Efficient Measurement of Orbital Angular Momentum Entanglement Using Convolutional Neural Network

Abstract

High-dimensional (HD) entanglement of photonic orbital angular momentum (OAM) offers significant potential for enhancing channel capacity and improving noise resistance in quantum information processing. However, the challenge of achieving simple and rapid measurement has limited its practical applications. In this work, a quantum state tomography (QST) framework is demonstrated that utilizes convolutional neural networks to rapidly reconstruct the density matrix of OAM entanglement from only two coincidence measurements. The experimental results for a 5D OAM entangled state yield a fidelity of 0.973 ± 0.005. This method is also applicable to mixed OAM entangled states and scenarios with incomplete tomographic measurements. These findings represent a significant step toward implementing high-speed QST for applications involving HD spatial mode quantum state, whether in free space or integrated systems.