地理元胞自动机模型的尺度敏感性及原因

地理元胞自动机模型的模拟精度会受到元胞尺度的影响。以杭州市土地利用变化模拟为例,分析了元胞尺度分别为50m×50m、100m×100m、150m×150m和200m×200m时地理元胞自动机模型的模拟精度,对地理元胞自动机模型的尺度敏感性进行了分析;并从元胞转换规则入手,研究了元胞自动机模型尺度敏感性产生的原因:(1)元胞尺度会对地理元胞自动机模型的模拟精度产生影响,元胞尺度越精细模拟精度越高;(2)元胞自动机模型的尺度敏感性与元胞尺度相关,在有些尺度区间上表现得明显,而在有些尺度区间上表现并不明显;(3)孤立元胞是元胞自动机模型尺度敏感性产生的主要原因。研究表明,随着元胞尺度的增大,元胞空间的孤立元胞增多,这些孤立元胞本身及其周围元胞具有较低的邻域函数值和较小的转换概率值,并影响了地理元胞自动机模型的模拟精度。     

基于GA-MCE算法的不规则邻域CA土地利用模拟

不规则邻域元胞自动机通过定义一定的邻域规则,将对中心元胞影响较大的邻域元胞进行识别与计算从而确定邻域形态与影响范围,与传统元胞自动机模型相同尺寸邻域形态相比,模拟更加真实有效。基于不规则邻域识别算法对元胞邻域范围进行划分,再通过遗传算法和多准则评价相结合获取转化规则参数,继而对大连市金石滩国家旅游度假区2004年和2010年土地利用变化进行模拟研究,通过比对分析以及Kappa系数检验法对模拟精度做一检验,研究模拟结果总体Kappa系数为81.62%,具有一定的可靠性,研究显示该模型在多地类碎小斑块之间的转化模拟具有一定的优势,对于模拟土地利用/覆盖变化模型具有一定的改进。     

城市元胞自动机扩展邻域效应的测量与校准研究

城市元胞模型由于在定量分析与预测城市动态的潜力而受到众多研究者的持续关注.邻域规则是主导城市元胞模型模拟过程的关键组件.研究表明,不同土地利用组合间存在显著的邻域效应,且邻域效应具有惯性、排斥和吸引等影响.然而,传统城市元胞模型主要考虑的是特定分辨率下较小窗口的邻域范围.本文尝试刻画更大窗口的邻域效应及其对元胞模型的影响.基于测量的扩展邻域因子,应用粒子群优化算法校准大窗口邻域规则,并创建了考虑扩展邻域效应的城市元胞模型.为验证模型有效性,将其应用于模拟厦门市1995-2010年期间的城市扩张动态.与3×3摩尔邻域的逻辑回归模型相比较,1995-2010年期间的建设用地模拟精度从80.7％提高到83.9％,总体精度从87.8％提高到89.6％,Kappa系数从70.0％提高到74.5％,表明考虑扩展邻域效应的城市模型取得了更好的模拟效果.     

元胞邻域对空间直观模拟结果的影响

作为一种空间直观模拟模型,地理元胞自动机(Geo-CA)能够模拟及预测城市扩展与土地利用情景.地理CA模拟中,元胞邻域及其空间构型会对转换规则的挖掘与空间直观模拟结果的可靠性产生显著影响,从模拟进度和精度、景观格局及运行效率等角度可以定量分析这种影响.以logistic回归CA模型为例,基于Von:Neumann型和M...     

