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。     

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.     

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。     

基于局部化转换规则的元胞自动机土地利用模型

传统土地利用元胞自动机(Cellular automata,CA)模型基于空间同质性假设,使用全局性模型建立元胞转换规则,忽略了土地利用变化驱动因素的驱动作用在空间上的变化。以美国佛罗里达州的橙县(Orange County)2003-2009年土地利用变化为例,提出了基于局部化转化规则的CA土地利用模型,其中元胞的土地利用类型适宜性由地理加权多项logit模型(Geographically weighted multinomial logit,GWML)获得。结果表明:GWML模型较传统全局性多项logit(Multinomial logit,MNL)模型有更高的数据解释能力。基于GWML模型的土地利用CA模型能反映局部土地利用变化模式,因而较基于MNL模型的CA模型具有更高的模拟精度。所得结论对未来国内地区的研究有借鉴意义。     

Assimilating process context information of cellular automata into change detection for monitoring land use changes

This article presents a new method of assimilating process context information into change detection for monitoring land use changes. The accurate information about land use changes is important for implementing many global and regional environmental models. Two types of models have been independently developed to obtain such information, including change detection models (e.g. pixel-to-pixel comparison, post-classification comparison and object-based change analysis) and simulation models (e.g. cellular automata (CA) and agent-based modelling). These models may have limitations in capturing land use dynamics when used alone. In this study, the ensemble Kalman filter is used to obtain the best estimate of land use changes by combining remote-sensing observations with urban simulation. Urban simulation is able to provide process context information such as diffusion and coalescence of urban development. This type of complementary information is useful for improving the performance of change detection. Compared with traditional change detection models, this integrated model has the potential to improve the performance of change detection in terms of accuracies and landscape metrics. For example, the assimilating (MLC + CA) method can show improvement of the total accuracy and the kappa coefficient by 2.5–5.2% and 3.6–7.4%, respectively, in this study.     

拉萨地区土地利用变化情景分析

根据西藏拉萨地区1990年、1995年和2000年3个时点的土地利用数据,应用马尔科夫过程模型分析了未来20年内拉萨地区的土地利用情景变化,并与90年代制定的拉萨地区土地利用规划面积进行了对比研究。研究结果:1)10年间,土地利用类型变化最广泛的是牧草地。变化方向主要由牧草地向耕地、园地、林地、居民点及水域转变,其中变成林地的面积最大,为2338.25hm²(占变化面积的94.093%);2)拉萨地区未来20年中土地利用类型发展趋势是耕地、牧草地、水域和未利用土地面积将进一步减少,林地、园地和居民点面积将进一步增加;3)土地利用规划面积与基于马尔科夫模型的土地利用变化情景分析结果比较吻合,马尔科夫过程模型对制定该区域土地利用规划具有重要的参考价值;4)由于土地利用变化是一个复杂的过程,不仅受到众多自然因素的影响,而且受到未来土地利用政策、社会经济发展、区域内大型工程项目及其他人类活动等不确定因素的影响,从而不同土地利用类型之间的转移概率会发生变化,使得基于马尔科夫过程模型预测的精度有一定的局限性。     

Simulating urban land-use changes at a large scale by integrating dynamic land parcel subdivision and vector-based cellular automata

Cellular automata (CA) have been widely used to simulate complex urban development processes. Previous studies indicated that vector-based cellular automata (VCA) could be applied to simulate urban land-use changes at a realistic land parcel level. Because of the complexity of VCA, these studies were conducted at small scales or did not adequately consider the highly fragmented processes of urban development. This study aims to build an effective framework called dynamic land parcel subdivision (DLPS)-VCA to accurately simulate urban land-use change processes at the land parcel level. We introduce this model in urban land-use change simulations to reasonably divide land parcels and introduce a random forest algorithm (RFA) model to explore the transition rules of urban land-use changes. Finally, we simulate the land-use changes in Shenzhen between 2009 and 2014 via the proposed DLPS-VCA model. Compared to the advanced Patch-CA and RFA-VCA models, the DLPS-VCA model achieves the highest simulation accuracy (Figure-of-Merit = 0.232), which is 32.57% and 18.97% higher respectively, and is most similar to the actual land-use scenario (similarity = 94.73%) at the pattern level. These results indicate that the DLPS-VCA model can both accurately split the land during urban land-use changes and significantly simulate urban expansion and urban land-use changes at a fine scale. Furthermore, the land-use change rules that are based on DPLS-VCA mining and the simulation results of several future urban development scenarios can act as guides for future urban planning policy formulation.     

