A Downscaling Model Based on K-nearestneighbor(K-NN) Non-parametric Method

Document Type : Research Article

Authors

• H. Seyyed Kaboli
• A.M. AkhodAli
• A.R. Masah Bavani
• F. Radmanesh

https://doi.org/10.22067/jsw.v0i0.15232

Abstract

General Circulation Models (GCMs) have been identifiedas asuitable tool for studying climate change. Butthese models simulate climatic parametersinthe large-scale which has poor performance in the simulation of processes such asrain fall-run off. There fore, several of down scaling methods were developed. This researchis presented down scaling model based onk-nearest neighbor (K-NN) non-parametric method. The modelis used to simulate daily precipitation data in Ahvaz station for the next period (2015-2044) under climate change scenarios based on out puts of three General Circulation Models, including HADCM3, NCARPC Mand CSIROMK3.5. The results indicate that them odelhasa high capacity for down scaling data. It is predicted that the frequency of storm is increased with high intensity on future period in Ahvaz station while dry spells will be prolonged.

Keywords

• Climate change
• K-NN
• Downscaling
• Atmosphere-Ocean General Circulation Models (AOGCM)