Skip to main content
Disciplines
Automotive Business IT + Informatics Construction + Real Estate Electrical Engineering + Electronics Energy + Sustainability Insurance + Risk Finance + Banking Management + Leadership Marketing + Sales Mechanical Engineering + Materials
Events
DE
EN
Books
Journals
Topic Page
Marketing
Start single access now
Access for companies
EXTENDED SEARCH
Log in
Top

2022 | Book

Introduction Read chapter Read first chapter

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

Authors: Ph.D. Wengang Zhang, Assoc. Prof. Yanmei Zhang, Xin Gu, Chongzhi Wu, Liang Han

Publisher: Springer Singapore

Part of: Springer Professional "Wirtschaft+Technik" , Springer Professional "Technik" , Springer Professional "Wirtschaft"

Login to get access
insite
SEARCH

About this book

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

Frontmatter
Chapter 1. Introduction
Abstract
Before the introduction of the more commonly used Artificial intelligence (AI), Machine learning (ML), Deep learning (DL) and Optimization algorithm (OA) technical expressions, the definition of Soft computing (SC) should be firstly mentioned since the former three terms are more relevant with each other.
Wengang Zhang, Yanmei Zhang, Xin Gu, Chongzhi Wu, Liang Han
Chapter 2. Soft Computing
Abstract
As indicated in the introduction part and the plot, definition of SC has some overlaps with ML, DL, and OA. It uses component fields of study in: Fuzzy logic, Machine learning, Probabilistic reasoning, Evolutionary computation, Perceptron, Genetic algorithms, Differential algorithms, Support vector machines, Metaheuristics, Swarm intelligence, Ant colony optimization, Particle optimization, Bayesian networks, Artificial neural networks, Expert systems, etc. As a field of mathematical and computer study, SC has been around since the 1990s. The inspiration was the human mind's ability to form real-world solutions to problems through approximation. It contrasts with possibility, an approach that is used when there is not enough information available to solve a problem. In contrast, SC is used where the problem is not adequately specified for the use of conventional math and computer techniques. It has numerous real-world applications in domestic, commercial and industrial situations.
Wengang Zhang, Yanmei Zhang, Xin Gu, Chongzhi Wu, Liang Han
Chapter 3. Machine Learning and Applications
Abstract
By definition from IBM, ML is a branch of AI and computer science which focuses on the use of data and algorithms to imitate the way that humans learn, gradually improving its accuracy. ML falls into three primary categories: Supervised learning, Unsupervised learning, as well as the Semi-supervised learning.
Wengang Zhang, Yanmei Zhang, Xin Gu, Chongzhi Wu, Liang Han
Chapter 4. Deep Learning and Applications
Abstract
DL attempts to mimic the human brain, albeit far from matching its ability, enabling systems to cluster data and make predictions with incredible accuracy. It consist of multiple layers of interconnected nodes, each building upon the previous layer to refine and optimize the prediction or categorization. This progression of computations through the network is called forward propagation. The input and output layers of a deep neural network are called visible layers. The input layer is where the deep learning model ingests the data for processing, while the output layer is where the final prediction or classification is made.
Wengang Zhang, Yanmei Zhang, Xin Gu, Chongzhi Wu, Liang Han
Chapter 5. Optimization Algorithms and Applications
Abstract
When you’re trying to make tough decisions about questions that involve an inordinate number of factors, optimization helps you to capture key components to build a mathematical model of the engineering situation, giving you the confidence to make better decisions more quickly.
Wengang Zhang, Yanmei Zhang, Xin Gu, Chongzhi Wu, Liang Han
Chapter 6. Application of LSTM and Prophet Algorithm in Slope Displacement Prediction
Abstract
China is one of the countries with the most serious geological disasters in the world (Wang et al.,.Landslides 1:157–162, 2004; Keqiang et al.,.Environ Geol 55:55–63, 2008; Li et al., Environ Earth Sci 60:677–687, 2010; Du et al.,.Landslides 10:203–218, 2013). In some cases, landslides can cause huge losses in human lives and properties as well as impose significant impacts on the environment (Yin et al.,.Landslides 7:339–349, 2010; Zhang et al., Front Struct Civ Eng 14:1247–1261, 2020a). Specially, due to the complex geological conditions associated with high mountain areas and intensive human engineering activities, landslides occur frequently in the Three Gorges Reservoir (TGR) region, where steep slopes exist and flooding often occurs (Xu and Niu,.Comput Geosci 111:87–96, 2018; Xie et al.,.IEEE Access 7:54,305–54,311, 2019).
Wengang Zhang, Yanmei Zhang, Xin Gu, Chongzhi Wu, Liang Han
Chapter 7. Prediction of Undrained Shear Strength Using XGBoost and RF Based on BO
Abstract
Soft sensitive clays are generally characterized by low shear strength and high compressibility and widely distributed in a near marine environment. Therefore, geotechnical design involving soft sensitive clays is rather challenging (D’Ignazio et al. D’Ignazio et al. Can Geotech J 53:1628–1645, 2016).
Wengang Zhang, Yanmei Zhang, Xin Gu, Chongzhi Wu, Liang Han
Chapter 8. Prediction for TBM Penetration Rate Using Four Hyperparameter Optimization Methods and RF Model
Abstract
With the continuous development and progress of technology, the emergence of tunnel boring machine (TBM) provides a safer, more effective and cheaper construction method for tunnel digging.
Wengang Zhang, Yanmei Zhang, Xin Gu, Chongzhi Wu, Liang Han
Chapter 9. What We Have Learnt from the Applications
Abstract
It is well known that the use of SC and more advanced AI techniques including ML, DL and OA has greatly improved the accuracy and efficiency of prediction for the responses of geotechnical engineering structures.
Wengang Zhang, Yanmei Zhang, Xin Gu, Chongzhi Wu, Liang Han
Chapter 10. Work Ongoing and Future Recommendations
Abstract
Machine learning models are built on data, and by design they do not incorporate any physical law (such as mass and energy balance) and do not extrapolate well beyond the range of the training data. Historically, physical modelling and machine learning have generally been treated as two different fields or avenues with very different scientific paradigms (theory-driven versus data-driven, as depicted in Fig. 10.1).
Wengang Zhang, Yanmei Zhang, Xin Gu, Chongzhi Wu, Liang Han
Metadata
Title
Application of Soft Computing, Machine Learning, Deep Learning and Optimizations in Geoengineering and Geoscience
Authors
Ph.D. Wengang Zhang
Assoc. Prof. Yanmei Zhang
Xin Gu
Chongzhi Wu
Liang Han
Copyright Year
2022
Publisher
Springer Singapore
Electronic ISBN
978-981-16-6835-7
Print ISBN
978-981-16-6834-0
DOI
https://doi.org/10.1007/978-981-16-6835-7