Predicting Discharges in Sewer Pipes Using an Integrated Long Short-Term Memory and Entropy A-TOPSIS Modeling Framework
Predicting discharges in sewage systems play an essential role in reducing sewer overflows and impacts on the environment and public health. Choosing a suitable model to predict discharges in these systems is essential to realizing these aforementioned goals. Long Short-Term Memory (LSTM) has been p...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2022-01-01
|
Series: | Water |
Subjects: | |
Online Access: | https://www.mdpi.com/2073-4441/14/3/300 |
_version_ | 1797484060882239488 |
---|---|
author | Lam Van Nguyen Hoese Michel Tornyeviadzi Dieu Tien Bui Razak Seidu |
author_facet | Lam Van Nguyen Hoese Michel Tornyeviadzi Dieu Tien Bui Razak Seidu |
author_sort | Lam Van Nguyen |
collection | DOAJ |
description | Predicting discharges in sewage systems play an essential role in reducing sewer overflows and impacts on the environment and public health. Choosing a suitable model to predict discharges in these systems is essential to realizing these aforementioned goals. Long Short-Term Memory (LSTM) has been proposed as a robust technique for predicting discharges in wastewater networks. This study explored the potential application of an LSTM model to predict discharges using 3-month data set in a sewer network in Ålesund city, Norway. Different sequence-to-sequence LSTMs were investigated using various input and output datasets. The impact of data aggregation (10-min and 30-min intervals) was examined and compared to original sensor data (5-min intervals) to evaluate the performance of the LSTM model. The results show that 50-neuron LSTM architecture performed better (MAPE = 0.09, RMSE = 0.0008, <i>R</i><sup>2</sup> = 0.8) in predicting discharges for the study area. The study indicates that using the same sequence length for the prior and the forecast can improve the effectiveness of the LSTM model. Based on the results, using a 10-min aggregated discharge dataset reduces energy consumption, transmission bandwidth, and storage capacity. Additionally, it improves prediction performance compared to an original 5-min interval data in Ålesund city. |
first_indexed | 2024-03-09T22:57:03Z |
format | Article |
id | doaj.art-57e7fdfc49ba40bc898d72527d842671 |
institution | Directory Open Access Journal |
issn | 2073-4441 |
language | English |
last_indexed | 2024-03-09T22:57:03Z |
publishDate | 2022-01-01 |
publisher | MDPI AG |
record_format | Article |
series | Water |
spelling | doaj.art-57e7fdfc49ba40bc898d72527d8426712023-11-23T18:09:20ZengMDPI AGWater2073-44412022-01-0114330010.3390/w14030300Predicting Discharges in Sewer Pipes Using an Integrated Long Short-Term Memory and Entropy A-TOPSIS Modeling FrameworkLam Van Nguyen0Hoese Michel Tornyeviadzi1Dieu Tien Bui2Razak Seidu3Smart Water and Environmental Engineering Group, Department of Ocean Operations and Civil Engineering, Faculty of Engineering, Norwegian University of Science and Technology, N-6025 Ålesund, NorwaySmart Water and Environmental Engineering Group, Department of Ocean Operations and Civil Engineering, Faculty of Engineering, Norwegian University of Science and Technology, N-6025 Ålesund, NorwayGIS Group, Department of Business and IT, University of South-Eastern Norway, Gullbringvegen 36, N-3800 Bø i Telemark, NorwaySmart Water and Environmental Engineering Group, Department of Ocean Operations and Civil Engineering, Faculty of Engineering, Norwegian University of Science and Technology, N-6025 Ålesund, NorwayPredicting discharges in sewage systems play an essential role in reducing sewer overflows and impacts on the environment and public health. Choosing a suitable model to predict discharges in these systems is essential to realizing these aforementioned goals. Long Short-Term Memory (LSTM) has been proposed as a robust technique for predicting discharges in wastewater networks. This study explored the potential application of an LSTM model to predict discharges using 3-month data set in a sewer network in Ålesund city, Norway. Different sequence-to-sequence LSTMs were investigated using various input and output datasets. The impact of data aggregation (10-min and 30-min intervals) was examined and compared to original sensor data (5-min intervals) to evaluate the performance of the LSTM model. The results show that 50-neuron LSTM architecture performed better (MAPE = 0.09, RMSE = 0.0008, <i>R</i><sup>2</sup> = 0.8) in predicting discharges for the study area. The study indicates that using the same sequence length for the prior and the forecast can improve the effectiveness of the LSTM model. Based on the results, using a 10-min aggregated discharge dataset reduces energy consumption, transmission bandwidth, and storage capacity. Additionally, it improves prediction performance compared to an original 5-min interval data in Ålesund city.https://www.mdpi.com/2073-4441/14/3/300time-series forecastingdischarge predictionsewer pipeLong Short-Term MemoryÅlesundNorway |
spellingShingle | Lam Van Nguyen Hoese Michel Tornyeviadzi Dieu Tien Bui Razak Seidu Predicting Discharges in Sewer Pipes Using an Integrated Long Short-Term Memory and Entropy A-TOPSIS Modeling Framework Water time-series forecasting discharge prediction sewer pipe Long Short-Term Memory Ålesund Norway |
title | Predicting Discharges in Sewer Pipes Using an Integrated Long Short-Term Memory and Entropy A-TOPSIS Modeling Framework |
title_full | Predicting Discharges in Sewer Pipes Using an Integrated Long Short-Term Memory and Entropy A-TOPSIS Modeling Framework |
title_fullStr | Predicting Discharges in Sewer Pipes Using an Integrated Long Short-Term Memory and Entropy A-TOPSIS Modeling Framework |
title_full_unstemmed | Predicting Discharges in Sewer Pipes Using an Integrated Long Short-Term Memory and Entropy A-TOPSIS Modeling Framework |
title_short | Predicting Discharges in Sewer Pipes Using an Integrated Long Short-Term Memory and Entropy A-TOPSIS Modeling Framework |
title_sort | predicting discharges in sewer pipes using an integrated long short term memory and entropy a topsis modeling framework |
topic | time-series forecasting discharge prediction sewer pipe Long Short-Term Memory Ålesund Norway |
url | https://www.mdpi.com/2073-4441/14/3/300 |
work_keys_str_mv | AT lamvannguyen predictingdischargesinsewerpipesusinganintegratedlongshorttermmemoryandentropyatopsismodelingframework AT hoesemicheltornyeviadzi predictingdischargesinsewerpipesusinganintegratedlongshorttermmemoryandentropyatopsismodelingframework AT dieutienbui predictingdischargesinsewerpipesusinganintegratedlongshorttermmemoryandentropyatopsismodelingframework AT razakseidu predictingdischargesinsewerpipesusinganintegratedlongshorttermmemoryandentropyatopsismodelingframework |