The increase in greenhouse gases in recent decades has upset the planet's climate balance, which is called the phenomenon of climate change. The most important consequences of climate change will be an increase in the average temperature of the Earth, an increase in climatic phenomena such as floods, hurricanes, hail, heat waves, rising sea levels, melting polar ice, and untimely colds. The purpose of this study is to model the consequences of climate change using EANN (emotional artificial neural network) on rainfall in Rasht. Rasht is the capital of Guilan province and is located in northern Iran and south of the Caspian Sea. The city of Rasht is located at 49 degrees and 36 minutes east longitude and 37 degrees and 16 minutes north latitude of the Greenwich meridian and its area is about 136 kilometers. In this research, 12 large-scale models of the General Circulation Model (GCM) were selected for downscaling and rainfall modeling in Rasht. Because these models are large-scale and have a low spatial resolution, the output of these models needs to be downscaled. Exponential downscaling is a function for obtaining local-scale climate data from large-scale GCMs. Also, since GCM data is subject to error, the QM (Quantile mapping) method is used to correct the error. The results of modeling with an emotional artificial neural network showed that this model has a better performance in predicting precipitation compared to other statistical methods such as a classical artificial neural network.
Anahtar Kelimeler: Climate Change, Quantile Mapping, Emotional Artificial Network, Precipitation