Quality-Controlled Active Learning via Gaussian Processes for Robust Structure-Property Learning in Autonomous Microscopy

TL;DR

This paper presents a physics-informed gated active learning framework using Gaussian processes to improve data quality and robustness in autonomous microscopy, especially for structure-property prediction tasks.

Contribution

It introduces a novel quality control filter combined with curiosity-driven sampling, enhancing active learning in noisy, data-intensive microscopy applications.

Findings

Outperforms standard active learning and random sampling in noisy BEPS data

Improves Im2Spec and Spec2Im predictions by handling noise during training

Successfully deployed in real-time autonomous microscopy experiments

Abstract

Autonomous experimental systems are increasingly used in materials research to accelerate scientific discovery, but their performance is often limited by low-quality, noisy data. This issue is especially problematic in data-intensive structure-property learning tasks such as Image-to-Spectrum (Im2Spec) and Spectrum-to-Image (Spec2Im) translations, where standard active learning strategies can mistakenly prioritize poor-quality measurements. We introduce a gated active learning framework that combines curiosity-driven sampling with a physics-informed quality control filter based on the Simple Harmonic Oscillator model fits, allowing the system to automatically exclude low-fidelity data during acquisition. Evaluations on a pre-acquired dataset of band-excitation piezoresponse spectroscopy (BEPS) data from PbTiO3 thin films with spatially localized noise show that the proposed method outperforms random sampling, standard active learning, and multitask learning strategies. The gated approach enhances both Im2Spec and Spec2Im by handling noise during training and acquisition, leading to more reliable forward and inverse predictions. In contrast, standard active learners often misinterpret noise as uncertainty and end up acquiring bad samples that hurt performance. Given its promising applicability, we further deployed the framework in real-time experiments on BiFeO3 thin films, demonstrating its effectiveness in real autonomous microscopy experiments. Overall, this work supports a shift toward hybrid autonomy in self-driving labs, where physics-informed quality assessment and active decision-making work hand-in-hand for more reliable discovery.