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。     

顾及空间尺度效应的城市土地利用变化精细化模拟

城市土地利用变化模拟是优化土地资源配置的科学依据,提高其精细化程度和可靠性有助于准确把握城市用地发展趋势,对城市土地资源精准调控具有重要意义。基于宏观遥感分类的土地利用变化模拟,难以在街区尺度上揭示城市用地社会功能变化及精细化模拟中空间尺度效应来源和作用机理。本文联合遥感影像和POI数据识别出城市土地利用精细化特征,运用响应面法率定土地利用精细化模拟的最优空间尺度组合,在此基础上,利用CA-Markov模型开展了未来土地利用变化的精细化模拟。以武汉市中心城区为应用案例,研究结果表明：基于POI 的城市土地利用精细化识别方法,可以深度解析城市建设用地的社会功能,极大改善了传统基于遥感的土地覆被宏观解译效果;研究区土地利用变化元胞自动机精细化模拟的最优空间尺度组合是30 m元胞、7×7邻域以及冯诺依曼邻域类型,采用最优空间尺度组合能够提高土地利用变化精细化模拟的可靠性。响应面试验设计结果可有效识别精细化模拟过程中空间尺度效应的主要来源,并区分其对模拟精度的影响程度与正负效应;预计到2025年,研究区建设用地范围将继续向周边扩张,各类型用地之间互为交织,土地利用空间格局将呈更加破碎化趋势。     

地理元胞自动机模型研究进展

元胞自动机(Cellular Automata,简称CA)是一种基于微观个体的相互作用空间离散动态模型,其强大的计算功能、固有的平行计算能力、高度动态及空间概念等特征,使它在模拟空间复杂系统的时空动态演变研究具有较强的优势。文章回顾了元胞自动机的发展历程,阐述了CA在地理学中的主要应用领域和研究进展,在此基础上,以现实世界地理实体及现代城市扩张特征为视角,分析目前CA研究所面临的问题,并对其未来的研究趋势进行了初步探讨,认为以下3个方面将是未来CA研究的热点：① 利用不规则元胞及可控邻域的CA模型,对不同规则或不同邻域地理实体的模拟研究;② 采用三维元胞自动机对现代城市扩张进行立体化模拟,以克服二维CA模型的缺陷;③ 将矢量元胞自动机模型应用于地理实体的模拟研究,进一步提高模拟精度。     

MAUP效应在城市扩张元胞自动机模拟中的敏感性分析

利用元胞自动机模型进行城市扩张模拟时,其使用的栅格数据格式和基于统计的转换规则提取方法必然会导致可变面积单元问题(the Modifiable Areal Unit Problem,MAUP)的出现。采用系统的敏感性分析方法对该问题的粒度效应、划区效应和综合效应进行了分析,研究表明:1)MAUP问题在CA模拟时是客观存在的,且会对模拟结果造成影响,研究时不能忽视该问题。应进行系统的敏感性分析,获取其对研究问题的影响,寻找适宜的研究粒度和分区方案。2)该研究中粒度效应会呈现明显的尺度阈值,尺度域内的拟合优度和模拟精度较为稳定。尺度阈值在最精细粒度后随即出现,且该阈值与景观指数的尺度阈值一致,反映了景观对象大小对城市扩张模拟的重要影响。3)良好的划区方案能够提高拟合优度和模拟精度,其划区方案应使区域内城市扩张规律差异最小,区域间城市扩张规律差异最大。在大尺度城市扩张模拟时更应采用合理的划区方案以提高模拟精度。4)粒度效应和划区效应的综合影响表现为各区域模型的拟合优度和模拟精度在粒度范围内所受到的影响存在差异,但大多数区域都较为明显地表现出相同的尺度阈值。     

一种顾及驱动因子重要性的双约束RF-Patch-CA城市扩张模拟方法

城市扩张模拟为实现土地资源合理分配与制定城市发展规划政策提供依据。该文针对传统元胞自动机(CA)在城市扩张模拟中存在城市元胞密集区域团簇现象,耦合随机森林(RF)与基于斑块(Patch)扩张的CA模型,在顾及驱动因子重要性基础上构建基于斑块最大面积和城市扩张总量的双约束RF-Patch-CA模型,并利用该模型模拟重庆主城都市区2010-2017年城市扩张。结果显示:该模型总体精度达97.62%,相比传统的RF-CA、ANN-CA和Logistic-CA模型,Kappa系数分别提高了0.0222、0.0231和0.0245,FoM分别提高了0.0376、0.0391和0.0414;在景观相似度上,该模型相比以上3种模型分别提高了40.92%、41.16%和32.33%,最接近真实情况,而且避免了模拟结果产生城市元胞团簇现象,有效提高了城市扩张模拟精度。     

