Bayes_Opt-SWMM: A Gaussian process-based Bayesian optimization tool for real-time flood modeling with SWMM

Tanim, Ahad Hasan; Smith-Lewis, Corinne; Downey, Austin R.J.; Imran, Jasim; Goharian, Erfan

doi:10.1016/j.envsoft.2024.106122

Bayes_Opt-SWMM: A Gaussian process-based Bayesian optimization tool for real-time flood modeling with SWMM

Journal Article · Wed Jun 19 00:00:00 EDT 2024 · Environmental Modelling and Software

DOI:https://doi.org/10.1016/j.envsoft.2024.106122· OSTI ID:2378088

^[1]; Smith-Lewis, Corinne ^[2]; Downey, Austin R.J. ^[2]; Imran, Jasim ^[2]; ^[2]

Univ. of South Carolina, Columbia, SC (United States); Oak Ridge National Laboratory (ORNL), Oak Ridge, TN (United States)
Univ. of South Carolina, Columbia, SC (United States)

Real-time flood model plays a pivotal role in averting urban flood damage, particularly when there is minimal lead time for preparatory measures. However, urban flood modeling in real-time often contends with inherent uncertainties arising from input data uncertainty and parameter ambiguities. Here this study introduces a real-time calibration (RTC) tool called Bayes_Opt-SWMM, specifically tailored for real-time urban flood modeling and uncertainty optimization. This tool leverages the Gaussian process-based Bayesian optimization algorithm and interfaces seamlessly with the Stormwater Management Model (SWMM). It integrates real-time model forcing data and flood monitoring collected through sensors and gauges which are strategically placed within critical locations of urban drainage systems. Our approach hinges on the Surrogate Model based Uncertainty Optimization (SMUO) concept, providing an avenue for enhancing real-time flood modeling. Bayes_Opt-SWMM runs the optimization process using a surrogate model called Gaussian Process emulator with two inference methods: (1) the Gaussian Process (GP) model and (2) Markov Chain Monte Carlo (MCMC) algorithm in GP model (GP_MCMC). Furthermore, three acquisition functions, namely Expected Improvement (EI), Maximum Probability of Improvement (MPI), and Lower Confidence Bound (LCB), facilitate optimal parameter fitting within the surrogate models. The efficiency of GP-based surrogate models in learning SWMM model parameters, leads to an improved uncertainty quantification and accelerated real-time flood modeling in urban areas. Overall, Bayes_Opt-SWMM emerges as a cost-effective and valuable tool for real-time flood modeling and monitoring, with significant potential for managing intelligent storm water systems in urban environments.

View Accepted Manuscript (DOE)

Research Organization:: Oak Ridge National Laboratory (ORNL), Oak Ridge, TN (United States)

Sponsoring Organization:: USDOE

Grant/Contract Number:: AC05-00OR22725

OSTI ID:: 2378088

Journal Information:: Environmental Modelling and Software, Journal Name: Environmental Modelling and Software Vol. 179; ISSN 1364-8152

Publisher:: ElsevierCopyright Statement

Country of Publication:: United States

Language:: English

References (40)