Mining transition rules of cellular automata for simulating urban expansion by using the deep learning techniques

Along with the gradually accelerated urbanization process, simulating and predicting the future pattern of the city is of great importance to the prediction and prevention of some environmental, economic and urban issues. Previous studies have generally integrated traditional machine learning with cellular automaton (CA) models to simulate urban development. Nevertheless, difficulties still exist in the process of obtaining more accurate results with CA models; such difficulties are mainly due to the insufficient consideration of neighborhood effects during urban transition rule mining. In this paper, we used an effective deep learning method, named convolution neural network for united mining (UMCNN), to solve the problem. UMCNN has substantial potential to get neighborhood information from its receptive field. Thus, a novel CA model coupled with UMCNN and Markov chain was designed to improve the performance of simulating urban expansion processes. Choosing the Pearl River Delta of China as the study area, we excavate the driving factors and the transformational relations revealed by the urban land-use patterns in 2000, 2005 and 2010 and further simulate the urban expansion status in 2020 and 2030. Additionally, three traditional machine-learning-based CA models (LR, ANN and RFA) are built to attest the practicality of the proposed model. In the comparison, the proposed method reaches the highest simulation accuracy and landscape index similarity. The predicted urban expansion results reveal that the economy will continue to be the primary factor in the study area from 2010 to 2030. The proposed model can serve as guidance in urban planning and government decision-making.     

北京市土地利用变化的空间分布特征

土地利用变化是全球变化中的重要组成部分 ,是短期内人类活动对自然环境施加影响的显著表现形式。本文基于遥感和地理信息系统技术 ,利用LandsatTM图像的解译成果 ,分析了北京市 1985～ 2 0 0 0年土地利用变化的空间分布特征。研究表明 ,在这 15年的时间里 ,北京市林地和城乡、工矿、居住用地的转移趋势明显 ,两者的转移率分别达到 4 0 78%和37 60 % ,主要以林地内部、林地向草地转移、居住用地的内部和工矿废弃地还林还草等类型为主。同时 ,各类土地利用类型的净变化呈现出明显的区域差异。     

A comparative approach to modelling multiple urban land use changes using tree-based methods and cellular automata: the case of Greater Tokyo Area

Urban multiple land use change (LUC) modelling enables the realistic simulation of LUC processes in complex urban systems; however, such modelling suffers from technical challenges posed by complicated transition rules and high spatial heterogeneity when predicting the LUC of a highly developed area. Tree-based methods are powerful tools for addressing this task, but their predictive capabilities need further examination. This study integrates tree-based methods and cellular automata to simulate multiple LUC processes in the Greater Tokyo Area. We examine the predictive capability of 4 tree-based models – bagged trees, random forests, extremely randomised trees (ERT) and bagged gradient boosting decision trees (bagged GBDT) – on transition probability prediction for 18 land use transitions derived from 8 land use types. We compare the predictive power of a tree-based model with multi-layer perceptron (MLP) and among themselves. The results show that tree-based models generally perform better than MLP, and ERT significantly outperforms the three other tree-based models. The outstanding predictive performance of ERT demonstrates the advantages of introducing bagging ensemble and a high degree of randomisation into transition probability modelling. In addition, through variable importance evaluation, we found the strongest explanatory powers of neighbourhood characteristics for all land use transitions; however, the size of the impacts depends on the neighbourhood land use type and the neighbourhood size. Furthermore, socio-economic and policy factors play important roles in transitions ending with high-rise buildings and transitions related to industrial areas.     

