WATER CONSUMPTION PREDICTION USING MACHINE LEARNING: THE CASE OF HAWASSA CITY WATER SUPPLY AND SEWAGE SERVICE ENTERPRISE

Abstract

Proper management of water consumption ensures a better clean and healthy community. Therefore, predicting water consumption gives time to prepare and protect the community from unseen natural or unknown disasters. Previous studies have implemented many prediction models in specific areas that showed promise but were not applicable in developing countries. The study was conducted to develop a prediction model for water consumption for the Hawassa City Water Supply and Sewerage Service Enterprise (HCWSSSE), a city in the Sidama region, Ethiopia. The enterprise experienced water shortages due to its way of prediction solely based on the previous month's consumption rate and needed to consider seasonal changes. The models developed in the study use machine learning techniques on five-year Monthly Consumption data from 2009-2015 E.C of the Ethiopian budget year, with around 16012 data points, and modeled by training 80%, validating 10%, and testing 10%. This study explores the application of various machine learning algorithms including Random Forest (RF), Support Vector Regressor (SVR), Linear Regression (LR), and XGBoost for predicting. The performance of models was evaluated using key error evaluation metrics Mean Squared Error (MSE), Mean Absolute Error (MAE), Root Mean Squared Error (RMSE), and R-squared (R²). For the Models, their R2 rates for training, validation, and testing were Random Forest (RF) 97.23%, 97.24%, and 97.22%, Linear Regression (LR) 78.18%, 78.38%, and 77.98%, Support Vector Regressor (SVR) 79.37%, 79.92%, and 78.81% and XGBoost 97.08%, 97.07%, and 97.08% respectively. The Random Forest (RF) and XGBoost showed promise in prediction, they demonstrated effectiveness in handling complex datasets. Specifically, Random Forest (RF) offered better predictions with reduced risk of overfitting. The successful application of RF and XGBoost highlights the importance of leveraging machine learning for sustainable water management in an era of growing demand and climate variability.