Calibration of cellular automata models using differential evolution to simulate present and future land use

A key issue in cellular automata (CA) modeling is the minimization of the differences between the actual and simulated patterns, which can be mathematically formulated as an objective function. We develop a new hybrid model (termed DE‐CA) by integrating differential evolution (DE) into CA to solve the objective function and retrieve the optimal CA parameters. Constrained relations among factors were applied in DE to generate different sets of CA parameters for prediction of future scenarios. The DE‐CA model was calibrated using historical spatial data to simulate 2016 land use in Kunming and predict multiple scenarios to the year 2026. Assessment of quantitative accuracy shows that DE‐CA yields 92.4% overall accuracy, where 6.8% is the correctly captured urban growth; further, the model reported only 5.0% false alarms and 2.6% misses. Regarding the simulation ability, our new CA model performs as well as the widely applied genetic algorithm‐based CA model, and outperforms both the logistic regression‐based CA model and a no‐change NULL model. We projected three possible scenarios for the year 2026 using DE‐CA to adequately address the baseline urban growth, environmental protection and urban planning to show the strong prediction ability of the new model.     

A Patch‐based Cellular Automaton for Simulating Land‐use Changes at Fine Spatial Resolution

While cellular automata have become popular tools for modeling land‐use changes, there is a lack of studies reporting their application at very fine spatial resolutions (e.g. 5 m resolution). Traditional cell‐based CA do not generate reliable results at such resolutions because single cells might only represent components of land‐use entities (i.e. houses or parks in urban residential areas), while recently proposed entity‐based CA models usually ignore the internal heterogeneity of the entities. This article describes a patch‐based CA model designed to deal with this problem by integrating cell and object concepts. A patch is defined as a collection of adjacent cells that might have different attributes, but that represent a single land‐use entity. In this model, a transition probability map was calculated at each cell location for each land‐use transition using a weight of evidence method; then, land‐use changes were simulated by employing a patch‐based procedure based on the probability maps. This CA model, along with a traditional cell‐based model were tested in the eastern part of the Elbow River watershed in southern Alberta, Canada, an area that is under considerable pressure for land development due to its proximity to the fast growing city of Calgary. The simulation results for the two models were compared to historical data using visual comparison, K_simulation indices, and landscape metrics. The results reveal that the patch‐based CA model generates more compact and realistic land‐use patterns than the traditional cell‐based CA. The K_simulation values indicate that the land‐use maps obtained with the patch‐based CA are in higher agreement with the historical data than those created by the cell‐based model, particularly regarding the location of change. The landscape metrics reveal that the patch‐based model is able to adequately capture the land‐use dynamics as observed in the historical data, while the cell‐based CA is not able to provide a similar interpretation. The patch‐based approach proposed in this study appears to be a simple and valuable solution to take into account the internal heterogeneity of land‐use classes at fine spatial resolutions and simulate their transitions over time.     

Calibration of a Multi-criteria Evaluation Based Cellular Automata Model for Indian Cities Having Varied Growth Patterns

The study aims to investigate the efficiency of Cellular Automata (CA) based models for simulation of urban growth in two Indian cities (Dehradun and Saharanpur) having different growth patterns. The transition rules in the CA model were defined using Multi-Criteria Evaluation technique. The model was calibrated by varying two parameters namely the neighbourhood (type and size) and model iterations. The model results were assessed using two measures, i.e., percent correct match and Moran’s Index. It was found that for Dehradun, which had a dispersed growth pattern, Von Neumann neighbourhood of small size produced the highest accuracy, in terms of pattern and location of simulated urban growth. For Saharanpur, which had a compact growth pattern, large neighbourhoods, produced the most optimum results, irrespective of the type of neighbourhood. For both study areas, large number of model iterations failed to increase the accuracy of urban growth assessment.     

