Premium
Predicting Physical and Chemical Properties of US Soils with a Mid‐Infrared Reflectance Spectral Library
Author(s) -
Wijewardane Nuwan K.,
Ge Yufeng,
Wills Skye,
Libohova Zamir
Publication year - 2018
Publication title -
soil science society of america journal
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.836
H-Index - 168
eISSN - 1435-0661
pISSN - 0361-5995
DOI - 10.2136/sssaj2017.10.0361
Subject(s) - silt , partial least squares regression , cation exchange capacity , total organic carbon , soil water , soil test , soil carbon , chemistry , soil science , potassium , environmental chemistry , environmental science , mineralogy , mathematics , geology , paleontology , statistics , organic chemistry
Core Ideas A mid‐infrared spectral library containing 20,000+ samples was reported. Twelve soil physical and chemical properties were predicted with MIR spectra. ANN models performed better than PLSR for most soil properties. Horizon and taxonomic order as auxiliary variables improved prediction for PLSR. MIR library has the potential as an alternative to laboratory‐based analysis for OC and IC. Mid‐infrared (MIR) reflectance spectroscopy is commonly studied as a rapid and nondestructive method for predictive soil analysis under laboratory conditions. The first objective of this paper is to report an MIR spectral library based on 20,000+ soil samples collected from the United States. The second objective is to assess, using partial least squares regression (PLSR) and artificial neural networks (ANN), the performance of the library to predict 12 physical and chemical soil properties: organic carbon (OC), inorganic carbon (IC), total carbon (TC), total nitrogen (TN), clay, silt, sand, Mehlich‐3 extractable phosphorus (P), NH 4 OAc extractable potassium (K), cation exchange capacity (CEC), total sulfur (TS), and pH. The third objective is to investigate whether the use of auxiliary variables of master horizon (HZ), taxonomic order (TAXON), and land use land cover (LULC) would improve MIR model performance. The results showed that OC, IC, TC, TN and TS were predicted most satisfactorily with R 2 > 0.95 and RPD (ratio of performance to deviation) > 5.5. Soil CEC, pH, clay, silt, and sand were also predicted satisfactorily with R 2 > 0.75 and RPD > 2.0. P and K were predicted poorly, with R 2 < 0.4 and RPD < 1.4. The ANN models generally outperformed PLSR models, except for clay, silt and sand. Using auxiliary variables (HZ, TAXON, and LULC) to develop stratified models generally improved model performance. The HZ‐specific models showed the greatest improvements. Using an MIR spectral library for routine soil analysis would positively impact many modern applications where high spatial resolution, quantitative soil data are demanded.