Análise preditiva com redes neurais convolucionais para o geoprocessamento de imagens

Abstract

This course conclusion work presents the development of a Convolutional Neural Network (CNN) with the objective of executing image geoprocessing predictions, based on input data. The system allows the analysis of inputs and results in an output value characterized by the value of the prediction, making possible the predictability of future scenarios. A system was developed based on the developed techniques, obtained through research, to implement the prediction of image assertiveness by the applied training. The performance of the developed system was verified with values obtained through a hypothetical scenario. The results are presented and discussed.