Application of Artificial Neural Networks for Predicting Small Urban-Reservoir Volumes: The Case of Torregrotta Town (Italy)
In the hydraulic construction field, approximated formulations have been widely used for calculating tank volumes. Identifying the proper water reservoir volumes is of crucial importance in order to not only satisfy water demand but also to avoid unnecessary waste in the construction phase. In this...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-05-01
|
| Series: | Water |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2073-4441/15/9/1747 |
| _version_ | 1797601638784958464 |
|---|---|
| author | Biagio Saya Carla Faraci |
| author_facet | Biagio Saya Carla Faraci |
| author_sort | Biagio Saya |
| collection | DOAJ |
| description | In the hydraulic construction field, approximated formulations have been widely used for calculating tank volumes. Identifying the proper water reservoir volumes is of crucial importance in order to not only satisfy water demand but also to avoid unnecessary waste in the construction phase. In this perspective, the planning and management of small reservoirs may have a positive impact on their spatial distribution and storage capacities. The purpose of this study is, therefore, to suggest an alternative approach to estimate the optimal volume of small urban reservoirs. In particular, an artificial neural network (ANN) is proposed to predict future water consumption as a function of certain environmental parameters, such as rainy days, temperature and the number of inhabitants. As the water demand is strongly influenced by such quantities, their future trend is recovered by means of the Copernicus Climate Change Service (C3S) over the next 10 years. Finally, based on ANN prediction of the future consumption requirements, the continuity equation applied to tanks was resolved through integral-discretization obtaining the time-series volume variation and the total number of crisis events. |
| first_indexed | 2024-03-11T04:04:11Z |
| format | Article |
| id | doaj.art-f80b5c1203b8422bb3d22c67b3664ece |
| institution | Directory Open Access Journal |
| issn | 2073-4441 |
| language | English |
| last_indexed | 2024-03-11T04:04:11Z |
| publishDate | 2023-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Water |
| spelling | doaj.art-f80b5c1203b8422bb3d22c67b3664ece2023-11-17T23:57:57ZengMDPI AGWater2073-44412023-05-01159174710.3390/w15091747Application of Artificial Neural Networks for Predicting Small Urban-Reservoir Volumes: The Case of Torregrotta Town (Italy)Biagio Saya0Carla Faraci1Department of Engineering, University of Messina, 98166 Messina, ItalyDepartment of Engineering, University of Messina, 98166 Messina, ItalyIn the hydraulic construction field, approximated formulations have been widely used for calculating tank volumes. Identifying the proper water reservoir volumes is of crucial importance in order to not only satisfy water demand but also to avoid unnecessary waste in the construction phase. In this perspective, the planning and management of small reservoirs may have a positive impact on their spatial distribution and storage capacities. The purpose of this study is, therefore, to suggest an alternative approach to estimate the optimal volume of small urban reservoirs. In particular, an artificial neural network (ANN) is proposed to predict future water consumption as a function of certain environmental parameters, such as rainy days, temperature and the number of inhabitants. As the water demand is strongly influenced by such quantities, their future trend is recovered by means of the Copernicus Climate Change Service (C3S) over the next 10 years. Finally, based on ANN prediction of the future consumption requirements, the continuity equation applied to tanks was resolved through integral-discretization obtaining the time-series volume variation and the total number of crisis events.https://www.mdpi.com/2073-4441/15/9/1747application of neural networkhydraulic supply systemurban reservoirs |
| spellingShingle | Biagio Saya Carla Faraci Application of Artificial Neural Networks for Predicting Small Urban-Reservoir Volumes: The Case of Torregrotta Town (Italy) Water application of neural network hydraulic supply system urban reservoirs |
| title | Application of Artificial Neural Networks for Predicting Small Urban-Reservoir Volumes: The Case of Torregrotta Town (Italy) |
| title_full | Application of Artificial Neural Networks for Predicting Small Urban-Reservoir Volumes: The Case of Torregrotta Town (Italy) |
| title_fullStr | Application of Artificial Neural Networks for Predicting Small Urban-Reservoir Volumes: The Case of Torregrotta Town (Italy) |
| title_full_unstemmed | Application of Artificial Neural Networks for Predicting Small Urban-Reservoir Volumes: The Case of Torregrotta Town (Italy) |
| title_short | Application of Artificial Neural Networks for Predicting Small Urban-Reservoir Volumes: The Case of Torregrotta Town (Italy) |
| title_sort | application of artificial neural networks for predicting small urban reservoir volumes the case of torregrotta town italy |
| topic | application of neural network hydraulic supply system urban reservoirs |
| url | https://www.mdpi.com/2073-4441/15/9/1747 |
| work_keys_str_mv | AT biagiosaya applicationofartificialneuralnetworksforpredictingsmallurbanreservoirvolumesthecaseoftorregrottatownitaly AT carlafaraci applicationofartificialneuralnetworksforpredictingsmallurbanreservoirvolumesthecaseoftorregrottatownitaly |