Ocean Meteorological Large Model-Driven Digital Twin and Proactive Communication System for Evaporation Ducts

Evaporation ducts are the dominant natural medium for maritime beyond-line-of-sight communications. However, their minute-scale temporal variability causes significant decision latency and resource underutilization in conventional passive communication systems. This paper proposes an active communication framework driven by an ocean meteorological large model. A digital twin of the evaporation duct is constructed using a physics-informed neural network, fused with multi-source marine observations and real-time link feedback. Spatiotemporal Fourier neural operators accelerate electromagnetic propagation calculations to millisecond latency, and temporal generative models realize probabilistic channel prediction with rigorous uncertainty quantification. A distributed robust model predictive control scheme is designed to optimize communication resource allocation under confidence interval constraints. South China Sea simulations show that the proposed PINN digital twin achieves fitting MAEs of 0.13 m for duct height and 0.10 dB for path loss. Within a 10 min forecast horizon, the path loss prediction error remains below 0.98 dB. Compared with traditional passive methods, the proposed system reduces the safe outage probability by 46.3%, enhances effective throughput by 28.7%, and attenuates rainfall-induced band handover oscillation by 90.2%, enabling a methodological shift from reactive adaptation to proactive anticipation.