Learning from Multiple Models Using Artificial Intelligence to Improve Model Prediction Accuracies: Application to River Flows

Abstract

An investigation is presented in this paper to study the performance of Artificial Intelligence running Multiple Models (AIMM) using time series of river flows. This is a modelling strategy, which is formed by first running two Artificial Intelligence (AI) models: Support Vector Machine (SVM) and its hybrid with the Fire-Fly Algorithm (FFA) and they both form supervised learning at Level 1. The outputs of Level 1 models serve as inputs to another AI Model at Level 2. The AIMM strategy at Level 2 is run by Artificial Neural Network (MM-ANN) and this is compared with the Simple Averaging (MM-SA) of both inputs. The study of the performances of these models (SVM, SVM-FFA, MM-SA and MM-ANN) in the paper shows that the ability of SVM-FFA in matching observed values is significantly better than that of SVM and that of MM-ANN is considerably better than each SVM and/or SVM-FFA but the performances are deteriorated by using the MM-SA strategy. The results also show that the residuals of MM-ANN are less noisy than those shown by the models at Level 1 and those at Level 2 do not display any trend.