The shortage of information on soil chemical, physical and mineralogical properties is one of the major limitations to suitable management of agriculture and forest systems. In many areas knowledge on soil properties is based on (“ethno-knowledge”), rather than on precise laboratory measurements. One of the main causes of this behavior is the relatively high cost of conventional soil analysis. A need then exists to implement and/or validate alternative, low cost and reliable techniques to assist soil characterization. In the recent years, particular attention has been paid to reflectance spectrometry (RS) in 350-2500 spectral domain. A comparative study was then carried out to investigate the potential of Artificial Neural Network algorithms (ANN), Partial Least Squares Regression analysis (PLSR) and Simple Genetic Algorithms (SGA) to predict important soil physical and chemical properties from spectro-radiometric data.

Prediction of soil properties from reflectance spectroscopy using multivariate statistical analysis and artificial intelligence methods. A comparative study

Amenta P.
2010-01-01

Abstract

The shortage of information on soil chemical, physical and mineralogical properties is one of the major limitations to suitable management of agriculture and forest systems. In many areas knowledge on soil properties is based on (“ethno-knowledge”), rather than on precise laboratory measurements. One of the main causes of this behavior is the relatively high cost of conventional soil analysis. A need then exists to implement and/or validate alternative, low cost and reliable techniques to assist soil characterization. In the recent years, particular attention has been paid to reflectance spectrometry (RS) in 350-2500 spectral domain. A comparative study was then carried out to investigate the potential of Artificial Neural Network algorithms (ANN), Partial Least Squares Regression analysis (PLSR) and Simple Genetic Algorithms (SGA) to predict important soil physical and chemical properties from spectro-radiometric data.
2010
88-901015-8-X
soil reflectance; soil properties; artificial neural networks; genetic algorithms; partial least square regression analysis; pedometrics
File in questo prodotto:
File Dimensione Formato  
Prediction of soil properties from reflectance spectroscopy using multivariate statistical analysis and artificial intelligence methods. A comparative study.pdf

non disponibili

Licenza: Non specificato
Dimensione 1.94 MB
Formato Adobe PDF
1.94 MB Adobe PDF   Visualizza/Apri   Richiedi una copia

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/20.500.12070/7526
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus ND
  • ???jsp.display-item.citation.isi??? ND
social impact