Design of Urban Growth Probability Model by Using Spatial Association Rules

An effective and efficient planning of an urban growth and land use changes and its impact on the environment requires information about growth trends and patterns amongst other important information. Over the years, many urban growth models have been developed and used in the developed countries for forecasting growth patterns. In the developing countries however, there exist a very few studies showing the application of these models and their performances. In this study two models such as cellular automata (CA) and the SLEUTH models are applied in a geographical information system (GIS) to simulate and predict the urban growth and land use change for the City of Sana’a (Yemen) for the period 2004–2020. GIS based maps were generated for the urban growth pattern of the city which was further analyzed using geo-statistical techniques. During the models calibration process, a total of 35 years of time series dataset such as historical topographical maps, aerial photographs and satellite imageries was used to identify the parameters that influenced the urban growth. The validation result showed an overall accuracy of 99.6 %; with the producer’s accuracy of 83.3 % and the user’s accuracy 83.6 %. The SLEUTH model used the best fit growth rule parameters during the calibration to forecasting future urban growth pattern and generated various probability maps in which the individual grid cells are urbanized assuming unique “urban growth signatures”. The models generated future urban growth pattern and land use changes from the period 2004–2020. Both models proved effective in forecasting growth pattern that will be useful in planning and decision making. In comparison, the CA model growth pattern showed high density development, in which growth edges were filled and clusters were merged together to form a compact built-up area wherein less agricultural lands were included. On the contrary, the SLEUTH model growth pattern showed more urban sprawl and low-density development that included substantial areas of agricultural lands.

Time is a fundamental dimension in urban dynamics, but the effect of various definitions of time on urban growth models has rarely been evaluated. In urban growth models such as cellular automata (CA), time has typically been defined as a sequence of discrete time steps. However, most urban growth processes such as land‐use changes are asynchronous. The aim of this study is to examine the effect of various temporal dynamics scenarios on urban growth simulation, in terms of urban land‐use planning, and to introduce an asynchronous parcel‐based cellular automata (AParCA) model. In this study, eight different scenarios were generated to investigate the impact of temporal dynamics on CA‐based urban growth models, and their outputs were evaluated using various urban planning indicators. The obtained results show that different degrees of temporal dynamics lead to various patterns appearing in urban growth CA models, and the application of asynchronous (event‐driven) CA models achieves better simulation results than synchronous models.

Surakarta is one of the big cities in Central Java and is the centre of the development of the mainstay area of SUBOSUKOWONOSRATEN. The physical development of the city of Surakarta has unwittingly spread to the periphery. The material changes in land use illustrate the expansion of the city of Surakarta and social and economic towards urban areas, called urbanization. Spatially, urban development in the suburbs of Surakarta City tends to the south or, in other words, towards Sukoharjo Regency. In line with the unstoppable pace of urbanization, Sukoharjo Regency must maximize development opportunities. The growth of urban areas can indicate urbanization. Industrial and residential growth can be an indication of urban growth. Urban growth modelling uses landusesim, GIS and Cellular Automata as the basis. Expectations of land use change are for industry to increase by 405 ha and settlements to increase by 2103 ha. The most significant land use change from 2022-2032 is in residential land use with an area of 1714.95 ha, which has changed from 2022 by 9%. Changes in land use for settlements are below the previously predicted expectations. Industrial land use also experienced changes in 2032; it increased by 405 ha or 48% from 2022.

