Satellite image classification for environmental change prediction using image processing and machine learning techniques

• Autores: Quiroz Chavil, Helga Kelly, Pérez Díaz, Nelly Aurora, Capuñay Uceda, Oscar Efraín, Niño-de-Guzman-Tito, Michael, Aguilar Astudillo, Eduardo
• Formato: artículo
• Fecha de Publicación: 2022
• Institución: Universidad Tecnológica del Perú
• Repositorio: UTP-Institucional
• Lenguaje: español
• OAI Identifier: oai:repositorio.utp.edu.pe:20.500.12867/6007
• Enlace del recurso: https://hdl.handle.net/20.500.12867/6007; http://doi.org/10.14704/nq.2022.20.9.NQ44142
• Nivel de acceso: acceso abierto
• Materia: Satellite image; Predictive modelling; Machine learning; Environmental change; Image processing; https://purl.org/pe-repo/ocde/ford#2.00.00

In this research satellite image classification for environmental change prediction using image processing and machine learning methods is used. As we know satellite images is one of the important sources of collecting information for all area and region of interest which is suitable for any difficult situation around the world. The satellite image helps in collecting information on areas which is unpredictable and unreachable through digital cameras. In this research work, an advanced study on environmental change perdition has been examined using three classes’ ice land area, cropland area, and forest area. This research help in characterizing the type of satellite image classification for the particular three classes. The following stages have been considered are preprocessing, segmentation, and classification methods using K- Nearest Neighbor classifier. The present investigation results that db5 analysis works well in the classification of satellite image for environmental image prediction challenges with an accuracy of 94% using K- Nearest Neighbor classifier.