plantspec-package: plantspec: NIR Calibration and Spectral Data Management in R

In griffithdan/plantspec: NIR Calibration and Spectral Data Management in R

Description

This R package provides access to a global dataset of leaf NIR spectra and contains tools for developing Partial Least Squares (PLS) regression models for predicting leaf chemistry. Users can make use of pre-fitted calibrations, add new data and fit new calibrations, and manage their calibrations and datasets. The package represents an efficient workflow for producing robust spectral calibrations.

Details

Resources include:
- Functions for reading and writing spectra.
- Tools for spectral manipulation and management (e.g., preprocessing, conversion, subsetting).
- Tools for sample selection and experimental design (e.g., Kennard-Stone selection).
- Wrapper functions for optimization and fitting of spectral calibration models.
- Methods for plotting spectra and models.
- Data and global calibrations for leaf C, N, P, and K, documented in the companion data package plantspecDB.
- Data for examples, documented in shootout.

See the example below for a simple workflow for fitting a spectral calibration model for nitrogen in a sample dataset.

Package dependencies: - hyperSpec is used to read "spc" files. - soil.spec is used to read "opus" files. Temporarily suspended. - KernSmooth is required to calculate derivitives for spectral transformations. - The pls package is used for all PLS fitting. - Mahalanobis distances are calculated with StatMatch.

Author(s)

Daniel M Griffith <[e-mail]>; T. Michael Anderson <[e-mail]>

References

Bjorn-Helge Mevik, Ron Wehrens and Kristian Hovde Liland (2013). pls: Partial Least Squares and Principal Component regression. R package version 2.4-3. http://CRAN.R-project.org/package=pls

griffithdan/plantspec documentation built on May 17, 2019, 8:37 a.m.