Machine Learning in Earth, Environmental and Planetary Sciences

Theoretical and Practical Applications

1st Edition - June 27, 2023
Authors: Hossein Bonakdari, Isa Ebtehaj, Joseph Ladouceur
Language: English
Paperback ISBN:
9 7 8 - 0 - 4 4 3 - 1 5 2 8 4 - 9
eBook ISBN:
9 7 8 - 0 - 4 4 3 - 1 5 2 8 5 - 6

Machine Learning in Earth, Environmental and Planetary Sciences: Theoretical and Practical Applications is a practical guide on implementing different variety of extreme learning… Read more

Purchase options

Limited Offer

Save 50% on book bundles

Immediately download your ebook while waiting for your print delivery. No promo code is needed.

Institutional subscription on ScienceDirect

Request a sales quote

Machine Learning in Earth, Environmental and Planetary Sciences: Theoretical and Practical Applications is a practical guide on implementing different variety of extreme learning machine algorithms to Earth and environmental data. The book provides guided examples using real-world data for numerous novel and mathematically detailed machine learning techniques that can be applied in Earth, environmental, and planetary sciences, including detailed MATLAB coding coupled with line-by-line descriptions of the advantages and limitations of each method. The book also presents common postprocessing techniques required for correct data interpretation.

This book provides students, academics, and researchers with detailed understanding of how machine learning algorithms can be applied to solve real case problems, how to prepare data, and how to interpret the results.

Cover image
Title page
Table of Contents
Copyright
Dedication
About the authors
Preface
Acknowledgments
About the cover image
Chapter 1. Dataset preparation
Abstract
1.1 The modeling process
1.2 Data description
1.3 Different types of problems
1.4 Summary
Appendix 1A Supporting information
Appendix 1A Supplementary information
References
Chapter 2. Preprocessing approaches
Abstract
2.1 Normalization
2.2 Standardization
2.3 Data splitting
2.4 Cross-validation
2.5 Summary
Appendix 2A Supporting information
Appendix 2A Supplementary information
References
Chapter 3. Postprocessing approaches
Abstract
3.1 Introduction
3.2 Quantitative tools
3.3 Qualitative tools
3.4 Summary
Appendix 3A Supporting information
Appendix 3A Supplementary information
References
Chapter 4. Non-tuned single-layer feed-forward neural network learning machine—concept
Abstract
4.1 Machine learning application in applied science
4.2 Mathematical definition of extreme learning machine model
4.3 Activation function in the extreme learning machine model
4.4 Summary
References
Chapter 5. Non-tuned single-layer feed-forward neural network learning machine—coding and implementation
Abstract
5.1 Introduction
5.2 Extreme learning machine implementation in the MATLAB environment
5.3 Extreme learning machine modeling output
5.4 Calculator for extreme learning machine model
5.5 Effect of the extreme learning machine parameters
5.6 The effect of hidden layer neurons on Example 5
5.7 Summary
Appendix 5.A Supporting information
Appendix 5.A Supporting information
References
Chapter 6. Outlier-based models of the non-tuned neural network—concept
Abstract
6.1 Background of extreme learning machines
6.2 Extreme learning machine in the presence of outliers
6.3 Mathematical definition of extreme learning machine-based models
6.4 Summary
References
Chapter 7. Outlier-based models of the non-tuned neural network—coding and implementation
Abstract
7.1 Developed extreme learning machine-based approaches in the presence of outliers
7.2 Implementation of the developed extreme learning machine-based models in the MATLAB
7.3 Calculator for outlier-based extreme learning machine models
7.4 Evaluating the effects of user-defined parameters on the modeling results of the extreme learning machine-based models
7.5 Summary
Appendix 7.A Supporting information
References
Chapter 8. Online sequential non-tuned neural network—concept
Abstract
8.1 Introduction
8.2 Main architectures of the single-layer feed-forward neural network
8.3 Development of the sequential-based learning algorithm
8.4 Main drawbacks of the classical sequential-based learning algorithms
8.5 Introduction to the online sequential extreme learning machine
8.6 Mathematical description of the online sequential extreme learning machine
8.7 Summary
References
Chapter 9. Online sequential nontuned neural network—coding and implementation
Abstract
9.1 Summary of the online sequential extreme learning machine-based modeling algorithm
9.2 Implementation of the online sequential extreme learning machine in the MATLAB environment
9.3 Online sequential extreme learning machine calculator
9.4 Evaluating the effect of the online sequential extreme learning machine parameters on model performance
9.5 Summary
Appendix 9.A Supporting information
Appendix 9.A Supplementary information
References
Chapter 10. Self-adaptive evolutionary of non-tuned neural network—concept
Abstract
10.1 Development process of single-layer feedforward neural network
10.2 Mathematical explanation of self-adaptive evolutionary extreme learning machine
10.3 Summary
References
Chapter 11. Self-adaptive evolutionary of non-tuned neural network—coding and implementation
Abstract
11.1 Implementation of the self-adaptive evolutionary extreme learning machine in detail
11.2 Calculator for self-adaptive machine learning model
11.3 Sensitivity analysis of the self-adaptive machine learning model parameters
11.4 Summary
Appendix 11A Supporting information
Appendix 11.A Supplementary information
References
Index

