23. Classification Methods for Detecting and Evaluating Changes in Desertification-Related Features in Arid and Semi-arid Environments

Land cover, land use, soil salinisation and sand encroachment, which are desertification-indicating features, were integrated into a diachronic assessment, obtaining quantitative and qualitative information on the ecological state of the land, particularly degradation tendencies. In arid and semi-arid study areas of Algeria and Tunisia, sustainable development requires the understanding of these dynamics as it withstands the monitoring of desertification processes. Two different classification methods of salt and sand features have been set up, using historical and present Landsat imagery. Mapping of features of interest was achieved using both visual interpretation and automated classification approaches. The automated one implies a decision tree (DT) classifier and an unsupervised classification applied to the principal components (PC) extracted from Knepper ratios composite. Integrating results with ancillary spatial data, we could identify driving forces and estimate the metrics of desertification processes. In the Biskra area (Algeria), it emerged that the expansion of irrigated farmland in the past three decades has been contributing to an ongoing secondary salinisation of soils, with an increase of over 75%. In the Oum Zessar area (Tunisia), there has been a substantial change in several landscape components in the last decades, related to increased anthropic pressure and settlement, agricultural policies and national development strategies. One of the concerning aspects is the expansion of sand encroached areas over the last three decades of around 27%. This work is partly supported and developed within the WADIS-MAR Demonstration Project, funded by the EU Commission through the SWIM Programme (www.​wadismar.​eu).