| Grant number: | 16/23750-3 |
| Support type: | Scholarships in Brazil - Post-Doctorate |
| Effective date (Start): | January 01, 2017 |
| Effective date (End): | December 31, 2018 |
| Field of knowledge: | Physical Sciences and Mathematics - Geosciences |
| Principal Investigator: | Gilberto Camara Neto |
| Grantee: | Michelle Cristina Araujo Picoli |
| Home Institution: | Instituto Nacional de Pesquisas Espaciais (INPE). Ministério da Ciência, Tecnologia, Inovações e Comunicações (Brasil). São José dos Campos , SP, Brazil |
| Associated research grant: | 14/08398-6 - E-Sensing: big earth observation data analytics for land use and land cover change information, AP.ESCIENCE.TEM |
| Associated scholarship(s): | 17/19812-6 - Agricultural productivity and growth in Brazil: direct and indirect environmental impacts, BE.EP.PD |
Abstract Brazil is one of the largest agricultural producers in the world and a leading producer of biofuels. However, the use of remote sensing images to provide estimates of crop yield is still limited. This is due to the limitations of current data analysis methods, which focuses on processing a single image. The expectation of this project is that methods of "big analytics data" can significantly improve the use of satellite image in the generation of information about crop yield in Brazil. This project will focus in the specification and validation activities on methods for agricultural monitoring using big earth observation data. These methods should be based on analysis of satellite image time series. The tasks to be performed are: (a) detection of planted area of soybeans, maize and sugarcane, rice and wheat crops in selected areas, using methods that process large scale satellite image time series; (b) detailed assessment of big earth observation data analytics for agricultural mapping. In this project will development analytical methods for detecting large agricultural areas in Brasil, with the specific tasks of mapping land cover associated to soybeans, maize and sugarcane. The project results will be compare with ground truth data, that will be acquired, and with results from IBGE (Brazil's Census Bureau). The methods for agricultural monitoring should be developed in the R language and work with data stored in the SciDB array database. (AU) | |