A Forecasting Approach Combining Self-Organizing Map with Support Vector Regression for Reservoir Inflow during Typhoon Periods

This study describes the development of a reservoir inflow forecasting model for typhoon events to improve short lead-time flood forecasting performance. To strengthen the forecasting ability of the original support vector machines (SVMs) model, the self-organizing map (SOM) is adopted to group inpu...

Full description

Saved in:
Bibliographic Details
Main Authors: Gwo-Fong Lin, Tsung-Chun Wang, Lu-Hsien Chen
Format: Article
Language:English
Published: Wiley 2016-01-01
Series:Advances in Meteorology
Online Access:http://dx.doi.org/10.1155/2016/7575126
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850223519129927680
author Gwo-Fong Lin
Tsung-Chun Wang
Lu-Hsien Chen
author_facet Gwo-Fong Lin
Tsung-Chun Wang
Lu-Hsien Chen
author_sort Gwo-Fong Lin
collection DOAJ
description This study describes the development of a reservoir inflow forecasting model for typhoon events to improve short lead-time flood forecasting performance. To strengthen the forecasting ability of the original support vector machines (SVMs) model, the self-organizing map (SOM) is adopted to group inputs into different clusters in advance of the proposed SOM-SVM model. Two different input methods are proposed for the SVM-based forecasting method, namely, SOM-SVM1 and SOM-SVM2. The methods are applied to an actual reservoir watershed to determine the 1 to 3 h ahead inflow forecasts. For 1, 2, and 3 h ahead forecasts, improvements in mean coefficient of efficiency (MCE) due to the clusters obtained from SOM-SVM1 are 21.5%, 18.5%, and 23.0%, respectively. Furthermore, improvement in MCE for SOM-SVM2 is 20.9%, 21.2%, and 35.4%, respectively. Another SOM-SVM2 model increases the SOM-SVM1 model for 1, 2, and 3 h ahead forecasts obtained improvement increases of 0.33%, 2.25%, and 10.08%, respectively. These results show that the performance of the proposed model can provide improved forecasts of hourly inflow, especially in the proposed SOM-SVM2 model. In conclusion, the proposed model, which considers limit and higher related inputs instead of all inputs, can generate better forecasts in different clusters than are generated from the SOM process. The SOM-SVM2 model is recommended as an alternative to the original SVR (Support Vector Regression) model because of its accuracy and robustness.
format Article
id doaj-art-497d68ef47864e34a66b8fe6175c54e2
institution OA Journals
issn 1687-9309
1687-9317
language English
publishDate 2016-01-01
publisher Wiley
record_format Article
series Advances in Meteorology
spelling doaj-art-497d68ef47864e34a66b8fe6175c54e22025-08-20T02:05:56ZengWileyAdvances in Meteorology1687-93091687-93172016-01-01201610.1155/2016/75751267575126A Forecasting Approach Combining Self-Organizing Map with Support Vector Regression for Reservoir Inflow during Typhoon PeriodsGwo-Fong Lin0Tsung-Chun Wang1Lu-Hsien Chen2Department of Civil Engineering, National Taiwan University, Taipei 10617, TaiwanDepartment of Civil Engineering, National Taiwan University, Taipei 10617, TaiwanDepartment of Leisure Management, Taiwan Shoufu University, Tainan 72153, TaiwanThis study describes the development of a reservoir inflow forecasting model for typhoon events to improve short lead-time flood forecasting performance. To strengthen the forecasting ability of the original support vector machines (SVMs) model, the self-organizing map (SOM) is adopted to group inputs into different clusters in advance of the proposed SOM-SVM model. Two different input methods are proposed for the SVM-based forecasting method, namely, SOM-SVM1 and SOM-SVM2. The methods are applied to an actual reservoir watershed to determine the 1 to 3 h ahead inflow forecasts. For 1, 2, and 3 h ahead forecasts, improvements in mean coefficient of efficiency (MCE) due to the clusters obtained from SOM-SVM1 are 21.5%, 18.5%, and 23.0%, respectively. Furthermore, improvement in MCE for SOM-SVM2 is 20.9%, 21.2%, and 35.4%, respectively. Another SOM-SVM2 model increases the SOM-SVM1 model for 1, 2, and 3 h ahead forecasts obtained improvement increases of 0.33%, 2.25%, and 10.08%, respectively. These results show that the performance of the proposed model can provide improved forecasts of hourly inflow, especially in the proposed SOM-SVM2 model. In conclusion, the proposed model, which considers limit and higher related inputs instead of all inputs, can generate better forecasts in different clusters than are generated from the SOM process. The SOM-SVM2 model is recommended as an alternative to the original SVR (Support Vector Regression) model because of its accuracy and robustness.http://dx.doi.org/10.1155/2016/7575126
spellingShingle Gwo-Fong Lin
Tsung-Chun Wang
Lu-Hsien Chen
A Forecasting Approach Combining Self-Organizing Map with Support Vector Regression for Reservoir Inflow during Typhoon Periods
Advances in Meteorology
title A Forecasting Approach Combining Self-Organizing Map with Support Vector Regression for Reservoir Inflow during Typhoon Periods
title_full A Forecasting Approach Combining Self-Organizing Map with Support Vector Regression for Reservoir Inflow during Typhoon Periods
title_fullStr A Forecasting Approach Combining Self-Organizing Map with Support Vector Regression for Reservoir Inflow during Typhoon Periods
title_full_unstemmed A Forecasting Approach Combining Self-Organizing Map with Support Vector Regression for Reservoir Inflow during Typhoon Periods
title_short A Forecasting Approach Combining Self-Organizing Map with Support Vector Regression for Reservoir Inflow during Typhoon Periods
title_sort forecasting approach combining self organizing map with support vector regression for reservoir inflow during typhoon periods
url http://dx.doi.org/10.1155/2016/7575126
work_keys_str_mv AT gwofonglin aforecastingapproachcombiningselforganizingmapwithsupportvectorregressionforreservoirinflowduringtyphoonperiods
AT tsungchunwang aforecastingapproachcombiningselforganizingmapwithsupportvectorregressionforreservoirinflowduringtyphoonperiods
AT luhsienchen aforecastingapproachcombiningselforganizingmapwithsupportvectorregressionforreservoirinflowduringtyphoonperiods
AT gwofonglin forecastingapproachcombiningselforganizingmapwithsupportvectorregressionforreservoirinflowduringtyphoonperiods
AT tsungchunwang forecastingapproachcombiningselforganizingmapwithsupportvectorregressionforreservoirinflowduringtyphoonperiods
AT luhsienchen forecastingapproachcombiningselforganizingmapwithsupportvectorregressionforreservoirinflowduringtyphoonperiods