The South Nation watershed is located in Eastern Ontario, Canada and managed under the authority of the South Nation Conservation (SNC). The watershed covers an area of 400,000 hectares with four dominant categories of land-use classes (60% agriculture, 34% forest, 5% mixed urban, and 1% other). Water quality is a great concern for the SNC as many anthropogenic activities generate harmful pollutants (such as heavy metals, nitrogen, phosphorus, and pesticides) that are discharged to the river through surface and groundwater flow. The discharge patterns of these pollutants are mainly driven by land-use distribution within the watershed which has been constantly evolving with urbanization and intensification of agriculture. Major changes in land-uses can potentially offset current SNC efforts to mitigate water pollution. The objective of the current study is to predict land-use series of maps for the South Nation watershed starting from 1991 to 2020. The prediction is carried out using the land-use allocation algorithm of the Dyna-CLUE (Dynamic Conversion of Land-Use and its Effects) model which is implemented for local regions. Dyna-CLUE is a spatially explicit hybrid land-use allocation model that combines estimation and simulation models, and its allocation procedures predict future trends of land-use surface (estimated from historical trends). The binary logistic regression is used to link preferences of land-use classes and potential demographic and geographic driving factors. Expert judgment was used to select a set of spatial driving factors believed to be responsible for changes in land-use distribution in the South Nation watershed. Three different scenarios for future development of the region were considered, with different initial conditions and conversion restrictions. The simulation results were evaluated using visual and statistical validation techniques to assess the performance of the model in generating maps similar to reality. The Dyna-CLUE model was successfully applied to the South Nation watershed. It was observed that the simulated maps generated from the model were in good agreement with the reality maps. This was confirmed through statistical validation via map pair analysis (error matrix) used to assess the overall accuracy of the model predictions. Results showed that the model was sensitive to land-use restrictions. Such type of modeling can be valuable for assessing the land-use changes at the local level, and setting up a decision support system for the South Nation Conservation towards sustainable land-use management in the watershed. Better results are expected to be achieved with more reliable datasets (i.e., accurate classification of land-use types in reality maps). Data availability and quality were the main obstacles that faced this research work. Our work has the merit to be the first application of CLUE model in Eastern Ontario.

The South Nation watershed is located in Eastern Ontario, Canada and managed under the authority of the South Nation Conservation (SNC). The watershed covers an area of 400,000 hectares with four dominant categories of land-use classes (60% agriculture, 34% forest, 5% mixed urban, and 1% other). Water quality is a great concern for the SNC as many anthropogenic activities generate harmful pollutants (such as heavy metals, nitrogen, phosphorus, and pesticides) that are discharged to the river through surface and groundwater flow. The discharge patterns of these pollutants are mainly driven by land-use distribution within the watershed which has been constantly evolving with urbanization and intensification of agriculture. Major changes in land-uses can potentially offset current SNC efforts to mitigate water pollution. The objective of the current study is to predict land-use series of maps for the South Nation watershed starting from 1991 to 2020. The prediction is carried out using the land-use allocation algorithm of the Dyna-CLUE (Dynamic Conversion of Land-Use and its Effects) model which is implemented for local regions. Dyna-CLUE is a spatially explicit hybrid land-use allocation model that combines estimation and simulation models, and its allocation procedures predict future trends of land-use surface (estimated from historical trends). The binary logistic regression is used to link preferences of land-use classes and potential demographic and geographic driving factors. Expert judgment was used to select a set of spatial driving factors believed to be responsible for changes in land-use distribution in the South Nation watershed. Three different scenarios for future development of the region were considered, with different initial conditions and conversion restrictions. The simulation results were evaluated using visual and statistical validation techniques to assess the performance of the model in generating maps similar to reality. The Dyna-CLUE model was successfully applied to the South Nation watershed. It was observed that the simulated maps generated from the model were in good agreement with the reality maps. This was confirmed through statistical validation via map pair analysis (error matrix) used to assess the overall accuracy of the model predictions. Results showed that the model was sensitive to land-use restrictions. Such type of modeling can be valuable for assessing the land-use changes at the local level, and setting up a decision support system for the South Nation Conservation towards sustainable land-use management in the watershed. Better results are expected to be achieved with more reliable datasets (i.e., accurate classification of land-use types in reality maps). Data availability and quality were the main obstacles that faced this research work. Our work has the merit to be the first application of CLUE model in Eastern Ontario.

The South Nation watershed is located in Eastern Ontario, Canada and managed under the authority of the South Nation Conservation (SNC). The watershed covers an area of 400,000 hectares with four dominant categories of land-use classes (60% agriculture, 34% forest, 5% mixed urban, and 1% other). Water quality is a great concern for the SNC as many anthropogenic activities generate harmful pollutants (such as heavy metals, nitrogen, phosphorus, and pesticides) that are discharged to the river through surface and groundwater flow. The discharge patterns of these pollutants are mainly driven by land-use distribution within the watershed which has been constantly evolving with urbanization and intensification of agriculture. Major changes in land-uses can potentially offset current SNC efforts to mitigate water pollution. The objective of the current study is to predict land-use series of maps for the South Nation watershed starting from 1991 to 2020. The prediction is carried out using the land-use allocation algorithm of the Dyna-CLUE (Dynamic Conversion of Land-Use and its Effects) model which is implemented for local regions. Dyna-CLUE is a spatially explicit hybrid land-use allocation model that combines estimation and simulation models, and its allocation procedures predict future trends of land-use surface (estimated from historical trends). The binary logistic regression is used to link preferences of land-use classes and potential demographic and geographic driving factors. Expert judgment was used to select a set of spatial driving factors believed to be responsible for changes in land-use distribution in the South Nation watershed. Three different scenarios for future development of the region were considered, with different initial conditions and conversion restrictions. The simulation results were evaluated using visual and statistical validation techniques to assess the performance of the model in generating maps similar to reality. The Dyna-CLUE model was successfully applied to the South Nation watershed. It was observed that the simulated maps generated from the model were in good agreement with the reality maps. This was confirmed through statistical validation via map pair analysis (error matrix) used to assess the overall accuracy of the model predictions. Results showed that the model was sensitive to land-use restrictions. Such type of modeling can be valuable for assessing the land-use changes at the local level, and setting up a decision support system for the South Nation Conservation towards sustainable land-use management in the watershed. Better results are expected to be achieved with more reliable datasets (i.e., accurate classification of land-use types in reality maps). Data availability and quality were the main obstacles that faced this research work. Our work has the merit to be the first application of CLUE model in Eastern Ontario.

Comparison of Dyna-CLUE and Land Change Modeler software for predictive modelling in the suburban area of Prague Abstract The objective of this work was to predict the development of the suburban area of Prague, using Dyna- CLUE and Land Change Modeler (LCM) software, and based on the results compare the capabilities of both these software tools. In this work I used time series of land cover data obtained by the department of applied geoinformatics and cartography, local plans of the municipalities, and information about soil protection provided by the Research Institute for Soil and Water Conservation. Based on these data, a predicted land cover map for 2020 was created in both software tools. The results were then compared and showed that the models respect the restriction of development in predetermined areas. In accordance with local plans, new residential development was properly allocated. For commercial development, the requirements were not completely fulfilled. It is evident that both models are able to create a correct map of future land cover based on specified requirements. However, the instability of LCM and the necessity of using other software while working with Dyna- CLUE somewhat complicated the work. Keywords: Dyna-CLUE, Land Change Modeler, predictive modelling, land cover, residential...