English

TempEE: Temporal-Spatial Parallel Transformer for Radar Echo Extrapolation Beyond Auto-Regression

Signal Processing 2023-11-14 v2 Machine Learning

Abstract

Meteorological radar reflectivity data (i.e. radar echo) significantly influences precipitation prediction. It can facilitate accurate and expeditious forecasting of short-term heavy rainfall bypassing the need for complex Numerical Weather Prediction (NWP) models. In comparison to conventional models, Deep Learning (DL)-based radar echo extrapolation algorithms exhibit higher effectiveness and efficiency. Nevertheless, the development of reliable and generalized echo extrapolation algorithm is impeded by three primary challenges: cumulative error spreading, imprecise representation of sparsely distributed echoes, and inaccurate description of non-stationary motion processes. To tackle these challenges, this paper proposes a novel radar echo extrapolation algorithm called Temporal-Spatial Parallel Transformer, referred to as TempEE. TempEE avoids using auto-regression and instead employs a one-step forward strategy to prevent cumulative error spreading during the extrapolation process. Additionally, we propose the incorporation of a Multi-level Temporal-Spatial Attention mechanism to improve the algorithm's capability of capturing both global and local information while emphasizing task-related regions, including sparse echo representations, in an efficient manner. Furthermore, the algorithm extracts spatio-temporal representations from continuous echo images using a parallel encoder to model the non-stationary motion process for echo extrapolation. The superiority of our TempEE has been demonstrated in the context of the classic radar echo extrapolation task, utilizing a real-world dataset. Extensive experiments have further validated the efficacy and indispensability of various components within TempEE.

Keywords

Cite

@article{arxiv.2304.14131,
  title  = {TempEE: Temporal-Spatial Parallel Transformer for Radar Echo Extrapolation Beyond Auto-Regression},
  author = {Shengchao Chen and Ting Shu and Huan Zhao and Guo Zhong and Xunlai Chen},
  journal= {arXiv preprint arXiv:2304.14131},
  year   = {2023}
}

Comments

Have been accepted by IEEE Transactions on Geoscience and Remote Sensing, see https://ieeexplore.ieee.org/document/10238744

R2 v1 2026-06-28T10:19:36.525Z