Autonomous Reliability Qualification of Ga$_2$O$_3$-based Hydrogen and Temperature Sensors via Safe Active Learning

2026-04-22

AI Summary

This study addresses the challenge of characterizing the reliability of Ga₂O₃-based hydrogen and temperature sensors under thermo-hydrogen coupled stress, where conventional experimental approaches entail high risk and limited observability. To overcome this, the authors propose a Safe Active Learning (SAL) framework that leverages rectification characteristics as a physically interpretable and safe observable. SAL integrates a Gaussian process surrogate model to capture the degradation dynamics over time, temperature, and hydrogen concentration, enhanced by an adaptive time window, a lower-confidence-bound safety check, and a trust-region mechanism. The method employs a novel two-stage strategy: initially conservatively exploring safe operating regions, then progressively relaxing constraints to track degradation behavior. Experiments on both simulated and real automated probe stations demonstrate that SAL extends the safe operational boundary with only a single unsafe measurement and constructs an offline model capable of accurately predicting long-term saturation degradation trends.

Abstract

We present a Safe Active Learning (SAL) framework for autonomous reliability characterization of rectifying Ga$_2$O$_3$-based devices under coupled thermal and hydrogen stress. SAL treats rectification as a device-physics-motivated safety observable and models its evolution over elapsed time, temperature, and H$_2$ concentration using a Gaussian-process surrogate. To handle condition-dependent and uncertain experiment durations, the method combines an adaptive completion-time window, time-window lower-confidence-bound safety checks, a trust region anchored to previously verified safe conditions, and a two-phase strategy that transitions from conservative safe exploration to progressively relaxed rectification targets as the device degrades. We first evaluate SAL in simulation, where it safely expands the explored region while learning the evolving rectification surface. We then demonstrate SAL experimentally on an automated high-temperature probe-station platform using a Pt/Cr$_2$O$_3$:Mg/$\beta$-Ga$_2$O$_3$ device. In the reported campaign, phase 1 incurred only one unsafe measurement associated with spurious current-voltage sweeps, while phase 2 intentionally probed lower-rectification regimes. Finally, we use the curated SAL dataset for offline long-horizon forecasting of device response at a target voltage using a structured Gaussian-process model with a condition-dependent Kohlrausch--Williams--Watts mean and a residual covariance kernel. The model captures long-time, saturating degradation trends in an auxiliary validation dataset, illustrating how safety-aware autonomous experimentation enables both conservative characterization and subsequent degradation modeling. Although demonstrated for a rectifying Ga$_2$O$_3$ device, SAL is applicable to other systems where a measurable in situ safety observable can be defined.

Problem

• reliability qualification
• Ga2O3 sensors
• hydrogen sensing
• temperature sensing
• safe experimentation

Innovation

• Safe Active Learning
• Gaussian Process
• Reliability Qualification
• β-Ga₂O₃ Sensors
• Autonomous Experimentation