Assessing Rainfall Erosivity with Artificial Neural Networks for the Ribeira Valley, Brazil

Soil loss is one of the main causes of pauperization and alteration of agricultural soil properties. Various empirical models (e.g., USLE) are used to predict soil losses from climate variables which in general have to be derived from spatial interpolation of point measurements. Alter...

Full description

Saved in:
Bibliographic Details
Main Authors: Reginald B. Silva, Piero Iori, Cecilia Armesto, Hugo N. Bendini
Format: Article
Language:English
Published: Wiley 2010-01-01
Series:International Journal of Agronomy
Online Access:http://dx.doi.org/10.1155/2010/365249
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849307031014473728
author Reginald B. Silva
Piero Iori
Cecilia Armesto
Hugo N. Bendini
author_facet Reginald B. Silva
Piero Iori
Cecilia Armesto
Hugo N. Bendini
author_sort Reginald B. Silva
collection DOAJ
description Soil loss is one of the main causes of pauperization and alteration of agricultural soil properties. Various empirical models (e.g., USLE) are used to predict soil losses from climate variables which in general have to be derived from spatial interpolation of point measurements. Alternatively, Artificial Neural Networks may be used as a powerful option to obtain site-specific climate data from independent factors. This study aimed to develop an artificial neural network to estimate rainfall erosivity in the Ribeira Valley and Coastal region of the State of São Paulo. In the development of the Artificial Neural Networks the input variables were latitude, longitude, and annual rainfall and a mathematical equation of the activation function for use in the study area as the output variable. It was found among other things that the Artificial Neural Networks can be used in the interpolation of rainfall erosivity values for the Ribeira Valley and Coastal region of the State of São Paulo to a satisfactory degree of precision in the estimation of erosion. The equation performance has been demonstrated by comparison with the mathematical equation of the activation function adjusted to the specific conditions of the study area.
format Article
id doaj-art-25b8da75cea344889f442e16997fdd63
institution Kabale University
issn 1687-8159
1687-8167
language English
publishDate 2010-01-01
publisher Wiley
record_format Article
series International Journal of Agronomy
spelling doaj-art-25b8da75cea344889f442e16997fdd632025-08-20T03:54:52ZengWileyInternational Journal of Agronomy1687-81591687-81672010-01-01201010.1155/2010/365249365249Assessing Rainfall Erosivity with Artificial Neural Networks for the Ribeira Valley, BrazilReginald B. Silva0Piero Iori1Cecilia Armesto2Hugo N. Bendini3Campus Experimental de Registro, UNESP-Universidade Estadual Paulista, 11900-000 Registro, SP, BrazilDepartment of Soil Science, UFLA, Caixa Postal 3037, 37200-000 Lavras, MG, BrazilDepartment of Phytopathology, UFLA, Caixa Postal 3037, 37200-000 Lavras, MG, BrazilCampus Experimental de Registro, UNESP-Universidade Estadual Paulista, 11900-000 Registro, SP, BrazilSoil loss is one of the main causes of pauperization and alteration of agricultural soil properties. Various empirical models (e.g., USLE) are used to predict soil losses from climate variables which in general have to be derived from spatial interpolation of point measurements. Alternatively, Artificial Neural Networks may be used as a powerful option to obtain site-specific climate data from independent factors. This study aimed to develop an artificial neural network to estimate rainfall erosivity in the Ribeira Valley and Coastal region of the State of São Paulo. In the development of the Artificial Neural Networks the input variables were latitude, longitude, and annual rainfall and a mathematical equation of the activation function for use in the study area as the output variable. It was found among other things that the Artificial Neural Networks can be used in the interpolation of rainfall erosivity values for the Ribeira Valley and Coastal region of the State of São Paulo to a satisfactory degree of precision in the estimation of erosion. The equation performance has been demonstrated by comparison with the mathematical equation of the activation function adjusted to the specific conditions of the study area.http://dx.doi.org/10.1155/2010/365249
spellingShingle Reginald B. Silva
Piero Iori
Cecilia Armesto
Hugo N. Bendini
Assessing Rainfall Erosivity with Artificial Neural Networks for the Ribeira Valley, Brazil
International Journal of Agronomy
title Assessing Rainfall Erosivity with Artificial Neural Networks for the Ribeira Valley, Brazil
title_full Assessing Rainfall Erosivity with Artificial Neural Networks for the Ribeira Valley, Brazil
title_fullStr Assessing Rainfall Erosivity with Artificial Neural Networks for the Ribeira Valley, Brazil
title_full_unstemmed Assessing Rainfall Erosivity with Artificial Neural Networks for the Ribeira Valley, Brazil
title_short Assessing Rainfall Erosivity with Artificial Neural Networks for the Ribeira Valley, Brazil
title_sort assessing rainfall erosivity with artificial neural networks for the ribeira valley brazil
url http://dx.doi.org/10.1155/2010/365249
work_keys_str_mv AT reginaldbsilva assessingrainfallerosivitywithartificialneuralnetworksfortheribeiravalleybrazil
AT pieroiori assessingrainfallerosivitywithartificialneuralnetworksfortheribeiravalleybrazil
AT ceciliaarmesto assessingrainfallerosivitywithartificialneuralnetworksfortheribeiravalleybrazil
AT hugonbendini assessingrainfallerosivitywithartificialneuralnetworksfortheribeiravalleybrazil