Temporal generalization of an artificial neural network for land use/land cover classification

• Autor(a) principal: Tolentino, Franciele M. [UNESP]
• Data de Publicação: 2018
• Outros Autores: Galo, Maria de Lourdes B. T. [UNESP], Christovam, Luiz E. [UNESP], Coladello, Leandro F. [UNESP], Michel, U., Schulz, K.
• Tipo de documento: Artigo de conferência
• Idioma: eng
• Título da fonte: Repositório Institucional da UNESP
• Texto Completo: http://dx.doi.org/10.1117/12.2325607; http://hdl.handle.net/11449/185198
• topic: artificial neural networks; LULC; NDVI; NDWI

This work evaluated the performance of an Artificial Neural Network (ANN) in the temporal generalization of the Land Use and Land Cover (LULC) classes in the surroundings of the Salto Grande reservoir, located in a highly urbanized region of the Sao Paulo State, Brazil. Landsat-8 OLI (Operational Land Imager) multispectral images acquired in 2015, 2016 and 2017 were submitted to an ANN supervised classification. The ANN was trained with the image acquired in May 2015 to recognize five types of land cover (continental waters, forest, bare soil, agricultural area and urbanized area), using a learning rate of 0.1 and momentum of 0.5. As a classifier, the Multilayer Perceptron (MLP) ANN was used and the training algorithm was the backpropagation. To estimate classifications accuracies, checkpoints were randomly selected, and the error matrix was constructed for each date. The measures used in accuracy assessment were kappa, overall accuracy and the commission and omission errors per class. The results show that the image classification of 2015, the same year as the training data, resulted in a kappa index of 0.96, while the 2016 and 2017 classifications had kappa values of 0.72 and 0.74, respectively. Therefore, the experiments carried out to LULC classification from multitemporal scenes using a single-date trained ANN indicate the ANN's generalization capability and its potential in multitemporal analyzes. In addition, the 2016 classification, however, indicates the need to add non-spectral input data, which allows separate types of coverage of the body of water and landfill to be present when similar spectral responses.