Artificial neural networks applied for soil class prediction in mountainous landscape of the Serra do Mar¹
Soil information is needed for managing the agricultural environment. The aim of this study was to apply artificial neural networks (ANNs) for the prediction of soil classes using orbital remote sensing products, terrain attributes derived from a digital elevation model and local geology information as data sources. This approach to digital soil mapping was evaluated in an area with a high degree of lithologic diversity in the Serra do Mar. The neural network simulator used in this study was JavaNNS and the backpropagation learning algorithm. For soil class prediction, different combinations of the selected discriminant variables were tested: elevation, declivity, aspect, curvature, curvature plan, curvature profile, topographic index, solar radiation, LS topographic factor, local geology information, and clay mineral indices, iron oxides and the normalized difference vegetation index (NDVI) derived from an image of a Landsat-7 Enhanced Thematic Mapper Plus (ETM+) sensor. With the tested sets, best results were obtained when all discriminant variables were associated with geological information (overall accuracy 93.2 - 95.6 %, Kappa index 0.924 - 0.951, for set 13). Excluding the variable profile curvature (set 12), overall accuracy ranged from 93.9 to 95.4 % and the Kappa index from 0.932 to 0.948. The maps based on the neural network classifier were consistent and similar to conventional soil maps drawn for the study area, although with more spatial details. The results show the potential of ANNs for soil class prediction in mountainous areas with lithological diversity.
Main Authors: | , , , , , , |
---|---|
Format: | Digital revista |
Language: | English |
Published: |
Sociedade Brasileira de Ciência do Solo
2014
|
Online Access: | http://old.scielo.br/scielo.php?script=sci_arttext&pid=S0100-06832014000600003 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
id |
oai:scielo:S0100-06832014000600003 |
---|---|
record_format |
ojs |
spelling |
oai:scielo:S0100-068320140006000032015-01-30Artificial neural networks applied for soil class prediction in mountainous landscape of the Serra do Mar¹Calderano Filho,BrazPolivanov,HelenaChagas,César da SilvaCarvalho Júnior,Waldir deBarroso,Emílio VellosoGuerra,Antônio José TeixeiraCalderano,Sebastião Barreiros artificial neural networks terrain attributes digital mapping Soil information is needed for managing the agricultural environment. The aim of this study was to apply artificial neural networks (ANNs) for the prediction of soil classes using orbital remote sensing products, terrain attributes derived from a digital elevation model and local geology information as data sources. This approach to digital soil mapping was evaluated in an area with a high degree of lithologic diversity in the Serra do Mar. The neural network simulator used in this study was JavaNNS and the backpropagation learning algorithm. For soil class prediction, different combinations of the selected discriminant variables were tested: elevation, declivity, aspect, curvature, curvature plan, curvature profile, topographic index, solar radiation, LS topographic factor, local geology information, and clay mineral indices, iron oxides and the normalized difference vegetation index (NDVI) derived from an image of a Landsat-7 Enhanced Thematic Mapper Plus (ETM+) sensor. With the tested sets, best results were obtained when all discriminant variables were associated with geological information (overall accuracy 93.2 - 95.6 %, Kappa index 0.924 - 0.951, for set 13). Excluding the variable profile curvature (set 12), overall accuracy ranged from 93.9 to 95.4 % and the Kappa index from 0.932 to 0.948. The maps based on the neural network classifier were consistent and similar to conventional soil maps drawn for the study area, although with more spatial details. The results show the potential of ANNs for soil class prediction in mountainous areas with lithological diversity.info:eu-repo/semantics/openAccessSociedade Brasileira de Ciência do SoloRevista Brasileira de Ciência do Solo v.38 n.6 20142014-12-01info:eu-repo/semantics/othertext/htmlhttp://old.scielo.br/scielo.php?script=sci_arttext&pid=S0100-06832014000600003en10.1590/S0100-06832014000600003 |
