Tuning arrays with rays: Physics-informed tuning of quantum dot charge states

TL;DR

This paper introduces a physics-informed, automated tuning framework for quantum dot charge states that combines machine learning and physics knowledge, achieving high success rates on both simulated and real devices, including industrial-scale samples.

Contribution

The paper presents a novel physics-informed tuning (PIT) framework that enhances automated calibration of quantum dot systems with high accuracy and robustness across different fabrication processes.

Findings

Success rate exceeds 95% on simulated data

Achieves nearly 90% success rate on experimental data

Effective on both academic and industrial quantum dot devices

Abstract

Quantum computers based on gate-defined quantum dots (QDs) are expected to scale. However, as the number of qubits increases, the burden of manually calibrating these systems becomes unreasonable and autonomous tuning must be used. There has been a range of recent demonstrations of automated tuning of various QD parameters such as coarse gate ranges, global state topology (e.g. single QD, double QD), charge, and tunnel coupling with a variety of methods. Here, we demonstrate an intuitive, reliable, and data-efficient set of tools for an automated global state and charge tuning in a framework deemed physics-informed tuning (PIT). The first module of PIT is an action-based algorithm that combines a machine learning classifier with physics knowledge to navigate to a target global state. The second module uses a series of one-dimensional measurements to tune to a target charge state by first emptying the QDs of charge, followed by calibrating capacitive couplings and navigating to the target charge state. The success rate for the action-based tuning consistently surpasses 95 % on both simulated and experimental data suitable for off-line testing. The success rate for charge setting is comparable when testing with simulated data, at 95.5(5.4) %, and only slightly worse for off-line experimental tests, with an average of 89.7(17.4) % (median 97.5 %). It is noteworthy that the high performance is demonstrated both on data from samples fabricated in an academic cleanroom as well as on an industrial 300 mm} process line, further underlining the device agnosticism of PIT. Together, these tests on a range of simulated and experimental devices demonstrate the effectiveness and robustness of PIT.