Machine learning unveils multiple Pauli blockades in the transport spectroscopy of bilayer graphene double-quantum dots

Recent breakthroughs in the transport spectroscopy of 2-D material quantum-dot platforms have engendered a fervent interest in spin–valley qubits. In this context, Pauli blockades in double quantum dot structures form a crucial basis for multi-qubit initialization and manipulation. Focusing on double quantum dot structures in the bilayer graphene platform, and the experimental results, we develop detailed multi-faceted computational models aimed at predictive transport spectroscopy across such setups. Apart from reliably simulating occurrences of Pauli blockades, notably, our simulations unravel two remarkable phenomena: (i) the existence of multiple resonances within a bias triangle and (ii) the occurrence of multiple spin–valley blockades. Leveraging our model to train a machine learning algorithm, we successfully develop an automated method for the real-time detection of multiple Pauli blockade regimes. Through numerical predictions and validations against test data, we identify where and how many Pauli blockades are likely to occur. The detailed and composite computational models developed here can thus serve as the foundation for future experiments on transport spectroscopy in 2-D material platforms for the realization of spin–valley qubits.