Post-Experiment Forensics and Human-in-the-Loop Interventions in Explainable Autonomous Scanning Probe Microscopy

Abstract

The broad adoption of machine learning (ML)-based automated and autonomous experiments (AE) in physical characterization and synthesis requires development of strategies for understanding and intervention in the experimental workflow. Here, we introduce and realize strategies for post-acquisition forensic analysis applied to the deep kernel learning based AE scanning probe microscopy. This approach yields real-time and post-acquisition indicators of the progression of an active learning process interacting with an experimental system. We further illustrate that this approach can be extended towards human-in-the-loop autonomous experiments, where human operators make high-level decisions at high latencies setting the policies for AE, and the ML algorithm performs low-level fast decisions. The proposed approach is universal and can be extended to other physical and chemical imaging techniques and applications such as combinatorial library analysis. The full forensic analysis notebook is publicly available on GitHub at https://github.com/yongtaoliu/Forensics-DKL-BEPS.

arXiv comment24 pages, 8 figures

References in corpus (7)

• AtomAI: A Deep Learning Framework for Analysis of Image and Spectroscopy Data in (Scanning) Transmission Electron Microscopy and Beyond
• Hypothesis Learning in Automated Experiment: Application to Combinatorial Materials Libraries
• Physics discovery in nanoplasmonic systems via autonomous experiments in Scanning Transmission Electron Microscopy
• Exploring the microstructural origins of conductivity and hysteresis in metal halide perovskites via active learning driven automated scanning probe microscopy
• Autonomous Investigations over WS${}_2$ and Au{111} with Scanning Probe Microscopy
• Autonomous scanning probe microscopy with hypothesis learning: Exploring the physics of domain switching in ferroelectric materials
• Data Mining Graphene: Correlative Analysis of Structure and Electronic Degrees of Freedom in Graphenic Monolayers with Defects

Cited by in corpus (2)

• Bayesian Co-navigation: Dynamic Designing of the Materials Digital Twins via Active Learning
• Unraveling the Impact of Initial Choices and In-Loop Interventions on Learning Dynamics in Autonomous Scanning Probe Microscopy