Land-use change is crucial for environmental management as it affects biodiversity, water and radiation budgets, trace gas emissions, carbon cycling, and livelihoods. Land-use planning aims to influence land-use change to achieve configurations that balance environmental and stakeholder needs. Environmental management and land-use planning occur at different spatial and organizational levels, often corresponding with eco-regional or administrative units. Information needed and management decisions vary at different levels. At the national level, identifying "hot-spots" of land-use change is often sufficient, while more detailed analysis is needed at the regional level. At the regional level, land-use change impacts on natural resources can be assessed using models like water balance, nutrient balance, and erosion/sedimentation models, which require high-resolution land-use data. Land-use change models have evolved to address various conversions, including urbanization and agricultural intensification. These models often use cellular automata to simulate land-use change based on neighborhood functions and transition rules. However, they often lack the ability to simulate competition between land-use types and are limited to simulating one land-use type at a time. The CLUE modeling framework was developed to simulate land-use change using empirically quantified relations between land use and driving factors. It allows the simulation of multiple land-use types simultaneously through dynamic modeling of competition. The CLUE model is used at national and continental levels, with applications in Central America, Ecuador, China, and Java. Due to the large extent of these areas, the spatial resolution is coarse. For smaller areas, land-use data are based on land-use maps or remote sensing images, which may lead to biases if not properly represented. Because of differences in data representation and other regional features, the CLUE model cannot be directly applied at the regional scale. This paper describes a modified approach for regional applications, now called CLUE-S. The next section describes the theories underlying the development of the model, followed by a discussion of its functioning and applications.Land-use change is crucial for environmental management as it affects biodiversity, water and radiation budgets, trace gas emissions, carbon cycling, and livelihoods. Land-use planning aims to influence land-use change to achieve configurations that balance environmental and stakeholder needs. Environmental management and land-use planning occur at different spatial and organizational levels, often corresponding with eco-regional or administrative units. Information needed and management decisions vary at different levels. At the national level, identifying "hot-spots" of land-use change is often sufficient, while more detailed analysis is needed at the regional level. At the regional level, land-use change impacts on natural resources can be assessed using models like water balance, nutrient balance, and erosion/sedimentation models, which require high-resolution land-use data. Land-use change models have evolved to address various conversions, including urbanization and agricultural intensification. These models often use cellular automata to simulate land-use change based on neighborhood functions and transition rules. However, they often lack the ability to simulate competition between land-use types and are limited to simulating one land-use type at a time. The CLUE modeling framework was developed to simulate land-use change using empirically quantified relations between land use and driving factors. It allows the simulation of multiple land-use types simultaneously through dynamic modeling of competition. The CLUE model is used at national and continental levels, with applications in Central America, Ecuador, China, and Java. Due to the large extent of these areas, the spatial resolution is coarse. For smaller areas, land-use data are based on land-use maps or remote sensing images, which may lead to biases if not properly represented. Because of differences in data representation and other regional features, the CLUE model cannot be directly applied at the regional scale. This paper describes a modified approach for regional applications, now called CLUE-S. The next section describes the theories underlying the development of the model, followed by a discussion of its functioning and applications.