Meteorological Visualization Data Generation of Transmission Lines Scenes Based on Diffusion Model

As a critical infrastructure for the transmission and assurance of power supply, the safe and stable operation of transmission lines is directly related to national development, public welfare, and social stability. In recent times, the frequent occurrence of extreme weather events such as rain, snow, and freezing conditions has posed severe threats to both the physical equipment and the security of the power grid. The lack of meteorological visualization datasets for transmission line scenarios has significantly hindered the development of meteorological monitoring technologies. Existing image generation algorithms face challenges in handling such complex scenarios, often exhibiting slow inference speed and poor performance. To address these issues, this paper proposes a Masked Diffusion Transformer and introduces an inference capability enhancement strategy based on a masking mechanism to improve the model's inference efficiency. Experimental results demonstrate that the proposed model achieves an FID of 16.5738 and an IS of 2.347, indicating improved image quality, which contributes to advancing research in meteorological monitoring technologies.