Seismic Resilience Evaluation of Urban Water Distribution Network using Machine Learning
Subject Areas : Farm water management with the aim of improving irrigation management indicatorsMahnaz Haghighi 1 , Ali Delnavaz 2 , Majid Safehian 3 , Mohammad Delnavaz 4
1 - Ph.D. Candidate in Construction Engineering and Management, Department of Civil Engineering, Science and Research Branch, Islamic Azad University, Tehran, Iran.
2 - Assistant professor 'Department of Civil Engineering, Qazvin Branch, Islamic Azad University, Qazvin, Iran.
3 - Assistant professor, Department of Civil Engineering, Science and Research Branch, Islamic Azad University, Tehran, Iran.
4 - Associate professor "Faculty of Engineering, Civil Engineering Department, Kharazmi University, Tehran, Iran.
Keywords: Seismic vulnerability, Seismic resilience, Machine learning, Water distribution network,
Abstract :
Background and Aim: Seismic resilience focuses on the performance, recovery, and functionality of urban infrastructures after earthquakes, with water supply networks being critical for providing drinking water and firefighting support. Assessing and enhancing the seismic resilience of these networks is a key challenge for researchers. This study evaluates the seismic resilience of urban water distribution, specifically focusing on Tehran's water network in Districts 1-4.
Method: This research introduces a machine learning-based model to predict seismic vulnerability and evaluate the resilience of urban water supply networks. Machine learning models are based on primary data sets, so to provide the primary database initially, finite element modeling (720 scenarios) using Abaqus software was conducted to extract the seismic behavior of buried pipes. Various machine learning algorithms were then applied to develop a predictive model, which was optimized and paired with a numerical algorithm to assess damage under uncertainty using the Monte Carlo method. The model was tested on five seismic scenarios in Tehran’s Districts 1-4, extracting results on pipe damage, and seismic resilience was evaluated based on damage, water supply needs, and recovery time.
Results: The results obtained from the performance of the machine learning model using various algorithms demonstrated that Gaussian algorithms performed better compared to other computational machine learning algorithms. Specifically, the Rational Quadratic Gaussian algorithm exhibited minimal error, with a mean squared error (MSE) of 3.0564 and a correlation coefficient (R) of 0.94. For the purpose of assessing seismic resilience of the water transmission and distribution network in Tehran's areas 1 to 4, the extent of damage to the water supply network (number and location of pipe breaks/leaks in the network) under 5 seismic loading scenarios was calculated and extracted using the vulnerability prediction model. Additionally, an assessment of the relative damage index (Bridge index) in the pipeline network under study was conducted. In evaluating the minimum required water supply considering the population of each area and the required water quantity, calculations were made and assessments were carried out. The recovery time/recovery rate index of the water distribution network following an earthquake event, based on the level of pipe damage in each area and repair and restoration strategies, was studied. Based on the results obtained, it is evident that the longest recovery time of the system was for area 4 of Tehran under S1 loading (earthquake magnitude of 7.4 Richter), amounting to 493.5 hours, while the shortest recovery time was for area 3 of Tehran under S2 loading (earthquake magnitude of 6.2 Richter), amounting to 316.5 hours. The results indicate that the water supply network under scenarios with larger earthquake magnitudes experienced longer recovery times compared to scenarios with smaller earthquake magnitudes.
Conclusion: The results demonstrated that the machine learning model for predicting seismic damage in the water transmission network had acceptable accuracy in assessing damage under incident conditions. The main points and solutions proposed in this study towards enhancing seismic resilience of the water supply network include: accurate prediction of seismic damage levels in the water transmission network using the proposed model (for precision and improvement of vulnerability indices), making precise management decisions to secure alternative water resources in high earthquake risk areas (to enhance augmentation indices), and implementing repair and restoration strategies for damaged pipelines by equipping areas with skilled support teams (to improve recovery time indices). Based on the obtained results, the model presented in this study can be utilized as a comprehensive model for various regions and under different seismic loading conditions. In addition to estimating seismic vulnerability of the water supply network, it can provide a detailed assessment of seismic resilience and enhance the flexibility of this critical infrastructure.
Adachi, T., & Ellingwood, B. R. (2008). Serviceability of earthquake-damaged water systems: Effects of electrical power availability and power backup systems on system vulnerability. Reliability engineering & system safety, 93(1), 78-88.
ALA (American Lifelines Alliance). (2001). Guidelines for the design of buried steel pipe. Reston, VA: ASCE.
