Simulating urban land use change by integrating a convolutional neural network with vector-based cellular automata

ABSTRACT

Vector-based cellular automata (VCA) models have been applied in land use change simulations at fine scales. However, the neighborhood effects of the driving factors are rarely considered in the exploration of the transition suitability of cells, leading to lower simulation accuracy. This study proposes a convolutional neural network (CNN)-VCA model that adopts the CNN to extract the high-level features of the driving factors within a neighborhood of an irregularly shaped cell and discover the relationships between multiple land use changes and driving factors at the neighborhood level. The proposed model was applied to simulate urban land use changes in Shenzhen, China. Compared with several VCA models using other machine learning methods, the proposed CNN-VCA model obtained the highest simulation accuracy (figure-of-merit = 0.361). The results indicated that the CNN-VCA model can effectively uncover the neighborhood effects of multiple driving factors on the developmental potential of land parcels and obtain more details on the morphological characteristics of land parcels. Moreover, the land use patterns of 2020 and 2025 under an ecological control strategy were simulated to provide decision support for urban planning.     

基于粗集的知识发现与地理模拟——以深圳市土地利用变化为例

为了更有效地模拟地理现象的复杂演变过程,提出了用粗集理论来确定元胞自动机 (CA)不确定性转换规则的新方法。CA可以通过局部规则来有效地模拟许多地理现象的演变过程。但目前缺乏很好定义CA转换规则的方法。往往采用启发式的方法来定义CA的转换规则,这些转换规则是静态的,而且其参数值多是确定的。在反映诸如城市扩张、疾病扩散等不确定性复杂现象时,具有一定的局限性。利用粗集从GIS和遥感数据中发现知识,自动寻找CA的不确定性转换规则,基于粗集的CA在缩短建模时间的同时,能提取非确定性的转换规则,更好地反映复杂系统的特点。采用所提出的方法模拟了深圳市的城市发展过程,取得了比传统MCE方法更好的模拟效果。     

基于CA-ABM模型的福州城市用地扩张研究

以中国海西地区重要门户福州市为研究区,结合其地理位置多层次约束性条件,以地理加权回归模型作为元胞自动机(CA)层的转换规则,同时以2000-2015年多期LandsatTM/ETM+影像的城市用地情况为参照,借助GIS空间分析技术,对CA和多智能体(ABM)相耦合的城市用地扩张模型进行改进。然后利用传统的和改进后的CA-ABM模型,多角度、多层次地模拟福州市2000年、2005年、2010年、2015年城市用地扩张在微观格局上的变化。结果表明,传统的和改进后的CA-ABM模型的整体精度均在80%以上,模拟结果具有较强的可信度;改进的 CA-ABM模型模拟的点对点总体精度和Kappa系数均高于传统的CA-ABM模型,而且模拟结果更加接近实际的城市用地扩张分布情况。结论可为平衡城市化进程和合理规划城市用地提供重要的理论技术支撑。     

多层次矢量元胞自动机建模及土地利用变化模拟

城市规划对土地利用变化起着重要的引导作用,各层次规划相互支撑、互为补充,自上而下影响着土地利用格局的演变。矢量元胞自动机以不规则的地理实体作为基本单元,可以更逼真地表达客观复杂的城市用地空间结构。然而,当面向具有层次协同性、空间引导性和管控传导性等特征的城市规划时,其元胞多层次体系构造、层次间协同方法和转换规则获取等关键问题凸显出来。本文以江阴市2007年、2012年、2017年3期土地利用现状数据为基础,在多层次矢量元胞自动机建模基础上,模拟了2017年土地利用变化,通过模拟结果与用地现状对比分析,对模型个别参数进行了修正,进一步提高了模型的可行性与适用性,进而预测了2022年城市土地利用格局。模拟结果显示,中心城片区建设用地发展已经趋于饱和,澄南、澄东南和澄东片区建设用地扩张较为明显,有逐步形成“中心城区—城镇组团—村庄”三级城乡空间聚落体系的趋势。最后利用FoM指标对模拟结果进行了评价,得到整体和各片区的精度基本都大于或接近于0.21,表明模拟结果精度较高,其构建的模型在面向多层次规划的用地变化模拟方面具有更好的效果。     

