A Data-Driven Surrogate Modelling Approach for Acceleration of Short-Term Simulations of a Dynamic Urban Drainage Simulator
In this study, applicability of a data-driven Gaussian Process Emulator (GPE) technique to develop a dynamic surrogate model for a computationally expensive urban drainage simulator is investigated. Considering rainfall time series as the main driving force is a challenge in this regard due to the h...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2018-12-01
|
Series: | Water |
Subjects: | |
Online Access: | https://www.mdpi.com/2073-4441/10/12/1849 |
_version_ | 1811256688728080384 |
---|---|
author | Mahmood Mahmoodian Jairo Arturo Torres-Matallana Ulrich Leopold Georges Schutz Francois H. L. R. Clemens |
author_facet | Mahmood Mahmoodian Jairo Arturo Torres-Matallana Ulrich Leopold Georges Schutz Francois H. L. R. Clemens |
author_sort | Mahmood Mahmoodian |
collection | DOAJ |
description | In this study, applicability of a data-driven Gaussian Process Emulator (GPE) technique to develop a dynamic surrogate model for a computationally expensive urban drainage simulator is investigated. Considering rainfall time series as the main driving force is a challenge in this regard due to the high dimensionality problem. However, this problem can be less relevant when the focus is only on short-term simulations. The novelty of this research is the consideration of short-term rainfall time series as training parameters for the GPE. Rainfall intensity at each time step is counted as a separate parameter. A method to generate synthetic rainfall events for GPE training purposes is introduced as well. Here, an emulator is developed to predict the upcoming daily time series of the total wastewater volume in a storage tank and the corresponding Combined Sewer Overflow (CSO) volume. Nash-Sutcliffe Efficiency (<i>NSE</i>) and Volumetric Efficiency (<i>VE</i>) are calculated as emulation error indicators. For the case study herein, the emulator is able to speed up the simulations up to 380 times with a low accuracy cost for prediction of the total storage tank volume (medians of <i>NSE</i> = 0.96 and <i>VE</i> = 0.87). CSO events occurrence is detected in 82% of the cases, although with some considerable accuracy cost (medians of <i>NSE</i> = 0.76 and <i>VE</i> = 0.5). Applicability of the emulator for consecutive short-term simulations, based on real observed rainfall time series is also validated with a high accuracy (<i>NSE</i> = 0.97, <i>VE</i> = 0.89). |
first_indexed | 2024-04-12T17:45:03Z |
format | Article |
id | doaj.art-316915e7bb4b48cc8e2e0d8cf49cc4c6 |
institution | Directory Open Access Journal |
issn | 2073-4441 |
language | English |
last_indexed | 2024-04-12T17:45:03Z |
publishDate | 2018-12-01 |
publisher | MDPI AG |
record_format | Article |
series | Water |
spelling | doaj.art-316915e7bb4b48cc8e2e0d8cf49cc4c62022-12-22T03:22:42ZengMDPI AGWater2073-44412018-12-011012184910.3390/w10121849w10121849A Data-Driven Surrogate Modelling Approach for Acceleration of Short-Term Simulations of a Dynamic Urban Drainage SimulatorMahmood Mahmoodian0Jairo Arturo Torres-Matallana1Ulrich Leopold2Georges Schutz3Francois H. L. R. Clemens4Environmental Informatics Group, ERIN Department, Luxembourg Institute of Science and Technology (LIST), L-4422 Belvaux, LuxembourgEnvironmental Informatics Group, ERIN Department, Luxembourg Institute of Science and Technology (LIST), L-4422 Belvaux, LuxembourgEnvironmental Informatics Group, ERIN Department, Luxembourg Institute of Science and Technology (LIST), L-4422 Belvaux, LuxembourgRTC4Water, L-4362 Belval, LuxembourgSanitary Engineering Section, Water Management Department, Faculty of Civil Engineering and Geosciences, Delft University of Technology, 2628 CN Delft, The NetherlandsIn this study, applicability of a data-driven Gaussian Process Emulator (GPE) technique to develop a dynamic surrogate model for a computationally expensive urban drainage simulator is investigated. Considering rainfall time series as the