Alavi, S., Masoud, M., & Karimi, A. (2020). Urban Resilience: Restoration Analysis of Urban Water Infrastructures in A Potential Earthquake (Case study: Region 2 of Tehran Municipality). Human Geography Research, 52(2), 533-550.
Assad, A., Moselhi, O., & Zayed, T. (2020). Resilience-driven multiobjective restoration planning for water distribution networks. Journal of Performance of Constructed Facilities, 34(4), 04020072.
Bata, M. T. H., Carriveau, R., & Ting, D. S. K. (2022). Urban water supply systems’ resilience under earthquake scenario. Scientific Reports, 12(1), 20555.
Bonneau, A. L., & O'Rourke, T. D. (2009). Water supply performance during earthquakes and extreme events (Vol. 234). Mceer.
Bruneau, M., Eeri, M., & Chang, S. E. (2003). Ronald T, George C Lee, Thomas DO Rourke, Andrei M Reinhorn, Masanobu Shinozuka, William A Wallace, and Detlof Von Winterfeldt. A Framework to Quantitatively Assess and Enhance the Seismic Resilience of Communities. Engineering, 19(4), 733-752.
CEN (EuropeanCommitteeforStandardization). (2006) .Eurocode8, part4: Silos, tanks and pipelines. CEN EN1998-4. Brussels, Belgium: CEN.
Chang, S. E., McDaniels, T., Fox, J., Dhariwal, R., & Longstaff, H. (2014). Toward disaster‐resilient cities: Characterizing resilience of infrastructure systems with expert judgments. Risk analysis, 34(3), 416-434.
Cheng, X., Ma, C., Huang, R., Huang, S., & Yang, W. (2019). Failure mode analysis of X80 buried steel pipeline under oblique-reverse fault. Soil Dynamics and Earthquake Engineering, 125, 105723.
Cimellaro, G. P., Tinebra, A., Renschler, C., & Fragiadakis, M. (2016). New resilience index for urban water distribution networks. Journal of Structural Engineering, 142(8), C4015014.
CSA (Standard Association Canadian). (2007). Oil and gas pipeline system. CSA-Z662. Mississauga, ON: CSA.
Dueñas‐Osorio, L., Craig, J. I., & Goodno, B. J. (2007). Seismic response of critical interdependent networks. Earthquake engineering & structural dynamics, 36(2), 285-306.
Farahmandfar, Z., Piratla, K. R., & Andrus, R. D. (2017). Resilience evaluation of water supply networks against seismic hazards. Journal of Pipeline Systems Engineering and Practice, 8(1), 04016014.
Fragiadakis, M., & Christodoulou, S. E. (2014). Seismic reliability assessment of urban water networks. Earthquake engineering & structural dynamics, 43(3), 357-374.
Haghighi, M., Delnavaz, A., Rashvand, P., & Delnavaz, M. (2024). Assessment through Machine Learning of Groundwater Vulnerability after Seismic Damage to Fuel Pipeline. Journal of Pipeline Systems Engineering and Practice, 15(3), 04024025.
Hou, B. W., & Du, X. L. (2014). Comparative study on hydraulic simulation of earthquake-damaged water distribution system. In International Efforts in Lifeline Earthquake Engineering (pp. 113-120).
Huang, T., & Dilkina, B. (2020, June). Enhancing Seismic Resilience of Water Pipe Networks. In Proceedings of the 3rd ACM SIGCAS Conference on Computing and Sustainable Societies (pp. 44-52).
Hwang, H. H., Lin, H., & Shinozuka, M. (1998). Seismic performance assessment of water delivery systems. Journal of Infrastructure Systems, 4(3), 118-125.
Ilanlu, M., Ardakani, A., Paknezhad, H., Ebrahimi Gelsefid, M., & Soltani, Y. A. (2013). Identifying the Urban Vulnerable Areas Against the Earthquake with Giscase Study-Radio Darya St. Chalous. International Journal of Advanced Studies in Humanities and Social Science, 2(4), 230-237.
Ito, A., M. Okutsu, A. Furukawa, G. Shoji, and T. Suzuki. 2022. “Earthquake damage prediction of underground steel pipe with screw joint using machine learning.” In Lifelines 2022, 613–620. https://doi.org/10 .1061/9780784484449.055
Karamy Moghadam, A., and M. Mahdavi Adeli. 2020. “Application of artificial neural networks for seismic analysis and design of buried pipelines in heterogeneous soils.” J. Hydraul. Struct. 6 (4): 60–74. https:// doi.org/10.22055/JHS.2021.35453.1153.