An analysis of changes in the urban landscape composition and configuration in the Sancaktepe District of Istanbul Metropolitan City,Turkey using landscape metrics and satellite data

Changes in landscape composition and configuration patterns of Sancaktepe Municipal District in the Asian side of Istanbul Metropolitan City of Turkey were analysed using landscape metrics. Class-level and landscape-level metrics were calculated from the land cover/land use data using Patch Analyst, an extension in the Arc View GIS. The land cover/land use data were derived from classified satellite images of Landsat Thematic Mapper of 2002 and 2009 for Sancaktepe District. There was evidence of increase in agglomeration process of built-up patches as indicated by the increases in mean patch size, decrease in total edge and number of patches between 2002 and 2009. The urban expansion pattern experienced overall was not fragmented but concentrated due to infilling around existing patches. Changes in Area-Weighted Mean Shape Index and Area-Weighted Patch Fractal Dimension Index indicated that the physical shapes within built-up, forest and bareland areas were relatively complex and irregular. A conclusion is made in this study that spatial metrics are useful tools to describe the urban landscape composition and configuration in its various aspects and certain decisions whether to approve a specific development in urban planning could, for example, be based on some measures of urban growth form or pattern in terms of uniformity and irregularity, attributable to the dynamic processes of agglomeration and fragmentation of land cover/land use patches caused by urban expansion.     

Modelling coastal land use change by incorporating spatial autocorrelation into cellular automata models

This paper presents a spatial autoregressive (SAR) method-based cellular automata (termed SAR-CA) model to simulate coastal land use change, by incorporating spatial autocorrelation into transition rules. The model captures the spatial relationships between explained and explanatory variables and then integrates them into CA transition rules. A conventional CA model (LogCA) based on logistic regression (LR) was studied as a comparison. These two CA models were applied to simulate urban land use change of coastal regions in Ningbo of China from 2000 to 2015. Compared to the LR method, the SAR model yielded smaller accumulated residuals that showed a random distribution in fitting the CA transition rules. The better-fitting SAR model performed well in simulating urban land use change and scored an overall accuracy of 85.3%, improving on the LogCA model by 3.6%. Landscape metrics showed that the pattern generated by the SAR-CA model has less difference with the observed pattern.     

Assessing the effect of temporal dynamics on urban growth simulation: Towards an asynchronous cellular automata

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.     

Exploring the Historical Determinants of Urban Growth Patterns through Cellular Automata

We have adapted METRONAMICA, an established cellular automata (CA) modelling system, to simulate the historical growth of a section of a large world city. Our model is tuned to reflect the morphology of land use patterns more accurately than traditional CA models, which abstract those patterns to more aggregate spatial scales. We explore the spatial determinants of land use patterns with detailed empirical data, documenting the historical growth of West London at an unusually high level of spatial and temporal resolution. The results of the study provide support for our considered speculations: (1) that the spatial relationships between land uses and the physical environment are remarkably consistent through time, showing little variation relative to changes in historical context; and (2) that these relationships constitute a basic code for urban growth which determines the spatial signature of land development in a given metropolitan area.     

基于支持向量机的元胞自动机及土地利用变化模拟

提出了利用遥感数据，并采用支持向量机来确定元胞自动机非线性转换规则的新方法。元胞自动机在模拟复杂地理现象时，需要采用非线性转换规则。目前元胞自动机主要采用线性方法来获取转换规则，在反映复杂的非线性地理现象时有一定的局限性。以城市扩张的模拟为例，将模拟城市系统的主要特征变量映射到Hilbert空间后，通过SVM建立最优分割超平面，分割超平面的分类决策函数由径向基核（Radial Basis Kernel）构造。利用历史遥感数据校正超平面的决策函数，确定城市元胞自动机的非线性转换规则，计算出城市发展概率。利用所提出的方法，对深圳市1988-2010年的城市发展进行了模拟，取得了较理想的模拟效果。研究结果表明，基于SVM-CA模型的模拟精度比传统MCE方法模拟精度高，MoranⅠ指数与实际更为接近。     

