Machine Learning-Based Predictive Model for Designing Transmon Qubits in Superconducting Quantum Computer

The transmon qubit enables the scalable design of superconducting circuit-based quantum computing hardware due to the low sensitivity to charge noise while enabling qubit-photon coupling for interaction. The pursuit of fault-tolerant and computationally powerful quantum processors may require more qubits, increasing the design and simulation complexity before the final fabrication and application. In this work, we attempt to predict the characteristics of individual transmon qubits with a machine learning-based approach based on the simulation data collected with Qiskit Metal and ANSYS Electronics. Similarly, we can also set the targeted characteristics of transmon and generate some feasible geometrical designs with a machine learning model. Further application of our method is possible for future quantum electronic design and automation of superconducting quantum computing circuits.