A heuristic cellular automata approach for modelling urban land-use change based on simulated annealing

This article presents a novel cellular automata (CA) approach to simulate the spatio-temporal process of urban land-use change based on the simulated annealing (SA) algorithm. The SA algorithm enables dynamic optimisation of the CA's transition rules that would otherwise be difficult to configure using conventional mathematical methods. In this heuristic approach, an objective function is constructed based on a theoretical accumulative disagreement between the simulated land-use pattern and the actual land-use pattern derived from remotely sensed imagery. The function value that measures the mismatch between the actual and the simulated land-use patterns would be minimised randomly through the SA process. Hence, a set of attribution parameters that can be used in the CA model is achieved. An SA optimisation tool was developed using Matlab and incorporated into the cellular simulation in GIS to form an integrated SACA model. An application of the SACA model to simulate the spatio-temporal process of land-use change in Jinshan District of Shanghai Municipality, PR China, from 1992 to 2008 shows that this modelling approach is efficient and robust and can be used to reconstruct historical urban land-use patterns to assist with urban planning policy-making and actions. Comparison of the SACA model with a typical CA model based on a logistic regression method without the SA optimisation (also known as LogCA) shows that the SACA model generates better simulation results than the LogCA model, and the improvement of the SACA over the LogCA model is largely attributed to higher locational accuracy, a feature desirable in most spatially explicit simulations of geographical processes.     

基于动态约束的元胞自动机与复杂城市系统的模拟

为获得复杂城市系统更理想的模拟效果,提出时空动态约束的城市元胞自动机(CA)模型。用不同区域、不同时间新增加的城市用地总量作为CA模型的约束条件,形成时空动态约束的CA模型,并利用该模型模拟1988—2010年东莞市和深圳市城市扩张过程。结果表明,利用CA模型模拟的1993年城市用地总精度比静态CA模型提高了5.86%,而且模型中的动态约束条件可以反映城市发展的时空差异性。     

Modeling dynamic urban land-use change with geographical cellular automata and generalized pattern search-optimized rules

A novel generalized pattern search (GPS)-based cellular automata (GPS-CA) model was developed to simulate urban land-use change in a GIS environment. The model is built on a fitness function that computes the difference between the observed results produced from remote-sensing images and the simulated results produced by a general CA model. GPS optimization incorporating genetic algorithms (GAs) searches for the minimum difference, i.e. the smallest accumulated residuals, in fitting the CA transition rules. The CA coefficients captured by the GPS method have clear physical meanings that are closely associated with the dynamic mechanisms of land-use change. The GPS-CA model was applied to simulate urban land-use change in Kunshan City in the Yangtze River Delta from 2000 to 2015. The results show that the GPS method had a smaller root mean squared error (0.2821) than a logistic regression (LR) method (0.5256) in fitting the CA transition rules. The GPS-CA model thus outperformed the LR-CA model, with an overall accuracy improvement of 4.7%. As a result, the GPS-CA model should be a superior tool for modeling land-use change as well as predicting future scenarios in response to different conditions to support the sustainable urban development.     

A CA-based land system change model: LANDSCAPE

Cellular automata (CA) models are widely used to simulate land-use changes because of their simplicity, flexibility, intuitiveness and ability to incorporate the spatial and temporal dimensions of processes. A small number of CA-based models have been developed to simulate changes in multiple land uses, most of which use the hierarchical allocation strategy and/or inertia factors to enable these CA models to do so accurately. However, only some of these models allow explicit determination of the allocation sequence for active land uses according to the hierarchical allocation strategy and the objective calculation of inertia factors. In this paper, we proposed a CA-based model, i.e. the LAND System Cellular Automata model for Potential Effects (LANDSCAPE), with a hierarchical allocation strategy and resistances, to simulate changes in multiple land uses. Furthermore, we introduced effective ways to objectively determine the allocation sequence for active land uses and calculate resistances for individual land uses. The results show that the LANDSCAPE model, with a calibrated allocation sequence and resistances, is reliable and accurate for simulating multiple land-use changes.     

