Closed-loop discovery of out-of-distribution processing protocols by evolutionary search and uncertainty-aware learning

2026-06-11

AI Summary

This work addresses the challenge of discovering out-of-distribution, high-efficiency protocols in high-dimensional waveform design for materials processing—a task hindered by conventional methods’ reliance on interpolation families or prohibitive experimental costs. The authors reformulate protocol optimization as an out-of-distribution discovery problem and introduce a closed-loop workflow that integrates evolutionary search with uncertainty-aware deep kernel learning to autonomously generate, rank, and validate candidate waveforms within a compact waveform space. Coupled with scanning probe microscopy and nonlinear electromechanical response measurements, this approach enables the first autonomous exploration of rejuvenation waveforms in ferroelectric thin films, uncovering a new family of waveforms that significantly enhance nonlinearity. Experiments reveal that optimal waveforms selectively activate weakly pinned pre-existing domain walls, whereas suboptimal ones trigger irreversible long-range switching, elucidating the underlying physical mechanisms.

Abstract

Many materials and chemical systems exhibit history-dependent responses, where functional outcomes are governed not only by final-state variables but by the time-dependent sequence of fields, temperatures, or chemical potentials applied during operation. Discovering new processing protocols is therefore a high-dimensional search problem in which the control variable is an entire waveform or sample history, and conventional strategies either remain confined to conservative interpolative families or become prohibitively measurement intensive. Here, a closed-loop workflow is introduced that couples evolutionary search over a compact waveform representation with uncertainty-aware deep kernel learning to generate, rank, and experimentally validate candidate protocols. Applied to ferroelectric thin films, with the scanning-probe tip-bias waveform as the protocol and the nonlinear electromechanical response as the reward, the workflow discovers waveform families that enhance nonlinearity by de-aging the film. Spatially resolved before/after measurements show that the best-performing waveforms selectively activate pre-existing, weakly pinned domain-wall segments, whereas the worst drive long-range irreversible switching. This framework reframes protocol tuning as out-of-distribution discovery, generalizable to synthesis and annealing trajectories, battery formation protocols, and other high-dimensional control problems.

Problem

• out-of-distribution discovery
• processing protocols
• history-dependent response
• high-dimensional control
• waveform optimization

Innovation

• evolutionary search
• uncertainty-aware learning
• closed-loop discovery
• out-of-distribution protocols
• waveform optimization