Weather Radar Image Superresolution Using a Nonlocal Residual Network
Accurate and high-resolution weather radar images reflecting detailed structure information of radar echo are vital for analysis and forecast of extreme weather. Typically, this is performed by using interpolation schemes, which only use several neighboring data values for computational approximatio...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2021-01-01
|
| Series: | Journal of Mathematics |
| Online Access: | http://dx.doi.org/10.1155/2021/4483907 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832566403417243648 |
|---|---|
| author | Haoxuan Yuan Qiangyu Zeng Jianxin He |
| author_facet | Haoxuan Yuan Qiangyu Zeng Jianxin He |
| author_sort | Haoxuan Yuan |
| collection | DOAJ |
| description | Accurate and high-resolution weather radar images reflecting detailed structure information of radar echo are vital for analysis and forecast of extreme weather. Typically, this is performed by using interpolation schemes, which only use several neighboring data values for computational approximation to get the estimated value regardless of the large-scale context feature of weather radar images. Inspired by the striking performance of the convolutional neural network (CNN) applied in feature extraction and nonlocal self-similarity of weather radar images, we proposed a nonlocal residual network (NLRN) on the basis of CNN. The proposed network mainly consists of several nonlocal residual blocks (NLRB), which combine short skip connection (SSC) and nonlocal operation to train the deep network and capture large-scale context information. In addition, long skip connection (LSC) added in the network avoids learning low-frequency information, making the network focus on high-level features. Extensive experiments of ×2 and ×4 super-resolution reconstruction demonstrate that NLRN achieves superior performance in terms of both quantitative evaluation metrics and visual quality, especially for the reconstruction of the edge and detailed information of the weather radar echo. |
| format | Article |
| id | doaj-art-586011d30d84472f9190d63a8e4e7b48 |
| institution | Kabale University |
| issn | 2314-4785 |
| language | English |
| publishDate | 2021-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | Journal of Mathematics |
| spelling | doaj-art-586011d30d84472f9190d63a8e4e7b482025-02-03T01:04:17ZengWileyJournal of Mathematics2314-47852021-01-01202110.1155/2021/4483907Weather Radar Image Superresolution Using a Nonlocal Residual NetworkHaoxuan Yuan0Qiangyu Zeng1Jianxin He2College of Electronic EngineeringCollege of Electronic EngineeringCollege of Electronic EngineeringAccurate and high-resolution weather radar images reflecting detailed structure information of radar echo are vital for analysis and forecast of extreme weather. Typically, this is performed by using interpolation schemes, which only use several neighboring data values for computational approximation to get the estimated value regardless of the large-scale context feature of weather radar images. Inspired by the striking performance of the convolutional neural network (CNN) applied in feature extraction and nonlocal self-similarity of weather radar images, we proposed a nonlocal residual network (NLRN) on the basis of CNN. The proposed network mainly consists of several nonlocal residual blocks (NLRB), which combine short skip connection (SSC) and nonlocal operation to train the deep network and capture large-scale context information. In addition, long skip connection (LSC) added in the network avoids learning low-frequency information, making the network focus on high-level features. Extensive experiments of ×2 and ×4 super-resolution reconstruction demonstrate that NLRN achieves superior performance in terms of both quantitative evaluation metrics and visual quality, especially for the reconstruction of the edge and detailed information of the weather radar echo.http://dx.doi.org/10.1155/2021/4483907 |
| spellingShingle | Haoxuan Yuan Qiangyu Zeng Jianxin He Weather Radar Image Superresolution Using a Nonlocal Residual Network Journal of Mathematics |
| title | Weather Radar Image Superresolution Using a Nonlocal Residual Network |
| title_full | Weather Radar Image Superresolution Using a Nonlocal Residual Network |
| title_fullStr | Weather Radar Image Superresolution Using a Nonlocal Residual Network |
| title_full_unstemmed | Weather Radar Image Superresolution Using a Nonlocal Residual Network |
| title_short | Weather Radar Image Superresolution Using a Nonlocal Residual Network |
| title_sort | weather radar image superresolution using a nonlocal residual network |
| url | http://dx.doi.org/10.1155/2021/4483907 |
| work_keys_str_mv | AT haoxuanyuan weatherradarimagesuperresolutionusinganonlocalresidualnetwork AT qiangyuzeng weatherradarimagesuperresolutionusinganonlocalresidualnetwork AT jianxinhe weatherradarimagesuperresolutionusinganonlocalresidualnetwork |