An approach based on satellite image time series mining to identify region susceptible to desertification

After extensive and devastating drought in the Sahel, Africa, in the late 60's and early 70's (1968-1973) which resulted in the deaths of thousands of people and millions of animals, the desertification issue has been considered in the international agenda being ultimately relevant for the scientific community and governments in the worldwide. In 1992, the United Nations (UN), through Agenda 21 Chapter 12, defined desertification as ”land degradation in arid, semi-arid and dry sub-humid areas resulting from various factors, including climatic variations and human activities”. Desertification exacerbates socio-economic problems such as poverty and migration, which mainly affects the most vulnerable people and communities, bringing risk to global food security [1]. According to the UN, the annual economic losses are close to 4 billion dollars, with a cost for recovery of 10 billion dollars per year on a global scale.