MAPEAMENTO AÉREO DA REGIÃO DO CAMPUS TRINDADE: UMA ANÁLISE DO CRESCIMENTO URBANO

Abstract

This study investigates the impact of the construction of Federal Educational Institutions (IFEs) on urban growth and socioeconomic development in their respective regions, using the Federal Institute of Goiás (IF Goiano) – Campus Trindade as a case study. The central hypothesis is that the establishment of an IFE promotes significant changes in urbanization and the local economy. The methodology combines advanced aerial mapping techniques, convolutional neural networks (U-Net), and satellite image processing, integrating geospatial data for a detailed analysis of spatial transformations from 2013 to 2024. The results suggest that increasing the number of layers in the convolutional neural network (U-Net) leads to significant improvements in accuracy and the Dice coefficient, a widely used metric to evaluate segmentation quality. The Dice coefficient measures the similarity between regions segmented by the model and actual reference areas. With six layers, a value of 46.238% was achieved, indicating satisfactory performance in detecting and delineating urbanized areas. This progress enabled the detection and quantification of urban growth in the region, supporting the hypothesis that IF Goiano drove urban expansion and local development. Furthermore, significant urban growth was identified, accompanied by economic and social benefits, such as increased job creation and enhanced local commerce. The research contributes to the debate on the role of IFEs in regional development, demonstrating the importance of their establishment in remote areas. The findings underscore the need for public policies aimed at sustainable urban planning, supported by robust quantitative and qualitative analyses. In conclusion, the study highlights the importance of methodological innovations, such as the use of artificial intelligence, in advancing the understanding of the socioeconomic impacts of educational institutions.