Application of Soft Computing, Machine Learning, Deep Learning and Optimizations in Geoengineering and Geoscience

✍ Scribed by Wengang Zhang, Yanmei Zhang, Xin Gu, Chongzhi Wu, Liang Han

• Publisher: Springer
• Year: 2021
• Tongue: English
• Leaves: 143
• Edition: 1
• Category: Library

✦ Synopsis

This book summarizes the application of soft computing techniques, machine learning approaches, deep learning algorithms and optimization techniques in geoengineering including tunnelling, excavation, pipelines, etc. and geoscience including the geohazards, rock and soil properties, etc. The book features state-of-the-art studies on use of SC,ML,DL and optimizations in Geoengineering and Geoscience. 

Considering these points and understanding, this book will be compiled with highly focussed chapters that will discuss the application of SC,ML,DL and optimizations in Geoengineering and Geoscience. 

Target audience: (1) Students of UG, PG, and Research Scholars: Several applications of SC,ML,DL and optimizations in Geoengineering and Geoscience can help students to enhance their knowledge in this domain. (2) Industry Personnel and Practitioner: Practitioners from different fields can be able to implement standard and advanced SC,ML,DL and optimizations for solving critical problems of civil engineering.

✦ Table of Contents

Preface
Contents
About the Authors
Abbreviations
1 Introduction
References
2 Soft Computing
2.1 What is Soft Computing
2.2 Components of Soft Computing
2.3 Heuristics and Metaheuristics
2.4 Hybrid Metaheuristics in Soft Computing
2.5 A Data-Driven Nonparametric Explainable MARS Model
References
3 Machine Learning and Applications
3.1 Supervised Learning
3.1.1 ANN
3.1.2 ELM
3.1.3 DT
3.1.4 LR
3.1.5 GP
3.1.6 NB
3.1.7 SVM
3.1.8 KNN
3.2 Unsupervised Learning
3.2.1 K-means
3.2.2 PCA
3.3 Semi-Supervised Learning
References
4 Deep Learning and Applications
4.1 AE
4.2 DBN
4.3 CNN
4.4 RNN
4.5 LSTM
References
5 Optimization Algorithms and Applications
5.1 Precise Algorithm
5.2 Evolutionary Algorithm
5.2.1 GA
5.2.2 BO
5.2.3 PSO
5.2.4 DE
5.2.5 ABC
5.2.6 ACO
5.2.7 CS
5.2.8 FA
5.2.9 GWO
5.2.10 WOA
5.2.11 SFLA
5.2.12 CSO
References
6 Application of LSTM and Prophet Algorithm in Slope Displacement Prediction
6.1 Introduction
6.2 Methodology: Prophet Model
6.2.1 Model Development
6.2.2 The Prediction Process
6.2.3 Evaluation of Modeling Performance
6.3 Case Study
6.3.1 Background
6.3.2 Analysis of the Monitoring Data
6.4 Data Processing and Results Analysis
6.4.1 Displacement Decomposition
6.4.2 Prediction of Trend Displacement
6.4.3 Prediction of Periodic Displacement
6.5 Discussion
6.6 Summary of this Chapter
References
7 Prediction of Undrained Shear Strength Using XGBoost and RF Based on BO
7.1 Introduction
7.2 Methodology
7.2.1 Bayesian Hyper-Parameter Optimization
7.2.2 Sequential Model-Based Optimization (SMBO)
7.3 Databases
7.3.1 Correlation Analysis
7.3.2 Removal of Outliers for USS
7.4 Implementation Procedure
7.4.1 K-fold CV
7.4.2 Comparison Models
7.4.3 Performance Measures
7.5 Calculation Results
7.5.1 Predictive Comparisons Among Different Models
7.5.2 Fitting Performance of XGBoost and RF
7.5.3 Features Importance Analysis
7.6 Summary and Conclusions
References
8 Prediction for TBM Penetration Rate Using Four Hyperparameter Optimization Methods and RF Model
8.1 Introduction
8.2 Engineering Background and Data Introduction
8.2.1 Project Description and Geological Survey
8.2.2 Data Description
8.3 Prediction and Sensitivity Analysis of Driving Speed
8.3.1 Prediction Model
8.3.2 Sensitivity Analysis
8.4 Discussion
8.5 Summary
References
9 What We Have Learnt from the Applications
10 Work Ongoing and Future Recommendations
References