Performance comparison of multiple and single surrogate models for pumping optimization of coastal aquifers

被引:27
作者
Christelis, Vasileios [1 ,2 ]
Kopsiaftis, George [1 ]
Mantoglou, Aristotelis [1 ]
机构
[1] Natl Tech Univ Athens, Sch Rural & Surveying Engn, Lab Reclamat Works & Water Resources Management, Athens, Greece
[2] British Geol Survey, Environm Sci Ctr, Nottingham, England
关键词
coastal aquifers; pumping optimization; surrogate models; multiple surrogates; computational cost; SALTWATER INTRUSION MANAGEMENT; EFFICIENT GLOBAL OPTIMIZATION; EVOLUTIONARY ALGORITHMS; SOLUTE TRANSPORT; META-MODELS; GROUNDWATER; SIMULATION; ENSEMBLE; STRATEGIES; SURFACE;
D O I
10.1080/02626667.2019.1584400
中图分类号
TV21 [水资源调查与水利规划];
学科分类号
081501 ;
摘要
Single and multiple surrogate models were compared for single-objective pumping optimization problems of a hypothetical and a real-world coastal aquifer. Different instances of radial basis functions and kriging surrogates were utilized to reduce the computational cost of direct optimization with variable density and salt transport models. An adaptive surrogate update scheme was embedded in the operations of an evolutionary algorithm to efficiently control the feasibility of optimal solutions in pumping optimization problems with multiple constraints. For a set of independent optimization runs, results showed that multiple surrogates, either by selecting the best or by using ensembles, did not necessarily outperform the single surrogate approach. Nevertheless, the ensemble with optimal weights produced slightly better results than selecting only the best surrogates or applying a simple averaging approach. For all cases, the computational cost, by using single or multiple surrogate models, was reduced by up to 90% of the direct optimization.
引用
收藏
页码:336 / 349
页数:14
相关论文
共 67 条
  • [1] Various approaches for constructing an ensemble of metamodels using local measures
    Acar, Erdem
    [J]. STRUCTURAL AND MULTIDISCIPLINARY OPTIMIZATION, 2010, 42 (06) : 879 - 896
  • [2] [Anonymous], SURROGATES TOOLB US
  • [3] [Anonymous], ASCE
  • [4] [Anonymous], 2002, DACE MATLAB KRIGING
  • [5] [Anonymous], SUSTAINABLE HYDRAULI
  • [6] [Anonymous], 2002, P 5 INT C HYDR
  • [7] [Anonymous], WAT RES MAN SYST TOO
  • [8] [Anonymous], MODELING EARTH SYSTE
  • [9] [Anonymous], 2017, WATER RESOUR MANAG, DOI DOI 10.1007/s11269-016-1531-3
  • [10] A review of surrogate models and their application to groundwater modeling
    Asher, M. J.
    Croke, B. F. W.
    Jakeman, A. J.
    Peeters, L. J. M.
    [J]. WATER RESOURCES RESEARCH, 2015, 51 (08) : 5957 - 5973