High-accuracy data readout in multi-dimensional optical data storage using convolutional neural networks

Abstract

The escalating global volume of digital data poses a critical challenge for storage solutions. Optical data storage techniques have garnered lots of interests due to their excellent offline storage capabilities, including low energy consumption, high capacity, and long lifespan. However, despite the focus on data recording, minimal attention has been dedicated to the readout aspect. This study introduced femtosecond laser direct writing to perform multi-dimensional optical data storage and employed a specialized convolutional neural network to enhance voxel readout accuracy. The proposed network architecture achieved a remarkable voxel readout accuracy of 98.83%, surpassing support vector machine method (90.07%) and LeNet (96.85%). Furthermore, the proposed method yielded a substantial increase in actual user capacity, outperforming traditional approaches and presenting a novel solution for addressing readout challenges in multi-dimensional optical data storage.