Spatiotemporal nowcasting of atmospheric optical turbulence for LEO satellite-to-ground laser communication...

Satellite-to-ground laser communication (SGLC) is a viable technology for future high-speed feeder links in mega Low Earth Orbit (LEO) constellation networks. However, it is constrained by the dynamic and non-stationary nature of atmospheric optical turbulence during rapid communication windows. To address the operational requirements for network scheduling, this study captures transient atmospheric states by deriving high-resolution Fried parameter (r₀) fields. This study proposes the Diffusion Schrödinger Bridge Graph Transformer (DSBGT) for minute-scale spatiotemporal nowcasting. The DSBGT architecture employs a Graph Wavelet Network-based Transformer (GWNformer) backbone to predict spatiotemporal patterns via dynamic graphs and parallel attention mechanisms. To address the non-stationarity of atmospheric optical turbulence, a Diffusion Schrödinger Bridge is incorporated to establish probabilistic optimal transport mappings from current r₀ distributions to their future states. Experimental results indicate that the DSBGT model achieves seasonal average mean absolute error (MAE) values below 0.24 cm for 30-min forecasts, outperforming baseline models. These results suggest the potential for facilitating proactive operational link scheduling and dynamic resource optimization in future LEO-SGLC networks.