Land use/land cover change detection and prediction in the north-western coastal desert of Egypt using Markov-CA

Detecting land-use change has become of concern to environmentalists, conservationists and land use planners due to its impact on natural ecosystems. We studied land use/land cover (LULC) changes in part of the northwestern desert of Egypt and used the Markov-CA integrated approach to predict future changes. We mapped the LULC distribution of the desert landscape for 1988, 1999, and 2011. Landsat Thematic Mapper 5 data and ancillary data were classified using the random forests approach. The technique produced LULC maps with an overall accuracy of more than 90%. Analysis of LULC classes from the three dates revealed that the study area was subjected to three different stages of modification, each dominated by different land uses. The use of a spatially explicit land use change modeling approach, such as Markov-CA approach, provides ways for projecting different future scenarios. Markov-CA was used to predict land use change in 2011 and project changes in 2023 by extrapolating current trends. The technique was successful in predicting LULC distribution in 2011 and the results were comparable to the actual LULC for 2011. The projected LULC for 2023 revealed more urbanization of the landscape with potential expansion in the croplands westward and northward, an increase in quarries, and growth in residential centers. The outcomes can help management activities directed toward protection of wildlife in the area. The study can also be used as a guide to other studies aiming at projecting changes in arid areas experiencing similar land use changes.     

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。     

基于元胞自动机模型的土地利用变化模拟——以大连经济技术开发区为例

元胞自动机模型已经成为模拟土地利用变化的重要方法。传统土地模拟方法中侧重于通过分析影响土地利用变化的因素来构建预测模型,较少从土地利用类型变化及其相互作用的空间角度来关注模型构建。本文以1998年、2004年和2009年1:10000土地利用数据,利用Python语言结合GDAL与Numpy类库实现局部土地利用竞争的元胞自动机模型原型开发,并用于模拟大连市经济技术开发区1998-2009年土地利用变化模拟。研究结果:1建立了发掘多地类之间相互作用关系的试验方法,研究适用于具有明确物理意义的多地类元胞自动机模拟模型;2该模型具有好的模拟精度,对建设用地、农用地和林地等3种不同类型用地进行同时模拟,其对应Kappa系数分别为0.762,0.634和0.678;3该模型建立了研究不同种地类协调作用的基本方法,可以用于进一步研究土地利用变化地类之间驱动原理。     

Exploring the impacts of future tourism development on land use/cover changes

Land use/cover changes (LUCC) are central to tourism because land is used in multiple ways as a resource for tourism-focused activities. Tourism is essentially a geographical phenomenon, encompassing the movement and flow of people (seen as the demand side) and spatial distribution patterns relating to land use consumption (seen as the supply side). However, the impacts of tourism on LUCC are difficult to track and monitor. Contributing factors of this problem include a lack of empirical studies, shortage of micro-level LUCC datasets, and scarce methodological frameworks which can be used for assessments. This paper aims to provide a LUCC modelling approach in order to explore the impacts of tourism development on built-up areas. We developed a Cellular automata model (CA) which integrates Markovian transition probabilities and logistic regression transition suitability maps. LUCC rules for tourism development are framed within the national land use policy guidelines for the development of new tourism accommodation establishments (TAE). This primarily takes into consideration land cover compatibility and the proposed development's proximity to the coastline.Three scenarios were established to explore the impacts of tourism development in LUCC for the year 2020 in a Portuguese coastal region: business as usual (BAU); tourism trends (TOUR); and natural restrictions (NATR). TOUR results indicate that the tourism and urban land use/cover growth is higher and focuses heavily on the coastal region (within 5,000 m) when compared to the other scenarios. The overall results for BAU and NATR show a general convergence with the land use policy guidelines in terms of tourism nucleation and new TAE distance to the coastline.     

Linear interpolation and joint model fitting of experimental transiograms for Markov chain simulation of categorical spatial variables

In Markov chain random field (MCRF) simulation of categorical spatial variables with multiple classes, joint modeling of a large number of experimental auto and cross-transiograms is needed. This can be tedious when mathematical models are used to fit the complex features of experimental transiograms. Linear interpolation can be used to perform the joint modeling quickly regardless of the number and the complexity of experimental transiograms. In this paper, we demonstrated the mathematical validity of linear interpolation as a joint transiogram-modeling method, explored its applicability and limitations, and tested its effect on simulated results by case studies with comparison to the joint model-fitting method. Simulations of a five-class variable showed little difference in patterns for interpolated and fitted transiogram models when samples were sufficient and experimental transiograms were in regular shapes; however, they neither showed large difference between these two kinds of transiogram models when samples were relatively sparse, which might indicate that MCRFs were not much sensitive to the difference in the detail of the two kinds of transiogram models as long as their change trends were identical. If available, expert knowledge might play an important role in transiogram modeling when experimental transiograms could not reflect the real spatial variation of the categorical variable under study. An extra finding was that class enclosure feature (i.e., a class always appears within another class) was captured by the asymmetrical property of transiograms and further generated in simulated patterns, whereas this might not be achieved in conventional geostatistics. We conclude that (i) when samples are sufficient and experimental transiograms are reliable, linear interpolation is satisfactory and more efficient than model fitting; (ii) when samples are relatively sparse, choosing a suitable lag tolerance is necessary to obtain reliable experimental transiograms for linear interpolation; (iii) when samples are very sparse (or few) and experimental transiograms are erratic, coarse model fitting based on expert knowledge is recommended as a better choice whereas both linear interpolation and precise model fitting do not make sense anymore.     

