Reply on AC2

Abstract

The alteration in river flow patterns, particularly those that originate in the Himalayas, has been caused by the increased temperature and rainfall variability brought on by climate change. Due to the impending intensification of extreme climate events, as predicted by the Intergovernmental Panel on Climate Change (IPCC) in its sixth assessment report, it is more essential than ever to predict changes in streamflow for future periods. Despite the fact that some research has utilised machine learning-based models to predict streamflow patterns in response to climate change, very few studies have been undertaken for a mountainous catchment, with the number of studies for the western Himalaya being so small as to be considered insignificant. This study investigates the capability of different machine learning (ML) models, including the Gaussian Linear Regression Model (GLM), Gaussian Generalized Additive Model (GAM), Multivariate Adaptive Regression Splines (MARS), Artificial Neural Network (ANN), and Random Forest (RF), in streamflow prediction over the Sutlej River Basin in western Himalaya during the periods 2041–2070 (2050s) and 2071–2100 (2080s) for two greenhouse gas trajectories (SSP245 and SSP585). Coupled Model Intercomparison Project Phase 6 (CMIP6) bias corrected data downscaled at grid resolution of 0.25°× 0.25° for 6 General Circulation Models (GCMs) were used for this purpose. Four different rainfall scenarios (R0, R1, R2, and R3) were applied to the models trained with daily data (1979–2009) at Kasol (the outlet of the basin) in order to better understand how catchment size and the geo-hydro-morphological aspects of the basin affect runoff. RF model with rainfall scenario R3 which outperformed other models during the training and testing period therefore was chosen to simulate streamflow in the Sutlej River in the 2050s and 2080s under the SSP245 and SSP585 scenarios. The mean ensemble of model results show that the mean annual streamflow of the Sutlej River is expected to rise between 2050s and 2080s by 5.51 to 6.04 % for SSP585 and by 6.65 to 6.75 % for SSP245. The seasonal streamflow also is expected to increase in the 2050s and 2080s under both emission scenarios, with the exception of the pre-monsoon, where a decline in streamflow is anticipated for SSP585 in the 2080s. However, under both the emission scenarios, there seemed to be significant variation in the streamflow simulations among the individual models for various time periods. It has been found that the pattern of this variability is highly correlated with the pattern of precipitation and temperature predicted by various GCMs for future emission scenarios. The present study will therefore assist in strategy planning for ensuring the sustainable use of water resources downstream by acquiring a knowledge of the nature and causes of unpredictable streamflow patterns.