure
Researchers have demonstrated a robot that designs and executes gold nanoparticle synthesis by targeting precise atomic arrangements, rather than relying on trial-and-error chemistry. The advance could accelerate materials development for electronics, catalysts, and pharmaceuticals by automating the expensive, time-consuming process of synthesizing particles with exact specifications.
Originaltitel: Autonomous Synthesis of Nanoparticles with Target Scattering Patterns
are particularly challenging to synthesize due to numerous tunable parameters. Here, we introduce an autonomous approach that explicitly targets atomic-scale structure through scattering patterns. Our method autonomously designs synthesis protocols by matching real-time experimental total scattering (TS) and pair distribution function (PDF) data to simulated target patterns, without requiring embedded synthesis knowledge. We demonstrate this capability at a synchrotron by targeting two structurally distinct gold NP scattering patterns: 5 nm decahedral and 10 nm face-centered cubic structures. Ultimately, specifying target scattering patterns and autonomously approaching synthesis protocols that reproduce them experimentally may enable on-demand, atomic structure-informed materials design. ScatterLab thus provides a generalizable blueprint for autonomous, atomic structure-targeted synthesis across diverse systems and applications.