返回
SCECA-Net: A Deep Learning-Based Model for Precipitation Nowcasting
DOI:10.1109/TGRS.2025.3534278.png)
摘要
En 中文
In the context of precipitation nowcasting of severe convective weather, radar echo extrapolation is a commonly employed method. However, existing methods still face numerous challenges, such as inaccurate echo boundary predictions, redundant feature extraction, and prolonged inference time, which reduce efficiency. This article proposes an innovative spatial-channel enhanced convolutional attention network (SCECA-Net) model aimed at improving feature extraction and enhancing prediction accuracy. SCECA-Net adopts a convolutional neural network (CNN) architecture and incorporates SCECA modules [spatial and channel reconstruction convolution (SCConv) and efficient channel attention (ECA)], effectively reducing spatial and channel redundancies while increasing attention to critical echo regions and enhancing the extraction of temporal sequence features. Additionally, continuous convolutions in the Dense Layer further mitigate the risk of overfitting and reduce interference between features. The experimental results demonstrate that the proposed model exhibits outstanding performance in both efficiency and accuracy.
Keyword:
Radar
Feature extraction
Predictive models
Precipitation
Radar tracking
Extrapolation
Computational modeling
Accuracy
Deep learning
Atmospheric modeling
Deep learning (DL)
precipitation nowcasting
radar echo extrapolation
spatiotemporal (ST) prediction
期刊
IF:
8.6
论文数:
2.1W
被引数:
10.7W
机构
暂无机构信息
引用论文
Flood forecasting based on radar precipitation nowcasting using U-net and its improved models
JOURNAL OF HYDROLOGY
IF6.3
Deciphering and Enhancing Rate‐Determining Step of Sodium Deposition towards Ultralow‐Temperature Sodium Metal Batteries解析并提升钠金属电池在超低温下钠沉积的速率决定步骤
Characterization of Dendrolimus houi Lajonquiere (Lepidoptera: Lasiocampidae) Transcriptome across All Life Stages
Insects
IF0

