Search papers, labs, and topics across Lattice.
To enable closed-loop optimization in self-driving laboratories, the authors constructed a real-time structure-matching pipeline that maps total X-ray scattering data to atomistic nanoparticle configurations using machine-learned interatomic potentials (MLIPs) and molecular dynamics (MD). Traditional autonomous workflows rely on rigid geometric models that systematically underestimate particle size and misclassify morphology due to unmodeled surface relaxation and thermal strain. By coupling rapid geometric pre-screening with selective MLIP relaxation and MD ensemble averaging, the system delivers high-fidelity structural identification within the latency constraints of continuous experimental beamlines.
Standard geometric priors in autonomous scattering experiments systematically misassign nanoparticle morphology and size, a failure mode resolved here by embedding real-time ML-potential relaxation directly into the live data-collection loop.
The emergence of autonomous laboratories motivates rapid conversion of experimental data into reliable atomistic models on time-scales compatible with closed-loop optimization. Here we develop an energetically driven structure matching framework for analysis during ongoing total X-ray scattering experiments. Using data from gold nanoparticles, we match against idealized spherical, octahedral, decahedral, and icosahedral geometries, their machine-learned interatomic potential (MLIP)-relaxed structures, and molecular dynamics (MD) ensembles. Idealized models are fast to generate but can misassign morphology and systematically underestimate size by neglecting surface relaxation, strain, and thermal disorder. MLIP relaxation markedly improves both, while MD ensemble averaging agrees best with experiment. We therefore introduce a hierarchical workflow combining rapid idealized screening with targeted MLIP and MD refinement of top candidates, delivering improved structural feedback without interrupting autonomous operation. This framework provides a route towards autonomous campaigns in which the target structure itself can be updated in response to the evolving energy landscape of structures compatible with the experimental data.
