Benchmark examples for data-driven site characterisation

被引:30
|
作者
Phoon, Kok-Kwang [1 ]
Shuku, Takayuki [2 ]
Ching, Jianye [3 ]
Yoshida, Ikumasa [4 ]
机构
[1] Singapore Univ Technol & Design, Architecture & Sustainable Design Informat Syst T, Singapore, Singapore
[2] Okayama Univ, Dept Civil Engn, Okayama, Japan
[3] Natl Taiwan Univ, Dept Civil Engn, Taipei, Taiwan
[4] Tokyo City Univ, Dept Urban & Civil Engn, Tokyo, Japan
关键词
data-driven site characterisation (DDSC); benchmark examples; data-centric geotechnics; virtual ground; GLasso; TRANSFORMATION MODELS; SPATIAL VARIABILITY; LIQUEFACTION; PARAMETERS; RELIABILITY; SIMULATION; DESIGN; CLAYS;
D O I
10.1080/17499518.2022.2025541
中图分类号
P5 [地质学];
学科分类号
0709 ; 081803 ;
摘要
Decision making in geotechnical engineering is always related to a project carried out at a specific site. It is natural for data-driven site characterization (DDSC) to attract the most attention in data-centric geotechnics. This paper proposed eight benchmark examples and a benchmarking procedure to support unbiased and competitive evaluation of emerging ML methods. The primary goal of DDSC is to bring the value of a "data first" agenda to practice, specifically to produce a 3D stratigraphic map of the subsurface volume below a full-scale project site and to estimate relevant engineering properties at each spatial point based on site investigation data and other relevant Big Indirect Data (BID). A reasonable full-scale ground 20 m long x 20 m wide x 10 m deep is adopted. Virtual grounds containing horizontal, inclined, or discontinuous soil layers and spatially varying synthetic cone penetration test data are created to test the performance of DDSC methods over a range of ground conditions. A benchmark example is defined by a combination of a virtual ground ("reality") and a training dataset (measured "reality"). An additional benchmark example based on actual CPT data is included to check whether performance under virtual ground conditions holds under real ground conditions.
引用
收藏
页码:599 / 621
页数:23
相关论文
共 50 条
  • [41] A data-driven method for unsupervised electricity consumption characterisation at the district level and beyond
    Mor, Gerard
    Cipriano, Jordi
    Martirano, Giacomo
    Pignatelli, Francesco
    Lodi, Chiara
    Lazzari, Florencia
    Grillone, Benedetto
    Chemisana, Daniel
    [J]. ENERGY REPORTS, 2021, 7 : 5667 - 5684
  • [42] funcExplorer: a tool for fast data-driven functional characterisation of high-throughput expression data
    Kolberg, Liis
    Kuzmin, Ivan
    Adler, Priit
    Vilo, Jaak
    Peterson, Hedi
    [J]. BMC GENOMICS, 2018, 19
  • [43] funcExplorer: a tool for fast data-driven functional characterisation of high-throughput expression data
    Liis Kolberg
    Ivan Kuzmin
    Priit Adler
    Jaak Vilo
    Hedi Peterson
    [J]. BMC Genomics, 19
  • [44] A data-driven paradigm to develop and tune data-driven realtime system
    Wabiko, Y
    Nishikawa, H
    [J]. PDPTA'2001: PROCEEDINGS OF THE INTERNATIONAL CONFERENCE ON PARALLEL AND DISTRIBUTED PROCESSING TECHNIQUES AND APPLICATIONS, 2001, : 350 - 356
  • [45] Data-driven wavefield focusing and imaging with multidimensional deconvolution: Numerical examples for reflection data with internal multiples
    Broggini, Filippo
    Snieder, Roel
    Wapenaar, Kees
    [J]. GEOPHYSICS, 2014, 79 (03) : WA107 - WA115
  • [46] Data-driven prestack-waveform inversion using genetic algorithm: Methodology and examples
    Jia, Lingxiao
    Mallick, Subhashis
    Wang, Cheng
    [J]. INTERPRETATION-A JOURNAL OF SUBSURFACE CHARACTERIZATION, 2021, 9 (04): : T1065 - T1084
  • [47] Data-driven approaches to neuroimaging biomarkers for neurological and psychiatric disorders: emerging approaches and examples
    Calhoun, Vince D.
    Pearlson, Godfrey D.
    Sui, Jing
    [J]. CURRENT OPINION IN NEUROLOGY, 2021, 34 (04) : 469 - 479
  • [48] Comparison of Data-Driven Site Characterization Methods in a Real Case History
    Huang, Menglu
    Shuku, Takayuki
    [J]. GEO-RISK 2023: INNOVATION IN DATA AND ANALYSIS METHODS, 2023, 345 : 20 - 27
  • [49] Data-Driven Site Characterization Based on a Markov Random Field Model
    Shuku, Takayuki
    [J]. GEO-RISK 2023: INNOVATION IN DATA AND ANALYSIS METHODS, 2023, 345 : 79 - 85
  • [50] Risk factors for surgical site infections using a data-driven approach
    van Niekerk, J. M.
    Vos, M. C.
    Stein, A.
    Braakman-Jansen, L. M. A.
    in't Holt, A. F. Voor
    Van Gemert-Pijnen, J. E. W. C.
    [J]. PLOS ONE, 2020, 15 (10):