Analytical Sciences

Use of Radial Basis Function Networks and Near-Infrared Spectroscopy for the Determination of Total Nitrogen Content in Soils from Sao Paulo State

Paulo H. FIDÊNCIO,* Ronei J. POPPI,** João C. de ANDRADE,** and Mônica F. de ABREU***

*Universidade Federal do Tocantins, CP 66, 77402-970, Gurupi-TO, Brazil
**Universidade Estadual de Campinas, Instituto de Química, CP 6154, 13083-970, Campinas-SP, Brazil
***Instituto Agronômico de Campinas, CP 28, 13001-970, Campinas-SP, Brazil

Total nitrogen has been determined by using a model developed between the conventional chemical measurements and diffuse reflectance spectra in the near-infrared region. Samples (244) from different types of soils with total nitrogen contents ranging from 0.20 to 13.60% (m/m) were modeled by partial least-squares regression (PLS), multi-layer perceptron feed-forward networks (MLP) and radial basis function networks (RBFN). The RBFN model produced a better square error of prediction (SEP) of 0.048 and R² = 0.93 in a procedure that is simpler, faster and less dependent on the initial conditions.

J-STAGE: View this article in J-STAGE