AN ASSESSMENT OF SPATIAL VARIATION OF LAND SURFACE CHARACTERISTICS OF MINNA, NIGER STATE NIGERIA FOR SUSTAINABLE URBANIZATION USING GEOSPATIAL TECHNIQUES

Interactions between cities play a significant role in the development of metropolitan regions. Although these interactions and their role in the urban growth modelling have already been investigated, there is still room for more studies. In this research, in addition to conventional urban growth factors, spatial interactions between the cities (SIBC) are incorporated into urban growth modelling. This causes directional trends in urban growth (DTUG). Therefore, first the DTUG of each city was measured using a developed indicator based on the history of urban growth that was extracted from satellite images and spatial statistics. The SIBC was then estimated by integrating the DTUG of the cities. Finally, the SIBC and other driving forces, including the physical suitability, accessibility and neighbourhood effects, were integrated using a cellular automata-based model. The accuracy of the model in the Tehran metropolitan region was increased by 6.44% after considering the SIBC. The analysis of the DTUG and SIBC in the Tehran metropolitan region during 1991–2000–2007–2014 revealed specific patterns as the spatial interactions intensified over time and usually peaked in the periphery of the central business districts and intense interactions existed between the metropolises and other major cities. These findings could help urban managers with strategic decision-making in the metropolitan regions and adjust the science and practice relation in this field.

While the rural population is decreasing day by day, the urban population is increasing rapidly. Urban growth, which occurs as a result of this increase, is sprawling toward natural and environmental areas in urban fringes, and constitutes the main source of many environmental, physical, social, and economic problems. In order to overcome these problems, the direction and rate of urban growth should be determined with simulation models. In this context, many urban growth models have been developed since the 1990s; the SLEUTH urban growth model is one of the most popular among them and has been used in many projects around the world. The brute force calibration process in which the best fit values of growth coefficients are determined is the most important stage of simulation models. The coefficient ranges are initially defined as being between 0 and 100 and are then narrowed in this step according to 13 separate regression scores, which are used to specify the characterization of urban growth. Consensus has not yet been reached as to which metrics should be used for calculating the best fit values, but the Lee–Sallee and Optimum SLEUTH Metric (OSM) methods have been mostly used in past studies. However, in rapidly growing study areas, these methods cannot truly explain urban growth properties. The main purpose of this paper is to precisely calibrate urban growth simulation models. Therefore, Exploratory Factor Analysis (EFA) was used to calculate the growth coefficients, as a new statistical approach for calibration, in this study. The district of Sancaktepe, Istanbul, which experienced population growth of 80% between 2008 and 2018, was selected as the study area in order to test the achievement of the EFA method, and two urban growth simulation models were generated for the years 2030 and 2050. According to the results, despite the fact that there is little effect of urban growth in the short term, more than 70% of forests and agricultural lands are at risk of urbanization by 2050.

Unplanned urban expansion poses significant challenges to environmental sustainability and urban planning. This study analyzes the spatiotemporal dynamics of Zinder’s urban landscape using Landsat satellite imagery from 1988, 2000, 2011, and 2022. The study applied remote sensing (RS), geographic information system (GIS) techniques, and urban growth models. The random forest classifier, a machine learning algorithm, was used to classify three land use/land cover categories: “vegetation”, “built-up”, and “others”. Zinder’s arid environment is characterized by sparse vegetation, which constitutes a limited but vital component of its landscape. Despite the already sparse vegetation in the area, the findings reveal a 3.5% reduction in vegetation cover between 1988 and 2022, alongside an 11.5% increase in “built-up” areas and an 8% decrease in the “others” category. This loss of already minimal vegetation raises significant concerns about environmental degradation and the exacerbation of desertification risks. Interestingly, urban expansion showed no significant correlation with population growth (r = 0.29, p > 0.5), suggesting that other factors, such as economic activities, infrastructure development, and land use policies, drive land conversion. Edge expansion emerged as the dominant growth type, with a significant directional preference (Chi-Square = 2334.41, p < 0.001) toward major roads and areas with higher accessibility to public services. These findings emphasize the need for strategic urban planning and land management policies to address the drivers of unplanned expansion. Prioritizing sustainable infrastructure development, enforcing land use regulations, and conserving natural landscapes are critical to balancing urban growth with environmental preservation, ensuring resilience and sustainability in Zinder.

