Seasonal prediction of winter extreme precipitation over Canada by support vector regression
For forecasting the maximum 5-day accumulated precipitation over the winter season at lead times of 3, 6, 9 and 12 months over Canada from 1950 to 2007, two nonlinear and two linear regression models were used, where the models were support vector regression (SVR) (nonlinear and linear versions), no...
Published in: | Hydrology and Earth System Sciences |
---|---|
Main Authors: | , , , |
Format: | Text |
Language: | English |
Published: |
2018
|
Subjects: | |
Online Access: | https://doi.org/10.5194/hess-15-65-2011 https://www.hydrol-earth-syst-sci.net/15/65/2011/ |
id |
ftcopernicus:oai:publications.copernicus.org:hess7630 |
---|---|
record_format |
openpolar |
spelling |
ftcopernicus:oai:publications.copernicus.org:hess7630 2023-05-15T14:57:46+02:00 Seasonal prediction of winter extreme precipitation over Canada by support vector regression Zeng, Z. Hsieh, W. W. Shabbar, A. Burrows, W. R. 2018-09-27 application/pdf https://doi.org/10.5194/hess-15-65-2011 https://www.hydrol-earth-syst-sci.net/15/65/2011/ eng eng doi:10.5194/hess-15-65-2011 https://www.hydrol-earth-syst-sci.net/15/65/2011/ eISSN: 1607-7938 Text 2018 ftcopernicus https://doi.org/10.5194/hess-15-65-2011 2019-12-24T09:57:04Z For forecasting the maximum 5-day accumulated precipitation over the winter season at lead times of 3, 6, 9 and 12 months over Canada from 1950 to 2007, two nonlinear and two linear regression models were used, where the models were support vector regression (SVR) (nonlinear and linear versions), nonlinear Bayesian neural network (BNN) and multiple linear regression (MLR). The 118 stations were grouped into six geographic regions by K -means clustering. For each region, the leading principal components of the winter maximum 5-d accumulated precipitation anomalies were the predictands. Potential predictors included quasi-global sea surface temperature anomalies and 500 hPa geopotential height anomalies over the Northern Hemisphere, as well as six climate indices (the Niño-3.4 region sea surface temperature, the North Atlantic Oscillation, the Pacific-North American teleconnection, the Pacific Decadal Oscillation, the Scandinavia pattern, and the East Atlantic pattern). The results showed that in general the two robust SVR models tended to have better forecast skills than the two non-robust models (MLR and BNN), and the nonlinear SVR model tended to forecast slightly better than the linear SVR model. Among the six regions, the Prairies region displayed the highest forecast skills, and the Arctic region the second highest. The strongest nonlinearity was manifested over the Prairies and the weakest nonlinearity over the Arctic. Text Arctic North Atlantic North Atlantic oscillation Copernicus Publications: E-Journals Arctic Canada Pacific Hydrology and Earth System Sciences 15 1 65 74 |
institution |
Open Polar |
collection |
Copernicus Publications: E-Journals |
op_collection_id |
ftcopernicus |
language |
English |
description |
For forecasting the maximum 5-day accumulated precipitation over the winter season at lead times of 3, 6, 9 and 12 months over Canada from 1950 to 2007, two nonlinear and two linear regression models were used, where the models were support vector regression (SVR) (nonlinear and linear versions), nonlinear Bayesian neural network (BNN) and multiple linear regression (MLR). The 118 stations were grouped into six geographic regions by K -means clustering. For each region, the leading principal components of the winter maximum 5-d accumulated precipitation anomalies were the predictands. Potential predictors included quasi-global sea surface temperature anomalies and 500 hPa geopotential height anomalies over the Northern Hemisphere, as well as six climate indices (the Niño-3.4 region sea surface temperature, the North Atlantic Oscillation, the Pacific-North American teleconnection, the Pacific Decadal Oscillation, the Scandinavia pattern, and the East Atlantic pattern). The results showed that in general the two robust SVR models tended to have better forecast skills than the two non-robust models (MLR and BNN), and the nonlinear SVR model tended to forecast slightly better than the linear SVR model. Among the six regions, the Prairies region displayed the highest forecast skills, and the Arctic region the second highest. The strongest nonlinearity was manifested over the Prairies and the weakest nonlinearity over the Arctic. |
format |
Text |
author |
Zeng, Z. Hsieh, W. W. Shabbar, A. Burrows, W. R. |
spellingShingle |
Zeng, Z. Hsieh, W. W. Shabbar, A. Burrows, W. R. Seasonal prediction of winter extreme precipitation over Canada by support vector regression |
author_facet |
Zeng, Z. Hsieh, W. W. Shabbar, A. Burrows, W. R. |
author_sort |
Zeng, Z. |
title |
Seasonal prediction of winter extreme precipitation over Canada by support vector regression |
title_short |
Seasonal prediction of winter extreme precipitation over Canada by support vector regression |
title_full |
Seasonal prediction of winter extreme precipitation over Canada by support vector regression |
title_fullStr |
Seasonal prediction of winter extreme precipitation over Canada by support vector regression |
title_full_unstemmed |
Seasonal prediction of winter extreme precipitation over Canada by support vector regression |
title_sort |
seasonal prediction of winter extreme precipitation over canada by support vector regression |
publishDate |
2018 |
url |
https://doi.org/10.5194/hess-15-65-2011 https://www.hydrol-earth-syst-sci.net/15/65/2011/ |
geographic |
Arctic Canada Pacific |
geographic_facet |
Arctic Canada Pacific |
genre |
Arctic North Atlantic North Atlantic oscillation |
genre_facet |
Arctic North Atlantic North Atlantic oscillation |
op_source |
eISSN: 1607-7938 |
op_relation |
doi:10.5194/hess-15-65-2011 https://www.hydrol-earth-syst-sci.net/15/65/2011/ |
op_doi |
https://doi.org/10.5194/hess-15-65-2011 |
container_title |
Hydrology and Earth System Sciences |
container_volume |
15 |
container_issue |
1 |
container_start_page |
65 |
op_container_end_page |
74 |
_version_ |
1766329894517604352 |