Surrogate-based multiobjective optimization to rapidly size low impact development practices for outflow capture

被引:10
|
作者
Yang, Yuanyuan [1 ,2 ]
Li, Yabin [1 ]
Huang, Qiang [1 ]
Xia, Jun [3 ]
Li, Jiake [1 ]
机构
[1] Xian Univ Technol, State Key Lab Ecohydraul Northwest Arid Reg, Xian 710048, Peoples R China
[2] Shaanxi Key Lab Water Resources & Environm, Xian, Peoples R China
[3] Wuhan Univ, State Key Lab Water Resources & Hydropower Engn S, Wuhan 430072, Peoples R China
基金
中国国家自然科学基金; 中国博士后科学基金;
关键词
Storm water management model (SWMM); Non-dominated sorting genetic algorithm-II  (NSGA-II); Design storm; Surrogate; Metamodel; GLOBAL OPTIMIZATION; URBAN; DESIGN; STRATEGIES; PERFORMANCE; SYSTEMS; MODEL; SWMM; BMPS; TOOL;
D O I
10.1016/j.jhydrol.2022.128848
中图分类号
TU [建筑科学];
学科分类号
0813 ;
摘要
The optimal implementation of low impact development (LID) practices remains an open research issue. Mul-tiobjective optimization (MOO) based on physically-based models facilitates LID sizing but requires large computational budgets. We developed and validated a surrogate MOO framework based on machine learning (ML) models to obtain satisfactory optimal solutions with an affordable computational cost. First, a calibrated and validated storm water management model (SWMM) was driven by a 2-year, 120 min Chicago pattern storm with random LID areas for generating 10,000 samples. Second, ML models, including multiple linear regression (MLR), generalized regression neural network (GRNN), and backpropagation neural network (BPNN), were trained and validated to predict catchment total outflow (CTO) and catchment peak outflow (CPO). Third, using the outperformed ML models as surrogates, the LID areas were optimized by non-dominated sorting genetic algorithm-II to minimize construction costs, CTO, and CPO. The results obtained for an urban catchment in Fengxi, China, demonstrated that: (1) BPNN outperformed MLR and GRNN in terms of accuracy, while the training time (-40 min) was-6857 times and-706 times that of MLR (-0.35 s) and GRNN (3.4 s) models, respectively. (2) The optimization process using BPNN models as surrogates converged well, indicating the ef-ficiency of the proposed framework. (3) Under the marginal effect, the permeable pavement was identified as the leading practice for most Pareto solutions, followed by bioretention cell and green roof. Moreover, a sub -catchment with a higher runoff coefficient was deemed preferable for LID implementation. (4) Outflow reduction by the LIDs was significant (CTO and CPO were reduced by 28.6-56.9 % and 27.5-48.3 %, respectively) but negligible for retarding the time of CPO. (5) The optimization time was reduced by-95.82 % using the surrogate-based MOO instead of the SWMM-based model when the training time of the BPNN models was ignored. This study provides insights into the efficient optimization of LIDs.
引用
收藏
页数:11
相关论文
共 50 条
  • [31] The blade shape optimization of a low-pressure axial fan using the surrogate-based multi-objective optimization method
    Kong, Chuang
    Wang, Meng
    Jin, Tao
    Liu, Shaoliang
    JOURNAL OF MECHANICAL SCIENCE AND TECHNOLOGY, 2023, 37 (01) : 179 - 189
  • [32] The blade shape optimization of a low-pressure axial fan using the surrogate-based multi-objective optimization method
    Chuang Kong
    Meng Wang
    Tao Jin
    Shaoliang Liu
    Journal of Mechanical Science and Technology, 2023, 37 : 179 - 189
  • [33] Multiobjective layout optimization for low impact development considering its ecosystem services
    Jin, Xuanyi
    Fang, Delin
    Chen, Bin
    Wang, Hao
    RESOURCES CONSERVATION AND RECYCLING, 2024, 209
  • [34] Integrating Social Equity into Multiobjective Optimization of Urban Stormwater Low-Impact Development
    Herbst, R. Seth
    Culver, Teresa B. B.
    Band, Lawrence E. E.
    Wilson, Bev
    Quinn, Julianne D. D.
    JOURNAL OF WATER RESOURCES PLANNING AND MANAGEMENT, 2023, 149 (08)
  • [35] Explicit Size-Reduction-Oriented Design of a Compact Microstrip Rat-Race Coupler Using Surrogate-Based Optimization Methods
    Koziel, Slawomir
    Bekasiewicz, Adrian
    Leifsson, Leifur
    Du, Xiaosong
    Tesfahunegn, Yonatan
    COMPUTATIONAL SCIENCE - ICCS 2018, PT II, 2018, 10861 : 584 - 592
  • [36] Aircraft Configuration Development Through Surrogate-Based Robust Optimization Using A Real-Coded Fuzzy-Genetic Algorithm
    Banal, Lemuel F.
    Gan Lim, Laurence A.
    Ubando, Aristotle T.
    Fernando, Arvin H.
    Augusto, Gerardo L.
    2017 IEEE 9TH INTERNATIONAL CONFERENCE ON HUMANOID, NANOTECHNOLOGY, INFORMATION TECHNOLOGY, COMMUNICATION AND CONTROL, ENVIRONMENT AND MANAGEMENT (IEEE HNICEM), 2017,
  • [37] Expedite Design of Variable-Topology Broadband Hybrid Couplers for Size Reduction Using Surrogate-Based Optimization and Co-Simulation Coarse Models
    Kurgan, Piotr
    Koziel, Slawomir
    Leifsson, Leifur
    Du, Xiaosong
    INTERNATIONAL CONFERENCE ON COMPUTATIONAL SCIENCE (ICCS 2017), 2017, 108 : 1483 - 1492
  • [38] Degrees of hydrologic restoration by low impact development practices under different runoff volume capture goals
    Guo, Xiaochen
    Guo, Qizhong
    Zhou, Zikai
    Du, Pengfei
    Zhao, Dongquan
    JOURNAL OF HYDROLOGY, 2019, 578
  • [39] Integrating cost-effectiveness optimization and robustness analysis for low impact development practices design
    Zhi, Xiaosha
    Xiao, Yuechen
    Chen, Lei
    Hou, Xiaoshu
    Yu, Yu
    Zhou, Xuehui
    Fu, Yijia
    Chen, Bin
    Shen, Zhenyao
    RESOURCES CONSERVATION AND RECYCLING, 2022, 185
  • [40] A systematic bibliometric review of optimization and resilience within low impact development stormwater management practices
    Islam, Arpita
    Hassini, Sonia
    El-Dakhakhni, Wael
    JOURNAL OF HYDROLOGY, 2021, 599