SuperCond-GNN: Scalable Graph Neural Network Surrogate for Superconducting Circuit Simulations
2026-06-22 • Machine Learning
Machine Learning
AI summaryⓘ
The authors developed SuperCond-GNN, a type of graph neural network that predicts voltage in high-temperature superconducting magnets by representing their circuits as graphs. They trained it using simulated data from various configurations and showed it can accurately estimate voltage with about 4.3% error. This model helps quickly understand how current moves in complex circuits without running slower traditional simulations. They also tested methods to include basic electrical laws and checked how well the model works on new circuit designs. Although demonstrated on simple tape stacks, their graph-based approach can be extended to more complicated superconducting systems.
Graph Neural NetworkHigh-Temperature SuperconductorLumped-Element CircuitVoltage DistributionMessage PassingKirchhoff’s Current LawSurrogate ModelCurrent RedistributionDesign Space ExplorationZero-Shot Inference
Authors
Nandana Menon, Giorgio Vallone
Abstract
This paper presents SuperCond-GNN, a graph neural network-based surrogate model for predicting the voltage distribution in high-temperature superconducting (HTS) magnets. HTS magnets are modeled as lumped-element equivalent circuits and mapped onto graph representations, enabling message passing GNNs to learn the electrical response as a function of circuit topology, material properties, and operating current. As a proof of concept, tape stacks of up to 10 tapes are considered across a range of circuit topologies and operating conditions. The surrogate is trained on data generated from circuit simulations and achieves a mean MAPE of 4.3 % within the prescribed design space. The predicted nodal voltages enable fast and scalable inference of current redistribution and local operating conditions across a wide range of circuit configurations. The effect of incorporating physics-informed regularization via Kirchhoff's current law is also evaluated, and generalizability to unseen topologies is assessed through zero-shot inference and few-shot fine-tuning. While demonstrated on tape stack circuits, the graph-based framework is topology-agnostic and naturally extensible to more complex HTS cable and magnet configurations, offering a scalable alternative to conventional circuit solvers for downstream applications such as design space exploration, current sharing analysis, and real-time magnet monitoring.