用卫星图像实时预测未来六小时降雨，精度达2公里。
Data-driven Precipitation Nowcasting Using Satellite Imagery
- 基于卫星红外与水汽通道数据，结合位置编码建模时序变化。
- 每小时更新一次，可提前六小时预测2公里分辨率降雨。
- 适合缺乏雷达系统的地区，尤其对防灾预警有实用价值。
精准的降水预报对洪水、滑坡等灾害的早期预警至关重要。传统方法依赖地面雷达，但存在空间限制和高维护成本，多数发展中国家只能使用低分辨率全球数值模型。为此，我们提出神经降水模型（NPM），利用全球尺度静止卫星影像进行降水预测，可实现每小时更新、最多六小时的预报。输入包括三个关键波段：10.5 μm红外辐射、6.3 μm上层水汽及7.3 μm下层水汽通道。NPM引入位置编码以捕捉季节与时间模式，应对降水变化。实验表明，该模型可实现2公里分辨率的实时降雨预测。代码与数据集已公开于 https://github.com/seominseok0429/Data-driven-Precipitation-Nowcasting-Using-Satellite-Imagery。
原文摘要 · Abstract (English)
Accurate precipitation forecasting is crucial for early warnings of disasters, such as floods and landslides. Traditional forecasts rely on ground-based radar systems, which are space-constrained and have high maintenance costs. Consequently, most developing countries depend on a global numerical model with low resolution, instead of operating their own radar systems. To mitigate this gap, we propose the Neural Precipitation Model (NPM), which uses global-scale geostationary satellite imagery. NPM predicts precipitation for up to six hours, with an update every hour. We take three key channels to discriminate rain clouds as input: infrared radiation (at a wavelength of 10.5 $μm$), upper- (6.3 $μm$), and lower- (7.3 $μm$) level water vapor channels. Additionally, NPM introduces positional encoders to capture seasonal and temporal patterns, accounting for variations in precipitation. Our experimental results demonstrate that NPM can predict rainfall in real-time with a resolution of 2 km. The code and dataset are available at https://github.com/seominseok0429/Data-driven-Precipitation-Nowcasting-Using-Satellite-Imagery.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。