基于特征条件扩散模型的雷达回波外推算法
Extrapolation Algorithms for Radar Echoes Based on Characteristic Conditional Diffusion Models
吴其亮 1王兴 1苗子书 2叶威良 3王思成 1向磊1
作者信息
- 1. 南京信息工程大学人工智能学院,南京 210044
- 2. 包头市气象局,包头 014030
- 3. 南京信息工程大学计算机学院,南京 210044
- 折叠
摘要
随着外推时效的延长,回波强度愈发衰减,且对于强回波的预报性能迅速下降.这是当前雷达外推结果不准确的两个典型特征.为改善上述问题,提出了 一种通过雷达回波帧驱动的扩散雷达外推算法(diffusion radar echo extrapolation,Dif-fREE).该算法利用条件编码模块将过去雷达回波帧的空间信息和时效信息深度融合,通过Transformer编码器自动提取回波的时空特征,并作为条件扩散模型的条件,驱动扩散模型重建当前雷达回波帧.实验结果表明,该方法可以生成高精度、高质量的雷达预报帧,较最好的基线算法在CSI、ETS、HSS和POD上分别提升42.2％、51.1％、49.8％和39.5％.
Abstract
With the extension of lead time for extrapolation,the attenuation of radar echoes becomes increasingly pronounced,and the predictive performance for intense echoes rapidly deteriorates.These constitute two quintessential characteristics of the current radar extrapolation results'inaccuracy.To address the issues mentioned above,a novel methodology called DiffREE(diffusion radar echo ex-trapolation algorithm)was introduced.This algorithm skillfully fuses the spatial and temporal information from past radar echo frames using a conditional encoding module.It employs a Transformer encoder to automatically extract spatiotemporal features from the echoes,which are then used as conditions to drive the diffusion model in reconstructing the current radar echo frames.Experimental results demonstrate that this method can produce high-precision,high-quality radar forecast frames,achieving significant improvements of 42.2％,51.1％,49.8％,and 39.5％in CSI,ETS,HSS,and POD,respectively,compared to the best-performing baseline algo-rithm.
关键词
深度学习/短时预报/雷达回波外推/扩散模型/条件编码Key words
deep learning/short-term forecasting/radar echo extrapolation/diffusion model/conditional coding引用本文复制引用
基金项目
国家自然科学基金(41805033)
江苏省自然科学基金面上项目(BK20221344)
教育部产学合作协同育人项目(220702331220448)
出版年
2024
NETL
NSTL
万方数据