用卫星数据提升南美降雨短时预报精度，效果优于现有模型。
DYffCast: Regional Precipitation Nowcasting Using IMERG Satellite Data. A case study over South America
- 改进扩散模型框架，适配降水数据特性
- 新损失函数融合误差与视觉感知，4小时预报最优
- 适合气象预警、防灾决策等实际应用
气候变化正加剧极端降水事件频发，导致洪涝和滑坡等灾害风险上升。准确的短时降雨预报对社会安全防护至关重要。本文将DYffusion框架拓展至降水预报任务，基于IMERG卫星降水数据，在4小时预报范围内进行评估。通过改进模型结构并引入结合均方误差、平均绝对误差与感知相似性（LPIPS）的新损失函数，训练出的模型在定量评估中超越四类对比模型。在弱、中、强雨量阈值下均取得最高命中率评分（CSI），且全程预测的LPIPS得分低于0.2，随预报时效增长退化最小。案例研究显示，该模型在强降雨情景下2小时内可生成视觉稳定且清晰的预报结果。代码已开源：https://github.com/Dseal95/DYffcast。
原文摘要 · Abstract (English)
Climate change is increasing the frequency of extreme precipitation events, making weather disasters such as flooding and landslides more likely. The ability to accurately nowcast precipitation is therefore becoming more critical for safeguarding society by providing immediate, accurate information to decision makers. Motivated by the recent success of generative models at precipitation nowcasting, this paper: extends the DYffusion framework to this task and evaluates its performance at forecasting IMERG satellite precipitation data up to a 4-hour horizon; modifies the DYffusion framework to improve its ability to model rainfall data; and introduces a novel loss function that combines MSE, MAE and the LPIPS perceptual score. In a quantitative evaluation of forecasts up to a 4-hour horizon, the modified DYffusion framework trained with the novel loss outperforms four competitor models. It has the highest CSI scores for weak, moderate, and heavy rain thresholds and retains an LPIPS score $<$ 0.2 for the entire roll-out, degrading the least as lead-time increases. The proposed nowcasting model demonstrates visually stable and sharp forecasts up to a 2-hour horizon on a heavy rain case study. Code is available at https://github.com/Dseal95/DYffcast.
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。