Assessing the Benefits of Nature-Inspired Algorithms for the Parameterization of ANN in the Prediction of Water Demand

Abstract

Accurate forecasting techniques for a stochastic pattern of water demand are essential for any city that faces high variability in climate factors and a shortage of water resources. This is the first research that assesses the impact of climatic factors on urban water demand in Iraq, which is one of the hottest countries in the world. We present a novel forecasting methodology that includes data preprocessing and an artificial neural network (ANN) model, which is integrated by a recently nature-inspired metaheuristic algorithm (marine predators algorithm (MPA)). The MPA-ANN algorithm will be compared with four different nature-inspired metaheuristic algorithms. Nine climatic factors were examined with different scenarios to simulate the monthly stochastic urban water demand over eleven years for Baghdad City, Iraq. The results reveal that: 1) precipitation, solar radiation, and dew point temperature are the most relevant factors to develop the models. 2) The ANN model becomes more accurate when it is used in combination with the MPA. 3) This methodology can accurately forecast the water demand considering the variability in climatic factors. These findings are of considerable significance to water utilities to plan, review, and compare the availability of freshwater resources and increase water requests (i.e., adaptation variability of climatic factors).