Details
| Originalsprache | Englisch |
|---|---|
| Aufsatznummer | 107588 |
| Seitenumfang | 17 |
| Fachzeitschrift | Engineering geology |
| Jahrgang | 337 |
| Frühes Online-Datum | 6 Juni 2024 |
| Publikationsstatus | Veröffentlicht - Aug. 2024 |
Abstract
In engineering geology and geotechnical engineering, it is well recognized that subsurface soils/rocks are natural materials and exhibit variability in stratigraphy due to the complex geological formation processes they have undergone. Knowledge of subsurface soil stratigraphy is of great importance to geotechnical engineers. However, accurate and reliable interpretation of subsurface soil stratigraphy is challenging due to the limited number of site investigation boreholes available at the site and the highly heterogeneous properties of soil stratigraphy (e.g., interbedded or non-ordered layers). This paper proposes an improved data-driven machine learning framework boosted with the neighborhood aggregation technique for modelling three-dimensional (3D) subsurface soil stratigraphy in a more general and robust manner. Neighborhood aggregation, a technique often adopted in graph network learning, is integrated into this framework to regulate and improve the prediction results of classical machine learning models. The proposed framework is then cross-validated using 165 real site investigation boreholes for four selected machine learning models respectively. Cross-validation results suggest that the eXtreme Gradient Boosting (XGBoost) and Random Forest (RF) models are more suitable for the task of soil stratigraphy prediction than Artificial Neural Network (ANN) and Support Vector Machine (SVM). Particularly, the XGBoost and RF are also amenable to neighborhood aggregation and can yield around 5% improvement in terms of average borehole prediction accuracy after introducing neighborhood aggregation. The improved machine learning framework allows for explicit 1D to 3D geological modelling, uncertainty quantification, and convenient visualization. The proposed framework facilitates digital transformation of geological and geotechnical site investigation.
ASJC Scopus Sachgebiete
- Erdkunde und Planetologie (insg.)
- Geotechnik und Ingenieurgeologie
- Erdkunde und Planetologie (insg.)
- Geologie
Zitieren
- Standard
- Harvard
- Apa
- Vancouver
- BibTex
- RIS
in: Engineering geology, Jahrgang 337, 107588, 08.2024.
Publikation: Beitrag in Fachzeitschrift › Artikel › Forschung › Peer-Review
}
TY - JOUR
T1 - Three-dimensional reconstruction of subsurface stratigraphy using machine learning with neighborhood aggregation
AU - Hu, Yue
AU - Wang, Ze Zhou
AU - Guo, Xiangfeng
AU - Kek, Hardy Yide
AU - Ku, Taeseo
AU - Goh, Siang Huat
AU - Leung, Chun Fai
AU - Tan, Ernest
AU - Zhang, Yunhuo
PY - 2024/8
Y1 - 2024/8
N2 - In engineering geology and geotechnical engineering, it is well recognized that subsurface soils/rocks are natural materials and exhibit variability in stratigraphy due to the complex geological formation processes they have undergone. Knowledge of subsurface soil stratigraphy is of great importance to geotechnical engineers. However, accurate and reliable interpretation of subsurface soil stratigraphy is challenging due to the limited number of site investigation boreholes available at the site and the highly heterogeneous properties of soil stratigraphy (e.g., interbedded or non-ordered layers). This paper proposes an improved data-driven machine learning framework boosted with the neighborhood aggregation technique for modelling three-dimensional (3D) subsurface soil stratigraphy in a more general and robust manner. Neighborhood aggregation, a technique often adopted in graph network learning, is integrated into this framework to regulate and improve the prediction results of classical machine learning models. The proposed framework is then cross-validated using 165 real site investigation boreholes for four selected machine learning models respectively. Cross-validation results suggest that the eXtreme Gradient Boosting (XGBoost) and Random Forest (RF) models are more suitable for the task of soil stratigraphy prediction than Artificial Neural Network (ANN) and Support Vector Machine (SVM). Particularly, the XGBoost and RF are also amenable to neighborhood aggregation and can yield around 5% improvement in terms of average borehole prediction accuracy after introducing neighborhood aggregation. The improved machine learning framework allows for explicit 1D to 3D geological modelling, uncertainty quantification, and convenient visualization. The proposed framework facilitates digital transformation of geological and geotechnical site investigation.
AB - In engineering geology and geotechnical engineering, it is well recognized that subsurface soils/rocks are natural materials and exhibit variability in stratigraphy due to the complex geological formation processes they have undergone. Knowledge of subsurface soil stratigraphy is of great importance to geotechnical engineers. However, accurate and reliable interpretation of subsurface soil stratigraphy is challenging due to the limited number of site investigation boreholes available at the site and the highly heterogeneous properties of soil stratigraphy (e.g., interbedded or non-ordered layers). This paper proposes an improved data-driven machine learning framework boosted with the neighborhood aggregation technique for modelling three-dimensional (3D) subsurface soil stratigraphy in a more general and robust manner. Neighborhood aggregation, a technique often adopted in graph network learning, is integrated into this framework to regulate and improve the prediction results of classical machine learning models. The proposed framework is then cross-validated using 165 real site investigation boreholes for four selected machine learning models respectively. Cross-validation results suggest that the eXtreme Gradient Boosting (XGBoost) and Random Forest (RF) models are more suitable for the task of soil stratigraphy prediction than Artificial Neural Network (ANN) and Support Vector Machine (SVM). Particularly, the XGBoost and RF are also amenable to neighborhood aggregation and can yield around 5% improvement in terms of average borehole prediction accuracy after introducing neighborhood aggregation. The improved machine learning framework allows for explicit 1D to 3D geological modelling, uncertainty quantification, and convenient visualization. The proposed framework facilitates digital transformation of geological and geotechnical site investigation.
KW - Complex soil stratification
KW - Engineering geology
KW - Machine learning
KW - Neighborhood aggregation
KW - Three-dimensional geological models
UR - http://www.scopus.com/inward/record.url?scp=85195650041&partnerID=8YFLogxK
U2 - 10.1016/j.enggeo.2024.107588
DO - 10.1016/j.enggeo.2024.107588
M3 - Article
AN - SCOPUS:85195650041
VL - 337
JO - Engineering geology
JF - Engineering geology
SN - 0013-7952
M1 - 107588
ER -