Evaluating Hybrid Models and Google Earth Engine for Predicting Climate Change Impacts on Runoff in the Kasilian Catchment, Northern Iran

Abstract

This study investigates the impact of climate change on annual rainfall and runoff of Kasilian catchment through two distinct approaches. Firstly, it utilizes hybrid models by integrating the Hydrologic Engineering Center's Hydrologic Modeling System (HEC-HMS) with Artificial Neural Networks (ANN), Support Vector Machines (SVM), Adaptive Neuro-Fuzzy Inference System (ANFIS), and Gene Expression Programming (GEP) separately, as well as employing the Long Ashton Research Station Weather Generator (LARS-WG). Secondly, it employs Google Earth Engine (GEE) to analyze changes in annual rainfall and runoff for the observed period, compensating for incomplete data from hydrometric and climatological stations. The results demonstrate that under the SSP585 scenario, from various climate models in LARS WG and when employing hybrid models, the median annual rainfall is projected to increase in the future compared to the base period, while the median annual runoff is expected to decrease due to rising temperatures and increased evapotranspiration. Consistent with these projections, GEE data from 1981 to 2023 also indicates an increase in annual rainfall and a decrease in annual runoff. Additionally, there is a reduction in annual erosion and sedimentation rates, attributed to the reduced capacity of runoff to transport sediment. These findings highlight the potential for more extreme rainfall events, increased annual precipitation, and a subsequent decrease in annual runoff and sediment yield in the Kasilian catchment, providing valuable insights for future water resource management and climate adaptation strategies in the region.