Keywords
R Programming, ,Spectral Data Analysis, Hyperspectral Modeling, Data Pre-processing, Wavelet Transform, Savitzky–Golay Smoothing, Fractional Derivatives PLSR (Partial Least Squares Regression), Machine Learning, Support Vector Machine (SVM), Random Forest (RF), XGBoost, LASSO Regression,Ridge Regression, Elastic Net, K-Nearest Neighbors (KNN), Cross-Validation, Taylor Diagram, Soil Spectroscopy, Calibration and ValidationSoil Spectral Analysis in R
edited by: Nirmal Kumar, Roshan Wakode, Sudarshan Bhoyar, N K Sinha, R N Sahoo & P SantraLength: 22.9 mm | Breadth: 15.2 mm | Height: 1.610 mm | Imprint: NIPA | Weight: 0.446 GMS
This manual aims to highlight the importance of soil spectral data in advancing soil science and underscores the central role of R software in this transformation. Whether applied in academic research, agricultural consultancy, or environmental conservation, this manual may be useful to understand and effectively utilize soil spectral data in predicting soil properties. However, new users often find it difficult to navigate R’s extensive functionality, especially when it comes to soil spectral analysis, as comprehensive resources and codes for all types of spectral analysis are not readily available in one place.
The book Soil Spectral Analysis in R aims to bridge this gap by providing a comprehensive guide with ready-to-use codes for most operations related to spectral data analysis. This book is designed to give the user a guided tour of the R platform for spectral data modeling using machine learning, with a focus on methods used predominantly in scientific publication. There are 5 chapters which mainly deal with Introduction to R, soil spectral data handling in R, spectral data pre-processing, and Spectral data modeling.
Nirmal Kumar: Senior Scientist, Division of Remote Sensing Applications,ICAR-NBSS&LUP,Nagpur-440 033, Maharashtra
Roshan Wakode: Young Professional-II,Division of Remote Sensing Applications,ICAR-NBSS&LUP,Nagpur-440 033, Maharashtra
Sudarshan Bhoyar:Senior Research Fellow, Division of Remote Sensing Applications,ICAR-NBSS&LUP,Nagpur-440 033, Maharashtra
N K Sinha: Senior Scientist,Division of Soil Physics, ICAR-IISS, Bhopal- 462038, Madhya Pradesh
R N Sahoo: Principal Scientist, Division of Agricultural Physics,ICAR-IARI,New Delhi-110 012
P Santra: Principal Scientist and Head, Division of Natural Resources,ICAR-CAZRI,Jodhpur- 342 003, Rajasthan
Preface
Chapter 1. Introduction to R
1.1. Download and Install R
1.2. Download and Install R Studio
1.3. Updating R
1.4. R Packages
1.5. Setting up working directory
Chapter 2. Data Handling in R
2.1. Primary spectral data Processing
2.2. Importing Data in R
2.3. Viewing Imported Data
2.4. Importing Microsoft Office Excel Files
2.5. Creating a Data Frame in R
2.6. Exporting Data
2.7. Data Manipulation
2.8. Prepare data for spectral modeling
Chapter 3. Spectral Data Pre-Processing
3.1. Wavelet Transform
3.2. Fractional derivative
3.3. Moving Average Smoothing of Spectra
3.4. Savitzky-Golay filter
3.5. Transformation to 1st, 2nd derivatives
3.6. Plotting reflectance spectra
Chapter 4. Spectral Data Modeling
4.1. Data set generation for modelling
4.2. Parttion of Data into calibration and validation of data sets
4.3. Cross-validation
4.4. PLSR Model fit for spectral data and soil properties
4.5. Visualization, Prediction and Presentation of models for interpretation
Chapter 5. Spectral Data Modelling with other Machine Learning Algorithms
5.1 Principal Component Regression (PCR)
5.2. Support Vector Machine (SVM)
5.3 Random Forest: RF
5.4 Quantile Regression Forests (QRF)
5.5 Extreme Gradient Boosting (XGBoost)
5.6. Least Absolute Shrinkage and Selection Operator (LASSO)
5.7. RIDGERegression
5.8. Elastic Net (EN)
5.9. K-Nearest Neighbors (KNN)
5.10. Model performance comparision with Taylor Diagram
References