Detection and attribution of urbanization effect on flood extremes using nonstationary flood-frequency models: URBANIZATION AND NONSTATIONARITY Prosdocimi, I.; Kjeldsen, T. R.; Miller, J. D. Water Resources Research, Vol. 51, Issue 6 https://doi.org/10.1002/2015WR017065	journal	June 2015
A Bayesian exploration-exploitation approach for optimal online sensing and planning with a visually guided mobile robot Martinez-Cantin, Ruben; de Freitas, Nando; Brochu, Eric Autonomous Robots, Vol. 27, Issue 2 https://doi.org/10.1007/s10514-009-9130-2	journal	August 2009
Automated calibration of the EPA-SWMM model for a small suburban catchment using PEST: a case study Perin, Roberto; Trigatti, Matteo; Nicolini, Matteo Environmental Monitoring and Assessment, Vol. 192, Issue 6 https://doi.org/10.1007/s10661-020-08338-7	journal	May 2020
Modification of the SCE-UA to Include Constraints by Embedding an Adaptive Penalty Function and Application: Application Approach Kang, Taeuk; Lee, Sangho Water Resources Management, Vol. 28, Issue 8 https://doi.org/10.1007/s11269-014-0602-6	journal	April 2014
River flow forecasting through conceptual models part I — A discussion of principles Nash, J. E.; Sutcliffe, J. V. Journal of Hydrology, Vol. 10, Issue 3 https://doi.org/10.1016/0022-1694(70)90255-6	journal	April 1970
Dual state–parameter estimation of hydrological models using ensemble Kalman filter Moradkhani, Hamid; Sorooshian, Soroosh; Gupta, Hoshin V. Advances in Water Resources, Vol. 28, Issue 2 https://doi.org/10.1016/j.advwatres.2004.09.002	journal	February 2005
Understanding, management and modelling of urban hydrology and its consequences for receiving waters: A state of the art Fletcher, T. D.; Andrieu, H.; Hamel, P. Advances in Water Resources, Vol. 51 https://doi.org/10.1016/j.advwatres.2012.09.001	journal	January 2013
OSTRICH-SWMM: A new multi-objective optimization tool for green infrastructure planning with SWMM Macro, Kristina; Matott, L. Shawn; Rabideau, Alan Environmental Modelling & Software, Vol. 113 https://doi.org/10.1016/j.envsoft.2018.12.004	journal	March 2019
Leveraging open source software and parallel computing for model predictive control of urban drainage systems using EPA-SWMM5 Sadler, Jeffrey M.; Goodall, Jonathan L.; Behl, Madhur Environmental Modelling & Software, Vol. 120 https://doi.org/10.1016/j.envsoft.2019.07.009	journal	October 2019
A review of parallel computing applications in calibrating watershed hydrologic models Asgari, Marjan; Yang, Wanhong; Lindsay, John Environmental Modelling & Software, Vol. 151 https://doi.org/10.1016/j.envsoft.2022.105370	journal	May 2022
Global sensitivity analysis in hydrodynamic modeling and flood inundation mapping Alipour, Atieh; Jafarzadegan, Keighobad; Moradkhani, Hamid Environmental Modelling & Software, Vol. 152 https://doi.org/10.1016/j.envsoft.2022.105398	journal	June 2022
Decomposition of the mean squared error and NSE performance criteria: Implications for improving hydrological modelling Gupta, Hoshin V.; Kling, Harald; Yilmaz, Koray K. Journal of Hydrology, Vol. 377, Issue 1-2 https://doi.org/10.1016/j.jhydrol.2009.08.003	journal	October 2009
Hydrological modelling of urbanized catchments: A review and future directions Salvadore, Elga; Bronders, Jan; Batelaan, Okke Journal of Hydrology, Vol. 529 https://doi.org/10.1016/j.jhydrol.2015.06.028	journal	October 2015
The effect of interactions between rainfall patterns and land-cover change on flood peaks in upland peatlands Gao, Jihui; Kirkby, Mike; Holden, Joseph Journal of Hydrology, Vol. 567 https://doi.org/10.1016/j.jhydrol.2018.10.039	journal	December 2018
Optimal design of low impact development practices in response to climate change Ghodsi, Seyed Hamed; Zahmatkesh, Zahra; Goharian, Erfan Journal of Hydrology, Vol. 580 https://doi.org/10.1016/j.jhydrol.2019.124266	journal	January 2020
