Daily Precipitation Prediction Based on SVM-CEEMDAN-BiLSTM Model
In order to solve the problem of low prediction accuracy of the maximum value and rain-free days in daily precipitation series,a coupled model of precipitation prediction based on a support vector machine (SVM),complete ensemble empirical modal decomposition (CEEMDAN),and bi-directional long and sho...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | zho |
| Published: |
Editorial Office of Pearl River
2023-01-01
|
| Series: | Renmin Zhujiang |
| Online Access: | http://www.renminzhujiang.cn/thesisDetails#10.3969/j.issn.1001-9235.2023.09.008 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | In order to solve the problem of low prediction accuracy of the maximum value and rain-free days in daily precipitation series,a coupled model of precipitation prediction based on a support vector machine (SVM),complete ensemble empirical modal decomposition (CEEMDAN),and bi-directional long and short-term memory neural network (BiLSTM) was proposed. This paper applied the coupled model to predict the daily precipitation at Jingdezhen Station and Ganxian Station in the Poyang Lake Basin, and the results were compared with those of traditional model combinations. The results show that the precipitation prediction results of the coupled model are basically consistent with the measured ones, with the highest accuracy. It thus provides a reference for solving the problem of low prediction accuracy of the maximum value and rain-free days during daily precipitation prediction. |
|---|---|
| ISSN: | 1001-9235 |