MLAM: Multi-Layer Attention Module for Radar Extrapolation Based on Spatiotemporal Sequence Neural Network
Precipitation nowcasting is mainly achieved by the radar echo extrapolation method. Due to the timing characteristics of radar echo extrapolation, convolutional recurrent neural networks (ConvRNNs) have been used to solve the task. Most ConvRNNs have been proven to perform far better than traditiona...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-09-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/23/19/8065 |
| _version_ | 1827722234400079872 |
|---|---|
| author | Shengchun Wang Tianyang Wang Sihong Wang Zixiong Fang Jingui Huang Zuxi Zhou |
| author_facet | Shengchun Wang Tianyang Wang Sihong Wang Zixiong Fang Jingui Huang Zuxi Zhou |
| author_sort | Shengchun Wang |
| collection | DOAJ |
| description | Precipitation nowcasting is mainly achieved by the radar echo extrapolation method. Due to the timing characteristics of radar echo extrapolation, convolutional recurrent neural networks (ConvRNNs) have been used to solve the task. Most ConvRNNs have been proven to perform far better than traditional optical flow methods, but they still have fatal problems. These models lack differentiation in the prediction of echoes of different intensities, which leads to the omission of responses from regions with high intensities. Moreover, because it is difficult for these models to capture long-term feature dependencies among multiple echo maps, the extrapolation effect declines sharply over time. This paper proposes an embedded multi-layer attention module (MLAM) to address the shortcomings of ConvRNNs. Specifically, an MLAM mainly enhances attention to critical regions in echo images and the processing of long-term spatiotemporal features through the interaction between input and memory features in the current moment. Comprehensive experiments were conducted on the radar dataset HKO-7 provided by the Hong Kong Observatory and the radar dataset HMB provided by the Hunan Meteorological Bureau. Experiments show that ConvRNNs embedded with MLAMs achieve more advanced results than standard ConvRNNs. |
| first_indexed | 2024-03-10T21:36:15Z |
| format | Article |
| id | doaj.art-dee7f003cdc74b5aae5414f892912576 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-10T21:36:15Z |
| publishDate | 2023-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-dee7f003cdc74b5aae5414f8929125762023-11-19T15:02:13ZengMDPI AGSensors1424-82202023-09-012319806510.3390/s23198065MLAM: Multi-Layer Attention Module for Radar Extrapolation Based on Spatiotemporal Sequence Neural NetworkShengchun Wang0Tianyang Wang1Sihong Wang2Zixiong Fang3Jingui Huang4Zuxi Zhou5College of Information Science and Engineering, Hunan Normal University, Changsha 410081, ChinaCollege of Information Science and Engineering, Hunan Normal University, Changsha 410081, ChinaCollege of Information Science and Engineering, Hunan Normal University, Changsha 410081, ChinaCollege of Information Science and Engineering, Hunan Normal University, Changsha 410081, ChinaCollege of Information Science and Engineering, Hunan Normal University, Changsha 410081, ChinaCollege of Civil Aviation, Nanjing University of Aeronautics and Astronautics, Nanjing 211106, ChinaPrecipitation nowcasting is mainly achieved by the radar echo extrapolation method. Due to the timing characteristics of radar echo extrapolation, convolutional recurrent neural networks (ConvRNNs) have been used to solve the task. Most ConvRNNs have been proven to perform far better than traditional optical flow methods, but they still have fatal problems. These models lack differentiation in the prediction of echoes of different intensities, which leads to the omission of responses from regions with high intensities. Moreover, because it is difficult for these models to capture long-term feature dependencies among multiple echo maps, the extrapolation effect declines sharply over time. This paper proposes an embedded multi-layer attention module (MLAM) to address the shortcomings of ConvRNNs. Specifically, an MLAM mainly enhances attention to critical regions in echo images and the processing of long-term spatiotemporal features through the interaction between input and memory features in the current moment. Comprehensive experiments were conducted on the radar dataset HKO-7 provided by the Hong Kong Observatory and the radar dataset HMB provided by the Hunan Meteorological Bureau. Experiments show that ConvRNNs embedded with MLAMs achieve more advanced results than standard ConvRNNs.https://www.mdpi.com/1424-8220/23/19/8065precipitation nowcastingradar echo extrapolationconvolutional recurrent neural networksattention mechanism |
| spellingShingle | Shengchun Wang Tianyang Wang Sihong Wang Zixiong Fang Jingui Huang Zuxi Zhou MLAM: Multi-Layer Attention Module for Radar Extrapolation Based on Spatiotemporal Sequence Neural Network Sensors precipitation nowcasting radar echo extrapolation convolutional recurrent neural networks attention mechanism |
| title | MLAM: Multi-Layer Attention Module for Radar Extrapolation Based on Spatiotemporal Sequence Neural Network |
| title_full | MLAM: Multi-Layer Attention Module for Radar Extrapolation Based on Spatiotemporal Sequence Neural Network |
| title_fullStr | MLAM: Multi-Layer Attention Module for Radar Extrapolation Based on Spatiotemporal Sequence Neural Network |
| title_full_unstemmed | MLAM: Multi-Layer Attention Module for Radar Extrapolation Based on Spatiotemporal Sequence Neural Network |
| title_short | MLAM: Multi-Layer Attention Module for Radar Extrapolation Based on Spatiotemporal Sequence Neural Network |
| title_sort | mlam multi layer attention module for radar extrapolation based on spatiotemporal sequence neural network |
| topic | precipitation nowcasting radar echo extrapolation convolutional recurrent neural networks attention mechanism |
| url | https://www.mdpi.com/1424-8220/23/19/8065 |
| work_keys_str_mv | AT shengchunwang mlammultilayerattentionmoduleforradarextrapolationbasedonspatiotemporalsequenceneuralnetwork AT tianyangwang mlammultilayerattentionmoduleforradarextrapolationbasedonspatiotemporalsequenceneuralnetwork AT sihongwang mlammultilayerattentionmoduleforradarextrapolationbasedonspatiotemporalsequenceneuralnetwork AT zixiongfang mlammultilayerattentionmoduleforradarextrapolationbasedonspatiotemporalsequenceneuralnetwork AT jinguihuang mlammultilayerattentionmoduleforradarextrapolationbasedonspatiotemporalsequenceneuralnetwork AT zuxizhou mlammultilayerattentionmoduleforradarextrapolationbasedonspatiotemporalsequenceneuralnetwork |