A new tool for automatic calibration of the Storm Water Management Model (SWMM) Shahed Behrouz, Mina; Zhu, Zhenduo; Matott, L. Shawn Journal of Hydrology, Vol. 581 https://doi.org/10.1016/j.jhydrol.2019.124436	journal	February 2020
Process-oriented SWMM real-time correction and urban flood dynamic simulation Ma, Bingyan; Wu, Zening; Hu, Caihong Journal of Hydrology, Vol. 605 https://doi.org/10.1016/j.jhydrol.2021.127269	journal	February 2022
UAV rapidly-deployable stage sensor with electro-permanent magnet docking mechanism for flood monitoring in undersampled watersheds Smith, Corinne; Satme, Joud; Martin, Jacob HardwareX, Vol. 12 https://doi.org/10.1016/j.ohx.2022.e00325	journal	October 2022
A new LID spatial allocation optimization system at neighborhood scale: Integrated SWMM with PICEA-g using MATLAB as the platform Yu, Yang; Zhou, Yongchao; Guo, Zhiyong Science of The Total Environment, Vol. 831 https://doi.org/10.1016/j.scitotenv.2022.154843	journal	July 2022
Sherpa: Robust hyperparameter optimization for machine learning Hertel, Lars; Collado, Julian; Sadowski, Peter SoftwareX, Vol. 12 https://doi.org/10.1016/j.softx.2020.100591	journal	July 2020
Improved treatment of uncertainty in hydrologic modeling: Combining the strengths of global optimization and data assimilation: TREATMENT OF UNCERTAINTY IN HYDROLOGIC MODELING Vrugt, Jasper A.; Diks, Cees G. H.; Gupta, Hoshin V. Water Resources Research, Vol. 41, Issue 1 https://doi.org/10.1029/2004WR003059	journal	January 2005
Uncertainty in hydrologic modeling: Toward an integrated data assimilation framework: HYDROLOGIC DATA ASSIMILATION Liu, Yuqiong; Gupta, Hoshin V. Water Resources Research, Vol. 43, Issue 7 https://doi.org/10.1029/2006WR005756	journal	July 2007
What Did Really Improve Our Mesoscale Hydrological Model? A Multidimensional Analysis Based on Real Observations Francke, Till; Baroni, Gabriele; Brosinsky, Arlena Water Resources Research, Vol. 54, Issue 11 https://doi.org/10.1029/2018WR022813	journal	November 2018
A Comprehensive Distributed Hydrological Modeling Intercomparison to Support Process Representation and Data Collection Strategies Baroni, Gabriele; Schalge, Bernd; Rakovec, Oldrich Water Resources Research, Vol. 55, Issue 2 https://doi.org/10.1029/2018WR023941	journal	February 2019
Function Space Optimization: A Symbolic Regression Method for Estimating Parameter Transfer Functions for Hydrological Models Feigl, M.; Herrnegger, M.; Klotz, D. Water Resources Research, Vol. 56, Issue 10 https://doi.org/10.1029/2020WR027385	journal	October 2020
Automatic Regionalization of Model Parameters for Hydrological Models Feigl, Moritz; Thober, Stephan; Schweppe, Robert Water Resources Research, Vol. 58, Issue 12 https://doi.org/10.1029/2022WR031966	journal	December 2022
Automatic Calibration of the U.S. EPA SWMM Model for a Large Urban Catchment Barco, Janet; Wong, Kenneth M.; Stenstrom, Michael K. Journal of Hydraulic Engineering, Vol. 134, Issue 4 https://doi.org/10.1061/(ASCE)0733-9429(2008)134:4(466)	journal	April 2008
Distributed Stormwater Controls for Flood Mitigation within Urbanized Watersheds: Case Study of Rocky Branch Watershed in Columbia, South Carolina Morsy, Mohamed M.; Goodall, Jonathan L.; Shatnawi, Fadi M. Journal of Hydrologic Engineering, Vol. 21, Issue 11 https://doi.org/10.1061/(ASCE)HE.1943-5584.0001430	journal	November 2016
Development of a Robust Automated Tool for Calibrating a SWMM Watershed Model Alamdari, Nasrin World Environmental and Water Resources Congress 2016 https://doi.org/10.1061/9780784479841.025	conference	May 2016
