Mapping the Risk of Burning in the Brazilian Amazon with the Use of Logistic Regression and Fuzzy Inference
- PDF / 2,018,780 Bytes
- 16 Pages / 439.37 x 666.142 pts Page_size
- 2 Downloads / 196 Views
Mapping the Risk of Burning in the Brazilian Amazon with the Use of Logistic Regression and Fuzzy Inference Camil Wadih Salame · Joaquim Carlos Barbosa Queiroz · Gilberto de Miranda Rocha · Mario Miguel Amin
Received: 10 April 2011 / Accepted: 10 January 2012 / Published online: 9 February 2012 © International Association for Mathematical Geosciences 2012
Abstract Through the PRODESDIGITAL Project, the National Institute for Space Research (INPE) has been mapping vegetal coverage in the Brazilian Legal Amazon using Landsat satellite images. INPE not only identifies deforested areas but also releases a daily map of burning areas. Burning is frequently used as the cheapest way to deforest, to clear areas for farming and to increase the soil’s fertility in a short period of time. In many instances, these fires get out of control and end up accidentally invading areas of forest exploited by the lumber industry, agricultural plantations and pastures. However, the deforestation and burning area maps alone are insufficient for monitoring and control on a regional scale. It is necessary to know in an analytical way how actions (deforestation and burnings) that characterize human occupation are occurring in a region. In this research, two methods are used that allow the inclusion of co-variation in the estimation of variables of interest: logistic regression, which is a statistical method that considers a categorical or discrete response variable and discrete and/or continuous co-variation; and fuzzy logic, which makes use of artificial intelligence methods to incorporate into computational models information based on the knowledge or experience of a specialist. In both methods, the response variable may be related to the probability of occurrence of the environmental variable under study. Keywords Legal Amazon · Deforestation · Burning · Fuzzy logic C.W. Salame () · J.C.B. Queiroz Department of Statistics (ICEN), Federal University of Para, Brazil, 66075-110, Belem, Para, Brazil e-mail: [email protected] G. de Miranda Rocha Environment Nucleus (NUMA), Federal University of Para, Brazil, 66075-110, Belem, Para, Brazil M.M. Amin Nucleus for Amazon Research (NAEA), Federal University of Para, Brazil, 66075-110, Belem, Para, Brazil
242
Math Geosci (2012) 44:241–256
1 Introduction The monitoring of the forest area of the Legal Amazon (encompassing the States of Acre, Amapá, Amazonas, Pará, Rondônia, Roraima, Tocantins, Mato Grosso and the western part of Maranhão) performed by the National Institute for Space Research (INPE) revealed deforestation rates that varied between 1 and 3 × 106 ha/year in the period 1991 to 1999 and the loss of about 6 × 107 ha (more than half a million km2 ) of forest until 2000. This deforestation results from an Amazon occupation process occurring from the second half of the 20th century and is associated with the expansion of the agriculture margin, the construction of highway transportation systems and development poles. Environmental damage caused by this deforestation has led to signifi
Data Loading...