Cellular Automata Based Model of Urban Spatial Growth

In the study reported in this paper an attempt has been made to develop a Cellular Automata (CA) model for simulating future urban growth of an Indian city. In the model remote sensing data and GIS were used to provide the empirical data about urban growth while Markov chain process was used to predict the amount of land required for future urban use based on the empirical data. Multi-criteria evaluation (MCE) technique was used to reveal the relationships between future urban growth potential and site attributes of a site. Finally using the CA model, land for future urban development was spatially allocated based on the urban suitability image provided by MCE, neighbourhood information of a site and the amount of land predicted by Markov chain process. The model results were evaluated using Kappa Coefficient and future urban growth was simulated using the calibrated model     

A novel approach for predicting the spatial patterns of urban expansion by combining the chi-squared automatic integration detection decision tree,Markov chain and cellular automata models in GIS

Urban development is a continuous and dynamic spatio-temporal phenomenon associated with economic developments and growing populations. To understand urban expansion, it is important to establish models that can simulate urbanization process and its deriving factors behaviours, monitor deriving forces interactions and predict spatio-temporally probable future urban growth patterns explicitly. In this research, therefore, we presented a hybrid model that integrates the chi-squared automatic integration detection decision tree (CHAID-DT), Markov chain (MC) and cellular automata (CA) models to analyse, simulate and predict future urban expansions in Tripoli, Libya in 2020 and 2025. First, CHAID-DT model was applied to investigate the contributions of urban factors to the expansion process, to explore their interactions and to provide future urban probability map; second, MC model was employed to estimate the future demand of urban land; third, CA model was used to allocate estimated urban land quantity on the probability map to present future projected land use map. Three satellite images of the study area were obtained from the periods of 1984, 2002 and 2010 to extract land use maps and urban expansion data. We validated the model with two methods, namely, receiver operating characteristic and the kappa statistic index of agreement. Results confirmed that the proposed hybrid model could be employed in urban expansion modelling. The applied hybrid model overcame the individual shortcomings of each model and explicitly described urban expansion dynamics, as well as the spatio-temporal patterns involved.     

Spatial Metrics to Analyse the Impact of Regional Factors on Pattern of Urbanisation in Gurgaon,India

In recent years, there has been lot of emphasis on the study of urban land use/ land cover changes to discover the growth pattern due to rapid urbanisation. This study presents spatial metrics and gradient analysis approach for quantifying and capturing changes in urban landscape using LISS III imagery of 1999, 2001 and 2004 of Gurgaon, India. A combination of spatial metrics i.e. percentage of landscape, mean patch size, number of patches, landscape shape index and largest patch index, available in Fragstats ver. 3.3, have been used to quantify the patterns of urban growth in different directions in terms of size, shape and complexity of development. The local built-up areas were quantified by the “moving window” technique. A gradient analysis has been carried out through sampling from a reference point to 8 km in 16 directions with a window size of 500 mts. Results of this study demonstrate the potential of spatial metrics and gradient modelling to quantify the impact of regional factors on the growth pattern of Gurgaon city.     

A grey wolf optimizer–cellular automata integrated model for urban growth simulation and optimization

This article proposes a grey wolf optimizer (GWO) and cellular automata (CA) integrated model for the simulation and spatial optimization of urban growth. A new grey wolf‐inspired approach is put forward to determine the urban growth rules of CA cells by using the GWO algorithm, which is suitable for solving optimization problems. The inspiration for GWO comes from the social leadership of wolf groups, as well as their hunting behavior. The GWO‐optimized urban growth rules for CA describe the relationship between the spatial variables and the urban land‐use status for each cell in the formation of “if–then.” The GWO algorithm and CA model are then integrated as the GWO–CA model for urban growth simulation and optimization. By taking Nanjing City as an example, the simulation accuracy in terms of urban cells is 86.6%, and the kappa coefficient is 0.715, indicating that the GWO algorithm is efficient at obtaining urban growth rules from spatial variables. The validation of the GWO–CA model also illustrates that it performs well in terms of the simulation and spatial optimization of urban growth, and can further contribute to urban planning and management.     