Africa has been a hotspot of rapid urban growth since 2000, yet no review exists that describes the current state of urban growth modeling. This review aims to fill this gap by synthesizing urban growth modeling approaches, input variables and challenges across Africa. Using Web of Science, Google Scholar, Geobase, and Compendex databases, we selected 49 studies that projected urban land use and cover change or modeled probabilities of future urban change associated with a variety of input variables. We found increasing trends in the numbers of studies employing cellular automata, statistical regression, agent-based, video prediction, and integrated approaches. The modeling approaches used and their corresponding increases differed across Africa. The input variables used to project urban growth also varied across subregions. Studies were biased towards populous countries rather than the most urbanized. 78 % of the studies focused on primary cities, while secondary cities were less frequently studied. Comparison of urban growth modeling across multiple regions and for different types of cities is currently difficult due to inconsistent definitions and limited availability of data and computational resources. We recommend that the scientific community develop consistent definitions of African city types and urban land use and land cover classifications, create regional urban land cover products for Africa, and build repositories of models and their input data.

Jinan City, with rapid urban growth and prominent ecological environmental pressure, was selected for the research area. We used SLEUTH model to simulate scenes of urban dynamic growth. On the basis of the actual situation of Jinan urban area, this paper presents three urban growth models to reveal the trend of urban growth under different types of land protection intensity. The results show that scene 1 was based on a hypothesis that the intensity of urban development remained basically unchanged in the scene of future urban growth and changed with the form of simulation. At this time, urban land use growth was fast and the urban expansion was mainly marginal growth; Scene 2 increased the degree of water protection to 80%, and the degree of farmland and woodland protection to 50%, which effectively controlled the urban growth; Scene 3 increased the degree of cultivated land and woodland protection to 80% and 90% respectively, resulting in a significant deterrence of the urban growth trend. The study proved the applicability of the SLEUTH model to urban growth prediction in China, and provided a theoretical basis for urban planning of Jinan.

Monitoring and modelling spatio-temporal urban growth of Delhi using Cellular Automata and geoinformatics

This paper presents a linguistic approach for modeling urban growth. The authors developed a methodological framework which utilizes Fuzzy Set theory to capture and describe the effect of urban features on urban growth and applies Cellular Automata techniques to simulate urban growth. Although several approaches exist that combine Fuzzy Logic and Cellular Automata for urban growth modeling, the authors focused on the ability to use partial knowledge and combine theory-driven and data driven knowledge. To achieve this, a parallel connection between the input variables is introduced which further allows the model to disengage from severe data limitations. In this approach, a number of parallel fuzzy systems are used, each one of which focuses on different types of urban growth factors, different drivers or restrictions of development. The effects of all factors under consideration are merged into a single internal thematic layer that maps the suitability for urbanization for each area, providing thus an information flow familiar to the human conceptualization of the phenomenon. Following, cellular automata techniques are used to simulate urban growth. The proposed methodology is applied in the Mesogeia area in the Attica basin (Athens) for the period 1990-2004 and provides realistic estimations for urban growth.

