AI image enhancement for failure analysis in 3D quantum information technology

TL;DR

This paper introduces an AI-powered workflow to enhance and speed up failure analysis in 3D quantum computing devices by improving defect detection and classification.

Contribution

The novel contribution is an AI workflow combining scanning acoustic microscopy with ML-SR and object detection for efficient micrometer-scale defect analysis.

Findings

The AI workflow improves time-efficiency by 4x for TSV analysis and 6x for delamination analysis.

ML-SR approaches enable self-supervised quality enhancement of image data.

The method is applicable beyond SAM data to various failure analysis fields.

Abstract

3D integration and miniaturization techniques get more widely used in conventional integrated circuits but also represent crucial ingredients for future quantum computing devices. This consolidates the need for efficiently detecting increasingly small defects on wafer size. Here we present a time-efficient and accurate way of measuring, localizing and statistically classifying defects down to the micrometer regime, utilizing a combination of scanning acoustic microscopy (SAM), You Only Look Once object detection, semantic segmentation and a machine learning super-resolution (ML-SR) approach. In particular, we test the capabilities of different ML-SR approaches to enable self-supervised quality enhancement of the measured image data. We reveal that the developed AI-powered workflow enhances time-efficiency by a factor of around 4x and 6x for the TSV and delamination analysis, respectively. Yet, the mentioned approach is not limited to SAM image data but presents a general way for speeding-up failure analysis in various fields.

The online version contains supplementary material available at 10.1038/s41598-025-08308-4.

Figures