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

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.