An agent-integrated irregular automata model of urban land-use dynamics

Urban growth models are useful tools to understand the patterns and processes of urbanization. In recent years, the bottom-up approach of geo-computation, such as cellular automata and agent-based modeling, is commonly used to simulate urban land-use dynamics. This study has developed an integrated model of urban growth called agent-integrated irregular automata (AIIA) by using vector geographic information system environment (i.e. both the data model and operations). The model was tested for the city of San Marcos, Texas to simulate two scenarios of urban growth. Specifically, the study aimed to answer whether incorporating commercial, industrial and institutional agents in the model and using social theories (e.g. utility functions) improves the conventional urban growth modeling. By validating against empirical land-use data, the results suggest that a holistic framework such as AIIA performs better than the existing irregular-automata-based urban growth modeling.     

基于随机森林的元胞自动机城市扩展模拟——以佛山市为例

本文提出一种基于随机森林的元胞自动机城市扩展(RF-CA)模型。通过在多个决策树的生成过程中分别对训练样本集和分裂节点的候选空间变量引入随机因素,提取城市扩展元胞自动机的转换规则。该模型便于并行构建,能在运算量没有显著增加的前提下提高预测的精度,对城市扩展中存在的随机因素有较强的容忍度。RF-CA模型可进行袋外误差估计,以快速获取模型参数;也可度量空间变量重要性,解释各空间变量在城市扩展中的作用。将该模型应用于佛山市1988-2012年的城市扩展模拟中,结果表明,与常用的逻辑回归模型相比,RF-CA模型进行模拟和预测分别能够提高1.7%和2.6%的精度,非常适用于复杂非线性特征的城市系统演变模型与扩展研究;通过对影响佛山市城市扩展的空间变量进行重要性度量,发现对佛山城市扩张模拟研究而言,距国道的距离与距城市中心的距离具有最重要的作用。     

分析学习智能元胞自动机及优化的城市模拟

元胞自动机被广泛应用于城市及其他地理现象的模拟,模拟过程中的最大问题是如何确定模型的结构和参数。该文提出一种基于分析学习的智能优化元胞自动机,该模型在逻辑回归模型的基础上,基于分析学习的智能方法,寻找元胞自动机模型的最佳参数。该方法允许用户控制空间变量影响权重,进而模拟出不同的城市发展模式,可为城市规划提供重要参考。     

Urban expansion in Auckland,New Zealand: a GIS simulation via an intelligent self-adapting multiscale agent-based model

ABSTRACT

Abstract: When modelling urban expansion dynamics, cellular automata models focus mostly on the physical environments and cell neighbours, but ignore the ‘human’ aspect of the allocation of urban expansion cells. This limitation is overcome here using an intelligent self-adapting multiscale agent-based model. To simulate the urban expansion of Auckland, New Zealand, a total of 15 urban expansion drivers/constraints were considered over two periods (2000–2005, 2005–2010). The modelling takes into consideration both a macro-scale agent (government) and micro-scale agents (residents of three income levels), and their multi-level interactions. In order to achieve reliable simulation results, ABM was coupled with an artificial neural network to reveal the learning process and heterogeneity of the multi-sub-residential agents. The ANN-ABM accurately simulated the urban expansion of Auckland at both the global and local scales, with kappa simulation value at 0.48 and 0.55, respectively. The validated simulation result shows that the intelligent and self-adapting ANN-ABM approach is more accurate than an ABM with a general type of agent model (kappa simulation = 0.42) at the global scale, and more accurate than an ANN-based CA model (kappa simulation = 0.47) at the local scale. Simulation inaccuracy stems mostly from the outdated master land use plan.     

