Generalizing Deep Surrogate Solvers for Broadband Electromagnetic Field Prediction at Unseen Wavelengths
This work addresses the limitation of narrow-spectrum electromagnetic field prediction for computational simulations, offering a domain-specific improvement.
The paper tackles the problem of electromagnetic surrogate solvers failing at unseen wavelengths by introducing spectral consistency and a framework with refined wave prior and WIME, achieving a 71% reduction in error and 42x speedup compared to state-of-the-art methods.
Recently, electromagnetic surrogate solvers, trained on solutions of Maxwell's equations under specific simulation conditions, enabled fast inference of computationally expensive simulations. However, conventional electromagnetic surrogate solvers often consider only a narrow range of spectrum and fail when encountering even slight variations in simulation conditions. To address this limitation, we define spectral consistency as the property by which the spatial frequency structure of wavelength-dependent condition embeddings matches that of the target electromagnetic field patterns. In addition, we propose two complementary components: a refined wave prior, which is the condition embedding that satisfies spectral consistency, and Wave-Informed element-wise Multiplicative Encoding (WIME), which integrates these embeddings throughout the model while preserving spectral consistency. This framework enables accurate field prediction across the broadband spectrum, including untrained intermediate wavelengths. Our approach reduces the normalized mean squared error at untrained wavelengths by up to 71% compared to the state-of-the-art electromagnetic surrogate solver and achieves a speedup of over 42 times relative to conventional numerical simulations.