大地测量与地球动力学2025，Vol.45Issue(9)：881-887,893,8.DOI:10.14075/j.jgg.2025.02.040
基于GAN和Transformer模型组合的格陵兰地区PWV短时预报方法
A Short-Term Forecast Method for PWV in Greenland Based on the Combination of GAN and Transformer Models
摘要
Abstract
Based on the PWV time series data inverted from GPS during 2010-2018 and the PWV data calculated from the ERA5 reanalysis data for the same period,a combination of the generative adver-sarial networks(GAN)model and the Transformer neural network model in deep learning was em-ployed to achieve short-term forecasting of PWV in Greenland using GPS-PWV data.The prediction results were evaluated using the ERA5 data from 2019.The results show that the model performed well in most areas,with a root mean square error(RMSE)better than 4.5 mm and a correlation coeffi-cient greater than 0.7.The correlation coefficients in spring,autumn,and winter were all above 0.5,while in summer,the correlation coefficients on some dates were slightly lower due to severe weather changes.This method is capable of predicting the spatial distribution and temporal variations of PWV in Greenland.关键词
生成对抗网络/Transformer/GPS/格陵兰/PWV/短时预报Key words
generative adversarial networks(GAN)/Transformer/GPS/Greenland/PWV/short-term forecast分类
天文与地球科学引用本文复制引用
张胜凯,胡希成,龚力,雷锦韬,李文浩,马超,肖峰..基于GAN和Transformer模型组合的格陵兰地区PWV短时预报方法[J].大地测量与地球动力学,2025,45(9):881-887,893,8.基金项目
国家重点研发计划(2023YFC2809103) （2023YFC2809103）
中央高校基本科研业务费专项(2042022kf1204,2042023gf0012,2042022KF1069) （2042022kf1204,2042023gf0012,2042022KF1069）
中国科学院精密测量科学与技术创新研究院大地测量与地球动力学国家重点实验室开放基金(SKLGED2023-2-6) （SKLGED2023-2-6）
湖北省自然科学基金(2022CFB081). National Key Research and Development Program,No.2023YFC2809103 （2022CFB081）
Fundamental Research Funds for the Cen-tral Universities,No.2042022kf1204,2042023gf0012,2042022kf1069 （）
Open Fund of State Key Laboratory of Geodesy and Earth's Dy-namics,Innovation Academy for Precision Measurement Science and Technology,CAS,No.SKLGED2023-2-6 （）
Natural Science Founda-tion of Hubei Province,No.2022CFB081. （）
