Application of GIS and remote sensing techniques in generation of land use scenarios for hydrological modeling

Changes in land use and the relationship between land use changes and different explanatory variables were studied. Future scenarios of land use were developed using logistic regression (Reg-Log) and Neural Networks (MPL) for a horizon year 2001, applying in both cases a process of multiobjective allocation of land uses (MOLA). Validated the results, we generated a scenario of land occupation to 2012. [Display omitted] ► The persistence of the different land occupations is the predominant state in the study area. The changes are produced in the boundary area among categories. ► The greater explanatory power of the occurrence of the different coverage was presented by biophysical variables. ► The best estimate of the land use change was produced when applying logistic regression. ► The most difficult land use to predict was of crops. ► The scenery generated for 2012 showed a remarkable similarity with the map of land use corresponding to 2001; this is due to little dynamism of the explanatory variables. This research studies the change in land use in a binational hydrographic basin in South America. In addition, a future perspective for land use is generated according to the trends in the development observed. A multi-temporal analysis of land use change is carried out and variables that can explain the observed transitions will be selected. The relations between changes and explicative variables are studied in order to stochastically model future land use maps. Persistence was found to be the predominant state. Higher transitions were observed in the zones of boundaries between categories. Biophysical variables had the most explicative power with a better performance of the model based on logistic regression than the one made by using neural networks.