institution |
SCIELO |
collection |
OJS |
country |
Brasil |
countrycode |
BR |
component |
Revista |
access |
En linea |
databasecode |
rev-scielo-br |
tag |
revista |
region |
America del Sur |
libraryname |
SciELO |
language |
English |
format |
Digital |
author |
Calderano Filho,Braz Polivanov,Helena Chagas,César da Silva Carvalho Júnior,Waldir de Barroso,Emílio Velloso Guerra,Antônio José Teixeira Calderano,Sebastião Barreiros |
spellingShingle |
Calderano Filho,Braz Polivanov,Helena Chagas,César da Silva Carvalho Júnior,Waldir de Barroso,Emílio Velloso Guerra,Antônio José Teixeira Calderano,Sebastião Barreiros Artificial neural networks applied for soil class prediction in mountainous landscape of the Serra do Mar¹ |
author_facet |
Calderano Filho,Braz Polivanov,Helena Chagas,César da Silva Carvalho Júnior,Waldir de Barroso,Emílio Velloso Guerra,Antônio José Teixeira Calderano,Sebastião Barreiros |
author_sort |
Calderano Filho,Braz |
title |
Artificial neural networks applied for soil class prediction in mountainous landscape of the Serra do Mar¹ |
title_short |
Artificial neural networks applied for soil class prediction in mountainous landscape of the Serra do Mar¹ |
title_full |
Artificial neural networks applied for soil class prediction in mountainous landscape of the Serra do Mar¹ |
title_fullStr |
Artificial neural networks applied for soil class prediction in mountainous landscape of the Serra do Mar¹ |
title_full_unstemmed |
Artificial neural networks applied for soil class prediction in mountainous landscape of the Serra do Mar¹ |
title_sort |
artificial neural networks applied for soil class prediction in mountainous landscape of the serra do mar¹ |
description |
Soil information is needed for managing the agricultural environment. The aim of this study was to apply artificial neural networks (ANNs) for the prediction of soil classes using orbital remote sensing products, terrain attributes derived from a digital elevation model and local geology information as data sources. This approach to digital soil mapping was evaluated in an area with a high degree of lithologic diversity in the Serra do Mar. The neural network simulator used in this study was JavaNNS and the backpropagation learning algorithm. For soil class prediction, different combinations of the selected discriminant variables were tested: elevation, declivity, aspect, curvature, curvature plan, curvature profile, topographic index, solar radiation, LS topographic factor, local geology information, and clay mineral indices, iron oxides and the normalized difference vegetation index (NDVI) derived from an image of a Landsat-7 Enhanced Thematic Mapper Plus (ETM+) sensor. With the tested sets, best results were obtained when all discriminant variables were associated with geological information (overall accuracy 93.2 - 95.6 %, Kappa index 0.924 - 0.951, for set 13). Excluding the variable profile curvature (set 12), overall accuracy ranged from 93.9 to 95.4 % and the Kappa index from 0.932 to 0.948. The maps based on the neural network classifier were consistent and similar to conventional soil maps drawn for the study area, although with more spatial details. The results show the potential of ANNs for soil class prediction in mountainous areas with lithological diversity. |
publisher |
Sociedade Brasileira de Ciência do Solo |
publishDate |
2014 |
url |
http://old.scielo.br/scielo.php?script=sci_arttext&pid=S0100-06832014000600003 |
work_keys_str_mv |
AT calderanofilhobraz artificialneuralnetworksappliedforsoilclasspredictioninmountainouslandscapeoftheserradomar1 AT polivanovhelena artificialneuralnetworksappliedforsoilclasspredictioninmountainouslandscapeoftheserradomar1 AT chagascesardasilva artificialneuralnetworksappliedforsoilclasspredictioninmountainouslandscapeoftheserradomar1 AT carvalhojuniorwaldirde artificialneuralnetworksappliedforsoilclasspredictioninmountainouslandscapeoftheserradomar1 AT barrosoemiliovelloso artificialneuralnetworksappliedforsoilclasspredictioninmountainouslandscapeoftheserradomar1 AT guerraantoniojoseteixeira artificialneuralnetworksappliedforsoilclasspredictioninmountainouslandscapeoftheserradomar1 AT calderanosebastiaobarreiros artificialneuralnetworksappliedforsoilclasspredictioninmountainouslandscapeoftheserradomar1 |
_version_ |
1756385136585211904 |