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

作　　者：吴其亮 王兴[1] 苗子书 叶威良 王思成 向磊 WU Qi-liang;WANG Xing;MIAO Zi-shu;YE Wei-liang;WANG Si-cheng;XIANG Lei(School of Artificial Intelligence,Nanjing University of Information Science&Technology,Nanjing 210044,China;Baotou Meteorological Bureau,Baotou 014030,China;School of Computer Science,Nanjing University of Information Science&Technology,Nanjing 210044,China)

机构地区：[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

出　　处：《科学技术与工程》2024年第22期9498-9509,共12页Science Technology and Engineering

基　　金：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)。

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,DiffREE)。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%。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 resultsinaccuracy.To address the issues mentioned above,a novel methodology called DiffREE(diffusion radar echo extrapolation 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 algorithm.

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 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]