PINN-TurbNet for predicting atmospheric turbulence in LEO satellite-to-ground laser communication links

<p dir="ltr">Atmospheric turbulence significantly impacts the performance of laser communication links between low Earth orbit (LEO) satellites and ground stations. In this study, we analyze minute-level meteorological data to reveal the spatial distribution of turbulence intensity. Based on these insights, we propose a physics-informed neural network model, PINN-TurbNet, which integrates physical constraints into a Transformer-based architecture to enhance turbulence prediction accuracy. To further improve computational efficiency, a multi-layer atmospheric turbulence analysis approach is introduced. Experimental results demonstrate that the PINN-TurbNet achieves a mean squared error (MSE) of 0.318 and a mean absolute error (MAE) of 0.209. The proposed model offers valuable guidance for the design and deployment of LEO satellite-to-ground laser communication links.</p>