Spiking of NIR regional models using samples from target sites: effect of model size on prediction accuracy.

By César Guerrero, R. Zornoza, I. Gómez, J. Mataix‐Beneyto. 2010

167 citations recorded by the source corpus.

Subfields: Analytical Chemistry, Artificial Intelligence, Environmental Engineering

View Paper: https://www.semanticscholar.org/paper/ce7f0a47e23b15192fd7f0f18d14b8bc8b1fe243

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Analytical Chemistry

1. Abdul Mounem Mouazen
2. Boyan Kuang
3. R. Joffre

In Artificial Intelligence

1. Abdul Mounem Mouazen
2. Boyan Kuang
3. Bo Stenberg
4. R. Joffre
5. Johanna Wetterlind
6. Claudy Jolivet

In Environmental Engineering

1. Abdul Mounem Mouazen
2. Boyan Kuang

Citations in the corpus

• Assessment of soil organic carbon at local scale with spiked NIR calibrations: effects of selection and extra‐weighting on the spiking subset (2014, methodology): “…national calibrations to make predictions at local scales (Brown et al., 2005; Brown, 2007; Janik et al., 2007; Christy, 2008; Sankey et al., 2008; Guerrero et al., 2010; Stenberg et al., 2010; Wetterlind & Stenberg, 2010), even when the local samples fall within the model domain and are not…”
• Influence of the number of samples on prediction error of visible and near infrared spectroscopy of selected soil properties at the farm scale (2011, background): “Guerrero et al. (2010) achieved more accurate calibration (larger R2 and smaller RMSEP) for local, small-size dataset models, after spiking with a few local samples, than models derived from very large libraries.”
• Optimization criteria in sample selection step of local regression for quantitative analysis of large soil NIRS database (2012, background): “Although our spectral library is large and diverse, since samples come from a wide range of soil types, geological bedrocks and land use types, it should be further extended since previous studies have demonstrated that soil property prediction at local scales can be inaccurate even with large spect”
• Prediction of soil organic matter using a spatially constrained local partial least squares regression and the Chinese vis–NIR spectral library (2015, methodology): “A classical way to solve this problem is to use spiking models with a set of local samples from the geographical target site, and the subsequent recalibration of models (Guerrero et al., 2010).”