Li, F., W. Wang, J. Xu, J. Yi, and Q. Wang. 2019. “Comparative study onvulnerabilityassessmentforur banburiedgaspipelinenetworkbased on SVM and ANN methods.” Process Saf. Environ. Prot. 122 (Feb): 23–32. https://doi.org/10.1016/j.psep.2018.11.014.
Makhoul, N., Navarro, C., & Lee, J. (2018). Earthquake damage estimations of Byblos potable water network. Natural Hazards, 93, 627-659.
Makrakis, N., P. N. Psarropoulos, and Y. Tsompanakis. 2022. “ANN-based assessment of soft surface soil layers’ impact on fault rupture propagation and kinematic distress of gas pipelines.” Infrastructures 8 (1): 6. https://doi.org/10.3390/infrastructures8010006.
Nariman, A., Fattahi, M. H., Talebbeydokhti, N., & Sadeghian, M. S. (2023). Assessment of Seismic Resilience in Urban Water Distribution Network Considering Hydraulic Indices. Iranian Journal of Science and Technology, Transactions of Civil Engineering, 47(2), 1165-1179.
Paez, D., Filion, Y., Castro-Gama, M., Quintiliani, C., Santopietro, S., Sweetapple, C., ... & Walski, T. (2020). Battle of postdisaster response and restoration. Journal of Water Resources Planning and Management, 146(8), 04020067.
Qian, L., Endong, G., Tianyang, Y., & Mingzhen, W. (2017). Evaluation of post-quake resilience of water supply pipelines [J]. Revista de la Facultad de Ingeniería, 32(10), 283-295.
Qian, L., Wei, S., Tianlai, Y., Tiancheng, W., & Mohamed, H. (2023). Mathematical methodology in the seismic resilience evaluation of the water supply system. Applied Mathematics and Nonlinear Sciences.
Renschler, C. S., Frazier, A. E., Arendt, L. A., Cimellaro, G. P., Reinhorn, A. M., & Bruneau, M. (2010). A framework for defining and measuring resilience at the community scale: The PEOPLES resilience framework (pp. 10-0006). Buffalo: MCEER.
Salgado-Gálvez, M. A., Zuloaga, D., Henao, S., Bernal, G. A., & Cardona, O. D. (2018). Probabilistic assessment of annual repair rates in pipelines and of direct economic losses in water and sewage networks: application to Manizales, Colombia. Natural Hazards, 93, 5-24.
SelÇuk, A. S., & Yücemen, M. S. (2000). Reliability of lifeline networks with multiple sources under seismic hazard. Natural Hazards, 21, 1-18.
Shi, P. (2006). Seismic response modeling of water supply systems. Cornell University.
Shinozuka, M., Tan, R. Y., & Toike, T. (1981, August). Serviceability of water transmission systems under seismic risk. In Lifeline Earthquake Engineering: The Current State of Knowledge, 1981 (pp. 97-110). ASCE.
Tang, H., Zhong, Q., Chen, C., & Martek, I. (2023). The Adaptive Seismic Resilience of Infrastructure Systems: A Bayesian Networks Analysis. Systems, 11(2), 84.
Tanyimboh, T. T., Tietavainen, M. T., & Saleh, S. (2011). Reliability assessment of water distribution systems with statistical entropy and other surrogate measures. Water Science and Technology: Water Supply, 11(4), 437-443.
Tsatsis, A., Loli, M., & Gazetas, G. (2019). Pipeline in dense sand subjected to tectonic deformation from normal or reverse faulting. Soil Dynamics and Earthquake Engineering, 127, 105780.
Wang, Y. (2006). Seismic performance evaluation of water supply systems. Cornell University.
Yang, Y., Ng, S. T., Xu, F. J., & Skitmore, M. (2018). Towards sustainable and resilient high density cities through better integration of infrastructure networks. Sustainable Cities and Society, 42, 407-422.
Yoo, D. G., Jung, D., Kang, D., & Kim, J. H. (2016). Seismic-reliability-based optimal layout of a water distribution network. Water, 8(2), 50.
Zhai, C., Zhao, Y., Wen, W., Qin, H., & Xie, L. (2023). A novel urban seismic resilience assessment method considering the weighting of post-earthquake loss and recovery time. International Journal of Disaster Risk Reduction, 84, 103453.