用于沿海城市扩展模拟的一种CA模型

对传统的克拉克城市扩展模型进行了分析,构造了一种适合沿海城市扩展的CA模型.利用建立的CA模型,对沿海城市青岛市的城市扩展进行了模拟,试验结果表明,模型对沿海城市的扩展具有很好的模拟效果.     

An Artificial-Neural-Network-based,Constrained CA Model for Simulating Urban Growth

Insufficient research has been done on integrating artificial-neural-network-based cellular automata (CA) models and constrained CA models, even though both types have been studied for several years. In this paper, a constrained CA model based on an artificial neural network (ANN) was developed to simulate and forecast urban growth. Neural networks can learn from available urban land-use geospatial data and thus deal with redundancy, inaccuracy, and noise during the CA parameter calibration. In the ANN-Urban-CA model we used, a two-layer Back-Propagation (BP) neural network has been integrated into a CA model to seek suitable parameter values that match the historical data. Each cell's probability of urban transformation is determined by the neural network during simulation. A macro-scale socio-economic model was run together with the CA model to estimate demand for urban space in each period in the future. The total number of new urban cells generated by the CA model was constrained, taking such exogenous demands as population forecasts into account. Beijing urban growth between 1980 and 2000 was simulated using this model, and long-term (2001–2015) growth was forecast based on multiple socio-economic scenarios. The ANN-Urban-CA model was found capable of simulating and forecasting the complex and non-linear spatial-temporal process of urban growth in a reasonably short time, with less subjective uncertainty.     

Deriving urban dynamic evolution rules from self-adaptive cellular automata with multi-temporal remote sensing images

Cellular automata (CA) have proven to be very effective for simulating and predicting the spatio-temporal evolution of complex geographical phenomena. Traditional methods generally pose problems in determining the structure and parameters of CA for a large, complex region or a long-term simulation. This study presents a self-adaptive CA model integrated with an artificial immune system to discover dynamic transition rules automatically. The model’s parameters are allowed to be self-modified with the application of multi-temporal remote sensing images: that is, the CA can adapt itself to the changed and complex environment. Therefore, urban dynamic evolution rules over time can be efficiently retrieved by using this integrated model. The proposed AIS-based CA model was then used to simulate the rural-urban land conversion of Guangzhou city, located in the core of China’s Pearl River Delta. The initial urban land was directly classified from TM satellite image in the year 1990. Urban land in the years 1995, 2000, 2005, 2009 and 2012 was correspondingly used as the observed data to calibrate the model’s parameters. With the quantitative index figure of merit (FoM) and pattern similarity, the comparison was further performed between the AIS-based model and a Logistic CA model. The results indicate that the AIS-based CA model can perform better and with higher precision in simulating urban evolution, and the simulated spatial pattern is closer to the actual development situation.     

Evaluation and development of sustainable urban land use plans through spatial optimization

Along with rapid global urbanization, cities are challenged by environmental risks and resource scarcity. Sustainable urban planning is central to address the dilemma of economic growth and ecosystem protection, where the use of land is critical. Sustainable land use patterns are spatially explicit in nature, and can be structured and addressed using spatial optimization integrating GIS and mathematical models. This research discusses prominent sustainability concerns in land use planning and suggests a generalized multi‐objective spatial optimization model to facilitate conventional planning. The model is structured to meet land use demand while satisfying the requirements of the physical environment, society and economy. Unlike existing work relying on raster data, due to its simple data structure and ease of spatial relationship evaluation, this research develops an approach for identifying land use solutions based on vector data that better reflects the actual shape and spatial layout of land parcels as well as the ways land use information is managed in practice. An evolutionary algorithm is developed to find the set of efficient (Pareto) solutions given the complexity of vector‐based representations of space. The proposed approach is applied in an empirical study of Dafeng, China in order to support local urban growth and development. The results demonstrate that spatial optimization can be a powerful tool for deriving effective and efficient land use planning strategies. A comparison to results using a raster data approach supports the superiority of land use optimization using vector data as part of planning practice.     

