Streamflow prediction using machine learning approaches with different shared socioeconomic pathways (SSPs)

Streamflow prediction using machine learning approaches with different shared socioeconomic pathways (SSPs)

Streamflow prediction is crucial for effective water resource management and flood prediction. Therefore, this study aims to predict streamflow within the Klang river catchment. Two machine learning approaches, namely artificial neural network (ANN) and support vector machine (SVM), were employed to forecast streamflow within the Klang river catchment. The performance of each model was evaluated using mean absolute error (MAE), root mean square error (RMSE), and percentage error. SVM outperformed ANN in streamflow prediction, achieving the lowest values of MAE, RMSE and percentage error, recorded as 7.23, 9.03 and 19.24, respectively. The model was then used to run the future scenarios, under two shared socioeconomic pathways (SSPs), which are SSP2-4.5 and SSP5-8.5, from coupled model intercomparison project phase 6 (CMIP6). SSP5-8.5 displays greater fluctuations than SSP2-4.5. This heightened variability evident in SSP5-8.5 can be attributed to its premise of rapid population expansion, significant technological advancements, and inadequate measures to address environmental issues. Consequently, these factors contribute to more frequent occurrences of extreme climate events.