Rapid urbanization and climate change jointly shape future flood exposure in coastal cities, particularly in the Global South, where urban growth rates are high and adaptive capacity is often constrained. While scenario-based frameworks such as the Shared Socioeconomic Pathways (SSPs) and Representative Concentration Pathways (RCPs) provide consistent narratives of socioeconomic and climatic change, their integration into spatially explicit urban growth modelling and flood exposure analysis remains limited.This study applies the SLEUTH urban growth model to project high-resolution (30 m) urban expansion trajectories up to 2050 for nine coastal urban agglomerations across Africa, Asia, and Latin America under SSP1, SSP2, and SSP5. SSP-based urban population projections were translated into scenario-specific SLEUTH parameters, enabling consistent representation of divergent socioeconomic pathways. Model calibration was supported by harmonized historical settlement data from the World Settlement Footprint and enhanced through a kernel density–based zonation and spatial tiling approach to capture heterogeneous urban–rural growth dynamics across large study areas. Projected urban extents were overlaid with RCP-based coastal, fluvial, and pluvial flood hazard maps to assess future flood exposure at the 50th and 83rd percentiles for a 100-year return period.Results reveal pronounced inter-city and inter-scenario variability in both urban expansion and flood exposure. Four cities (Dar es Salaam, Ho Chi Minh City, Khulna, and Surat) are projected to expand by more than 50% by 2050 under SSP1 and SSP5. Flood exposure is driven by the combined effects of climate forcing and urban development patterns: high radiative forcing scenarios amplify hazard extent, while socioeconomic pathways strongly influence where and how cities expand into flood-prone areas [1]. In several cities, newly developed urban areas exhibit disproportionately higher exposure than existing settlements, particularly for fluvial and pluvial flooding. However, exposure patterns are highly city-specific, underscoring the limitations of generalized assumptions.The findings demonstrate that future urban flood exposure cannot be explained by climate change alone, but emerges from the interaction between climate scenarios and socioeconomic pathways shaping urban growth. By combining SSP/RCP frameworks with spatially explicit urban growth modelling across multiple cities, this study provides comparative insights relevant for scenario-based urban planning and flood risk management in rapidly urbanizing coastal regions of the Global South.[1] Bachofer, F., Wang, Z., Huth, J., Eisfelder, C., Reimuth, A., & Kuenzer, C. (2026). Urban growth prediction along Shared Socioeconomic Pathways (SSPs) for future flood exposure risk assessment: a cross-continental analysis of coastal cities. Anthropocene Coasts, 9(1). https://doi.org/10.1007/s44218-025-00109-

Measuring the Effect of Stochastic Perturbation Component in Cellular Automata Urban Growth Model

In recent years, urban growth has become the center of attention and preoccupation for many researchers especially those concerned with urban planning. Some scholars only take into consideration the social dynamism and demographic data of an area of interest while analyzing the urban growth. However, those approaches fail to consider other physical conditions such as the urban extent and exclusion zones (e.g. rivers and forest reserves). This makes it difficult to correctly model the urban expansion as well as simulate for future forecast, which is vital for policymakers and city planners when making informed decisions. This study, therefore, used the Geographic Information System (GIS) to compile the data obtained from a time series of satellite images between 1984 and 2018 for the urban growth model calibration. A modified cellular automata methodology called SLEUTH was then applied to supervise and forecast the urban sprawl in Praia city, the capital of Cabo Verde from the year 1984 to 2050. The forecasted result showed that breed (100) and road (62) coefficients would influence the urban growth in Praia city. This means that there is a likelihood of newly generated detached settlements and many new buildings along the roadside.

Emerging megacities in the global south face unprecedented transformation dynamics, manifested in rapid demographic, economic, and physical growth. Anticipating the associated sustainability and resilience challenges requires an understanding of future trajectories. Global change models provide consistent high-level urbanization scenarios. City-scale urban growth models accurately simulate complex physical growth. Modeling approaches linking the global and the local scale, however, are underdeveloped. This work introduces a novel approach to inform a local urban growth model by global Shared Socioeconomic Pathways to produce consistent maps of future urban expansion and population density via cellular automaton and dasymetric mapping. We demonstrate the approach for the case of Pune, India. Three scenarios are explored until 2050: business as usual (BAU), high, and low urbanization. After calibration and validation, the BAU scenario yields a 55% growth in Pune’s population and 90% in built-up extent, entailing significant impacts: Pune’s core city densifies further with up to 60,000 persons/km2, adding pressure to its strained infrastructure. In addition, 66–70% more residents are exposed to flood risk. Half of the urban expansion replaces agriculture, converting 167 km2 of land. The high-urbanization scenario intensifies these impacts. These results illustrate how spatially explicit scenario projections help identify impacts of urbanization and inform long-term planning.