內容大鋼
This book focuses on the application of machine learning in slope stability assessment.The contents include: overview of machine learning approaches, the mainstream smart in-situ monitoring techniques, the applications of the main machine learning algorithms, including the supervised learning, unsupervised learning, semi- supervised learning, reinforcement learning, deep learning, ensemble learning, etc., in slopeengineering and landslide prevention, introduction of the smart in-situ monitoring and slope stability assessment based on two well-documented case histories, the prediction of slope stability using ensemble learning techniques, the application of Long Short-Term Memory Neural Network and Prophet Algorithm in Slope Displacement Prediction, displacement prediction of Jiuxianping landslide using gated recurrent unit (GRU) networks, seismic stability analysis of slopes subjected to water level changes using gradient boosting algorithms, efficient reliability analysis of slopes in spatially variable soils using XGBoost, efficient time-variant reliability analysis of Bazimen landslide in the Three Gorges Reservoir Area using XGBoost and LightGBM algorithms, as well as the future work recommendation.The authors also provided their own thoughts learnt from these applications as well as work ongoing and future recommendations.
目錄
1 Overview
1.1 Slope Stability Analysis Methods
1.1.1 Theoretical Solutions
1.1.2 Numerical Simulations
1.1.3 Physical Experimentations
1.2 Remote Monitoring Methods
1.3 Machine Learning Approaches
1.3.1 What is Machine Learning
1.3.2 How Machine Learning Works
1.3.3 Machine Learning Methods
1.3.4 What is Deep Learning
1.3.5 Deep Learning Versus Machine Learning
1.3.6 How Deep Learning Works
1.4 Organization of This Book
References
2 Machine Learning Algorithms
2.1 Supervised Learning
2.2 Unsupervised Learning
2.3 Semi-supervised Learning
2.4 Reinforcement Learning
2.5 Regression Algorithm
2.6 Case-Based Algorithm
2.7 Regularization Method
2.8 Decision Tree
2.9 Bayesian Method
2.10 Kernel-Based Algorithm
2.11 Clustering
2.12 Association Rule Learning
2.13 Artificial Neural Network
2.14 Deep Learning
2.15 Dimension Reduction
2.16 Ensemble Learning
References
3 Real-Time Monitoring and Early Warning of Landslide
3.1 Introduction
3.2 Real-Time Monitoring Network
3.3 Intelligent Early Warning System
3.3.1 Early Warning Model and Alert Criteria
3.3.2 3D-Web Early Warning System
3.4 Application
3.4.1 Introduction of Longjing Rocky Landslide
3.4.2 Geological Setting and Deformation History
3.4.3 Successful Monitoring and Early Warning
3.5 Conclusions
References
4 Prediction of Slope Stability Using Ensemble Learning Techniques
4.1 Introduction
4.2 Study Area
4.2.1 Topographic Conditions
4.2.2 Geological Conditions
4.2.3 The Features of Landslide Cases
4.3 Methodology
4.3.1 Extreme Gradient Boosting
4.3.2 Random Forest
4.3.3 Data Preprocessing and Performance Measures
4.4 Results and Discussion
4.5 Summary and Conclusions
References
5 Landslide Susceptibility Research Combining Qualitative Analysis and Quantitative Evaluation: A Case Study of Yunyang County in Chongqing, China
5.1 Introduction
5.2 Study Area
5.3 Method Explanation
5.3.1 Random Forest
5.3.2 Grid Search
5.3.3 Performance Measure
5.4 Methodology
5.4.1 Data Collection and Preparation
5.4.2 Model Development and Application
5.5 Results
5.6 Discussion
5.6.1 Feature Importance Analysis
5.6.2 Model Comparison
5.7 Summary and Conclusion
References
6 Application of Transfer Learning to Improve Landslide Susceptibility Modeling Performance
6.1 Introduction
6.2 Study Area
6.3 Transfer Learning
6.4 Methodology
6.4.1 Data Preparation
6.4.2 Data Extraction and Model Preparation
6.4.3 Model Application and Evaluation
6.5 Results and Discussion
6.6 Summary and Conclusion
References
7 Displacement Prediction of Jiuxianping Landslide Using GRU Networks
7.1 Introduction
7.2 Machine Learning Techniques
7.2.1 Multivariate Adaptive Regression Splines
7.2.2 Random Forest Regression
7.2.3 Artificial Neural Network
7.2.4 Gated Recurrent Unit
7.3 Case Study: Jiuxianping Landslide
7.3.1 Geological Conditions
7.3.2 Deformation Characteristics Analysis
7.3.3 Decomposition of the Curnulative Displacement
7.3.4 Performance Measures
7.4 Results and Discussion
7.4.1 Trend Displacement Prediction
7.4.2 Periodic Displacement Prediction
7.4.3 Cumulative Displacement Prediction
7.5 Summary and Conclusions
References
8 Efficient Seismic Stability Analysis of Slopes Subjected to Water Level Changes Using Gradient Boosting Algorithms
8.1 Introduction
8.2 Methodologies
8.2.1 Categorical Boosting
8.2.2 Light Gradient Boosting Machine
8.2.3 Extreme Gradient Boosting
8.3 Implementation Procedure
8.4 Illustrative Example
8.4.1 Database Preparation for Model Calibration
8.5 Summary and Conclusions
References
9 Efficient Reliability Analysis of Slopes in Spatially Variable Soils Using XGBoost
9.1 Introduction
9.2 Deterministic Analysis of Earth Dam Slope Stability
9.2.1 Seepage Analysis Under Steady Seepage Condition
9.2.2 Slope Stability Analysis
9.3 Random Field Modeling of Spatially Variable Soil Properties
9.4 XGBoost-Based Reliability Analysis Approach
9.4.1 Introduction of XGBoost
9.4.2 Evaluation of the Failure Probability Using XGBoost
9.5 Implementation Procedure
9.6 Application to Ashigong Earth Dam Slope
9.6.1 Construction of XGBoost Model
9.6.2 Effect of COV on the Earth Dam Slope Failure Probability
9.7 Summary and Conclusions
References
10 Efficient Time-Variant Reliability Analysis of Bazimen Landslide in the TGRA Using XGBoost and LightGBM
10.1 Introduction
10.2 Methodology
10.2.1 Extreme Gradient Boosting
10.2.2 Light Gradient Boosting Machine
10.2.3 Hyperparameter Optimization
10.2.4 Evaluation Indicators
10.3 ML-Based Time-Variant Reliability Analysis
10.3.1 Monte Carlo Simulation
10.3.2 Calculation of Time-Variant Failure Probability
10.4 Implementation Procedure
10.5 Application to Bazimen Landslide in the TGRA
10.5.1 Construction of XGBoost and LightGBM Models
10.5.2 Performance of Model Averaging
10.5.3 Comparison of the Proposed Approaches and Prophet Model
10.5.4 Feature Importance Analysis
10.6 Summary and Conclusions
References
11 Future Work Recommendation
Appendix
[