Hossein Bonakdari

Dr. Bonakdari obtained his PhD in Civil Engineering from the University of Caen Normandy (France). He has worked for several organizations and most recently as an Associate Professor at the Department of Civil Engineering of the University of Ottawa (Canada). He is one of the most influential scientists in the field of developing novel algorithms for solving practical problems through the decision-making abilities of AI. His research also focuses on creating comprehensive methodologies in the areas of simulation modeling, optimization, and machine learning algorithms. The results obtained from his research have been published in international journals and presented at international conferences. He was included in the list of the world's top 2% scientists, published by Stanford University, and is on the Editorial board of several journals.

Affiliations and expertise

Associate Professor, Department of Civil Engineering, Faculty of Engineering, University of Ottawa, Ottawa, Ontario, Canada

Isa Ebtehaj

Isa Ebtehaj is a PhD student in the Soil and Environment department at the Faculty of Agriculture and Food Science, Laval University, Canada. He obtained his MSc degree from Razi University in 2014 and his MSc thesis was nominated as the best thesis by the Iranian Water and Wastewater Engineering Association, the Iranian Hydraulic Association, and the Vice-Presidency for Science and Technology (Iran). His fields of specialization and interest include machine learning, development of hybrid model methods, evolutionary optimization, hydrological time series, and sediment transport. From 2014 to 2019, he participated as a researcher in several industrial research projects through the Water and Wastewater Research Center and the Environmental Research Center, Razi University. Results obtained from his research studies have been published in more than 100 papers in international journals. He also has more than 30 presentations at national and international conferences and has published eight book chapters.

Affiliations and expertise

PhD Student, Soil and Environment Department, Faculty of Agriculture and Food Science, Laval University, Canada

Joseph Ladouceur

Joseph Ladouceur is a current PhD Student at the University of Ottawa. Having completed his BASc in civil engineering at the University of Ottawa with Summa Cum Laude distinction, Joseph fast-tracked to the PhD program under the supervision of Dr. Roberto Narbaitz and Dr. Christopher Lan. A previous NSERC CGS-M award holder, his research interests are focused on pre-treatment strategies for drinking water. Prior to commencing his doctoral studies, Joseph worked as a senior inspector at McIntosh Perry Consulting Engineers Ltd. performing services on provincial bridge infrastructure projects. Joseph is a registered EIT with Professional Engineers Ontario and a member of the American Water Works Association.

Affiliations and expertise

PhD Student, Department of Civil Engineering, Faculty of Engineering, University of Ottawa, Canada