Urban growth is among the most profound transformations of the landscape. When natural or working landscapes are converted to urban uses there are implications for habitat, impervious surfaces, greenhouse gas emissions, water consumption, effluent, and even light pollution – all of which can affect the overall health of the socio-ecosystem. Thus, understanding the impacts of land use policies meant to mediate, direct, and mitigate urban growth is essential for forecasting future impacts of human transformations of the landscape. This poster explores the effects of land use policy on the amount and location of urban growth in Miami-Dade County (MDC), the most populous county within the FCE. By using techniques to identify areas where more fair comparisons can be made between the presence and the absence of a certain land use policy condition, a defensible and quantifiable impact of the land use policy in question can be ascertained. The contrivance used to identify the areas in MDC to make the fair comparisons is a cellular automata urban growth model called SLEUTH. A GIS is then used to measure the results and equations are used to translate the differences in urban growth rates into a single integer value that represents the resistance to development that should be assigned to that land use policy within the SLEUTH model. Then SLEUTH is run again to see if such assignations improve the goodness of fit metrics. An improvement indicates that the specific values used in the inclusion of the land use policy allows the model to better simulate actual past growth. Four different scenarios were run to test not only land use policies but also different planning areas that reflect the will of different planning commissions. The results indicate that the simplest scenario, involving a binary classification of those lands either inside or outside the Urban Development Boundary, improved model performance more than the more heterogeneous regulatory landscapes created in other scenarios. However, all attempts to integrate land use policy with these techniques resulted in improvements of model performance. These techniques for better understanding past urban growth and thus predicting future urban growth can be applied at all LTER sites subject to urbanization.