Neural networks-based simulation of land cover scenarios in Doon valley,India

Land cover transformation is one of the foremost aspects of human-induced environmental change, having an extensive history dating back to antiquity. The present study aims to simulate the process of land cover change based on different policy-based scenarios so as to provide a basis for sustainable development in Doon valley, India. For this purpose, an artificial neural network-based spatial predictive model was developed for the Doon valley. The predictive model generated future land cover patterns under three policy scenarios, i.e. baseline scenario, compact growth scenario and hierarchical growth scenario (HGS). The simulated land cover patterns mirror where land cover patterns are headed in the valley by year 2021. The result suggests that unabated continuation of the present pattern of land cover transformation will result in a regional imbalance. However, this skewed development can be corrected by altering the current growth trend as revealed in the compact growth and HGSs.     

Improving urban cellular automata performance by integrating global and geographically weighted logistic regression models

In many of the conventional cellular automata (CA) models, particularly Urban‐CA which are used for urban growth, the spatial heterogeneities and local differences of the land use conversion processes are ignored. Global logistic regression (LR) is a popular model employed to define the transition rules of Urban‐CA. By considering the local characteristics, Geographically Weighted Logistic Regression (GWLR) provides interesting capabilities for urban growth modelling. In this research, in addition to using GWLR in the definition of transition rules, the advantages of integrating GWLR and LR for urban growth simulation were evaluated; these have not been considered in previous studies. Local and global probabilities obtained from the calibration of GWLR and LR were combined to define the transition rules of an Urban‐CA. Urban growth was simulated in the Islamshahr sub‐region located southwest of Tehran, Iran for the two periods 1992‐1996 and 1996‐2002, and data from these periods were used for training and testing the prediction abilities, respectively. In the first period, GWLR showed good performance and a significant contribution to the enhancement of the simulation performance, but in the second period, the effectiveness of LR on the prediction accuracy increased. Due to their complementary roles, the integration of the GWLR and LR models resulted in improved simulation performance in both periods.     

Modeling sprawl of unauthorized development using geospatial technology: case study in Kuantan district,Malaysia

Abstract

The paper explores a framework combining remote sensing and GIS-cellular automata (CA) concepts aimed at improving the modeling of unauthorized land use sprawl. Remote sensing data have been used in urban modeling and analysis, the use of high-resolution remote sensing data in assessing unauthorized development is quite unexplored. This work has demonstrated systematic combination utilization of geospatial analyses tools to acquire a new level of information to enable urban modeling and sprawl analysis in assisting urban sustainable management. In this study, Kuantan city, Malaysia was selected in simulation of the unauthorized land use with CA concept for a period of 15 years (2000–2015), with main input time-series land use observation from 1995 to 2005. The 2000 and 2005 land use input was also used as calibrated and test assessment of the simulation. The results show excellent agreement between in-situ changes of the unauthorized land use classes and the corresponding simulated classes within the same periods. In conclusion, CA model can lead to new levels of understanding of how urban areas grow and change as in view of digital earth aspiration.     

A Temporal Variant‐Invariant Validation Approach for Agent‐based Models of Landscape Dynamics

Agent‐based modeling provides a means for addressing the way human and natural systems interact to change landscapes over time. Until recently, evaluation of simulation models has focused on map comparison techniques that evaluate the degree to which predictions match real‐world observations. However, methods that change the focus of evaluation from patterns to processes have begun to surface; that is, rather than asking if a model simulates a correct pattern, models are evaluated on their ability to simulate a process of interest. We build on an existing agent‐based modeling validation method in order to present a temporal variant‐invariant analysis (TVIA). The enhanced method, which focuses on analyzing the uncertainty in simulation results, examines the degree to which outcomes from multiple model runs match some reference to how land use parcels make the transition from one land use class to another over time. We apply TVIA to results from an agent‐based model that simulates the relationships between landowner decisions and wildfire risk in the wildland‐urban interface of the southern Willamette Valley, Oregon, USA. The TVIA approach demonstrates a novel ability to examine uncertainty across time to provide an understanding of how the model emulates the system of interest.