A travel time-based variable grid approach for an activity-based cellular automata model

Urban growth and population growth are used in numerous models to determine their potential impacts on both the natural and the socio-economic systems. Cellular automata (CA) land-use models became popular for urban growth modelling since they predict spatial interactions between different land uses in an explicit and straightforward manner. A common deficiency of land-use models is that they only deal with abstract categories, while in reality, several activities are often hosted at one location (e.g. population, employment, agricultural yield, nature…). Recently, a multiple activity-based variable grid CA model was proposed to represent several urban activities (population and economic activities) within single model cells. The distance-decay influence rules of the model included both short- and long-distance interactions, but all distances between cells were simply Euclidean distances. The geometry of the real transportation system, as well as its interrelations with the evolving activities, were therefore not taken into account. To improve this particular model, we make the influence rules functions of time travelled on the transportation system. Specifically, the new algorithm computes and stores all travel times needed for the variable grid CA. This approach provides fast run times, and it has a higher resolution and more easily modified parameters than the alternative approach of coupling the activity-based CA model to an external transportation model. This paper presents results from one Euclidean scenario and four different transport network scenarios to show the effects on land-use and activity change in an application to Belgium. The approach can add value to urban scenario analysis and the development of transport- and activity-related spatial indicators, and constitutes a general improvement of the activity-based CA model.     

土地利用动态模拟模型的构建及其应用——以北京市海淀区为例

CLUE-S模型是一个基于经验统计原理的模拟多土地利用类型空间变化的动态模拟模型,它在世界多个国家和地区的区域尺度农业、森林为主的土地利用变化模拟中得到应用。作者对CLUE-S模型进行了改进,改进后的模型 (CLUE-SII) 引入了动态计算的邻域分析因子,可以对土地利用变化中的自发过程、自组织过程和土地利用类型间的竞争进行模拟,还可以根据研究区域特点构建不同的模拟方案,在这些模拟方案中,局地因子和邻域因子在土地利用变化中的作用方式不同。应用CLUE-SII对北京市海淀区1991~2001年土地利用变化进行了多方案模拟,结果表明邻域因子对城镇用地变化具有重要作用,其中将邻域因子看作自发过程放大因子的模拟方案获得了较好的模拟结果,整图符合比达到77%,其中城镇用地符合比达到82%,Kappa值达到0.754。CLUE-SII在北京市海淀区的应用实例表明,该模型可以对高分辨率和多土地利用类型下的城市扩展进行有效模拟,扩展了CLUE-S的应用领域;通过构建多模拟方案,不但可以探索最佳的模拟结果,还可以研究和分析不同土地利用驱动因子在土地利用变化中的作用模式。     

Allocation of urban land uses by Multi-Objective Particle Swarm Optimization algorithm

Considering the ever-increasing urban population, it appears that land management is of major importance. Land uses must be properly arranged so that they do not interfere with one another and can meet each other's needs as much as possible; this goal is a challenge of urban land-use planning. The main objective of this research is to use Multi-Objective Particle Swarm Optimization algorithm to find the optimum arrangement of urban land uses in parcel level, considering multiple objectives and constraints simultaneously. Geospatial Information System is used to prepare the data and to study different spatial scenarios when developing the model. To optimize the land-use arrangement, four objectives are defined: maximizing compatibility, maximizing dependency, maximizing suitability, and maximizing compactness of land uses. These objectives are characterized based on the requirements of planners. As a result of optimization, the user is provided with a set of optimum land-use arrangements, the Pareto-front solutions. The user can select the most appropriate solutions according to his/her priorities. The method was tested using the data of region 7, district 1 of Tehran. The results showed an acceptable level of repeatability and stability for the optimization algorithm. The model uses parcel instead of urban blocks, as the spatial unit. Moreover, it considers a variety of land uses and tries to optimize several objectives simultaneously.     

