Mapping the Risk of Burning in the Brazilian Amazon with the Use of Logistic Regression and Fuzzy Inference |
| |
Authors: | Camil Wadih Salame Joaquim Carlos Barbosa Queiroz Gilberto de Miranda Rocha Mario Miguel Amin |
| |
Institution: | (1) Department of Statistics (ICEN), Federal University of Para, Brazil, 66075-110 Belem, Para, Brazil;(2) Environment Nucleus (NUMA), Federal University of Para, Brazil, 66075-110 Belem, Para, Brazil;(3) Nucleus for Amazon Research (NAEA), Federal University of Para, Brazil, 66075-110 Belem, Para, Brazil |
| |
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: | |
本文献已被 SpringerLink 等数据库收录! |
|