基于CEEMDAN 与TCN-Attention 的陆态网络GNSS高程时间序列多尺度预测

Multi-Scale Prediction of GNSS Elevation Time Series of CMONOC Based on CEEMDAN and TCN-Attention

ES评分 0

DOI 10.14075/j.jgg.2024.10.469
刊名
Journal of Geodesy and Geodynamics
年,卷(期) 2025, 45(8)
作者
作者单位

1 东华理工大学测绘与空间信息工程学院,南昌市广兰大道418号,330013

摘要
提出一种基于自适应噪声完备集合经验模态分解(complete ensemble empirical mode decomposition with adaptive noise, CEEMDAN)和时间卷积网络-注意力机制(temporal convolutional network-attention mechanism, TCN-Attention)算法的多尺度预测模型(简称C-TCN-A),该模型可有效应用于GNSS高程时间序列缺失数据的插补和未来趋势的预测。该模型利用CEEMDAN对时间序列进行多尺度分解,然后基于TCN-Attention对不同尺度分量进行预测和重构得到预测结果。为验证模型的性能,选取12个观测站进行1 d与5 d预测,并与其他多种模型进行对比。结果表明,在1 d预测中,C-TCN-A的RMSE和MAE分别降低35%~40%和36%~41%,相关系数R提高25%~29%;在5 d预测中,C-TCN-A的RMSE和MAE分别降低20%~26%和20%~28%,相关系数R提高26%~33%。为验证模型的普适性,利用C-TCN-A对陆态网络99个观测站进行1 d与5 d预测。结果表明,RMSE和MAE指标总体上结果较好,误差分布集中,大多数误差小于4 mm; 预测精度存在一定的空间分布差异,西北地区效果最佳。
Abstract
A multi-scale prediction model(referred to as C-TCN-A) based on complete ensemble empirical mode decomposition with adaptive noise(CEEMDAN) and temporal convolutional network-attention mechanism(TCN-Attention) algorithms is proposed, which can be effectively applied to missing data imputation and future trend prediction of GNSS elevation time series. The model first employs CEEMDAN for multi-scale decomposition of time series, then utilizes TCN-Attention for prediction and reconstruction of different scale components to obtain final results. To validate the model's performance, 12 observation stations were selected for 1-day and 5-day predictions, with comparisons made against multiple other models. Results demonstrate that in 1-day prediction, C-TCN-A reduces RMSE and MAE by 35%-40% and 36%-41% respectively while improving correlation coefficient R by 25%-29%. For 5-day prediction, it achieves reductions of 20%-26% in RMSE and 20%-28% in MAE, with R increasing by 26%-33%. To verify the model's universality, C-TCN-A was applied to 99 stations from the crustal movement observation network of China(CMONOC) for 1-day and 5-day predictions. Results indicate generally favorable RMSE and MAE metrics with concentrated error distribution, where most errors remain below 4 mm. Spatial analysis reveals regional performance differences, with optimal results achieved in the northwestern region.
关键词
GNSS高程时间序列; 陆态网络; 改进经验模态分解; 时间卷积网络
KeyWord
GNSS elevation time series; CMONOC; improved empirical mode decomposition; temporal convolutional network
基金项目
页码 781-790
  • 参考文献
  • 相关文献
  • 引用本文

罗亦泳, 占奥文, 冯小欢. 基于CEEMDAN 与TCN-Attention 的陆态网络GNSS高程时间序列多尺度预测 [J]. 大地测量与地球动力学. 2025; 45; (8). 781 - 790.

  • 文献评论

相关学者

相关机构