Self-driving lab discovers principles for steering spontaneous emission

TL;DR

This paper introduces an autonomous experimentation platform that uses machine learning to discover principles for controlling spontaneous emission in reconfigurable semiconductor metasurfaces, achieving significant emission directivity improvements.

Contribution

The study presents a self-driving lab that uncovers the governing equations for steering spontaneous emission, integrating advanced AI techniques to optimize and understand nanophotonic structures.

Findings

Discovered key factors like spatial gradient and curvature in refractive index for emission control.

Achieved a four-fold increase in emission directivity within 300 experiments.

Identified that positive gratings and lenses can effectively steer emission across all angles.

Abstract

We developed an autonomous experimentation platform to accelerate interpretable scientific discovery in ultrafast nanophotonics, targeting a novel method to steer spontaneous emission from reconfigurable semiconductor metasurfaces. Controlling spontaneous emission is crucial for clean-energy solutions in illumination, thermal radiation engineering, and remote sensing. Despite the potential of reconfigurable semiconductor metasurfaces with embedded sources for spatiotemporal control, achieving arbitrary far-field control remains challenging. Here, we present a self-driving lab (SDL) platform that addresses this challenge by discovering the governing equations for predicting the far-field emission profile from light-emitting metasurfaces. We discover that both the spatial gradient (grating-like) and the curvature (lens-like) of the local refractive index are key factors in steering spontaneous emission. The SDL employs a machine-learning framework comprising: (1) a variational autoencoder for generating complex spatial refractive index profiles, (2) an active learning agent for guiding experiments with real-time closed-loop feedback, and (3) a neural network-based equation learner to uncover structure-property relationships. The SDL demonstrated a four-fold enhancement in peak emission directivity (up to 77%) over a 72{\deg} field of view within ~300 experiments. Our findings reveal that combinations of positive gratings and lenses are as effective as negative lenses and gratings for all emission angles, offering a novel strategy for controlling spontaneous emission beyond conventional Fourier optics.