气象2026，Vol.52Issue(3)：312-324,13.DOI:10.7519/j.issn.1000-0526.2025.122501
一种基于深度学习的相似天气形势预报方法:Synoptic Similarity Net
A Deep Learning-Based Method for Synoptic Situation Similarity Forecasting:Synoptic Similarity Net
摘要
Abstract
Analog forecasting is a widely adopted statistical method in operational meteorological services.Traditional single-layer similarity approaches have such limitations as the lack of three-dimensional spatial information,the unstable performance of single similarity criteria,and the frequent interference from syn-optic system pattern and intensity(magnitude).To address these challenges and explore the feasibility of deep learning models in synoptic situation recognition and forecasting,in this study we develop a novel ap-proach using the ECMWF fifth-generation reanalysis(ERA5)dataset.We construct a deep learning archi-tecture that integrates convolutional neural networks(CNN)with Transformer modules,incorporating self-attention mechanisms.Verification shows that this model can effectively capture three-dimensional spatial features of synoptic situation.Then,utilizing the extracted feature vectors,we design a compre-hensive similarity framework that combines three complementary metrics:Pearson correlation(empha-sizing pattern shape),Euclidean distance(emphasizing magnitude),and Chebyshev distance(considering both shape and magnitude).This integration forms our proposed method:Synoptic Similarity Net.Finally,the operational application effect of this method is tested and evaluated in detail.The results indicate that this method can achieve the highest average structural similarity index(SSIM)and lowest mean squared error(MSE)relative to the traditional methods,demonstrating significant improvements in both metrics.Case studies across seasons confirm that the historical analogs identified by Synoptic Similarity Net exhibit both greater numerical accuracy and superior spatial pattern consistency compared to the original synoptic fields.These results demonstrate the promising potential of this method for meteorological operational ap-plications.关键词
天气形势/相似预报/深度学习/相似判据/检验评估Key words
synoptic situation/analog forecast/deep learning/similarity criterion/evaluation and verifica-tion分类
天文与地球科学引用本文复制引用
谭江红,袁凯,周悦..一种基于深度学习的相似天气形势预报方法:Synoptic Similarity Net[J].气象,2026,52(3):312-324,13.基金项目
全国暴雨研究开放基金(BYKJ2025M11)、广西重点研发计划(桂科AB25069132)、湖北省气象局面上项目(2025Y04)、中国气象局公共服务中心面上项目(M2024011)和武汉市气象科技联合项目(2023020201010574)共同资助 （BYKJ2025M11）
