Machine learning in earth, environmental and planetary sciences

• Verfasst von: Bonakdari, Hossein [VerfasserIn]
• Verfasst von: Ebtehaj, Isa [VerfasserIn]
• Verfasst von: Ladouceur, Joseph D. [VerfasserIn]
• Titel: Machine learning in earth, environmental and planetary sciences
• Titelzusatz: theoretical and practical applications
• Verf.angabe: Hossein Bonakdari (Department of Civil Engineering, Faculty of Engineering, University of Ottawa, Ottawa, Canada), Isa Ebtehaj (Soil and Environment Department, Faculy of Agriculture and Food Science, Laval University, Quebec City, Canada), Joseph D. Ladouceur (Department of Civil Engineering, Faculty of Engineering, University of Ottawa, Ottawa, Canada)
• Verlagsort: Amsterdam ; Kidlington, UK ; Cambridge, MA
• Verlag: Elsevier
• E-Jahr: 2023
• Jahr: [2023]
• Umfang: 1 Online-Ressource (xvii, 370 Seiten)
• Illustrationen: Illustrationen
• Fussnoten: Description based on publisher supplied metadata and other sources
• ISBN: 978-0-443-15285-6
• Schlagwörter: (s)Geowissenschaften / (s)Umweltwissenschaften / (s)Maschinelles Lernen
• Datenträger: Online-Ressource
• Sprache: eng
• Bibliogr. Hinweis: Erscheint auch als : Druck-Ausgabe: Bonakdari, Hossein: Machine learning in earth, environmental and planetary sciences. - Amsterdam : Elsevier, 2023. - xvii, 370 Seiten
• Sach-SW: Electronic books
• K10plus-PPN: 1852210435
• K10plus-PPN:
  Universitätsbibliothek
• Lokale URL UB: Zum Volltext

Abstract

Front Cover -- Machine Learning in Earth, Environmental and Planetary Sciences -- Copyright Page -- Dedication -- Contents -- About the authors -- Preface -- Acknowledgments -- About the cover image -- 1 Dataset preparation -- 1.1 The modeling process -- 1.2 Data description -- 1.3 Different types of problems -- 1.3.1 Example 1: a problem with six input variables -- 1.3.1.1 Statistical description of Example 1 data using barplot analysis -- 1.3.1.2 The barplot coding using MATLAB® -- 1.3.2 Example 2: A problem with three input variables -- 1.3.2.1 The histogram analysis for Example 2 training, testing, and total data -- 1.3.2.2 The coding of histogram in MATLAB -- 1.3.3 Example 3: a problem with four input variables -- 1.3.3.1 Boxplot fundamentals -- 1.3.3.2 The boxplot analysis of Example 3, train, test, and total data -- 1.3.3.3 The MATLAB coding of a boxplot -- 1.3.4 Example 4: a problem with five input variables -- 1.3.4.1 3D plot generation of training, testing, and all samples for Example 4 -- 1.3.4.2 The MATLAB coding of 3D plot -- 1.3.5 Example 5: a problem with two input variables -- 1.3.5.1 The time series of the training, testing, and all samples of Example 5 -- 1.3.5.2 The MATLAB coding of time series -- 1.4 Summary -- Appendix 1A Supporting information -- References -- 2 Preprocessing approaches -- 2.1 Normalization -- 2.1.1 The min-max normalization -- 2.1.2 The MATLAB coding of min-max normalization -- 2.1.2.1 The effect of normalization on data distribution -- 2.1.2.2 The details of boxplot coding -- 2.2 Standardization -- 2.2.1 The standardization concept -- 2.2.2 The MATLAB coding of standardization -- 2.2.2.1 The effect of standardization on data distribution -- 2.2.2.2 The details of barplot coding -- 2.3 Data splitting -- 2.3.1 Data splitting conditions -- 2.3.2 The MATLAB coding of data splitting -- 2.4 Cross-validation.