| DOI: | 10.1007/s11069-021-04806-6
|
| 论文题名: | Statistical forecast of the marine surge |
| 作者: | Quintana G.I.; Tandeo P.; Drumetz L.; Leballeur L.; Pavec M.
|
| 刊名: | Natural Hazards
|
| ISSN: | 0921030X
|
| 出版年: | 2021
|
| 卷: | 108, 期:3 | | 起始页码: | 2905
|
| 结束页码: | 2917
|
| 语种: | 英语
|
| 中文关键词: | Data science
; Machine learning
; Marine surge
; Neural networks
; Regression
; Sea level
; Time-series analysis
|
| 英文摘要: | This paper studies different machine learning methods for solving the regression problem of estimating the marine surge value given meteorological data. The marine surge is defined as the difference between the sea level predicted with the tides equations, and the real measured sea level. Different approaches are explored, from linear regression to multilayer perceptrons and recurrent neural networks. Stochastic networks are also considered, as they enable us to calculate a prediction error. These models are compared with a baseline method, which uses physical equations to calculate the surge. We show that all the statistical models outperform the baseline, being the multilayer perceptron the one that performs the best. (It reaches an R2 score of 0.68 and an RMSE of 7.3 cm.) © 2021, The Author(s), under exclusive licence to Springer Nature B.V. |
| Citation statistics: |
|
| 资源类型: | 期刊论文
|
| 标识符: | http://119.78.100.158/handle/2HF3EXSE/169312
|
| Appears in Collections: | 气候变化与战略
|
|
There are no files associated with this item.
|
|
作者单位: | IMT Atlantique, Lab-STICC, UMR CNRS 6285, Brest, F-29238, France; Actimar S.A.S., 36 quai de la douane, Brest, 29200, France
|
| Recommended Citation: | |
Quintana G.I.,Tandeo P.,Drumetz L.,et al. Statistical forecast of the marine surge[J]. Natural Hazards,2021-01-01,108(3)
|
|
|