Forecasting Time Series Water Levels on Mekong River Using Machine Learning Models

Forecasting water levels on Mekong river is an important problem needed to be studied for flood warning. In this paper, we investigate the application to forecasting of daily water levels at Thakhek station on Mekong river using machine learning models such as LASSO, Random Forests and Support Vector Regression (SVR). Experimental results showed that SVR was able to achieve feasible results, the mean absolute error of SVR is 0.486(m) while the acceptable error of a flood forecast model required by the Mekong River Commission is between 0.5(m) and 0.75(m).