Desertification Monitoring in Biskra, Algeria with Landsat Imagery by means of Supervised Classification and Change Detection Methods

[EN] Desertification is one of the most important problems driven by global climatic change. There are many factors that contribute to the environmental degradation of the Sahara desert surroundings. The first one is related to human activities like the change of land use. Other factors include natu...

Descripción completa

Detalles Bibliográficos
Autores: Azzouzi, Soufiane Abdelaziz, Bentounes, Hadj Adda, Vidal Pantaleoni, Ana|||0000-0002-3853-6260
Tipo de recurso: artículo
Fecha de publicación:2017
País:España
Institución:Universitat Politècnica de València (UPV)
Repositorio:RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Idioma:inglés
OAI Identifier:oai:riunet.upv.es:10251/102258
Acceso en línea:https://riunet.upv.es/handle/10251/102258
Access Level:acceso abierto
Palabra clave:Change detection
Desertification
Landsat
Land cover land change
Supervised classification
TEORIA DE LA SEÑAL Y COMUNICACIONES
Descripción
Sumario:[EN] Desertification is one of the most important problems driven by global climatic change. There are many factors that contribute to the environmental degradation of the Sahara desert surroundings. The first one is related to human activities like the change of land use. Other factors include natural degradation due to change in temperature, humidity and wind. All these complex causes may lead to the movement of sand from the desert to other places like cities and roads, affecting everyday life. For that reason, desertification is being analyzed by governmental agencies in the affected countries. The present work studies this phenomenon in the city of Biskra (Algeria) using optical satellite images taken from the freely available Landsat program. It presents a methodology that could help in the temporal evaluation of the desertification process. Land Use and Land Cover (LULC) change detection in a period of twentyfive years has been carried out using Support Vector Machine (SVM) per object classification. Change indices have been also employed for assessing the degradation. Excellent results using low human operator cost have been fully validated by visual inspection.