空间尺度上推方法的精度评价——以内蒙古锡林郭勒盟土地利用数据为例

不同的空间尺度上推方法会导致不同程度的信息丢失、信息歪曲等后果;但目前少有研究在较长的尺度序列上、对不同尺度上推方法所得成果开展精度分析。本研究首先提出尺度上推方法精度评价的三个准则,即:保持土地类型构成特征、保持土地面积精度、保持土地空间分布格局和斑块形态;继而使用格点中心值、最大面积斑块、最大聚合面积斑块等3种尺度上推方法,配合100 m～50 km土地利用数据开展尺度转化实验;最后基于上述评价准则和尺度上推实验所得的系列输出结果,分析了不同尺度上推方法的精度。研究表明:(1)格点中心值上推方法能更好地保留区域土地类型构成、土地面积精度等特征;(2)锡林郭勒盟地区土地研究的适宜尺度应小于10 km,最大不应超过30 km;(3)在尺度上推过程中,土地斑块的平均面积、形态以及空间分布格局对尺度上推成果精度有着重要影响。     

Examining the sensitivity of spatial scale in cellular automata Markov chain simulation of land use change

Understanding the spatial scale sensitivity of cellular automata is crucial for improving the accuracy of land use change simulation. We propose a framework based on a response surface method to comprehensively explore spatial scale sensitivity of the cellular automata Markov chain (CA-Markov) model, and present a hybrid evaluation model for expressing simulation accuracy that merges the strengths of the Kappa coefficient and of Contagion index. Three Landsat-Thematic Mapper remote sensing images of Wuhan in 1987, 1996, and 2005 were used to extract land use information. The results demonstrate that the spatial scale sensitivity of the CA-Markov model resulting from individual components and their combinations are both worthy of attention. The utility of our proposed hybrid evaluation model and response surface method to investigate the sensitivity has proven to be more accurate than the single Kappa coefficient method and more efficient than traditional methods. The findings also show that the CA-Markov model is more sensitive to neighborhood size than to cell size or neighborhood type considering individual component effects. Particularly, the bilateral and trilateral interactions between neighborhood and cell size result in a more remarkable scale effect than that of a single cell size.     

Characterization of neighborhood sensitivity of an irregular cellular automata model of urban growth

The neighborhood definition, which determines the influence on a cell from its nearby cells within a localized region, plays a critical role in the performance of a cellular automaton (CA) model. Raster CA models use a cellular grid to represent geographic space, and are sensitive to the cell size and neighborhood configuration. However, the sensitivity of vector-based CAs, an alternative to the raster-based counterpart, to neighborhood type and size remains uninvestigated. The present article reports the results of a detailed sensitivity analysis of an irregular CA model of urban land use dynamics. The model uses parcel data at the cadastral scale to represent geographic space, and was implemented to simulate urban growth in Central Texas, USA. Thirty neighborhood configurations defined by types and sizes were considered in order to examine the variability in the model outcome. Results from accuracy assessments and landscape metrics confirmed the model’s sensitivity to neighborhood configurations. Furthermore, the centroid intercepted neighborhood with a buffer of 120 m produced the most accurate simulation result. This neighborhood produced scattered development while the centroid extent-wide neighborhood resulted in a clustered development predominantly near the city center.     

A neighbor decay cellular automata approach for simulating urban expansion based on particle swarm intelligence