main driving force is a challenge in this regard due to the high dimensionality problem. However, this problem can be less relevant when the focus is only on short-term simulations. The novelty of this research is the consideration of short-term rainfall time series as training parameters for the GPE. Rainfall intensity at each time step is counted as a separate parameter. A method to generate synthetic rainfall events for GPE training purposes is introduced as well. Here, an emulator is developed to predict the upcoming daily time series of the total wastewater volume in a storage tank and the corresponding Combined Sewer Overflow (CSO) volume. Nash-Sutcliffe Efficiency (<i>NSE</i>) and Volumetric Efficiency (<i>VE</i>) are calculated as emulation error indicators. For the case study herein, the emulator is able to speed up the simulations up to 380 times with a low accuracy cost for prediction of the total storage tank volume (medians of <i>NSE</i> = 0.96 and <i>VE</i> = 0.87). CSO events occurrence is detected in 82% of the cases, although with some considerable accuracy cost (medians of <i>NSE</i> = 0.76 and <i>VE</i> = 0.5). Applicability of the emulator for consecutive short-term simulations, based on real observed rainfall time series is also validated with a high accuracy (<i>NSE</i> = 0.97, <i>VE</i> = 0.89).https://www.mdpi.com/2073-4441/10/12/1849surrogate modeldata-drivenGaussian processemulatorurban drainage |
spellingShingle | Mahmood Mahmoodian Jairo Arturo Torres-Matallana Ulrich Leopold Georges Schutz Francois H. L. R. Clemens A Data-Driven Surrogate Modelling Approach for Acceleration of Short-Term Simulations of a Dynamic Urban Drainage Simulator Water surrogate model data-driven Gaussian process emulator urban drainage |
title | A Data-Driven Surrogate Modelling Approach for Acceleration of Short-Term Simulations of a Dynamic Urban Drainage Simulator |
title_full | A Data-Driven Surrogate Modelling Approach for Acceleration of Short-Term Simulations of a Dynamic Urban Drainage Simulator |
title_fullStr | A Data-Driven Surrogate Modelling Approach for Acceleration of Short-Term Simulations of a Dynamic Urban Drainage Simulator |
title_full_unstemmed | A Data-Driven Surrogate Modelling Approach for Acceleration of Short-Term Simulations of a Dynamic Urban Drainage Simulator |
title_short | A Data-Driven Surrogate Modelling Approach for Acceleration of Short-Term Simulations of a Dynamic Urban Drainage Simulator |
title_sort | data driven surrogate modelling approach for acceleration of short term simulations of a dynamic urban drainage simulator |
topic | surrogate model data-driven Gaussian process emulator urban drainage |
url | https://www.mdpi.com/2073-4441/10/12/1849 |
work_keys_str_mv | AT mahmoodmahmoodian adatadrivensurrogatemodellingapproachforaccelerationofshorttermsimulationsofadynamicurbandrainagesimulator AT jairoarturotorresmatallana adatadrivensurrogatemodellingapproachforaccelerationofshorttermsimulationsofadynamicurbandrainagesimulator AT ulrichleopold adatadrivensurrogatemodellingapproachforaccelerationofshorttermsimulationsofadynamicurbandrainagesimulator AT georgesschutz adatadrivensurrogatemodellingapproachforaccelerationofshorttermsimulationsofadynamicurbandrainagesimulator AT francoishlrclemens adatadrivensurrogatemodellingapproachforaccelerationofshorttermsimulationsofadynamicurbandrainagesimulator AT mahmoodmahmoodian datadrivensurrogatemodellingapproachforaccelerationofshorttermsimulationsofadynamicurbandrainagesimulator AT jairoarturotorresmatallana datadrivensurrogatemodellingapproachforaccelerationofshorttermsimulationsofadynamicurbandrainagesimulator AT ulrichleopold datadrivensurrogatemodellingapproachforaccelerationofshorttermsimulationsofadynamicurbandrainagesimulator AT georgesschutz datadrivensurrogatemodellingapproachforaccelerationofshorttermsimulationsofadynamicurbandrainagesimulator AT francoishlrclemens datadrivensurrogatemodellingapproachforaccelerationofshorttermsimulationsofadynamicurbandrainagesimulator |