Variable selection in near infrared spectra for the biological characterization of soil and earthworm casts |
| |
| Authors: | Lauric Cécillon Nathalie Cassagne Sonia Czarnes Raphaël Gros Jean-Jacques Brun |
| |
| Institution: | 1. Cemagref Grenoble, Mountain Ecosystems Research Unit, 2 rue de la Papeterie, BP 76, 38402 Saint Martin d''Hères, France;2. French Agency for Environment and Energy Management (ADEME), 2 square La Fayette, BP 90406, 49004 Angers cedex 01, France;3. INRA, URFM, Ecologie des Forêts Méditerranéennes, UR 629, Domaine Saint Paul, Site Agroparc, 84914 Avignon cedex 9, France;4. Université de Lyon, Université Lyon 1, CNRS UMR5557, INRA USC 1193, Ecologie Microbienne, Bât G. Mendel, 43 bd du 11 novembre 1918, 69622 Villeurbanne, France;5. Institut Méditerranéen d''Ecologie et de Paléoécologie (IMEP), Facultés des Sciences St-Jérôme, Boîte 452, 13397 Marseille cedex 20, France |
| |
| Abstract: | Near infrared reflectance spectroscopy (NIRS) was used to predict six biological properties of soil and earthworm casts including extracellular soil enzymes, microbial carbon, potential nitrification and denitrification. Partial least squares regression (PLSR) models were developed with a selection of the most important near infrared wavelengths. They reached coefficients of determination ranging from 0.81 to 0.91 and ratios of performance-to-deviation above 2.3. Variable selection with the variable importance in the projection (VIP) method increased dramatically the prediction performance of all models with an important contribution from the 1750–2500 nm region. We discuss whether selected wavelengths can be attributed to macronutrient availability or to microbial biomass. Wavelength selection in NIR spectra is recommended for improving PLSR models in soil research. |
| |
| Keywords: | |
| 本文献已被 ScienceDirect 等数据库收录！ |
|
