Assessment of ERA5-Land Data in Medium-Term Drinking Water Demand Modelling with Deep Learning
Drinking water demand modelling and forecasting is a crucial task for sustainable management and planning of water supply systems. Despite many short-term investigations, the medium-term problem needs better exploration, particularly the analysis and assessment of meteorological data for forecasting...
Main Authors: | , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2023-04-01
|
Series: | Water |
Subjects: | |
Online Access: | https://www.mdpi.com/2073-4441/15/8/1495 |
_version_ | 1797603175076724736 |
---|---|
author | Pranav Dhawan Daniele Dalla Torre Ariele Zanfei Andrea Menapace Michele Larcher Maurizio Righetti |
author_facet | Pranav Dhawan Daniele Dalla Torre Ariele Zanfei Andrea Menapace Michele Larcher Maurizio Righetti |
author_sort | Pranav Dhawan |
collection | DOAJ |
description | Drinking water demand modelling and forecasting is a crucial task for sustainable management and planning of water supply systems. Despite many short-term investigations, the medium-term problem needs better exploration, particularly the analysis and assessment of meteorological data for forecasting drinking water demand. This work proposes to analyse the suitability of ERA5-Land reanalysis data as weather input in water demand modelling. A multivariate deep learning model based on the long short-term memory architecture is used in this study over a prediction horizon ranging from seven days to two months. The performance of the model, fed by ground station data and ERA5-Land data, is compared and analysed. Close-to-operative forecasting is then presented using observed data for training and ERA5-Land dataset for testing. The results highlight the reliability of the proposed architecture fed by ERA5-Land data for different time horizons. In particular, the ERA5-Land shows promising performance as input of the multivariate machine learning forecasting model, although some meteorological biases are present, which can be improved, especially in close-to-operative application with bias correction techniques. The proposed study leads to practical implications in the use of regional climate model outputs to support drinking water forecasting for sustainable and efficient management of water distribution systems. |
first_indexed | 2024-03-11T04:26:41Z |
format | Article |
id | doaj.art-f6483070e2554d4aa36bb325a26e3bb5 |
institution | Directory Open Access Journal |
issn | 2073-4441 |
language | English |
last_indexed | 2024-03-11T04:26:41Z |
publishDate | 2023-04-01 |
publisher | MDPI AG |
record_format | Article |
series | Water |
spelling | doaj.art-f6483070e2554d4aa36bb325a26e3bb52023-11-17T21:47:58ZengMDPI AGWater2073-44412023-04-01158149510.3390/w15081495Assessment of ERA5-Land Data in Medium-Term Drinking Water Demand Modelling with Deep LearningPranav Dhawan0Daniele Dalla Torre1Ariele Zanfei2Andrea Menapace3Michele Larcher4Maurizio Righetti5Faculty of Engineering, Free University of Bozen-Bolzano, Piazza Università 1, 39100 Bolzano, ItalyFaculty of Engineering, Free University of Bozen-Bolzano, Piazza Università 1, 39100 Bolzano, ItalyFaculty of Engineering, Free University of Bozen-Bolzano, Piazza Università 1, 39100 Bolzano, ItalyFaculty of Engineering, Free University of Bozen-Bolzano, Piazza Università 1, 39100 Bolzano, ItalyFaculty of Engineering, Free University of Bozen-Bolzano, Piazza Università 1, 39100 Bolzano, ItalyFaculty of Engineering, Free University of Bozen-Bolzano, Piazza Università 1, 39100 Bolzano, ItalyDrinking water demand modelling and forecasting is a crucial task for sustainable management and planning of water supply systems. Despite many short-term investigations, the medium-term problem needs better exploration, particularly the analysis and assessment of meteorological data for forecasting drinking water demand. This work proposes to analyse the suitability of ERA5-Land reanalysis data as weather input in water demand modelling. A multivariate deep learning model based on the long short-term memory architecture is used in this study over a prediction horizon ranging from seven days to two months. The performance of the model, fed by ground station data and ERA5-Land data, is compared and analysed. Close-to-operative forecasting is then presented using observed data for training and ERA5-Land dataset for testing. The results highlight the reliability of the proposed architecture fed by ERA5-Land data for different time horizons. In particular, the ERA5-Land shows promising performance as input of the multivariate machine learning forecasting model, although some meteorological biases are present, which can be improved, especially in close-to-operative application with bias correction techniques. The proposed study leads to practical implications in the use of regional climate model outputs to support drinking water forecasting for sustainable and efficient management of water distribution systems.https://www.mdpi.com/2073-4441/15/8/1495water distribution systemsdrinking water demandmedium-term forecastingregional climate modelsdeep learning |
spellingShingle | Pranav Dhawan Daniele Dalla Torre Ariele Zanfei Andrea Menapace Michele Larcher Maurizio Righetti Assessment of ERA5-Land Data in Medium-Term Drinking Water Demand Modelling with Deep Learning Water water distribution systems drinking water demand medium-term forecasting regional climate models deep learning |
title | Assessment of ERA5-Land Data in Medium-Term Drinking Water Demand Modelling with Deep Learning |
title_full | Assessment of ERA5-Land Data in Medium-Term Drinking Water Demand Modelling with Deep Learning |
title_fullStr | Assessment of ERA5-Land Data in Medium-Term Drinking Water Demand Modelling with Deep Learning |
title_full_unstemmed | Assessment of ERA5-Land Data in Medium-Term Drinking Water Demand Modelling with Deep Learning |
title_short | Assessment of ERA5-Land Data in Medium-Term Drinking Water Demand Modelling with Deep Learning |
title_sort | assessment of era5 land data in medium term drinking water demand modelling with deep learning |
topic | water distribution systems drinking water demand medium-term forecasting regional climate models deep learning |
url | https://www.mdpi.com/2073-4441/15/8/1495 |
work_keys_str_mv | AT pranavdhawan assessmentofera5landdatainmediumtermdrinkingwaterdemandmodellingwithdeeplearning AT danieledallatorre assessmentofera5landdatainmediumtermdrinkingwaterdemandmodellingwithdeeplearning AT arielezanfei assessmentofera5landdatainmediumtermdrinkingwaterdemandmodellingwithdeeplearning AT andreamenapace assessmentofera5landdatainmediumtermdrinkingwaterdemandmodellingwithdeeplearning AT michelelarcher assessmentofera5landdatainmediumtermdrinkingwaterdemandmodellingwithdeeplearning AT mauriziorighetti assessmentofera5landdatainmediumtermdrinkingwaterdemandmodellingwithdeeplearning |