El Niño Index Prediction Based on Deep Learning with STL Decomposition
ENSO is an important climate phenomenon that often causes widespread climate anomalies and triggers various meteorological disasters. Accurately predicting the ENSO variation trend is of great significance for global ecosystems and socio-economic aspects. In scientific practice, researchers predomin...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-07-01
|
| Series: | Journal of Marine Science and Engineering |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2077-1312/11/8/1529 |
| _version_ | 1797584298553901056 |
|---|---|
| author | Ningmeng Chen Cheng Su Sensen Wu Yuanyuan Wang |
| author_facet | Ningmeng Chen Cheng Su Sensen Wu Yuanyuan Wang |
| author_sort | Ningmeng Chen |
| collection | DOAJ |
| description | ENSO is an important climate phenomenon that often causes widespread climate anomalies and triggers various meteorological disasters. Accurately predicting the ENSO variation trend is of great significance for global ecosystems and socio-economic aspects. In scientific practice, researchers predominantly employ associated indices, such as Niño 3.4, to quantitatively characterize the onset, intensity, duration, and type of ENSO events. In this study, we propose the STL-TCN model, which combines seasonal-trend decomposition using locally weighted scatterplot smoothing (LOESS) (STL) and temporal convolutional networks (TCN). This method uses STL to decompose the original time series into trend, seasonal, and residual components. Each subsequence is then individually predicted by different TCN models for multi-step forecasting, and the predictions from all models are combined to obtain the final result. During the verification period from 1992 to 2022, the STL-TCN model effectively captures index features and improves the accuracy of multi-step forecasting. In historical event simulation experiments, the model demonstrates advantages in capturing the trend and peak intensity of ENSO events. |
| first_indexed | 2024-03-10T23:49:51Z |
| format | Article |
| id | doaj.art-cf866fe4c05b4891a36b3f7156bf682c |
| institution | Directory Open Access Journal |
| issn | 2077-1312 |
| language | English |
| last_indexed | 2024-03-10T23:49:51Z |
| publishDate | 2023-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Journal of Marine Science and Engineering |
| spelling | doaj.art-cf866fe4c05b4891a36b3f7156bf682c2023-11-19T01:45:21ZengMDPI AGJournal of Marine Science and Engineering2077-13122023-07-01118152910.3390/jmse11081529El Niño Index Prediction Based on Deep Learning with STL DecompositionNingmeng Chen0Cheng Su1Sensen Wu2Yuanyuan Wang3School of Earth Sciences, Zhejiang University, Hangzhou 310027, ChinaSchool of Earth Sciences, Zhejiang University, Hangzhou 310027, ChinaSchool of Earth Sciences, Zhejiang University, Hangzhou 310027, ChinaZhejiang Provincial Key Laboratory of Geographic Information Science, Hangzhou 310028, ChinaENSO is an important climate phenomenon that often causes widespread climate anomalies and triggers various meteorological disasters. Accurately predicting the ENSO variation trend is of great significance for global ecosystems and socio-economic aspects. In scientific practice, researchers predominantly employ associated indices, such as Niño 3.4, to quantitatively characterize the onset, intensity, duration, and type of ENSO events. In this study, we propose the STL-TCN model, which combines seasonal-trend decomposition using locally weighted scatterplot smoothing (LOESS) (STL) and temporal convolutional networks (TCN). This method uses STL to decompose the original time series into trend, seasonal, and residual components. Each subsequence is then individually predicted by different TCN models for multi-step forecasting, and the predictions from all models are combined to obtain the final result. During the verification period from 1992 to 2022, the STL-TCN model effectively captures index features and improves the accuracy of multi-step forecasting. In historical event simulation experiments, the model demonstrates advantages in capturing the trend and peak intensity of ENSO events.https://www.mdpi.com/2077-1312/11/8/1529ENSOEI Niño indexdeep learningTCNSTL |
| spellingShingle | Ningmeng Chen Cheng Su Sensen Wu Yuanyuan Wang El Niño Index Prediction Based on Deep Learning with STL Decomposition Journal of Marine Science and Engineering ENSO EI Niño index deep learning TCN STL |
| title | El Niño Index Prediction Based on Deep Learning with STL Decomposition |
| title_full | El Niño Index Prediction Based on Deep Learning with STL Decomposition |
| title_fullStr | El Niño Index Prediction Based on Deep Learning with STL Decomposition |
| title_full_unstemmed | El Niño Index Prediction Based on Deep Learning with STL Decomposition |
| title_short | El Niño Index Prediction Based on Deep Learning with STL Decomposition |
| title_sort | el nino index prediction based on deep learning with stl decomposition |
| topic | ENSO EI Niño index deep learning TCN STL |
| url | https://www.mdpi.com/2077-1312/11/8/1529 |
| work_keys_str_mv | AT ningmengchen elninoindexpredictionbasedondeeplearningwithstldecomposition AT chengsu elninoindexpredictionbasedondeeplearningwithstldecomposition AT sensenwu elninoindexpredictionbasedondeeplearningwithstldecomposition AT yuanyuanwang elninoindexpredictionbasedondeeplearningwithstldecomposition |