Comparison among principal component, partial least squares and back propagation neural network analyses for accuracy of measurement of selected soil properties with visible and near infrared…

By Abdul Mounem Mouazen, Boyan Kuang, J. Baerdemaeker, H. Ramon. 2010

418 citations recorded by the source corpus.

Subfields: Analytical Chemistry, Environmental Engineering, Mechanical Engineering

View Paper: https://www.semanticscholar.org/paper/8708b5d92c1bfe91815644fa0ec2e590d3041da5

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

In Environmental Engineering

In Mechanical Engineering

Citations in the corpus

Influence of the number of samples on prediction error of visible and near infrared spectroscopy of selected soil properties at the farm scale (2011, methodology): “…of PA. Visible and near infrared (vis-NIR) spectroscopy is a proven technique for a fast, inexpensive and relatively accurate alternative method to other laboratory analyses of soil properties (Viscarra Rossel & McBratney, 1998; Shepherd & Walsh, 2002; Mouazen et al., 2010; Stenberg et al., 2010).”
Evaluating calibration methods for predicting soil available nutrients using hyperspectral VNIR data (2018, methodology): “To avoid this, LVs obtained from the PLSR were adopted as the input spectral features for LS-SVM and BPNN; this proved to be an effective way of reducing computational resources and improving the generalization (e.g., Janik et al., 2007; Morellos et al., 2016; Mouazen et al., 2010).”
Estimating the soil clay content and organic matter by means of different calibration methods of vis-NIR diffuse reflectance spectroscopy (2016, neutral): “Therefore, selection of the calibration method and its performance in modelling reflectance spectra is one of the main factors for calibration success (Mouazen et al., 2010).”
Accurate and Precise Prediction of Soil Properties from a Large Mid-Infrared Spectral Library (2019, methodology): “Recently, machine learning (ML) algorithms, such as artificial neural networks (ANN), support vector machines (SVM), Cubist, random forest (RF) and memory-based learning (MBL), have been increasingly used to model and map soil properties at local to global scales [19,25,30,33,34].”
Variable indicators for optimum wavelength selection in diffuse reflectance spectroscopy of soils (2016, methodology): “…(Field Spec 3 FR, Analytical Spectral Devices Inc.) equipped with a contact probe of 10 mm spot size was used to record the proximal spectral reflectance (350–2500 nm) from a leveled surface (Mouazen et al., 2010) of about 50 g soil sample placed in an aluminum moisture box (10 cm diameter).”