Projection of Temperature and Precipitation using Multiple Linear Regression and Artificial Neural Network as a Downscaling Methodology for Upper Bhima Basin

Dattatray Kisan Rajmane, Milind L. Waikar

International Journal of Recent Technology and Engineering (IJRTE) · 24 September 2020

In one sentence. An ANN outperforms multiple linear regression for downscaling GCM temperature and precipitation projections over the Upper Bhima basin in India.

Abstract

Study of Climate change effect on water resources is very important for its effective management. Projection of temperature and precipitation can be performed by using General Circulation Model (GCM) outputs. GCM can make the projections of climate parameters with different emission scenarios at coarser scale. However hydrological models require climate parameters at smaller scale Downscaling technique is used for obtaining small scale climate variables from large scale variables of GCM outputs. In this study downscaling has been carried out by using Multiple Linear Regression (MLR) and Artificial Neural Network (ANN) techniques. Performance of MLR and ANN models has been evaluated considering Coefficient of determination value (R2). It has been observed that ANN performs better against MLR Model, showed the results that rainfall distribution pattern is varied, in monsoon season rainfall decreases while it increases in post monsoon period. Due to its good evaluation performance such techniques can be applicable for downscaling purpose.

Labels

Labels and summary are generated by Claude and reviewed weekly. Wrong? Edit this entry.