%0 Conference Proceedings
%4 sid.inpe.br/marte2/2017/10.27.16.33.20
%2 sid.inpe.br/marte2/2017/10.27.16.33.21
%@isbn 978-85-17-00088-1
%F 59379
%T Use of Remote Sensing to assess Ecosystem Integrity of the Brazilian Amazon rainforest A Bayesian approach
%D 2017
%A Ferraz, Rodrigo,
%A Simões, Margareth,
%A Alves, Andrei Olak,
%A Xaud, Haron Abrahim Magalhães,
%@electronicmailaddress rodrigo.demonte@embrapa.br
%E Gherardi, Douglas Francisco Marcolino,
%E Aragão, Luiz Eduardo Oliveira e Cruz de,
%B Simpósio Brasileiro de Sensoriamento Remoto, 18 (SBSR)
%C Santos
%8 28-31 maio 2017
%I Instituto Nacional de Pesquisas Espaciais (INPE)
%J São José dos Campos
%P 7923-7929
%S Anais
%1 Instituto Nacional de Pesquisas Espaciais (INPE)
%X Biodiversity supports many ecosystem services that are very important for climate change mitigation and adaptation. There is a functional link between the tropical forest ecosystem biodiversity and their capacity for carbon uptake and storage as well as regulation of evapotranspiration flux. Nevertheless, land use changes and agriculture expansion reduce the ecosystems integrity modifying the functions related directly to the ecosystem services. The relationship between biodiversity loss and the impacts on ecosystem services of tropical forests, in face of the ongoing global climate change needs to be better quantified. In this work, we considered the concept of Ecosystem Integrity (EI), which represents the connection of biodiversity with the ability of ecosystems to sustain the processes of self-organization. Bayesian Networks (BBN-Bayesian Belief Network) can provide metrics for the generation of Ecosystem Integrity Index, from the training of probabilistic relationships of evidence obtained through Remote Sensing data. The objective of this work is to present the methodological approach and the results of EI mapping, elaborated at the regional scale for different patterns of phyto-ecologic landscape of the Brazilian Amazon. The modelling was based on learning from the parameters (data-driven model) through the use of the Expectation Maximization algorithm. For the validation of this probabilistic model, an evaluation was carried out in controlled areas with field observation by experts. Results showed that it is possible to generate an Ecosystem Integrity Index at regional scale using a probabilistic model based on Bayesian Belief Networks (BBN), and totally free web-available satellite products.
%9 Degradação de florestas
%@language en
%3 59379.pdf