Treffer: Deep Learning for Supervised Classification of CBERS-4A Imagery in Rio Claro (SP) Urban Area ; Deep Learning para Classificação Supervisionada de Imagens CBERS-4A da Área Urbana de Rio Claro (SP)

This study evaluates the accuracy of land use and land cover (LULC) mapping in an urban area of Rio Claro (SP) using Deep Learning techniques and a CBERS-4A (WPM) image with 2 m spatial resolution. A U-Net convolutional neural network was developed using Python and the Keras and TensorFlow libraries. Ground truth data for training and accuracy assessment were generated through supervised classification of the same image in ArcGIS Pro, employing the Support Vector Machine (SVM) algorithm, followed by post-classification procedures, including majority filtering and manual pixel editing. U-Net results were compared with SVM results (pre-refinement) to evaluate potential accuracy improvements associated with the greater computational and human effort required by Deep Learning techniques. Both approaches were assessed using Overall Accuracy, Precision, Recall, F1 Score, and Kappa metrics. The U-Net model demonstrated superior performance across all metrics, with a notable increase in Precision from 0.48 (SVM) to 0.78 (U-Net). These findings highlight the potential of Deep Learning methods for high-resolution urban LULC mapping, providing valuable tools for urban planning and territorial management in Brazilian municipalities. ; O presente artigo tem por objetivo avaliar a acurácia do mapeamento do uso e cobertura da terra, realizado em um trecho da área urbana de Rio Claro (SP), a partir de técnicas de Deep Learning e utilizando uma imagem CBERS-4A (WPM) com 2 m de resolução espacial. Foi estruturada uma rede neural convolucional U-Net a partir de script em Python, utilizando as bibliotecas Keras e Tensor Flow. A verdade terrestre, utilizada para treinamento e verificação da acurácia do modelo, foi elaborada por meio de classificação supervisionada da mesma imagem no software ArcGIS Pro, utilizando o algoritmo Support Vector Machine (SVM) e procedimentos de pós-classificação, incluindo aplicação de filtro majoritário e edição manual de pixels. O resultado obtido pela U-Net foi comparado ao resultado obtido pelo SVM ...