This study focuses on the possibilities and the limits of a prospective GIS land cover modelling applied to two case studies (France and Spain). The methodology, based on available GIS tools, consists of using earlier land cover maps and relevant environmental factors (calibration data) to model actual, known land cover to validate the model. The model aggregates Markov chain analysis for time prediction and multi‐critera evaluation, multi‐objective evaluation and cellular automata to perform spatial contiguity of modelled land cover scores. The first results give an accurate, pixel by pixel prediction rate of approximately 75%. An important issue of this study consists of analysing prediction residues to improve the model.

Land use and land cover change is a major global environmental change issue, and projecting changes are essential for the assessment of the environment. The Gaza Strip will have grown over 2.4 million inhabitants by 2023, and the land demands will exceed the sustainable capacity of land use by far. Land use planning is one of the most difficult issues in the Gaza Strip given that this area is too small. Continuous urban and industrial growth will place additional stress on land cover, unless appropriate integrated planning and management actions are instituted immediately. Planners need further statistics and estimation tools to achieve their vision for the future based on sound information. Therefore, this study combines the use of satellite remote sensing with geographic information systems (GISs). The spatial database is developed by using five Landsat images gathered in 1972, 1982, 1990, 2002 and 2013. Three GIS models are selected for simulation by the year 2023: Geomod, CA_Markov and Land Change Modeler using Idrisi Selva. The projected urban area will have undergone an increase of 212.3 km² by the year 2023 in the used models, and the percentage of urban area will account for 58.83 % of the Gaza strip by 2023.

This study compares two types of intermediate soft-classified maps. The first type uses land use/cover suitability maps based on a multi-criteria evaluation (MCE). The second type focuses on the transition potential between land use/cover categories based on a multi-layer perceptron (MLP). The concepts and methodological approaches are illustrated in a comparable manner using a Corine data set from the Murcia region (2300 km², Spain) in combination with maps of drivers that were created with two stochastic, discretely operating, commonly used tools (MCE in CA_MARKOV and MLP in Land Change Modeler). The importance of the different approaches and techniques for the obtained results is illustrated by comparing the specific characteristics of both approaches by validating the suitability versus transition potential maps to each other using a Spearman correlation matrix and, between the Corine maps, using classical ROC (receiver operating characteristic) statistics. Then, we propose a new use of ROC statistics to compare these intermediate soft-classified maps with their respective hard-classified maps of the models for each category. The validation of these results can be beneficial in choosing a suitable model and provide a better understanding of the implications of the different modeling steps and the advantages and limitations of the modeling tools.