Research Grants 19/26222-6 - Mapeamento do solo, Agricultura - BV FAPESP
Advanced search
Start date
Betweenand

Agricultural mapping in the Cerrado via conbined use of multisensor images

Abstract

In recent decades, Brazil has established itself as one of the world´s leader in food production, largely due to the research, technological innovations, public policies, rural extension, environmental conditions and the farmers' focus on agricultural intensification. The increase in world´s food consumption brought more pressure on natural resources, especially in regions with high agricultural potential, such as the Cerrado biome. By now, different land use mapping initiatives have been undertaken to support regional planning. However, because of the complex agricultural dynamics of the region, there is a need for more detailed discrimination of agricultural crops and pasture productive conditions. This project aims is to improve and develop new agricultural mapping techniques from a multisensor perspective, using images from recently launched Landsat-8, Sentinel-2 and CBERS-4 satellites. The main innovation of the proposal is the use of supervised image classification techniques to process data obtained by these three satellites with different spatial, spectral and temporal resolutions involving annual and permanent crops, forestry and planted pastures in the Cerrado, with subsequent accuracy analysis. A multisensor approach has challenged the scientific community to optimize some traditional concepts, allowing the opening of new technical-scientific horizons: i) by the level of pre-processing required by different images and its relationship with the integrity and homogeneity of agricultural targets; ii) by the complexity of combining different temporal and spatial resolution of data sources, which allows data analyses with temporal resolution of up to 5 days and spatial resolution of 10 meters, considering the above mentioned three satellites; and iii) by the difficulty in generating multisensor analyses that enhance the digital classification methods by time series processing. Expected results of this proposal include new methods that allows the combined use of data obtained by these satellites for agricultural mapping of the Cerrado, public access of geospatial database with the main results obtained, publication of innovative scientific papers, and collaboration in the professional training of graduate students. In addition, results will support planning and implementation of new agricultural mapping and monitoring in Brazil, positively impacting the decision-making process of research groups and public and private organizations for the sustainable development of the Brazilian Cerrado. (AU)

Articles published in Agência FAPESP Newsletter about the research grant:
More itemsLess items
Articles published in other media outlets ( ):
More itemsLess items
VEICULO: TITULO (DATA)
VEICULO: TITULO (DATA)

Scientific publications
(References retrieved automatically from Web of Science and SciELO through information on FAPESP grants and their corresponding numbers as mentioned in the publications by the authors)
SANO, EDSON EYJI; BOLFE, EDSON LUIS; PARREIRAS, TAYA CRISTO; BETTIOL, GIOVANA MARANHAO; VICENTE, LUIZ EDUARDO; SANCHES, IEDA DEL'ARCO; VICTORIA, DANIEL DE CASTRO. Estimating Double Cropping Plantations in the Brazilian Cerrado through PlanetScope Monthly Mosaics. LAND, v. 12, n. 3, p. 19-pg., . (19/26222-6)
PARREIRAS, TAYA CRISTO; BOLFE, EDSON LUIS; DANTAS CHAVES, MICHEL EUSTAQUIO; SANCHES, IEDA DEL'ARCO; SANO, EDSON EYJI; VICTORIA, DANIEL DE CASTRO; BETTIOL, GIOVANA MARANHAO; VICENTE, LUIZ EDUARDO. Hierarchical Classification of Soybean in the Brazilian Savanna Based on Harmonized Landsat Sentinel Data. REMOTE SENSING, v. 14, n. 15, p. 22-pg., . (19/26222-6, 21/07382-2)
BOLFE, EDSON LUIS; PARREIRAS, TAYA CRISTO; DA SILVA, LUCAS AUGUSTO PEREIRA; SANO, EDSON EYJI; BETTIOL, GIOVANA MARANHAO; VICTORIA, DANIEL DE CASTRO; SANCHES, IEDA DEL'ARCO; VICENTE, LUIZ EDUARDO. Mapping Agricultural Intensification in the Brazilian Savanna: A Machine Learning Approach Using Harmonized Data from Landsat Sentinel-2. ISPRS INTERNATIONAL JOURNAL OF GEO-INFORMATION, v. 12, n. 7, p. 21-pg., . (19/26222-6)

Please report errors in scientific publications list using this form.
X

Report errors in this page


Error details: