Accurate characterization of quantum systems is essential for the development of quantum technologies, particularly in the noisy intermediate-scale quantum (NISQ) era. While traditional methods for Hamiltonian learning and noise characterization often require extensive measurements and scale poorly with system size, machine learning approaches offer promising alternatives. In this work, we extend the inverse physics-informed neural network (referred to as PINNverse) framework to open quantum systems governed by Lindblad master equations. By incorporating both coherent and dissipative dynamics into the neural network training, our method enables simultaneous identification of Hamiltonian parameters and decay rates from noisy experimental data. We demonstrate the effectiveness and robustness of the approach through numerical simulations of two-qubit open systems. Our results show that PINNverse provides a scalable and noise-resilient framework for quantum system identification, with potential applications in quantum control and error mitigation.
Lima et al. (Wed,) studied this question.