A Generative Adversarial and Spatiotemporal Differential Fusion Method in Radar Echo Extrapolation
As an important part of remote sensing data, weather radar plays an important role in convective weather forecasts to reduce extreme precipitation disasters. The existing radar echo extrapolation methods do not utilize the local natural characteristics of the radar echo effectively but only roughly...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-11-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/15/22/5329 |
| _version_ | 1797457852334342144 |
|---|---|
| author | Xianghua Niu Lixia Zhang Chunlin Wang Kailing Shen Wei Tian Bin Liao |
| author_facet | Xianghua Niu Lixia Zhang Chunlin Wang Kailing Shen Wei Tian Bin Liao |
| author_sort | Xianghua Niu |
| collection | DOAJ |
| description | As an important part of remote sensing data, weather radar plays an important role in convective weather forecasts to reduce extreme precipitation disasters. The existing radar echo extrapolation methods do not utilize the local natural characteristics of the radar echo effectively but only roughly extract the whole characteristics of the radar echo. To address these challenges, we design a spatiotemporal difference and generative adversarial fusion model (STDGAN). Specifically, a spatiotemporal difference module (STD) is designed to extract local weather patterns and model them in detail. In our model, spatiotemporal difference information and spatiotemporal features captured by the model itself are fused together. In addition, our model is trained in a generative adversarial network (GAN) framework; it helps to generate a clearer map of future radar echoes at the image level. The discriminator consists of multi-scale feature extractors, which can simulate weather models of various scales more completely. Finally, extrapolation experiments were conducted using actual radar echo data from Shijiazhuang and Nanjing. The experiments have shown that our model has a more accurate prediction performance for predicting local weather patterns and overall echo change trajectories compared with previous research models. Our model achieved MSE, PSNE, and SSIM values of 132.22, 37.87, and 0.796, respectively, on the Shijiazhuang radar echo dataset. In addition, our model also showed better performance results on the Nanjing radar echo dataset. The results show that the MSE was 49.570, the PSNR was 0.714, and the SSIM was 30.633. The CC value was 0.855. |
| first_indexed | 2024-03-09T16:29:41Z |
| format | Article |
| id | doaj.art-b3d2d6641930495899f0df18b1fdb757 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-09T16:29:41Z |
| publishDate | 2023-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-b3d2d6641930495899f0df18b1fdb7572023-11-24T15:04:26ZengMDPI AGRemote Sensing2072-42922023-11-011522532910.3390/rs15225329A Generative Adversarial and Spatiotemporal Differential Fusion Method in Radar Echo ExtrapolationXianghua Niu0Lixia Zhang1Chunlin Wang2Kailing Shen3Wei Tian4Bin Liao5State Key Laboratory of Geo-Information Engineering, Xi’an 710054, ChinaShijiazhuang Meteorological Bureau, Shijiazhuang 050081, ChinaSchool of Computer and Software, Nanjing University of Information Science and Technology, Nanjing 210044, ChinaSchool of Computer and Software, Nanjing University of Information Science and Technology, Nanjing 210044, ChinaSchool of Computer and Software, Nanjing University of Information Science and Technology, Nanjing 210044, ChinaState Key Laboratory of Geo-Information Engineering, Xi’an 710054, ChinaAs an important part of remote sensing data, weather radar plays an important role in convective weather forecasts to reduce extreme precipitation disasters. The existing radar echo extrapolation methods do not utilize the local natural characteristics of the radar echo effectively but only roughly extract the whole characteristics of the radar echo. To address these challenges, we design a spatiotemporal difference and generative adversarial fusion model (STDGAN). Specifically, a spatiotemporal difference module (STD) is designed to extract local weather patterns and model them in detail. In our model, spatiotemporal difference information and spatiotemporal features captured by the model itself are fused together. In addition, our model is trained in a generative adversarial network (GAN) framework; it helps to generate a clearer map of future radar echoes at the image level. The discriminator consists of multi-scale feature extractors, which can simulate weather models of various scales more completely. Finally, extrapolation experiments were conducted using actual radar echo data from Shijiazhuang and Nanjing. The experiments have shown that our model has a more accurate prediction performance for predicting local weather patterns and overall echo change trajectories compared with previous research models. Our model achieved MSE, PSNE, and SSIM values of 132.22, 37.87, and 0.796, respectively, on the Shijiazhuang radar echo dataset. In addition, our model also showed better performance results on the Nanjing radar echo dataset. The results show that the MSE was 49.570, the PSNR was 0.714, and the SSIM was 30.633. The CC value was 0.855.https://www.mdpi.com/2072-4292/15/22/5329radar extrapolationgenerative adversarial networkdifferencespatiotemporal fusion |
| spellingShingle | Xianghua Niu Lixia Zhang Chunlin Wang Kailing Shen Wei Tian Bin Liao A Generative Adversarial and Spatiotemporal Differential Fusion Method in Radar Echo Extrapolation Remote Sensing radar extrapolation generative adversarial network difference spatiotemporal fusion |
| title | A Generative Adversarial and Spatiotemporal Differential Fusion Method in Radar Echo Extrapolation |
| title_full | A Generative Adversarial and Spatiotemporal Differential Fusion Method in Radar Echo Extrapolation |
| title_fullStr | A Generative Adversarial and Spatiotemporal Differential Fusion Method in Radar Echo Extrapolation |
| title_full_unstemmed | A Generative Adversarial and Spatiotemporal Differential Fusion Method in Radar Echo Extrapolation |
| title_short | A Generative Adversarial and Spatiotemporal Differential Fusion Method in Radar Echo Extrapolation |
| title_sort | generative adversarial and spatiotemporal differential fusion method in radar echo extrapolation |
| topic | radar extrapolation generative adversarial network difference spatiotemporal fusion |
| url | https://www.mdpi.com/2072-4292/15/22/5329 |
| work_keys_str_mv | AT xianghuaniu agenerativeadversarialandspatiotemporaldifferentialfusionmethodinradarechoextrapolation AT lixiazhang agenerativeadversarialandspatiotemporaldifferentialfusionmethodinradarechoextrapolation AT chunlinwang agenerativeadversarialandspatiotemporaldifferentialfusionmethodinradarechoextrapolation AT kailingshen agenerativeadversarialandspatiotemporaldifferentialfusionmethodinradarechoextrapolation AT weitian agenerativeadversarialandspatiotemporaldifferentialfusionmethodinradarechoextrapolation AT binliao agenerativeadversarialandspatiotemporaldifferentialfusionmethodinradarechoextrapolation AT xianghuaniu generativeadversarialandspatiotemporaldifferentialfusionmethodinradarechoextrapolation AT lixiazhang generativeadversarialandspatiotemporaldifferentialfusionmethodinradarechoextrapolation AT chunlinwang generativeadversarialandspatiotemporaldifferentialfusionmethodinradarechoextrapolation AT kailingshen generativeadversarialandspatiotemporaldifferentialfusionmethodinradarechoextrapolation AT weitian generativeadversarialandspatiotemporaldifferentialfusionmethodinradarechoextrapolation AT binliao generativeadversarialandspatiotemporaldifferentialfusionmethodinradarechoextrapolation |