Scientific Exploration with Expert Knowledge (SEEK) in Autonomous Scanning Probe Microscopy with Active Learning

TL;DR

This paper enhances autonomous microscopy by integrating expert knowledge into active learning workflows, improving exploration efficiency and applicability across various microscopy techniques and autonomous experimental fields.

Contribution

It introduces methods to incorporate prior knowledge and human interest into deep kernel learning workflows for autonomous microscopy, advancing targeted exploration capabilities.

Findings

Enhanced exploration efficiency in autonomous microscopy.

Successful integration of prior knowledge into active learning workflows.

Potential applicability to other imaging and autonomous experimental techniques.

Abstract

Microscopy techniques have played vital roles in materials science, biology, and nanotechnology, offering high-resolution imaging and detailed insights into properties at nanoscale and atomic level. The automation of microscopy experiments, in combination with machine learning approaches, is a transformative advancement, offering increased efficiency, reproducibility, and the capability to perform complex experiments. Our previous work on autonomous experimentation with scanning probe microscopy (SPM) demonstrated an active learning framework using deep kernel learning (DKL) for structure-property relationship discovery. This approach has demonstrated broad applications in various microscopy techniques. Here, to address limitations of workflows based on DKL, we developed methods to incorporate prior knowledge and human interest into DKL-based workflows and implemented these workflows in SPM. By integrating expected rewards from structure libraries or spectroscopic features, we enhanced the exploration efficiency of autonomous microscopy, demonstrating more efficient and targeted exploration in autonomous microscopy. We demonstrated the application of these methods in SPM, but we suggest that these methods can be seamlessly applied to other microscopy and imaging techniques. Furthermore, the concept can be adapted for general Bayesian optimization in material discovery across a broad range of autonomous experimental fields.