The importance of sampling for the efficiency of artificial neural networks in digital soil mapping

Research output: Chapter in Book/Report/Conference proceedingChapter


In Portugal, soil mapping remains incomplete, and there are also significant problems with the existing cartography. Digital Soil Mapping uses advanced computerbased techniques such as Artificial Neural Networks (ANN) for mapping soil classes in a cheaper, more consistent and flexible way, using surrogate landscape data. This work used five different training sets to evaluate the impact that sampling has on the predictive accuracy of ANNs. The testes were carried out in IDRISI Taiga for two catchments in northern Portugal, using an ANN method known as multi-layer perceptron. Results show that sampling design is very important for the accuracy of soil mapping with ANNs.
Original languageUnknown
Title of host publicationXIII Coloquio Ibérico de Geografía
EditorsDominic Royé, José Antonio Aldrey Vázquez, Miguel Pazos Otón, María José Piñeira Mantiñán, Marcos Valcárcel Díaz
ISBN (Print)978-84-940469-7-1
Publication statusPublished - 1 Jan 2012
EventXIII Coloquio Ibérico de Geografía, AGE e APG, Santiago de Compostela -
Duration: 1 Jan 2012 → …

Publication series

NameRespuestas de la Geografia Ibérica a la crisis actual


ConferenceXIII Coloquio Ibérico de Geografía, AGE e APG, Santiago de Compostela
Period1/01/12 → …

Cite this