TY - JOUR

T1 - Improving Flood Forecasting in a Developing Country

T2 - A Comparative Study of Stepwise Multiple Linear Regression and Artificial Neural Network

AU - Latt, Zaw Zaw

AU - Wittenberg, Hartmut

PY - 2014/6

Y1 - 2014/6

N2 - Due to limited data sources, practical situations in most developing countries favor black-box models in real time operations. In a simple and robust approach, this study examines performances of stepwise multiple linear regression (SMLR) and artificial neural network (ANN) models, as tools for multi-step forecasting Chindwin River floods in northern Myanmar. Future river stages are modeled using past water levels and rainfall at the forecasting station as well as at the hydrologically connected upstream station. The developed models are calibrated with flood season data from 1990 to 2007 and validated with data from 2008 to 2011. Model performances are compared for 1- to 5-day ahead forecasts. With a high accuracy, both candidate models performed well for forecasting the full range of flood levels. The ANN models were superior to the SMLR models, particularly in predicting the extreme floods. Correlation analysis was found to be useful for determining the initial input variables. Contribution of upstream data to both models could improve the forecasting performance with higher R 2 values and lower errors. Considering the commonly available data in the region as primary predictors, the results would be useful for real time flood forecasting, avoiding the complexity of physical processes.

AB - Due to limited data sources, practical situations in most developing countries favor black-box models in real time operations. In a simple and robust approach, this study examines performances of stepwise multiple linear regression (SMLR) and artificial neural network (ANN) models, as tools for multi-step forecasting Chindwin River floods in northern Myanmar. Future river stages are modeled using past water levels and rainfall at the forecasting station as well as at the hydrologically connected upstream station. The developed models are calibrated with flood season data from 1990 to 2007 and validated with data from 2008 to 2011. Model performances are compared for 1- to 5-day ahead forecasts. With a high accuracy, both candidate models performed well for forecasting the full range of flood levels. The ANN models were superior to the SMLR models, particularly in predicting the extreme floods. Correlation analysis was found to be useful for determining the initial input variables. Contribution of upstream data to both models could improve the forecasting performance with higher R 2 values and lower errors. Considering the commonly available data in the region as primary predictors, the results would be useful for real time flood forecasting, avoiding the complexity of physical processes.

KW - Environmental planning

KW - Artificial neural network

KW - Flood forecast

KW - Rainfall

KW - Real time operation

KW - Stepwise regression

KW - Water level

UR - http://www.scopus.com/inward/record.url?scp=84901037108&partnerID=8YFLogxK

UR - https://www.mendeley.com/catalogue/1a8f3729-1f87-30d6-b14e-2e2407534976/

U2 - 10.1007/s11269-014-0600-8

DO - 10.1007/s11269-014-0600-8

M3 - Journal articles

AN - SCOPUS:84901037108

VL - 28

SP - 2109

EP - 2128

JO - Water Resources Management

JF - Water Resources Management

SN - 0920-4741

IS - 8

ER -