A Data-Driven Surrogate Modelling Approach for Acceleration of Short-Term Simulations of a Dynamic Urban Drainage Simulator

Mahmoodian, Mahmood; Torres-Matallana, Jairo Arturo; Leopold, Ulrich; Schutz, Georges; Clemens, F.H.L.R.

doi:10.3390/w10121849

Cited by 6 publications

(3 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Once the surrogate model is calibrated and validated, the input variables can be directly fed into it to generate the model outcomes within faster computational time. These outcomes are invoked as the multi-objective optimization functions and the set of condition constraints (Mahmoodian et al, 2018;Song et al, 2018).…”

Section: Insert Figure 2 Insert Table 1 42 Surrogate Machine Learningmentioning

confidence: 99%

Integrative Evolutionary-Based Method for Modeling and Optimizing Budget Assignment of Bridge Maintenance Priorities

Abdelkader

Moselhi

Marzouk

et al. 2021

J. Constr. Eng. Manage.

View full text Add to dashboard Cite

Recently, the number of deteriorating bridges has drastically increased. As such, enormous amount of resources are invested yearly to maintain the performance of bridges within acceptable levels. This entails the development of bridge management systems to manage the imbalance between the extensive needs for maintenance, repair and rehabilitation actions, and the limited available funds. In this regard, the present study introduces three-tier platform to model and allocate limited resources in bridge deck replacement projects. The first model involves building a discrete event simulation model to mimic the bridge deck replacement process. The second encompasses structuring an efficient and straightforward surrogate machine learning model for mimicking the computationally expensive discrete event simulation model. In the second phase, a novel hybrid Elman neural network-Invasive weed optimization model is developed for predicting time, cost, greenhouse gases and utilization rates of resource allocation plans using database generated from the previous model. The third constitutes formulation of a multi-objective differential evolution optimization model subject to the utilization rates of the involved resources and their dispersion. Results manifest superiority in cost prediction accuracies; achieving mean absolute percentage error, mean absolute error and root-mean squared error of 4.873%, 78.466 and 39.515, respectively. Additionally, the developed multiobjective optimization model significantly outperformed a set well-performing meta-heuristics;

show abstract

Section: Insert Figure 2 Insert Table 1 42 Surrogate Machine Learningmentioning

confidence: 99%

Integrative Evolutionary-Based Method for Modeling and Optimizing Budget Assignment of Bridge Maintenance Priorities

Abdelkader

Moselhi

Marzouk

et al. 2021

J. Constr. Eng. Manage.

View full text Add to dashboard Cite

show abstract

“…A possible solution to this problem is to replace the simulation of the system dynamics with computationally cheaper surrogate models. These include the Gaussian process emulator (Mahmoodian, Torres‐Matallana, et al., 2018; Owen & Liuzzo, 2019), artificial neural networks (ANNs; Kim et al., 2019; Latifi et al., 2019; Sayers et al., 2014, 2019; Seyedashraf, Mehrabi, et al., 2018; Yazdi & Salehi Neyshabouri, 2014), or conceptual models with simplified structures that mimic specific outputs of the real system (Mahmoodian, Carbajal, et al., 2018; Mahmoodian, Torres‐Matallana, et al., 2018).…”

Section: Introductionmentioning

confidence: 99%

A Disaggregation‐Emulation Approach for Optimization of Large Urban Drainage Systems

Seyedashraf

Bottacin‐Busolin

Harou

2021

Water Resources Research

View full text Add to dashboard Cite

Multi‐objective optimization can help identify efficient and appealing designs of urban drainage systems. However, their application to large‐scale problems is hindered by the computational cost of urban drainage simulation. We propose a novel disaggregation approach that allows simulating a portion of a drainage network while the remaining part is represented by a surrogate model that maps changes in the region of interest to hydraulic head time‐series at synthetic nodes shared with the remaining part of the network. The proposed approach is demonstrated with an application to the many‐objective optimization of sustainable urban drainage systems in two urban areas. The design problem's decision variables include the types of sustainable drainage systems, their combination within a subcatchment, their surface areas and spatial distribution, whereas the objectives include the minimization of capital cost, flood volume, flood duration, and total suspended solids or average peak runoff. The results show that the proposed disaggregation‐emulation approach can provide an accurate representation of the system dynamics while significantly reducing the computational time compared to a model that simulates the whole network dynamics. Two alternative surrogate models are considered based on multilayer perceptron (MLP) and generalized regression neural networks (GRNN). MLP is found to be more accurate compared to GRNN at the cost of a larger computational time for the training process.

show abstract

“…We adopt the GP model as an emulator of the complex simulator, in this study. The GP model has been used successfully in constructing a regression model for complex data [ 17 , 18 , 19 , 20 , 21 ] and in analyzing computer experiments [ 22 , 23 , 24 , 25 ].…”

Section: Introductionmentioning

confidence: 99%

Expectation-Maximization Algorithm for the Calibration of Complex Simulator Using a Gaussian Process Emulator

Seo

Park

2020

Entropy

View full text Add to dashboard Cite

The approximated non-linear least squares (ALS) tunes or calibrates the computer model by minimizing the squared error between the computer output and real observations by using an emulator such as a Gaussian process (GP) model. A potential defect of the ALS method is that the emulator is constructed once and it is no longer re-built. An iterative method is proposed in this study to address this difficulty. In the proposed method, the tuning parameters of the simulation model are calculated by the conditional expectation (E-step), whereas the GP parameters are updated by the maximum likelihood estimation (M-step). These EM-steps are alternately repeated until convergence by using both computer and experimental data. For comparative purposes, another iterative method (the max-min algorithm) and a likelihood-based method are considered. Five toy models are tested for a comparative analysis of these methods. According to the toy model study, both the variance and bias of the estimates obtained from the proposed EM algorithm are smaller than those from the existing calibration methods. Finally, the application to a nuclear fusion simulator is demonstrated.

show abstract

A Data-Driven Surrogate Modelling Approach for Acceleration of Short-Term Simulations of a Dynamic Urban Drainage Simulator

Cited by 6 publications

References 34 publications

Integrative Evolutionary-Based Method for Modeling and Optimizing Budget Assignment of Bridge Maintenance Priorities

Integrative Evolutionary-Based Method for Modeling and Optimizing Budget Assignment of Bridge Maintenance Priorities

A Disaggregation‐Emulation Approach for Optimization of Large Urban Drainage Systems

Expectation-Maximization Algorithm for the Calibration of Complex Simulator Using a Gaussian Process Emulator

Contact Info

Product

Resources

About