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

2026-03-30

AI Summary

This work addresses the challenge of degraded performance in structure–property learning tasks—such as image-to-spectrum mapping—in autonomous microscopy, where low-quality and noisy data severely hinder model accuracy, and conventional active learning often selects uninformative samples. To overcome this, the authors propose a gated active learning framework that uniquely integrates physical priors into the sampling process. By combining Gaussian process–driven curiosity-based acquisition with a physics-informed quality control filter derived from a harmonic oscillator model, the method automatically discards low-fidelity measurements during data collection, enabling joint denoising of acquisition and training. Evaluated on the PbTiO₃ thin-film BEPS dataset, the approach significantly outperforms random sampling, standard active learning, and multi-task learning, and demonstrates enhanced reliability in both forward and inverse predictions during real-time experiments on BiFeO₃ thin films.

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.

Problem

• active learning
• data quality
• structure-property learning
• autonomous microscopy
• noisy data

Innovation

• gated active learning
• Gaussian processes
• physics-informed quality control
• autonomous microscopy
• structure-property learning