A novel approach for prediction of daily streamflow discharge data using correlation based feature selection and random forest method

The accurate methods for the forecasting of hydrological characteristics are significantly important water resource management and environmental aspects. In this study, a novel approach daily streamflow discharge data is proposed. Streamflow discharge, temperature, precipitation were used feature extraction which systematically employed studies. While correlation-based selection (CFS) was selection, Random Forest (RF) model following 7 days. Moreover, an accuracy comparison between RF CFS-RF drawn by using data. Acquired results confirmed both, middle extended times compared to had similar values closer times. proved be much robust durations.