Beyond Scalar Objectives: Expert-Feedback-Driven Autonomous Experimentation for Scientific Discovery at the Nanoscale

2026-05-20

AI Summary

Traditional autonomous experiments rely on predefined scalar objectives, which often fail to capture subtle scientific phenomena discernible by human experts. This work proposes Deep Kernel Pairwise Learning (DKPL), a framework that directly incorporates expert relative judgments—grounded in interdisciplinary knowledge—into the active learning loop, thereby guiding autonomous scanning probe microscopy without requiring explicit scalar targets. By circumventing the limitations of conventional Bayesian optimization, DKPL establishes the first scalar-free, expert-informed experimental paradigm at the nanoscale. The approach successfully identifies high- and low-characteristic domain wall angles in bismuth ferrite and discovers head-to-head and tail-to-tail domain wall configurations in erbium manganite, demonstrating both its physical validity and its capacity for information-driven, priority-based exploration.

Abstract

Self-driving laboratories or autonomous experimentation are emerging as transformative platforms for accelerating scientific discovery. Bayesian optimization (BO) is among the most widely used machine learning frameworks for these purposes, but these BO-based frameworks rely on predefined scalar descriptors to guide experimentation. In many situations, the determination of an appropriate scalar descriptor can be challenging, and may fail to capture subtle yet scientifically important phenomena apparent to experts with interdisciplinary insight. To overcome this limitation, here we develop deep-kernel pairwise learning (DKPL), an approach for autonomous microscopy experiments which incorporates human expertise and interdisciplinary scientific knowledge into an active learning loop. Instead of relying on explicit scalar objectives, DKPL enables experts to directly evaluate which experimental output is more promising using interdisciplinary knowledge. DKPL then learns a latent utility function from these expert judgements to guide subsequent autonomous microscopy experiments. We demonstrate DKPL's performance in learning physically meaningful nanoscale structures while effectively prioritizing high-information measurement regions using an experimental model dataset with known ground truth. We further apply DKPL to analyze the character of ferroelectric domain walls, where we find DKPL capable of distinguishing between high and low characteristic domain-wall angles in bismuth ferrite, and able to discover both head-to-head and tail-to-tail domain-wall character in erbium manganite. This development establishes an approach to integrate expert knowledge into autonomous microscopy experiments and demonstrates a pathway toward expert-guided self-driving laboratories capable of addressing scientific problems beyond the limits of scalar-metrics-driven learning.

Problem

• autonomous experimentation
• scalar objectives
• expert feedback
• scientific discovery
• nanoscale

Innovation

• deep-kernel pairwise learning
• autonomous experimentation
• expert feedback
• Bayesian optimization
• self-driving laboratories