Enhancing Weather Services Through Remote Sensing and Converged Media Visualization
Year: 2025
Type: article
Abstract: Remote sensing data combined with converged media platforms are transforming weather services, though challenges like data heterogeneity and terminal diversity persist. This paper proposes a dual-layer visualization framework: the lower layer uses multi-source registration, intelligent slicing, and GPU rendering to generate high-resolution rasters quickly; the upper layer employs adaptive components to ensure consistent cross-platform delivery of synchronized graphics, text, and audio. To enhance visual clarity, a lightweight rendering pipeline with knowledge distillation sharpens cloud, dust, and rainfall boundary depictions. Built-in plugins support automated disaster map generation and API-level customization, reducing collaboration costs and speeding up product updates. Experiments confirm the framework's efficiency and user-friendliness, while paving the way for future enhancements through CubeSat networks, WebGPU acceleration, and semantic reasoning—offering a scalable model for smart meteorology and media convergence.
Authors: Junmei Jia, Haimin Cheng, Xiaowei Jia, Yushan Liu, Chunlei Zhao
Language: English
Field: Computer Science
Domain: Physical Sciences
SDG: Climate action
Open Access status: diamond
OpenAlex ID: W4414200641