Towards a universal model for spin--orbit coupled Wannier Hamiltonians

While machine learning interatomic potentials (MLIPs) have matured to revolutionize materials science, deep learning models for electronic structure are just beginning to emerge and are restricted, almost exclusively, to non-orthogonal basis Hamiltonians. We introduce G(Wa)NN, the first deep-learning model capable of generating the electronic Hamiltonian of solid-state systems in an orthogonal Wannier basis. G(Wa)NN is trained on an unprecedented, diverse dataset of more than 113K Wannier Hamiltonians (150M+ hopping matrices) spanning 69 elements, and evaluated on a held-out set of 2000 crystals disjoint from training. The combination of optimized inference and linear-scaling methods for orthogonal Hamiltonians unlocks transport simulations at massive scales (10K+ atoms). Crucially, the framework supports local finetuning, allowing users to adapt the base model to custom Wannier Hamiltonian datasets. To seamlessly translate these predictions into physical observables, we introduce a companion Python package providing an API interface to G(Wa)NN alongside a high-performance post-processing library. The package enables automated projection of the predicted Hamiltonian into an arbitrary low-energy subspace---directly mirroring familiar Wannier90 workflows---and includes a suite of Kernel Polynomial Method (KPM) functions that exploit the orthogonal basis to achieve strict linear scaling for spectral observables. This ecosystem, with the G(Wa)NN model at its core, aims to help bridge the gap between deep learning and macro-scale quantum transport simulations.