Predictive soil mapping in Presidente Prudente, SP, Brazil, using Artificial Neural Networks (ANN): a contribution to landscape analysis

• Grant number: 15/14461-5
• Support Opportunities: Scholarships abroad - Research Internship - Doctorate
• Start date: October 01, 2015
• End date: August 31, 2016
• Field of knowledge: Humanities - Geography - Human Geography
• Principal Investigator: José Tadeu Garcia Tommaselli
• Grantee: Janaina Natali Antonio
• Supervisor: Graciela Isabel Metternicht
• Host Institution: Faculdade de Ciências e Tecnologia (FCT). Universidade Estadual Paulista (UNESP). Campus de Presidente Prudente. Presidente Prudente , SP, Brazil
• Institution abroad: University of New South Wales (UNSW), Australia
• Associated to the scholarship: 13/03505-6 - Predictive mapping of soils in Presidente Prudente - SP, using artificial neural networks (ANN): a contribution to the analysis of the landscape, BP.DR

Abstract

The process of urbanization affects soils increasing degradation by environmental change. Rational use of information about urban soils can improve urban planning. The aim of this study is the elaboration of a predictive soil mapping in Presidente Prudente - SP - Brazil, using the classification methodology by Artificial Neural Networks (ANN), as approved in the regular research project in Brazil (FAPESP - Process: 2013 / 03505-6). The model will be used to evaluate landscape changes caused by human intervention in the old disposal areas of municipal solid waste, classified as Anthroposols. Recognition of soil characteristics and terrain will be performed by ANN associated with auxiliary data: geomorphology, slope, relief curvature and granulometric analysis of soil samples. It is intended to perform the research internship abroad in BEPE modality (Bolsa estágio de Pesquisa no Exterior) at the University of New South Wales, Australia in order to develop activities related to the use of ANN and the study of Anthroposols understudied geography in Brazil, as well as inserting in the research the principles of geomorphometrics in processes involved in soil occurrence using patterns extraction from ALOS satellite image of the area, which will bring improved results of regular research in the country.