Enhancing the Encoding-Forecasting Model for Precipitation Nowcasting by Putting High Emphasis on the Latest Data of the Time Step
Nowcasting is an important technique for weather forecasting because sudden weather changes significantly affect human life. The encoding-forecasting model, which is a state-of-the-art architecture in the field of data-driven radar extrapolation, does not particularly focus on the latest data when f...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-02-01
|
| Series: | Atmosphere |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2073-4433/12/2/261 |
| _version_ | 1797396397186613248 |
|---|---|
| author | Chang Hoo Jeong Wonsu Kim Wonkyun Joo Dongmin Jang Mun Yong Yi |
| author_facet | Chang Hoo Jeong Wonsu Kim Wonkyun Joo Dongmin Jang Mun Yong Yi |
| author_sort | Chang Hoo Jeong |
| collection | DOAJ |
| description | Nowcasting is an important technique for weather forecasting because sudden weather changes significantly affect human life. The encoding-forecasting model, which is a state-of-the-art architecture in the field of data-driven radar extrapolation, does not particularly focus on the latest data when forecasting natural phenomena. This paper proposes a weighted broadcasting method that emphasizes the latest data of the time step to improve the nowcasting performance. This weighted broadcasting method allows the most recent rainfall patterns to have a greater impact on the forecasting network by extending the architecture of the existing encoding-forecasting model. Experimental results show that the proposed model is 1.74% and 2.20% better than the existing encoding-forecasting model in terms of mean absolute error and critical success index, respectively. In the case of heavy rainfall with an intensity of 30 mm/h or higher, the proposed model was more than 30% superior to the existing encoding-forecasting model. Therefore, applying the weighted broadcasting method, which explicitly places a high emphasis on the latest information, to the encoding-forecasting model is considered as an improvement that is applicable to the state-of-the-art implementation of data-driven radar-based precipitation nowcasting. |
| first_indexed | 2024-03-09T00:50:40Z |
| format | Article |
| id | doaj.art-8c428886f5bc42289dd4fa5aaefbab19 |
| institution | Directory Open Access Journal |
| issn | 2073-4433 |
| language | English |
| last_indexed | 2024-03-09T00:50:40Z |
| publishDate | 2021-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Atmosphere |
| spelling | doaj.art-8c428886f5bc42289dd4fa5aaefbab192023-12-11T17:15:15ZengMDPI AGAtmosphere2073-44332021-02-0112226110.3390/atmos12020261Enhancing the Encoding-Forecasting Model for Precipitation Nowcasting by Putting High Emphasis on the Latest Data of the Time StepChang Hoo Jeong0Wonsu Kim1Wonkyun Joo2Dongmin Jang3Mun Yong Yi4Department of Data-Centric Problem-Solving Research, Korea Institute of Science and Technology Information (KISTI), Daejeon 34141, KoreaDepartment of Data-Centric Problem-Solving Research, Korea Institute of Science and Technology Information (KISTI), Daejeon 34141, KoreaDepartment of Data-Centric Problem-Solving Research, Korea Institute of Science and Technology Information (KISTI), Daejeon 34141, KoreaDepartment of Data-Centric Problem-Solving Research, Korea Institute of Science and Technology Information (KISTI), Daejeon 34141, KoreaDepartment of Industrial & Systems Engineering, Korea Advanced Institute of Science and Technology (KAIST), Graduate School of Knowledge Service Engineering, Daejeon 34141, KoreaNowcasting is an important technique for weather forecasting because sudden weather changes significantly affect human life. The encoding-forecasting model, which is a state-of-the-art architecture in the field of data-driven radar extrapolation, does not particularly focus on the latest data when forecasting natural phenomena. This paper proposes a weighted broadcasting method that emphasizes the latest data of the time step to improve the nowcasting performance. This weighted broadcasting method allows the most recent rainfall patterns to have a greater impact on the forecasting network by extending the architecture of the existing encoding-forecasting model. Experimental results show that the proposed model is 1.74% and 2.20% better than the existing encoding-forecasting model in terms of mean absolute error and critical success index, respectively. In the case of heavy rainfall with an intensity of 30 mm/h or higher, the proposed model was more than 30% superior to the existing encoding-forecasting model. Therefore, applying the weighted broadcasting method, which explicitly places a high emphasis on the latest information, to the encoding-forecasting model is considered as an improvement that is applicable to the state-of-the-art implementation of data-driven radar-based precipitation nowcasting.https://www.mdpi.com/2073-4433/12/2/261precipitation nowcastingdeep neural networkradar extrapolationspatiotemporal modelingencoding-forecasting |
| spellingShingle | Chang Hoo Jeong Wonsu Kim Wonkyun Joo Dongmin Jang Mun Yong Yi Enhancing the Encoding-Forecasting Model for Precipitation Nowcasting by Putting High Emphasis on the Latest Data of the Time Step Atmosphere precipitation nowcasting deep neural network radar extrapolation spatiotemporal modeling encoding-forecasting |
| title | Enhancing the Encoding-Forecasting Model for Precipitation Nowcasting by Putting High Emphasis on the Latest Data of the Time Step |
| title_full | Enhancing the Encoding-Forecasting Model for Precipitation Nowcasting by Putting High Emphasis on the Latest Data of the Time Step |
| title_fullStr | Enhancing the Encoding-Forecasting Model for Precipitation Nowcasting by Putting High Emphasis on the Latest Data of the Time Step |
| title_full_unstemmed | Enhancing the Encoding-Forecasting Model for Precipitation Nowcasting by Putting High Emphasis on the Latest Data of the Time Step |
| title_short | Enhancing the Encoding-Forecasting Model for Precipitation Nowcasting by Putting High Emphasis on the Latest Data of the Time Step |
| title_sort | enhancing the encoding forecasting model for precipitation nowcasting by putting high emphasis on the latest data of the time step |
| topic | precipitation nowcasting deep neural network radar extrapolation spatiotemporal modeling encoding-forecasting |
| url | https://www.mdpi.com/2073-4433/12/2/261 |
| work_keys_str_mv | AT changhoojeong enhancingtheencodingforecastingmodelforprecipitationnowcastingbyputtinghighemphasisonthelatestdataofthetimestep AT wonsukim enhancingtheencodingforecastingmodelforprecipitationnowcastingbyputtinghighemphasisonthelatestdataofthetimestep AT wonkyunjoo enhancingtheencodingforecastingmodelforprecipitationnowcastingbyputtinghighemphasisonthelatestdataofthetimestep AT dongminjang enhancingtheencodingforecastingmodelforprecipitationnowcastingbyputtinghighemphasisonthelatestdataofthetimestep AT munyongyi enhancingtheencodingforecastingmodelforprecipitationnowcastingbyputtinghighemphasisonthelatestdataofthetimestep |