Avaliação da Sustentabilidade em Agroecossistemas na Região Amazônica Através do Uso de Redes Neurais Artificiais (Assessment of the Sustainability of Agroecosystems in the Amazon Region Using Neural Artificial Networks)

José Gomes de Melo Júnior (josejunior@ufpa.br)1, Fabricio de Souza Farias (fabriciosf@ufpa.br)1, Osvaldo Ryohei Kato (osvaldo.kato@embrapa.br)2


1Universidade Federal do Pará
2Empresa Brasileira de Pesquisa Agropecuária

This paper appears in: Revista IEEE América Latina

Publication Date: Aug. 2016
Volume: 14,   Issue: 8 
ISSN: 1548-0992


Abstract:
The assessment of sustainability provides the actual situation of a site and provides information for decision making. In the Amazon, the assessment of the sustainability benefits of using adapted analytical models. However, this model is not always accurate. In this paper we propose a methodology that uses an artificial intelligence algorithm based on artificial neural networks (ANN), as a decision support tool, which aims to classify agroecosystems with agroforestry systems and without agroforestry systems. The sites are classified into two groups: Sustainable and Not Sustainable. For data collection we carried out technical visits to the rural community of Santa Luzia, in the municipality of Tomé-Açu, Pará Amazon. During the research data of 28 production units were collected. Finally, the data were submitted to the ANN and the results demonstrate the high potential of using computational intelligence algorithms for the purpose of monitoring the agroforestry systems in the Amazon region.

Index Terms:
Agroforestry systems, sustainability, artificial neural networks   


Documents that cite this document
This function is not implemented yet.


[PDF Full-Text (416)]