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

TL;DR

This paper introduces deep-kernel pairwise learning (DKPL), a novel method that incorporates expert judgments directly into autonomous microscopy experiments, enhancing scientific discovery at the nanoscale without relying solely on predefined scalar descriptors.

Contribution

DKPL enables experts to guide autonomous experiments through direct evaluation, learning a latent utility function that captures interdisciplinary knowledge for improved nanoscale analysis.

Findings

DKPL effectively learns meaningful nanoscale structures.

It distinguishes domain-wall characteristics in ferroelectric materials.

Demonstrates improved experimental prioritization without scalar descriptors.

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.