arXiv:2610.26223
Sidewall Metrology Protocol for Superconducting Qubit Devices
Jørgen Garnæs, Henrik S. Guttesen, Astrid T. Rømer, Oscar Danielsson, Emily P. Duggan, Zhenhai Sun, Asen Lyubenov Georgiev, Li Wei Chang, Morten Kjaergaard, Mark Bieler, Lukas Grünhaupt, Sabbir A. Khan
Abstract
Sidewall morphology is a potentially important factor influencing superconducting qubit performance, yet its quantitative characterization remains challenging due to the absence of standardized measurement protocols. In this work, we develop a scanning probe microscopy-based measurement framework for the quantitative characterization of superconducting qubit sidewalls. The framework introduces a refined root mean square lateral sidewall roughness descriptor and a new curvature-equivalent radius for quantifying vertical sidewall morphology. The descriptors and measurement procedures are applied to different components of qubit devices, forming the basis of a proposed sidewall characterization protocol. This provides a foundation for quantitative comparisons of fabrication processes across laboratories, enabling future investigations of correlations between sidewall geometry and qubit performance.
AI Summary
Sidewall geometry may affect interfacial loss in superconducting circuits, but quantitative comparisons require consistent measurement and analysis procedures. This paper proposes an atomic-force-microscopy (AFM) protocol for characterizing lateral roughness, vertical curvature, and sidewall-angle distributions, intended to support future studies relating fabrication morphology to device performance. Measurements use samples tilted by $50^\circ$ to expose sidewalls, covering components of seven aluminum transmon devices and five additional readout resonators. Processing includes reference subtraction where applicable, Gaussian spatial filtering, sidewall-region detection, and probe-radius correction. The principal descriptors are profile-averaged RMS lateral roughness, $R_q^{\mathrm{LSP}}$, and a curvature-equivalent radius, $R_\rho$, defined as the inverse of the mean arc-length-weighted RMS curvature across vertical profiles. Minimum curvature radii and local-angle distributions provide additional characterization. Measured lateral roughness is approximately $2$–$5\,\mathrm{nm}$ for Josephson-junction structures and $20\,\mathrm{nm}$ for readout resonators, rising to approximately $30\,\mathrm{nm}$ for a sidewall containing a pit. Curvature-equivalent radii span $35$–$82\,\mathrm{nm}$ for junction electrodes and $51$–$151\,\mathrm{nm}$ for capacitor pads. Angle distributions show asymmetry and sometimes bimodality. Repeated lateral-roughness measurements under mitigation procedures yield an average standard deviation of $4.1\%$; estimated combined standard uncertainties are $15$–$30\%$. The paper does not establish correlations with coherence or resonator loss. Reported descriptors depend on probe geometry, filtering, and sampled regions; inaccessible narrow features cannot be reconstructed. Spatial inhomogeneity requires separate assessment, and some uncertainty estimates rely on laboratory experience rather than comprehensive validation.
Error found: The Results and Methods sections interchange the 8 nm and 25 nm short-wavelength cutoffs for capacitor-pad and electrode curvature analysis, leaving the reported curvature descriptors ambiguously specified. The asserted general inverse relationship between electric field and local curvature radius does not follow from Gauss' law, so the curvature descriptor is not established as a general predictor of field concentration or dielectric loss. The effective probe radius of 10.9 nm is a heuristic midpoint of an upper-bound interval rather than an independently determined correction, although the paper acknowledges this limited knowledge through a broad uncertainty. The dielectric-loss equation incorrectly identifies ωΣᵢpᵢtanδᵢ as T1 rather than its reciprocal. The discussion of additive relaxation rates incorrectly calls individual channel lifetimes lower bounds on the total lifetime, when they are upper bounds.
Written by gpt-6.1-sol from the paper's full text. Automated: it can be wrong.
- Comments
- 13 pages, 5 figures main + 9 pages, 3 figures appendices