Open AccessMultivariate monthly water demand prediction using ensemble and gradient boosting machine learning techniques
Author(s) -
Paul Banda,
Mohammad Amir Hossain Bhuiyan,
Kevin Zhang,
Andy Song
Publication year - 2022
Publication title -
proceedings of the international conference on evolving cities
Language(s) - English
Resource type - Journals
ISSN - 2754-5768
DOI - 10.55066/proc-icec.2021.14
Subject(s) - gradient boosting , univariate , boosting (machine learning) , adaboost , computer science , ensemble learning , multivariate statistics , ensemble forecasting , curse of dimensionality , machine learning , dimensionality reduction , time series , predictive modelling , demand forecasting , random forest , artificial intelligence , econometrics , support vector machine , mathematics , operations research
Water management planning requires reliable and accurate water demand forecasting. Water demand prediction is affected by variables, such as climate, socio-economic, and demographic data. This paper investigates urban monthly average water demand prediction, using classical, ensemble, and gradient boosting-based machine learning models, using the available monthly water demand, climatic, economic, and demographic data. Three train-test data split schemes on water demand timeseries were considered to determine the effect of data size on water demand prediction. Sensitivity analysis was employed to reduce input feature dimensionality while maintaining model accuracy. A univariate timeseries (water demand only) produced R2 scores up to 0.91, which increased to 0.94 with the addition of calendar and climatic features. Increasing the training data size from 70% to 90% improved the RMSE and MAE scores by ensemble and gradient boosting methods, with the random forest and the AdaBoost models showing improvements of up to 69%. The sensitivity analysis revealed a successful input reduction scheme from a potential 17 input attributes to seven inputs. Gradient boosting models showed robust and faster execution time, especially with the increase in training data, which is attractive for medium-term urban water demand forecasting.