Scaling superconducting quantum processors is fundamentally limited by environmentally induced decoherence arising from nanoscale fabrication defects. Conventional heuristic microwave control protocols cannot dynamically adapt to device-specific material variations, while purely data-driven deep learning approaches often violate physical constraints. Here we introduce a compact quantum physics-informed neural network (QPINN) that learns device-aware microwave control pulses for superconducting qubits. Trained on empirical defect characteristics extracted from 162 InAs nanosheet Josephson junction measurements, the model embeds the Lindblad master equation directly into its loss function to enforce physical consistency. Open-system simulations demonstrate a 42% reduction in leakage to non-computational states. Hardware experiments executed on the 156-qubit IBM Quantum processor show an increase in Ramsey dephasing time from 83.3 ± 7.8 μs to 113.0 ± 1.1 μs while maintaining gate fidelity exceeding 99.99%.
Scaling superconducting quantum processors is fundamentally limited by environmentally induced decoherence arising from nanoscale fabrication defects. Conventional heuristic microwave control protocols cannot dynamically adapt to device-specific material variations, while purely data-driven deep learning approaches often violate physical constraints. Here we introduce a compact quantum physics-informed neural network (QPINN) that learns device-aware microwave control pulses for superconducting qubits. Trained on empirical defect characteristics extracted from 162 InAs nanosheet Josephson junction measurements, the model embeds the Lindblad master equation directly into its loss function to enforce physical consistency. Open-system simulations demonstrate a 42% reduction in leakage to non-computational states. Hardware experiments executed on the 156-qubit IBM Quantum processor show an increase in Ramsey dephasing time from 83.3 ± 7.8 μs to 113.0 ± 1.1 μs while maintaining gate fidelity exceeding 99.99%.
The potential of quantum computing is fundamentally constrained by the inherent susceptibility of qubits to noise and crosstalk, particularly during multi-qubit gate operations.
Existing strategies, such as hardware isolation and dynamical decoupling, face limitations in scalability, experimental feasibility, and robustness against complex noise sources.
In this manuscript, we propose a physics-guided neural control (PGNC) framework to generate robust control pulses for superconducting transmon qubit systems, specifically targeting crosstalk mitigation.
By combining a hardware aware parameterization with a Hamiltonian-informed objective that accounts for condition-dependent crosstalk distortions, PGNC steers the search toward smooth and physically realizable pulses while efficiently exploring high dimensional control landscapes.
Numerical simulations for the CZ gate demonstrate superior fidelity and pulse smoothness compared to a Krotov baseline under matched constraints.
Taken together, the results show consistent and practically meaningful improvements in both nominal and perturbed conditions, with pronounced gains in worst-case fidelity, supporting PGNC as a viable route to robust control on near-term transmon devices.
We propose a physics-informed neural network (PINN) approach for high-fidelity quantum gate learning in both one- and two-qubit systems. We train a PINN using the time-dependent Schrödinger equation, where smooth control fields with fixed boundary conditions are obtained by minimizing a loss function that considers model dynamics, gate error, physical constraints, regularization terms, and multiple initial conditions. Training considers pairs of mutually unbiased bases, while independent validation combines Haar-random input states with the average gate fidelity. Unitary simulations yield an average gate infidelity of 8.49×10−8 for Hadamard and values between 3.39×10−7 and 4.96×10−6 for controlled-NOT under XX, YY, and ZZ interactions. We examine how the learned control fields depend on the coupling, training configuration, and available local fields, including five exchange-type dipolar scenarios. We test the learned control fields under the Lindblad master equation with dephasing and amplitude damping, theoretically reproducing the expected first-order fidelity loss in the weak-dissipation regime. Finally, boundary-adapted Chebyshev expansions represent 139 learned controls with a minimum common count of K∗=24 coefficients per control for all eleven family-averaged mean squared errors to fall below 10−6. Separately, square-pulse and Strang propagation at K=30 preserve all 31 continuous polynomial references within infidelity 10−5 at N=128 and all larger tested resolutions, under both sampling rules. These results connect multi-state gate synthesis, control-resource characterization, and compact square-pulse playback.
The classical Internet faces increasing limitations as data generation and device interconnectivity expand at unprecedented rates. In recent years, this has highlighted the need for communication frameworks that surpass classical limitations. The quantum Internet (QI), composed of multiple layers of quantum communication networks (QCNs), holds promise for remarkable capabilities in secure transmission, distributed quantum computing, and quantum-enhanced sensing. Accurate and scalable modeling of QCNs is essential for designing, analyzing, and optimizing QI protocols under realistic physical conditions. To model such open quantum systems under Markovian noise, the Lindblad master equation is widely used, but its modeling complexity grows exponentially with the system size. In this work, we introduce a learned approach that utilizes a physics-informed neural network (PINN) to model the dynamics of open quantum systems, which embeds the Lindblad formalism directly into the neural network's loss function. We demonstrate the effectiveness of our method by simulating the entanglement fidelity decay of a two-qubit Bell state under energy damping and phase decoherence noise, which is a relevant scenario for entanglement-based QI protocols. Preliminary numerical results show that the PINN-based solver aligns with conventional partial differential equation techniques while offering improved scalability. These findings suggest that PINNs could serve as an efficient approach for accelerating the analysis of future quantum networking solutions. Finally, we conclude by outlining key future directions for scaling the framework to support QCN-level optimization.
