Amirkabir University of Technology Amirkabir Journal of Civil Engineering 2588-297X 52 4 2020 06 21 The conjunction of the feature extraction method with AI-based ensemble statistical downscaling models The conjunction of the feature extraction method with AI-based ensemble statistical downscaling models 841 858 3173 10.22060/ceej.2018.14986.5806 FA Zahra Razzaghzadeh civil engineer, faculty of civil engineering, Tabriz university, Tabriz, Iran Vahid Nourani water resource management, factuly of civil engineering, university of Tabriz, Tabriz,Iran Nazanin Behfar water resource management, faculty of civil engineering, university of Tabriz, Tabriz, Iran 0000-0002-8211-4006 Journal Article 2018 09 15 In this study, two general circulation models (GCMs) (Can-ESM2, BNU-ESM) were used to simulate the future precipitation of Tabriz city. The weakness of GCMs is the coarse resolution of climate variables in which the different methods of downscaling is about to solve this deficiency. In this study, the Artificial Intelligence (AI) models, i.e., Artificial Neural Network (ANN) and Adaptive neuro-fuzzy inference system (ANFIS), were used to statistically downscale the climate variables of GCMs. Without any doubt, the most important step during the use of these models is selecting the dominant inputs among huge large-scale GCM data. So in this study for the selection of dominant inputs, decision tree, and mutual information (MI) feature extraction methods were used. Also, the ensemble techniques were used to evaluate the efficiency of downscaling models and to decrease the uncertainties. A comparison of the result of downscaling models indicated that the ensemble technique (i.e., hybrid of ANN and ANFIS) with dominant inputs based on decision tree feature extraction methods presents better performance. In both GCMs, the application of the downscaling ensemble couple with dominant predictors based on a decision tree model in precipitation downscaling showed 10%-38% increase in DC in versus the individual ANN and ANFIS downscaling models. The projection precipitation of Tabriz synoptic station for future (2020-2060) by proposed ensemble AI-based model indicated 30%-40% precipitation decreases under RCP4.5 and RCP8.5 scenarios. In this study, two general circulation models (GCMs) (Can-ESM2, BNU-ESM) were used to simulate the future precipitation of Tabriz city. The weakness of GCMs is the coarse resolution of climate variables in which the different methods of downscaling is about to solve this deficiency. In this study, the Artificial Intelligence (AI) models, i.e., Artificial Neural Network (ANN) and Adaptive neuro-fuzzy inference system (ANFIS), were used to statistically downscale the climate variables of GCMs. Without any doubt, the most important step during the use of these models is selecting the dominant inputs among huge large-scale GCM data. So in this study for the selection of dominant inputs, decision tree, and mutual information (MI) feature extraction methods were used. Also, the ensemble techniques were used to evaluate the efficiency of downscaling models and to decrease the uncertainties. A comparison of the result of downscaling models indicated that the ensemble technique (i.e., hybrid of ANN and ANFIS) with dominant inputs based on decision tree feature extraction methods presents better performance. In both GCMs, the application of the downscaling ensemble couple with dominant predictors based on a decision tree model in precipitation downscaling showed 10%-38% increase in DC in versus the individual ANN and ANFIS downscaling models. The projection precipitation of Tabriz synoptic station for future (2020-2060) by proposed ensemble AI-based model indicated 30%-40% precipitation decreases under RCP4.5 and RCP8.5 scenarios. https://ceej.aut.ac.ir/article_3173_e8258e5140317ff36c7f8225a3bf9590.pdf