海湾型半城市化地区空间形态演化模拟

元胞自动机（CA）是模拟城市土地利用演变过程的有效工具,转换规则和元胞邻域是元胞模型的核心。综合考虑元胞邻域的距离衰减效应,基于模拟退火算法（SA）挖掘最优的转换规则,文章构建了一种考虑邻域衰减的城市演化模型（SA-NDCA）。模型以负幂指数函数作为元胞邻域的衰减曲线表示元胞邻域的距离衰减效应;运用模拟退火优化算法计算城市CA模型模拟结果与样本点的累积差异,在目标解空间快速搜索以提取最优的转换规则;最后以厦门市半城市化地区为研究案例,模拟了研究区域1995―2010年期间的城市空间形态演化,通过混淆矩阵和Kappa系数评价了模型的模拟精度,1995―2010年期间的建设用地模拟精度为68.5%,总体精度达到86.2%,Kappa系数达到66.3,取得了较好的模拟效果。利用提出的SA-NDCA模型,成功模拟了研究区2010―2020年期间的城市空间形态演化,结果显示,所预测的演化情景与中国当前实施的新型城镇化战略十分契合。     

基于区块特征的元胞自动机土地利用演化模型研究

针对传统元胞自动机模型中栅格式规则空间模拟复杂地理元素精度不高的问题,提出一种基于土地区块特征的非规则空间元胞自动机模型,以地理单元实质不规则实体形状作为元胞空间单元,进行土地利用变化的仿真模拟,运用MapInfo建立非规则空间元胞自动机模型的应用软件.对头灶镇土地利用演化的实证研究表明,非规则空间元胞自动机模型可以更真实地描述元胞地理信息、局部空间关系和演化规则,可为城市规划提供决策支持.     

Modelling urban expansion using a multi agentbased model in the city of Changsha

Although traditional urban expansion simulation models can simulate dynamic features, these models fail to address complex changes produced by different agents' behaviors. The paper has built up a set of spatial-temporal land resource allocation rules and developed a dynamic urban expansion model based on a multi-agent system, which can simulate the interaction among different agents, such as residents, peasants, and governments. This model is applied to simulate urban expansion process taking Changsha City, in China as a study area. The results show that this model can not only reflect basic characteristics of urban expansion, but also help explain the reasons for urban expansion process and understand the effect of agents' behavior on the expansion process, and provide insights into the causing factors behind the expansion. In addition, in contrast to simulation results with land use classification map from remote sensing images, the precision of the simulation reached over 68% with higher precision than cellular automata model according to the cell-by-cell comparison. The results suggest that the model can help to provide land use decision making support to government and urban planners.     

Simulating urban growth under planning policies through parcel-based cellular automata (ParCA) model

In recent decades, the cellular automata model, among the urban development prediction models, has been applied considerably. Studies show that the output of conventional cellular automata models is sensitive to cell size and neighborhood structure, and varies with changes in the size of these parameters. To solve this problem, vector-based cellular automata models have been introduced which have overcome the mentioned limitations and presented better results. The aim of this study was to present a parcel-based cellular automata (ParCA) model for simulating urban growth under planning policies. In this model, undeveloped areas are first subdivided into smaller parcels, based on some geometric parameters; then, neighborhood effect of parcels is defined in a radial structure, based on a weighted function of distance, area, land-use, and service level of irregular cadastral parcels. After that, neighborhood effect is evaluated using three components, including compactness, dependency and compatibility. The presented model was implemented and analyzed using data from municipal region 22 of Tehran. The obtained results indicated the high ability of ParCA model in allocating various land-uses to parcels in the appropriateness of the layout of different land-uses. This model can be used in decision-making and urban land-use planning activities, since it provides the possibility of allocating different urban land-use types and assessing different urban-growth scenarios.     

Modelling sustainable urban growth in a rapidly urbanising region using a fuzzy-constrained cellular automata approach

This article presents an application of a fuzzy-constrained cellular automata model to simulate the spatio-temporal processes of urban growth in the rapidly growing Gold Coast City in Southeast Queensland, Australia. Urban growth has been captured in the model as a continuous process in space and over time, which has been affected by a set of primary and secondary transition rules. The primary transition rules deal with the propensity of a local area for development and the impact of its neighbouring cells on such development, while the secondary transition rules reflect the influences of environmental and institutional factors on urban growth. Application of the model demonstrates its re-applicability to different regions and the effectiveness of the cellular automata technique in studying urban dynamics. It also provides tools to explore sustainable urban growth options under different socio-environmental and planning control factors. A sustainable urban future of the region is achievable if development is managed to maintain a balance amongst ecological conservation, economic growth and the contemporary Australian lifestyle.