Fault-tolerant quantum computation requires scaling quantum processors to millions of physical qubits, yet purely superconducting architectures face significant hardware and control overhead. Hybrid multimode piezomechanical systems offer a hardware-efficient alternative by encoding quantum information in dense bosonic acoustic modes. However, stabilizing entanglement in such networks is challenging because continuous measurement and environmental dissipation generate strongly nonlinear driven-dissipative dynamics that are difficult to optimize analytically. Here we present an autonomous artificial-intelligence framework for the design and control of multimode superconducting optomechanical circuits. Using a model-free Recurrent Proximal Policy Optimization agent, the system learns a dynamic control protocol that exploits weak continuous measurement backaction to emulate a squeezed-vacuum environment, stabilizing steady-state remote entanglement with logarithmic negativity EN = 0.506 ± 0.027. In parallel, a Physics-Informed Neural Network incorporating the Lindblad master equation identifies control trajectories near a Liouvillian exceptional point, enabling efficient navigation of the non-Hermitian phase space. This physics-guided optimization reduces the circuit depth of standard quantum parity-check routines by 43.2% relative to conventional compilation. These results demonstrate that integrating machine learning with quantum control can autonomously discover robust strategies for stabilizing entanglement and reducing circuit complexity, providing a scalable pathway toward hardware-efficient quantum networks and distributed quantum information processing.
Quantum information processing holds the promise of a paradigm shift in computational power for specific problem classes. While contemporary quantum processors operate in the Noisy Intermediate-Scale Quantum (NISQ) regime and remain highly susceptible to errors, ongoing experimental efforts on these near-term devices are crucial for advancing the underlying technology. Among the various hardware implementations, superconducting quantum circuits stand out as one of the most robust architectures for scalable quantum technologies. Nevertheless, the primary bottleneck in these systems is the fragility of quantum information: interactions with the environment inevitably perturb the quantum states, a phenomenon known as decoherence. This rapid loss of stored information imposes a fundamental limit on the time available to reliably execute computations on these devices. Within this context, this thesis focuses on the comprehensive experimental characterization of a planar chip featuring isolated, fixed-frequency superconducting transmon qubits. The measurements were conducted in a cryogenic environment, relying on a dilution refrigerator to maintain the device at millikelvin temperatures. To probe the quantum system under these conditions, custom measurement scripts were developed to operate state-of-the-art microwave control electronics (Keysight Quantum Control System), establishing full control over pulse generation, signal acquisition, and digital demodulation. The experimental workflow systematically mapped the physical properties of the device through a progressive series of characterization steps. Initial spectroscopic techniques probed the coupled resonator-qubit system, identifying its fundamental transition frequencies and relevant energy scales. Building upon these frequency-domain measurements, coherent control was achieved by calibrating resonant microwave pulses to drive single-qubit rotations, enabling the reliable preparation of the qubit in excited or coherent superposition states. Finally, specific time-domain protocols were implemented to evaluate the operational limits of the device. By executing standard pulse sequences, the characteristic decoherence metrics of the system, namely the longitudinal energy relaxation time (T1) and the inhomogeneous dephasing time (T2*), were successfully extracted, providing a quantitative assessment of the qubit's overall performance and establishing a baseline for future implementations of more advanced quantum control protocols.
Quantum error mitigation (QEM) is a prerequisite for extracting utility from noisy intermediate-scale quantum (NISQ) processors. Among emerging protocols, tensor network error mitigation (TEM) offers scalable noise inversion, yet its efficacy is strictly bounded by the fidelity of the underlying noise channel reconstruction. The prevailing “cold-start” unsupervised learning paradigm typically treats noise characterization as a black-box optimization problem, which may result in a nonconvex landscape, where standard optimizers consistently stall at suboptimal local minima. In this paper, we propose a physicsinformed quantum multi-head network (QMHN) to overcome the barrier. By embedding the structure of the sparse Pauli-Lindblad model (SPLM) directly into the neural architecture, our method explicitly decouples the learning manifolds of local single-qubit dissipation and correlated two-qubit crosstalk errors. Crucially, we demonstrate that such physical inductive bias reduces the training convergence time by approximately 88% and significantly reduces the reconstruction error floor compared to monolithic direct parameter optimization. To further approach the theoretical fidelity limit, we introduce an adaptive prior-guided mechanism, which dynamically balances simulated measurement statistics with prior physical constraints. Validated against a controlled ideal prior, our framework navigates the complex optimization landscape to achieve a reconstruction precision of 10−6. When applied to TEM on deep quantum circuits, this ultra-high-fidelity model enables near-exact observable recovery where conventional characterization methods fail. Our results demonstrate that incorporating physical structural constraints into tensor-network learning is essential for scalable, highprecision quantum noise characterization.