Model experiment description paper |
| 23 May 2023
CLGAN: a generative adversarial network (GAN)-based video prediction model for precipitation nowcasting
Yan Ji,Bing Gong,Michael Langguth,Amirpasha Mozaffari,and Xiefei Zhi
Yan Ji
Key Laboratory of Meteorological Disaster, Ministry of Education (KLME), Nanjing University of Information Science and Technology (NUIST), Nanjing 210044, China
Jülich Supercomputing Centre, Forschungszentrum Jülich, 52425 Jülich, Germany
Jülich Supercomputing Centre, Forschungszentrum Jülich, 52425 Jülich, Germany
Xiefei Zhi
Key Laboratory of Meteorological Disaster, Ministry of Education (KLME), Nanjing University of Information Science and Technology (NUIST), Nanjing 210044, China
Viewed
Total article views: 2,364 (including HTML, PDF, and XML)
HTML
PDF
XML
Total
BibTeX
EndNote
1,738
567
59
2,364
50
46
HTML: 1,738
PDF: 567
XML: 59
Total: 2,364
BibTeX: 50
EndNote: 46
Views and downloads (calculated since 14 Nov 2022)
Cumulative views and downloads
(calculated since 14 Nov 2022)
Total article views: 1,213 (including HTML, PDF, and XML)
HTML
PDF
XML
Total
BibTeX
EndNote
905
279
29
1,213
32
29
HTML: 905
PDF: 279
XML: 29
Total: 1,213
BibTeX: 32
EndNote: 29
Views and downloads (calculated since 23 May 2023)
Cumulative views and downloads
(calculated since 23 May 2023)
Total article views: 1,151 (including HTML, PDF, and XML)
HTML
PDF
XML
Total
BibTeX
EndNote
833
288
30
1,151
18
17
HTML: 833
PDF: 288
XML: 30
Total: 1,151
BibTeX: 18
EndNote: 17
Views and downloads (calculated since 14 Nov 2022)
Cumulative views and downloads
(calculated since 14 Nov 2022)
Viewed (geographical distribution)
Total article views: 2,364 (including HTML, PDF, and XML)
Thereof 2,276 with geography defined
and 88 with unknown origin.
Total article views: 1,213 (including HTML, PDF, and XML)
Thereof 1,163 with geography defined
and 50 with unknown origin.
Total article views: 1,151 (including HTML, PDF, and XML)
Thereof 1,113 with geography defined
and 38 with unknown origin.
Formulating short-term precipitation forecasting as a video prediction task, a novel deep learning architecture (convolutional long short-term memory generative adversarial network, CLGAN) is proposed. A benchmark dataset is built on minute-level precipitation measurements. Results show that with the GAN component the model generates predictions sharing statistical properties with observations, resulting in it outperforming the baseline in dichotomous and spatial scores for heavy precipitation.
Formulating short-term precipitation forecasting as a video prediction task, a novel deep...