Giovana Mira de Espindola

Learn More
Region-growing segmentation algorithms are useful for remote sensing image segmentation. These algorithms need the user to supply control parameters, which control the quality of the resulting segmentation. An objective function is proposed for selecting suitable parameters for region-growing algorithms to ensure best quality results. It considers that a(More)
This issue of Current Opinion in Environmental Sustainability provides an overview of recent advances in Land System Science while at the same time setting the research agenda for the Land System Science community. Land System Science is not just representing land system changes as either a driver or a consequence of global environmental change. Land(More)
The potential impact of deforestation in the Brazilian Amazon on greenhouse gas emissions to the atmosphere calls for policies that take account of changes in forest cover. Although much research has focused on the location and effects of deforestation, little is known about the distribution and reasons for the agricultural uses that replace forest cover.(More)
The Linked Brazilian Amazon Rainforest Data contains observations about deforestation of rainforests and related things such as rivers, road networks, population, amount of cattle, and market prices of agricultural products. The Linked Data approach offers thus to combine ecological, economical and social dimensions together. Our aim has been to 1)(More)
Linked Open Science is an approach to solve challenges of an executable paper. It is a combination of four “silver bullets”: 1) publication of scientific data, metadata, results, and provenance information using Linked Data principles, 2) open source and web-based environments for executing, validating and exploring research, 3) Cloud Computing for(More)
Different techniques, including remote sensing, are used to collect data about the deforestation in the Brazilian Amazon rainforest. However, a key problem for integrating all the resulting datasets for statistical analysis is the semantic diversity among these datasets. In this paper we identify key semantic interoperability challenges for the Brazilian(More)
Deforestation in the Brazilian Amazon has sharply decreased over the past five years. In this study we try to explain the spatio-temporal pattern of deforestation in a selected area by relating data from 2002-2008 to a number of explanatory variables, part of which are related to control actions conducted by the government. We do so by considering the(More)
This scientific research considers the problem of estimating class probabilities for an unknown pattern, which is represented by a feature vector, using a nonparametric method, such as Parzen Windows. This paper’s contribution is the application of the nonparametric density estimation approach in the intra-urban land cover classification.
  • 1