Banca de QUALIFICAÇÃO: Ismael Cavalcante Maciel Junior

Uma banca de QUALIFICAÇÃO de MESTRADO foi cadastrada pelo programa.
DISCENTE : Ismael Cavalcante Maciel Junior
DATA : 20/01/2023
HORA: 08:00
LOCAL: Google Meet (videoconferência)
TÍTULO:

Detection of maize areas through geo-object oriented analysis using orbital multi-sensors on the platform Google Earth Engine

PALAVRAS-CHAVES:

GLCM Textures, Landsat-8, MODIS, PlanetScope, Random Forest, Sentinel 2, SNIC segmentation.

PÁGINAS: 92
GRANDE ÁREA: Ciências Exatas e da Terra
ÁREA: Geociências
SUBÁREA: Geofísica
ESPECIALIDADE: Sensoriamento Remoto
RESUMO:

The state of Mato Grosso is the largest producer of corn in the country, with the predominance of cultivation concentrated in the second harvest. Given the desire for data with greater precision and agility, the agricultural intelligence needs to adapt its research and search for new technologies such as remote sensing satellite images and geographic information systems. Therefore, this work aimed to map the second-crop corn in the municipality of Canarana-MT via geo-object oriented analysis with different spatial, spectral, temporal and radiometric resolutions, using the sensors: Sentinel-2A/B (MSI), Landsat-8 (OLI), Terra/Aqua (MODIS) and PlanetScope (PS). It was expected that the area of safrinha corn, obtained through the satellite images, would be statistically similar and possibly follow the same trend as the official estimates, and concomitantly, the distinction of crops that structurally resemble corn. To achieve these objectives, the IBGE cartographic base of the Canarana municipal boundary was obtained, and later uploaded to the Google Earth Engine Assets (GEE). A filter was applied to the acquired images, with cloud filtering of up to 0.35%, and the median of the months of April and May 2022 was used. Besides the original bands, four vegetation indices (NDVI, EVI, PCI and PCEI) were added, and in order to achieve better results in the segmentation step, textural features extracted by means of Gray Level Co-occurrence (GLCM) were employed. After the mentioned procedure, a principal component analysis (PCA) was performed in order to reduce the dimensionality of the data. The images went through the segmentation stage, qualified by applying the SNIC algorithm. In the classification step, the Random Forest (RF) classifier was applied, which is considered a popular machine learning algorithm. After processing and classifying the images and making the thematic maps of the corn areas, we proceeded to the analysis of the numerical confusion matrix implemented in GEE and validation statistics using 2,200 field samples. From these procedures, the classified data generated the confusion matrices with GA ranging from 86.41% to 88.65%. The OLI image presented the best results, with a global accuracy of 88.65% and 84.61% for the Kappa index, with PAs for the analyzed classes ranging from 65.16% to 91.53%, being the lowest for the Other Land Use class and the highest corresponding to the second-crop corn class. The CA of the aforementioned class the result was 91.98%. For second-crop corn, the Planet satellite images resulted in the smallest area, and such value is the closest to the official estimates. Thus, it is concluded that the GEOBIA methodology using the combination SNIC + GLCM with the RF classifier on the GEE platform was satisfactory, emphasizing that despite the good result obtained, some processes of the methodology still need to be improved in order to be applied in large extensions of second-crop corn area.

MEMBROS DA BANCA:
Presidente - 265126001 - CARLOS ANTONIO DA SILVA JUNIOR
Interno - 131916001 - RIVANILDO DALLACORT
Externo à Instituição - CÁCIO LUIZ BOECHAT - UFPI