An Artificial Neural Network Based Runoff Forecasting Model in the Absence of Precipitation Data: A Case Study of Khlong U-Tapao River Basin, Songkhla Province, Thailand

This paper develops and evaluates an artificial neural network (ANN) based runoff forecasting model for river basins without good-quality precipitation data. The study area is Khlong U-Tapao River Basin, Songkhla Province, Thailand. ANNs were developed separately for Ban Takienphao and Ban Muangkong hydrological stations. Inputs for ANNs include observed water levels from upstream stations at different times at least 12 hours ahead of the forecast time. The 12-hour forecast accuracy was evaluated by using data from year 2008 for training and data from year 2009 for evaluation, and vice versa. Results show good forecast accuracy. Correlation coefficients between forecasted and observed water levels for Ban Takienphao station are higher than 0.92 and rms errors are within 1.92% of the annual mean water level. Correlation coefficients for Ban Muangkong station are higher than 0.86 and rms errors are within 6.67% of the annual mean water level.