A Comparison of Three Methods for Selecting Values of Input Variables in the Analysis of Output From a Computer Code Mckay, M. D.; Beckman, R. J.; Conover, W. J. Technometrics, Vol. 42, Issue 1 https://doi.org/10.1080/00401706.2000.10485979	journal	February 2000
Improving flood forecasting using an input correction method in urban models in poorly gauged areas Fava, Maria Clara; Mazzoleni, Maurizio; Abe, Narumi Hydrological Sciences Journal, Vol. 65, Issue 7 https://doi.org/10.1080/02626667.2020.1729984	journal	March 2020
A high resolution application of a stormwater management model (SWMM) using genetic parameter optimization Krebs, G.; Kokkonen, T.; Valtanen, M. Urban Water Journal, Vol. 10, Issue 6 https://doi.org/10.1080/1573062X.2012.739631	journal	December 2013
Taking the Human Out of the Loop: A Review of Bayesian Optimization Shahriari, Bobak; Swersky, Kevin; Wang, Ziyu Proceedings of the IEEE, Vol. 104, Issue 1 https://doi.org/10.1109/JPROC.2015.2494218	journal	January 2016
A new acquisition function for Bayesian optimization based on the moment-generating function Wang, Hao; van Stein, Bas; Emmerich, Michael 2017 IEEE International Conference on Systems, Man, and Cybernetics (SMC) https://doi.org/10.1109/SMC.2017.8122656	conference	October 2017
Gaussian Processes for Machine Learning Seeger, Matthias International Journal of Neural Systems, Vol. 14, Issue 02 https://doi.org/10.1142/S0129065704001899	journal	April 2004
Bayesian optimization for sensor set selection Garnett, R.; Osborne, M. A.; Roberts, S. J. Proceedings of the 9th ACM/IEEE International Conference on Information Processing in Sensor Networks https://doi.org/10.1145/1791212.1791238	conference	April 2010
PySWMM: The Python Interface to Stormwater Management Model (SWMM) McDonnell, Bryant; Ratliff, Katherine; Tryby, Michael Journal of Open Source Software, Vol. 5, Issue 52 https://doi.org/10.21105/joss.02292	journal	August 2020
Combining satellite data and appropriate objective functions for improved spatial pattern performance of a distributed hydrologic model Demirel, Mehmet C.; Mai, Juliane; Mendiguren, Gorka Hydrology and Earth System Sciences, Vol. 22, Issue 2 https://doi.org/10.5194/hess-22-1299-2018	journal	January 2018
Technical note: Inherent benchmark or not? Comparing Nash–Sutcliffe and Kling–Gupta efficiency scores Knoben, Wouter J. M.; Freer, Jim E.; Woods, Ross A. Hydrology and Earth System Sciences, Vol. 23, Issue 10 https://doi.org/10.5194/hess-23-4323-2019	journal	January 2019
Sequential data assimilation for real-time probabilistic flood inundation mapping Jafarzadegan, Keighobad; Abbaszadeh, Peyman; Moradkhani, Hamid Hydrology and Earth System Sciences, Vol. 25, Issue 9 https://doi.org/10.5194/hess-25-4995-2021	journal	September 2021

Similar Records

Using SWMM for emergency response planning: A case study evaluating biological agent transport under various rainfall scenarios and urban surfaces

Journal Article · Thu Jun 01 20:00:00 EDT 2023 · Journal of Hazardous Materials · OSTI ID:2427997

Effectiveness of nature-based solutions to reduce flooding in Quad Cities Metro Area (QCMA) using SWMM-HEC based flood model

Journal Article · Tue May 13 20:00:00 EDT 2025 · Frontiers of Earth Science · OSTI ID:3004214

BAYESIAN CALIBRATION OF SAFETY CODES USING DATA FROM SEPARATE-AND INTEGRAL EFFECTS TESTS

Conference · Wed Apr 01 00:00:00 EDT 2015 · Proceedings of the International Meeting on Probabilistic Assessment and Analysis · OSTI ID:1357901

Related Subjects

54 ENVIRONMENTAL SCIENCES
97 MATHEMATICS AND COMPUTING
Bayesian optimization
Gaussian process model
SWMM
hyperparameter
sensor

Bayes_Opt-SWMM: A Gaussian process-based Bayesian optimization tool for real-time flood modeling with SWMM

Citation Formats

References (40)

Similar Records

Related Subjects