This study's objective was to analyze the effect of land cover change, between 1965 and 2018, using statistical metrics and geoprocessing tools. And consequently, to provide information of area (ha) and spatial fragmentation of the Atlantic Forest in the municipality of Rio Largo/AL, Brazil. The samples were collected and transferred by CECA, CADEH, and INCRA, between November 2019 and April 2020. The basic materials used in this work were multi-temporal aerial images in digital format, derived from the 1965 aerophotogrametric survey on the scale 1:25000, belonging to the collection of the Engineering and Agrarian Sciences Campus - UFAL, and images of Landsat satellites (5 and 8) processed and made available by the Mapbiomas Project. The statistic landscape metrics were calculated using Landscape ecology Statistics (LECOs), a QGIS plugin. The analysis of forest fragmentation areas over the 53 years showed a reduction between 32.17% (1965) and 12.04% (2018) concerning the total extension of the municipality. In 1965, the average area obtained from 49 fragments was 201.13 ha. The values show a higher distance of forest fragments between 1965 and 1989, and disappearance by 2018.The Pearson correlation coefficient for 1965 and 2018 presented the value of r = -0.525, indicating a moderate and negative correlation between the mean values of areas (ha) of forest fragments and the number of forest fragments. The worst-case scenario for the maintenance of native forests occurred in 1989, where the reduction of continuous forest areas had 10.87 ha for forest area average, being spaced in 327 fragments. In the period 1986 and 1996, there was a decrease in fragmentation, reaching 200 fragments. In 1996 and 1997, there was an imbalance in forest maintenance, again increasing the number of fragments to 250 areas, and being explained by the loosening of surveillance in previous years, followed by deforestation.
Recurso de extrema relevância para estudos relativos a sociedade em diversos momentos históricos, as fotografias registram cidades e sua evolução, sendo uma importante fonte de pesquisa e estudo. Devido à ação do tempo, muitas fotografias se deterioram, perdendo-se informações essenciais para a compreensão do fenômeno urbano. Era o que estava prestes a ocorrer com o acervo físico recuperado a partir deste estudo, que vinha se deteriorando e prejudicando a qualidade e resolução das suas informações. O acervo refere-se a um conjunto de aerofotografias realizadas pela SUDENE entre as décadas de 1950-1970, e apresenta registros de grandes áreas da cidade de Maceió, capital de Alagoas. O processo resultou na recuperação do acervo, para posterior publicização a partir da criação de um geoportal, o que poderá viabilizar seu uso para fomentar pesquisas e estudos, gerando dados e informações sobre desenvolvimento, evolução e gestão urbana ocorridos em todo o território de Maceió.
Weed infestation is an essential factor in sugarcane productivity loss. The use of remote sensing data in conjunction with Artificial Intelligence (AI) techniques, can lead the cultivation of sugarcane to a new level in terms of weed control. For this purpose, an algorithm based on Convolutional Neural Networks (CNN) was developed to detect, quantify, and map weeds in sugarcane areas located in the state of Alagoas, Brazil. Images of the PlanetScope satellite were subdivided, separated, trained in different scenarios, classified and georeferenced, producing a map with weed information included. Scenario one of the CNN training and test presented overall accuracy (0,983), and it was used to produce the final mapping of forest areas, sugarcane, and weed infestation. The quantitative analysis of the area (ha) infested by weed indicated a high probability of a negative impact on sugarcane productivity. It is recommended that the adequacy of CNN’s algorithm for Remotely Piloted Aircraft (RPA) images be carried out, aiming at the differentiation between weed species, as well as its application in the detection in areas with different culture crops
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.