TY - JOUR
T1 - Data-driven spatio-temporal analysis of consolidation for rapid reclamation
AU - SHI, Chao
AU - WANG, Yu
PY - 2024/6
Y1 - 2024/6
N2 - Spatial extension of lands through rapid reclamation is attractive for congested coastal megacities, although reclamations might suffer from project delay and budget overrun, often due to encountering of unforeseen ground conditions. To accelerate reclamations, accurate prediction of soil consolidation over a construction duration of multiple years is needed for reclaimed lands, which often contain spatially varying subsurface stratigraphy and soil parameters. This calls for a spatio-temporal analysis of consolidation with a sound understanding of subsurface stratigraphic alternations of fine/coarse-grained soils and spatial variability of consolidation parameters (e.g., permeability). In this study, a unified framework, capable of simultaneously modelling stratigraphic variation and spatial variability of soil properties through machine learning of limited site investigation data, is combined with finite element method and Monte Carlo simulation for spatio-temporal consolidation analysis of reclaimed lands. The proposed method is applied to a real reclamation project in Hong Kong. Results indicate that the proposed method can accurately characterize subsurface geological cross-sections and spatially varying soil permeability with quantified uncertainty. The ignorance of spatial variability of soil permeability may result in an underestimation of consolidation time and an overestimation of undrained shear strength gain, thus pose significant risks to reclamation projects. © 2023 Thomas Telford Ltd.
AB - Spatial extension of lands through rapid reclamation is attractive for congested coastal megacities, although reclamations might suffer from project delay and budget overrun, often due to encountering of unforeseen ground conditions. To accelerate reclamations, accurate prediction of soil consolidation over a construction duration of multiple years is needed for reclaimed lands, which often contain spatially varying subsurface stratigraphy and soil parameters. This calls for a spatio-temporal analysis of consolidation with a sound understanding of subsurface stratigraphic alternations of fine/coarse-grained soils and spatial variability of consolidation parameters (e.g., permeability). In this study, a unified framework, capable of simultaneously modelling stratigraphic variation and spatial variability of soil properties through machine learning of limited site investigation data, is combined with finite element method and Monte Carlo simulation for spatio-temporal consolidation analysis of reclaimed lands. The proposed method is applied to a real reclamation project in Hong Kong. Results indicate that the proposed method can accurately characterize subsurface geological cross-sections and spatially varying soil permeability with quantified uncertainty. The ignorance of spatial variability of soil permeability may result in an underestimation of consolidation time and an overestimation of undrained shear strength gain, thus pose significant risks to reclamation projects. © 2023 Thomas Telford Ltd.
KW - Machine learning
KW - Probabilistic analysis
KW - Random finite-element analysis
KW - Soil spatial variability
KW - Stratigraphic uncertainty
KW - artificial intelligence
KW - settlement
UR - http://www.scopus.com/inward/record.url?scp=85148508372&partnerID=8YFLogxK
UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-85148508372&origin=recordpage
U2 - 10.1680/jgeot.22.00016
DO - 10.1680/jgeot.22.00016
M3 - RGC 21 - Publication in refereed journal
SN - 0016-8505
VL - 74
SP - 676
EP - 696
JO - Geotechnique
JF - Geotechnique
IS - 7
ER -