Predictive Model for Short-Term Water Demand Forecasting and Feature Analysis in Urban Networks

Variability in water use and user characteristics influences the operational management of water distribution systems (WDS). Types of water use and external factors including socioeconomic characteristics and weather variables can affect the normal operation of WDS. Accurate demand prediction is cru...

Full description

Saved in:
Bibliographic Details
Main Authors: Jorge E. Pesantez, Morgan DiCarlo, Fayzul Pasha, Emily Z. Berglund
Format: Article
Language:English
Published: MDPI AG 2024-09-01
Series:Engineering Proceedings
Subjects:
Online Access:https://www.mdpi.com/2673-4591/69/1/155
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850089545995911168
author Jorge E. Pesantez
Morgan DiCarlo
Fayzul Pasha
Emily Z. Berglund
author_facet Jorge E. Pesantez
Morgan DiCarlo
Fayzul Pasha
Emily Z. Berglund
author_sort Jorge E. Pesantez
collection DOAJ
description Variability in water use and user characteristics influences the operational management of water distribution systems (WDS). Types of water use and external factors including socioeconomic characteristics and weather variables can affect the normal operation of WDS. Accurate demand prediction is crucial, yet existing methods lack industry-wide comparability. This study applies a supervised learning model, IONET, that utilizes feedforward neural networks for short-term demand forecasting. IONET incorporates lagged demand, seasonal predictors, and weather variables. Tested on Italian DMA data, it swiftly produces accurate forecasts across various horizons. Feature importance analysis underscores the significance of seasonal variables and lagged demand. The IONET model offers prompt training and valuable insights for optimizing WDS management, facilitating the digital transformation of water infrastructure.
format Article
id doaj-art-a88ec937cc6c439e85c2aa89a8a95e1a
institution DOAJ
issn 2673-4591
language English
publishDate 2024-09-01
publisher MDPI AG
record_format Article
series Engineering Proceedings
spelling doaj-art-a88ec937cc6c439e85c2aa89a8a95e1a2025-08-20T02:42:45ZengMDPI AGEngineering Proceedings2673-45912024-09-0169115510.3390/engproc2024069155Predictive Model for Short-Term Water Demand Forecasting and Feature Analysis in Urban NetworksJorge E. Pesantez0Morgan DiCarlo1Fayzul Pasha2Emily Z. Berglund3Department of Civil and Geomatics Engineering, California State University Fresno, Fresno, CA 93740, USAAmerican Association for the Advancement of Science Fellowship Programs, Washington, DC 20005, USADepartment of Civil and Geomatics Engineering, California State University Fresno, Fresno, CA 93740, USADepartment of Civil, Construction, and Environmental Engineering, North Carolina State University, Raleigh, NC 27606, USAVariability in water use and user characteristics influences the operational management of water distribution systems (WDS). Types of water use and external factors including socioeconomic characteristics and weather variables can affect the normal operation of WDS. Accurate demand prediction is crucial, yet existing methods lack industry-wide comparability. This study applies a supervised learning model, IONET, that utilizes feedforward neural networks for short-term demand forecasting. IONET incorporates lagged demand, seasonal predictors, and weather variables. Tested on Italian DMA data, it swiftly produces accurate forecasts across various horizons. Feature importance analysis underscores the significance of seasonal variables and lagged demand. The IONET model offers prompt training and valuable insights for optimizing WDS management, facilitating the digital transformation of water infrastructure.https://www.mdpi.com/2673-4591/69/1/155water demand managementartificial neural networksdemand forecastingDistrict Metering Areas
spellingShingle Jorge E. Pesantez
Morgan DiCarlo
Fayzul Pasha
Emily Z. Berglund
Predictive Model for Short-Term Water Demand Forecasting and Feature Analysis in Urban Networks
Engineering Proceedings
water demand management
artificial neural networks
demand forecasting
District Metering Areas
title Predictive Model for Short-Term Water Demand Forecasting and Feature Analysis in Urban Networks
title_full Predictive Model for Short-Term Water Demand Forecasting and Feature Analysis in Urban Networks
title_fullStr Predictive Model for Short-Term Water Demand Forecasting and Feature Analysis in Urban Networks
title_full_unstemmed Predictive Model for Short-Term Water Demand Forecasting and Feature Analysis in Urban Networks
title_short Predictive Model for Short-Term Water Demand Forecasting and Feature Analysis in Urban Networks
title_sort predictive model for short term water demand forecasting and feature analysis in urban networks
topic water demand management
artificial neural networks
demand forecasting
District Metering Areas
url https://www.mdpi.com/2673-4591/69/1/155
work_keys_str_mv AT jorgeepesantez predictivemodelforshorttermwaterdemandforecastingandfeatureanalysisinurbannetworks
AT morgandicarlo predictivemodelforshorttermwaterdemandforecastingandfeatureanalysisinurbannetworks
AT fayzulpasha predictivemodelforshorttermwaterdemandforecastingandfeatureanalysisinurbannetworks
AT emilyzberglund predictivemodelforshorttermwaterdemandforecastingandfeatureanalysisinurbannetworks