We propose an approach for classifying land zones into categories indicating their resilience against desertification. Environmental management support is provided by a multi-criteria inference method that derives a set of value functions compatible with the given classification examples, and applies them to define, for the rest of the zones, their possible classes. In addition, a representative value function is inferred to explain the relative importance of the criteria to the stakeholders. We use the approach for classifying 28 administrative regions of the Khorasan Razavi province in Iran into three equilibrium classes: collapsed, transition, and sustainable zones. The model is parameterized with enhanced vegetation index measurements from 2005 to 2012, and 7 other natural and anthropogenic indicators for the status of the region in 2012. Results indicate that grazing density and land use changes are the main anthropogenic factors affecting desertification in Khorasan Razavi. The inference procedure suggests that the classification model is underdetermined in terms of attributes, but the approach itself is promising for supporting the management of anti-desertification efforts.

, , , ,
doi.org/10.1016/j.jenvman.2015.07.006, hdl.handle.net/1765/84384
Journal of Environmental Management
Department of Econometrics

Tervonen, T., Sepehr, A., & Kadziński, M. (2015). A multi-criteria inference approach for anti-desertification management. Journal of Environmental Management, 162, 9–19. doi:10.1016/j.jenvman.2015.07.006