Simulation and quantitative analysis of urban land use change are effective ways to investigate urban form evolution. Cellular Automata (CA) has been used as a convenient and useful tool for simulating urban land use change. However, the key issue for CA models is the definition of the transition rules, and a number of statistical or artificial intelligence methods may be used to obtain the optimal rules. Neighborhood configuration is a basic component of transition rules, and is characterized by a distance decay effect. However, many CA models do not consider the neighbor decay effect in cellular space. This paper presents a neighbor decay cellular automata model based on particle swarm optimization (PSO-NDCA). We used particle swarm optimization (PSO) to find transition rules and considered the decay effect of the cellular neighborhood. A negative power exponential function was used to compute the decay coefficient of the cellular neighborhood in the model. By calculating the cumulative differences between simulation results and the sample data, the PSO automatically searched for the optimal combination of parameters of the transition rules. Using Xiamen City as a case study, we simulated urban land use changes for the periods 1992–1997 and 2002–2007. Results showed that the PSO-NDCA model had a higher prediction accuracy for built-up land, and a higher overall accuracy and Kappa coefficient than the urban CA model based on particle swarm optimization. The study demonstrates that there exist optimal neighborhood decay coefficients in accordance with the regional characteristics of an area. Urban CA modelling should take into account the role of neighborhood decay.     

元胞自动机的地理过程模拟机制及扩展

地理空间、地理梯度、地理流和空间关系是经典地理学进行地理过程分析常用的4个基本概念,元胞自动机(CA)作为复杂空间系统研究的重要工具。分析表明,其与经典地理过程分析理论具有类似地表达机制,因而能有效地进行地理过程模拟。但由于标准CA是一种更广泛抽象的空间模型,其对地理特征的描述存在一定局限,限制了其更真实地模拟地理过程的能力。论文提出了基于地理特征的CA概念模型,深圳特区土地利用演化的实证研究表明,地理特征CA概念模型具有极大的应用价值。     

A review of assessment methods for cellular automata models of land-use change and urban growth

ABSTRACT

Cellular automata (CA) models are in growing use for land-use change simulation and future scenario prediction. It is necessary to conduct model assessment that reports the quality of simulation results and how well the models reproduce reliable spatial patterns. Here, we review 347 CA articles published during 1999–2018 identified by a Scholar Google search using ‘cellular automata’, ‘land’ and ‘urban’ as keywords. Our review demonstrates that, during the past two decades, 89% of the publications include model assessment related to dataset, procedure and result using more than ten different methods. Among all methods, cell-by-cell comparison and landscape analysis were most frequently applied in the CA model assessment; specifically, overall accuracy and standard Kappa coefficient respectively rank first and second among all metrics. The end-state assessment is often criticized by modelers because it cannot adequately reflect the modeling ability of CA models. We provide five suggestions to the method selection, aiming to offer a background framework for future method choices as well as urging to focus on the assessment of input data and error propagation, procedure, quantitative and spatial change, and the impact of driving factors.     

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。     

A high-performance cellular automata model for urban simulation based on vectorization and parallel computing technology

Cellular automata (CA) models can simulate complex urban systems through simple rules and have become important tools for studying the spatio-temporal evolution of urban land use. However, the multiple and large-volume data layers, massive geospatial processing and complicated algorithms for automatic calibration in the urban CA models require a high level of computational capability. Unfortunately, the limited performance of sequential computation on a single computing unit (i.e. a central processing unit (CPU) or a graphics processing unit (GPU)) and the high cost of parallel design and programming make it difficult to establish a high-performance urban CA model. As a result of its powerful computational ability and scalability, the vectorization paradigm is becoming increasingly important and has received wide attention with regard to this kind of computational problem. This paper presents a high-performance CA model using vectorization and parallel computing technology for the computation-intensive and data-intensive geospatial processing in urban simulation. To transfer the original algorithm to a vectorized algorithm, we define the neighborhood set of the cell space and improve the operation paradigm of neighborhood computation, transition probability calculation, and cell state transition. The experiments undertaken in this study demonstrate that the vectorized algorithm can greatly reduce the computation time, especially in the environment of a vector programming language, and it is possible to parallelize the algorithm as the data volume increases. The execution time for the simulation of 5-m resolution and 3 × 3 neighborhood decreased from 38,220.43 s to 803.36 s with the vectorized algorithm and was further shortened to 476.54 s by dividing the domain into four computing units. The experiments also indicated that the computational efficiency of the vectorized algorithm is closely related to the neighborhood size and configuration, as well as the shape of the research domain. We can conclude that the combination of vectorization and parallel computing technology can provide scalable solutions to significantly improve the applicability of urban CA.