Related references
Note: Only part of the references are listed.
Article
Engineering, Geological
Chao Shi et al.
Summary: A data-driven framework is proposed to predict geological cross-sections ahead of tunnel face. This method incorporates geological information revealed from tunnel excavation as additional data, providing accurate prediction of geological cross-sections along planned tunnel trajectory with quantified stratigraphic uncertainty.
Article
Geosciences, Multidisciplinary
Liang Han et al.
Summary: This paper presents a confidence ellipse-based method to evaluate the similarity of soil parametric data, and further estimates the site similarity through two proposed strategies. The results show the effectiveness of this method in evaluating parametric data similarity and reducing transformation uncertainty.
GEOSCIENCE FRONTIERS
(2022)
Article
Engineering, Geological
Liang Han et al.
Summary: In this study, the conditional random field (CRF) was improved to simulate rockhead profiles. With the assistance of Bayesian theory, the proposed method utilizes measurement data and prior information to handle uncertainty. The method provides reasonable estimations of rockhead depth at various locations and reduces subjectivity in determining prior mean.
JOURNAL OF ROCK MECHANICS AND GEOTECHNICAL ENGINEERING
(2022)
Article
Construction & Building Technology
Xiaohui Qi et al.
Summary: This paper evaluates three commonly used spatial prediction methods for geological interfaces and proposes a zonation method to improve prediction accuracy. The results show that the multivariate adaptive spline regression (MARS) method can more clearly depict the spatial trend of geological interfaces.
TUNNELLING AND UNDERGROUND SPACE TECHNOLOGY
(2022)
Article
Construction & Building Technology
Chao Shi et al.
Summary: In this study, a data-driven and deep learning method called IC-XGBoost3D is proposed for building a 3D geological model from limited site-specific boreholes and 2D training images reflecting prior geological knowledge. The method efficiently generates an anisotropic 3D geological model with high prediction accuracy and provides quantitative evaluation of associated stratigraphic uncertainty. Effects of irregular borehole spacing and single training image on simulation performance are also investigated.
TUNNELLING AND UNDERGROUND SPACE TECHNOLOGY
(2022)
Article
Engineering, Geological
Kok-Kwang Phoon et al.
Summary: Data-driven site characterisation, relying solely on measured data for site description, is crucial for industries undergoing rapid digital transformation. Challenges include data quality, accuracy, and practicality in application.
GEORISK-ASSESSMENT AND MANAGEMENT OF RISK FOR ENGINEERED SYSTEMS AND GEOHAZARDS
(2022)
Article
Engineering, Geological
Chao Shi et al.
Summary: A novel nonparametric, data-driven method based on multiple point statistics (MPS) is proposed to interpolate subsurface soil stratigraphy from sparse measurements. The method, which utilizes Bayesian supervised machine learning, is the first purely data-driven method for geotechnical site characterization. The effectiveness of the method is demonstrated through a simulated example and real data from a reclamation site in Hong Kong, providing accurate interpolation and quantification of uncertainty.
CANADIAN GEOTECHNICAL JOURNAL
(2021)
Article
Computer Science, Artificial Intelligence
Shengchao Wu et al.
Summary: The study proposes a method for 3D geotechnical site stratification based on CPTu measurements, which achieves 3D interpolation from 1D soil stratification. The method includes a soil classification model, soil layer boundary identification method, and incorporates local variation information to significantly improve identification accuracy.
ADVANCED ENGINEERING INFORMATICS
(2021)
Article
Engineering, Geological
Chao Shi et al.
Summary: This study introduces a smart sampling strategy based on multiple point statistics and information entropy for interpreting subsurface stratigraphy of multi-layered slopes and adaptively determining optimal borehole locations and numbers. The data-driven approach effectively reduces stratigraphic uncertainty.
CANADIAN GEOTECHNICAL JOURNAL
(2021)
Article
Engineering, Geological
Chao Shi et al.
Summary: A data-driven method based on edge orientation detection is proposed for selecting the optimal training image for delineation of subsurface geological cross-section. This method successfully differentiates soil stratigraphic patterns between different training images, providing a quantitative indicator for selection of the optimal training image.
ENGINEERING GEOLOGY
(2021)
Article
Engineering, Geological
Chao Shi et al.
Summary: The delineation of vertical geological cross-sections is crucial in geotechnical site characterization, especially in complex geological settings with limited boreholes. A novel iterative convolution eXtreme Gradient Boosting model is proposed in this study, which interpolates a subsurface geological cross-section from limited site-specific boreholes and a training geological cross-section from previous projects. This data-driven method does not require specifying parametric function form and can learn stratigraphic patterns automatically.
JOURNAL OF GEOTECHNICAL AND GEOENVIRONMENTAL ENGINEERING
(2021)
Article
Engineering, Civil
Xiaohui Qi et al.
Summary: The study used the MARS method to predict the elevations of geological interfaces, showing good accuracy compared to borehole data. Furthermore, the MARS method was able to generate reasonable prediction intervals that properly reflected the data density and geological complexity.
Article
Engineering, Geological
Yu Wang et al.
CANADIAN GEOTECHNICAL JOURNAL
(2020)
Article
Political Science
Tai Wei Lim
Article
Engineering, Geological
Wenping Gong et al.
ENGINEERING GEOLOGY
(2019)
Article
Chemistry, Multidisciplinary
Cuiying Zhou et al.
APPLIED SCIENCES-BASEL
(2019)
Article
Engineering, Civil
Xiangrong Wang et al.
Article
Computer Science, Interdisciplinary Applications
Wenjie Feng et al.
COMPUTERS & GEOSCIENCES
(2017)
Article
Computer Science, Interdisciplinary Applications
Cristian Perez et al.
COMPUTERS & GEOSCIENCES
(2014)
