Spatiotemporal Model Based on Deep Learning for ENSO Forecasts
El Niño and Southern Oscillation (ENSO) is closely related to a series of regional extreme climates, so robust long-term forecasting is of great significance for reducing economic losses caused by natural disasters. Here, we regard ENSO prediction as an unsupervised spatiotemporal prediction problem...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-06-01
|
| Series: | Atmosphere |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2073-4433/12/7/810 |
| _version_ | 1827688915660701696 |
|---|---|
| author | Huantong Geng Tianlei Wang |
| author_facet | Huantong Geng Tianlei Wang |
| author_sort | Huantong Geng |
| collection | DOAJ |
| description | El Niño and Southern Oscillation (ENSO) is closely related to a series of regional extreme climates, so robust long-term forecasting is of great significance for reducing economic losses caused by natural disasters. Here, we regard ENSO prediction as an unsupervised spatiotemporal prediction problem, and design a deep learning model called Dense Convolution-Long Short-Term Memory (DC-LSTM). For a more sufficient training model, we will also add historical simulation data to the training set. The experimental results show that DC-LSTM is more suitable for the prediction of a large region and a single factor. During the 1994–2010 verification period, the all-season correlation skill of the Nino3.4 index of the DC-LSTM is higher than that of the current dynamic model and regression neural network, and it can provide effective forecasts for lead times of up to 20 months. Therefore, DC-LSTM can be used as a powerful tool for predicting ENSO events. |
| first_indexed | 2024-03-10T10:07:18Z |
| format | Article |
| id | doaj.art-305699c628054517a2ea8fecd8aea397 |
| institution | Directory Open Access Journal |
| issn | 2073-4433 |
| language | English |
| last_indexed | 2024-03-10T10:07:18Z |
| publishDate | 2021-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Atmosphere |
| spelling | doaj.art-305699c628054517a2ea8fecd8aea3972023-11-22T01:24:04ZengMDPI AGAtmosphere2073-44332021-06-0112781010.3390/atmos12070810Spatiotemporal Model Based on Deep Learning for ENSO ForecastsHuantong Geng0Tianlei Wang1School 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, ChinaEl Niño and Southern Oscillation (ENSO) is closely related to a series of regional extreme climates, so robust long-term forecasting is of great significance for reducing economic losses caused by natural disasters. Here, we regard ENSO prediction as an unsupervised spatiotemporal prediction problem, and design a deep learning model called Dense Convolution-Long Short-Term Memory (DC-LSTM). For a more sufficient training model, we will also add historical simulation data to the training set. The experimental results show that DC-LSTM is more suitable for the prediction of a large region and a single factor. During the 1994–2010 verification period, the all-season correlation skill of the Nino3.4 index of the DC-LSTM is higher than that of the current dynamic model and regression neural network, and it can provide effective forecasts for lead times of up to 20 months. Therefore, DC-LSTM can be used as a powerful tool for predicting ENSO events.https://www.mdpi.com/2073-4433/12/7/810ENSOsea surface temperature predictiondeep learningLSTMspatiotemporal prediction |
| spellingShingle | Huantong Geng Tianlei Wang Spatiotemporal Model Based on Deep Learning for ENSO Forecasts Atmosphere ENSO sea surface temperature prediction deep learning LSTM spatiotemporal prediction |
| title | Spatiotemporal Model Based on Deep Learning for ENSO Forecasts |
| title_full | Spatiotemporal Model Based on Deep Learning for ENSO Forecasts |
| title_fullStr | Spatiotemporal Model Based on Deep Learning for ENSO Forecasts |
| title_full_unstemmed | Spatiotemporal Model Based on Deep Learning for ENSO Forecasts |
| title_short | Spatiotemporal Model Based on Deep Learning for ENSO Forecasts |
| title_sort | spatiotemporal model based on deep learning for enso forecasts |
| topic | ENSO sea surface temperature prediction deep learning LSTM spatiotemporal prediction |
| url | https://www.mdpi.com/2073-4433/12/7/810 |
| work_keys_str_mv | AT huantonggeng spatiotemporalmodelbasedondeeplearningforensoforecasts AT tianleiwang spatiotemporalmodelbasedondeeplearningforensoforecasts |