A generic framework for geotechnical subsurface modeling with machine learning
This study introduces a generic framework for geotechnical subsurface modeling, which accounts for spatial autocorrelation with local mapping machine learning (ML) methods. Instead of using XY coordinate fields directly as model input, a series of autocorrelated geotechnical distance fields (GDFs) i...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2022-10-01
|
| Series: | Journal of Rock Mechanics and Geotechnical Engineering |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S1674775522001664 |
| _version_ | 1811264398589689856 |
|---|---|
| author | Jiawei Xie Jinsong Huang Cheng Zeng Shan Huang Glen J. Burton |
| author_facet | Jiawei Xie Jinsong Huang Cheng Zeng Shan Huang Glen J. Burton |
| author_sort | Jiawei Xie |
| collection | DOAJ |
| description | This study introduces a generic framework for geotechnical subsurface modeling, which accounts for spatial autocorrelation with local mapping machine learning (ML) methods. Instead of using XY coordinate fields directly as model input, a series of autocorrelated geotechnical distance fields (GDFs) is designed to enable the ML models to infer the spatial relationship between the sampled locations and unknown locations. The whole framework using GDF with ML methods is named GDF-ML. This framework is purely data-driven which avoids the tedious work in the scale of fluctuations (SOFs) estimating and data detrending in the conventional spatial interpolation methods. Six local mapping ML methods (extra trees (ETs), gradient boosting (GB), extreme gradient boosting (XGBoost), random forest (RF), general regression neural network (GRNN) and k-nearest neighbors (KNN)) are compared in the GDF-ML framework. The results show that the GDFs are better than the conventional XY coordinate fields based ML methods in both accuracy and spatial continuity. GDF-ML is flexible which can be applied to high-dimensional, multi-variable and incomplete datasets. Among these six methods, GDF with ET method (GDF-ET) clearly shows the best accuracy and best spatial continuity. The proposed GDF-ET method can provide a fast and accurate interpretation of the soil property profile. Sensitivity analysis shows that this method is applicable to very small training dataset size. The associated statistical uncertainty can also be quantified so that the reliability of the subsurface modeling results can be estimated objectively and explicitly. The uncertainty results clearly show that the prediction becomes more accurate when more sampled data are available. |
| first_indexed | 2024-04-12T20:03:42Z |
| format | Article |
| id | doaj.art-7e4482bae25f474c9559fde86117866e |
| institution | Directory Open Access Journal |
| issn | 1674-7755 |
| language | English |
| last_indexed | 2024-04-12T20:03:42Z |
| publishDate | 2022-10-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Journal of Rock Mechanics and Geotechnical Engineering |
| spelling | doaj.art-7e4482bae25f474c9559fde86117866e2022-12-22T03:18:28ZengElsevierJournal of Rock Mechanics and Geotechnical Engineering1674-77552022-10-0114513661379A generic framework for geotechnical subsurface modeling with machine learningJiawei Xie0Jinsong Huang1Cheng Zeng2Shan Huang3Glen J. Burton4Discipline of Civil, Surveying and Environmental Engineering, Priority Research Centre for Geotechnical Science and Engineering, The University of Newcastle, Callaghan, NSW, 2308, AustraliaDiscipline of Civil, Surveying and Environmental Engineering, Priority Research Centre for Geotechnical Science and Engineering, The University of Newcastle, Callaghan, NSW, 2308, Australia; Corresponding author.Discipline of Civil, Surveying and Environmental Engineering, Priority Research Centre for Geotechnical Science and Engineering, The University of Newcastle, Callaghan, NSW, 2308, AustraliaDiscipline of Civil, Surveying and Environmental Engineering, Priority Research Centre for Geotechnical Science and Engineering, The University of Newcastle, Callaghan, NSW, 2308, AustraliaATC Williams Pty. Ltd., Singleton, NSW, 2330, AustraliaThis study introduces a generic framework for geotechnical subsurface modeling, which accounts for spatial autocorrelation with local mapping machine learning (ML) methods. Instead of using XY coordinate fields directly as model input, a series of autocorrelated geotechnical distance fields (GDFs) is designed to enable the ML models to infer the spatial relationship between the sampled locations and unknown locations. The whole framework using GDF with ML methods is named GDF-ML. This framework is purely data-driven which avoids the tedious work in the scale of fluctuations (SOFs) estimating and data detrending in the conventional spatial interpolation methods. Six local mapping ML methods (extra trees (ETs), gradient boosting (GB), extreme gradient boosting (XGBoost), random forest (RF), general regression neural network (GRNN) and k-nearest neighbors (KNN)) are compared in the GDF-ML framework. The results show that the GDFs are better than the conventional XY coordinate fields based ML methods in both accuracy and spatial continuity. GDF-ML is flexible which can be applied to high-dimensional, multi-variable and incomplete datasets. Among these six methods, GDF with ET method (GDF-ET) clearly shows the best accuracy and best spatial continuity. The proposed GDF-ET method can provide a fast and accurate interpretation of the soil property profile. Sensitivity analysis shows that this method is applicable to very small training dataset size. The associated statistical uncertainty can also be quantified so that the reliability of the subsurface modeling results can be estimated objectively and explicitly. The uncertainty results clearly show that the prediction becomes more accurate when more sampled data are available.http://www.sciencedirect.com/science/article/pii/S1674775522001664Site investigationMachine learning (ML)Spatial interpolationGeotechnical distance fields (GDFs)Tree-based models |
| spellingShingle | Jiawei Xie Jinsong Huang Cheng Zeng Shan Huang Glen J. Burton A generic framework for geotechnical subsurface modeling with machine learning Journal of Rock Mechanics and Geotechnical Engineering Site investigation Machine learning (ML) Spatial interpolation Geotechnical distance fields (GDFs) Tree-based models |
| title | A generic framework for geotechnical subsurface modeling with machine learning |
| title_full | A generic framework for geotechnical subsurface modeling with machine learning |
| title_fullStr | A generic framework for geotechnical subsurface modeling with machine learning |
| title_full_unstemmed | A generic framework for geotechnical subsurface modeling with machine learning |
| title_short | A generic framework for geotechnical subsurface modeling with machine learning |
| title_sort | generic framework for geotechnical subsurface modeling with machine learning |
| topic | Site investigation Machine learning (ML) Spatial interpolation Geotechnical distance fields (GDFs) Tree-based models |
| url | http://www.sciencedirect.com/science/article/pii/S1674775522001664 |
| work_keys_str_mv | AT jiaweixie agenericframeworkforgeotechnicalsubsurfacemodelingwithmachinelearning AT jinsonghuang agenericframeworkforgeotechnicalsubsurfacemodelingwithmachinelearning AT chengzeng agenericframeworkforgeotechnicalsubsurfacemodelingwithmachinelearning AT shanhuang agenericframeworkforgeotechnicalsubsurfacemodelingwithmachinelearning AT glenjburton agenericframeworkforgeotechnicalsubsurfacemodelingwithmachinelearning AT jiaweixie genericframeworkforgeotechnicalsubsurfacemodelingwithmachinelearning AT jinsonghuang genericframeworkforgeotechnicalsubsurfacemodelingwithmachinelearning AT chengzeng genericframeworkforgeotechnicalsubsurfacemodelingwithmachinelearning AT shanhuang genericframeworkforgeotechnicalsubsurfacemodelingwithmachinelearning AT glenjburton genericframeworkforgeotechnicalsubsurfacemodelingwithmachinelearning |