PATHFINDER: Multi-objective discovery in structural and spectral spaces

2026-04-05

AI Summary

This work addresses the limitation of conventional automated microscopy approaches, which often suffer from premature convergence due to single-objective optimization and struggle to identify rare yet scientifically valuable states under constrained experimental budgets. To overcome this, the authors propose PATHFINDER, a novel framework that uniquely integrates novelty-driven exploration with multi-objective Bayesian optimization. By leveraging structural-spectral latent representations, surrogate models of functional responses, and a Pareto-front acquisition strategy, PATHFINDER jointly explores structural, spectral, and measurement spaces in a coordinated manner. The method demonstrates its efficacy in both STEM-EELS and ferroelectric scanning probe microscopy experiments, successfully expanding structure–property maps and efficiently uncovering diverse scientific states. These results validate the framework’s generalizability and practical utility for autonomous scientific discovery.

Abstract

Automated decision-making is becoming key for automated characterization including electron and scanning probe microscopies and nano indentation. Most machine learning driven workflows optimize a single predefined objective and tend to converge prematurely on familiar responses, overlooking rare but scientifically important states. More broadly, the challenge is not only where to measure next, but how to coordinate exploration across structural, spectral, and measurement spaces under finite experimental budgets while balancing target-driven optimization with novelty discovery. Here we introduce PATHFINDER, a framework for autonomous microscopy that combines novelty driven exploration with optimization, helping the system discover more diverse and useful representations across structural, spectral, and measurement spaces. By combining latent space representations of local structure, surrogate modeling of functional response, and Pareto-based acquisition, the framework selects measurements that balance novelty discovery in feature and object space and are informative and experimentally actionable. Benchmarked on pre acquired STEM EELS data and realized experimentally in scanning probe microscopy of ferroelectric materials, this approach expands the accessible structure property landscape and avoids collapse onto a single apparent optimum. These results point to a new mode of autonomous microscopy that is not only optimization-driven, but also discovery-oriented, broad in its search, and responsive to human guidance.

Problem

• multi-objective discovery
• autonomous microscopy
• novelty exploration
• structural space
• spectral space

Innovation

• multi-objective optimization
• novelty-driven exploration
• autonomous microscopy
• Pareto-based acquisition
• latent space representation