东莞地区土地利用变化预测的CBR和CA方法对比研究(英文)

Many studies on land use change(LUC),using different approaches and models,have yielded good results.Applications of these methods have revealed both advantages and limitations.However,LUC is a complex problem due to influences of many factors,and variations in policy and natural conditions.Hence,the characteristics and regional suitability of different methods require further research,and comparison of typical approaches is re-quired.Since the late 1980s,CA has been used to simulate urban growth,urban sprawl and land use evolution successfully.Nowadays it is very popular in resolving the LUC estimating problem.Case-based reasoning(CBR),as an artificial intelligence technology,has also been employed to study LUC by some researchers since the 2000s.More and more researchers used the CBR method in the study of LUC.The CA approach is a mathematical system con-structed from many typical simple components,which together are capable of simulating complex behavior,while CBR is a problem-oriented analysis method to solve geographic problems,particularly when the driving mechanisms of geographic processes are not yet understood fully.These two methods were completely different in the LUC research.Thus,in this paper,based on the enhanced CBR model,which is proposed in our previous research(Du et al.2009),a comparison between the CBR and CA approaches to assessing LUC is presented.LUC in Dongguan coastal region,China is investigated.Applications of the im-proved CBR and the cellular automata(CA) to the study area,produce results demonstrating a similarity estimation accuracy of 89% from the improved CBR,and 70.7% accuracy from the CA.From the results,we can see that the accuracies of the CA and CBR approaches are both >70%.Although CA method has the distinct advantage in predicting the urban type,CBR method has the obvious tendency in predicting non-urban type.Considering the entire ana-lytical process,the preprocessing workload in CBR is less than that of the CA approach.As such,it could be concluded that the CBR approach is more flexible and practically useful than the CA approach for estimating land use change.     

土地变化科学中的尺度问题与解决途径

尺度问题是土地变化科学中的关键问题。总结国内外近10年来土地变化研究中尺度问题的进展表明:土地变化研究中的尺度问题多集中于数据处理、格局与过程的表征、驱动力的影响、模型运用、生态环境效应以及土地政策与可持续管理等方面。尺度问题主要产生于地理现象的异质性、地理系统的等级性、响应与反馈的非线性、干扰因素的影响及主观认识的局限等。土地变化中尺度问题研究的一般途径为尺度选择-尺度分析-尺度综合;尺度选择时应该以问题为指向,数据为基础,选择适宜的尺度;尺度分析中需要从更大尺度和更小尺度同时开展分析,找出重要的变化动态,防止信息的遗漏或夸大;尺度综合是认识全球与地方关系的纽带,可将其分为尺度上推和尺度下推,在尺度综合中方法是主导,目标是寻找各尺度之间的连通性。模型有助于深刻理解土地利用系统动态,发展嵌套式模型是目前尺度综合研究中的重要内容。     

Rural sustainability under threat in Zimbabwe – Simulation of future land use/cover changes in the Bindura district based on the Markov-cellular automata model

Spatially explicit land use/cover models are indispensable for sustainable rural land use planning, particularly in southern African countries that are experiencing rapid land use/cover changes. Using Zimbabwe as an example, we simulated future land use/cover changes up to 2030 based on a Markov-cellular automata model that integrates Markovian transition probabilities computed from satellite-derived land use/cover maps and a cellular automata spatial filter. A multicriteria evaluation (MCE) procedure was used to generate transition potential maps from biophysical and socioeconomic data. Dynamic adjustments of transition probabilities and transition potential map thresholds were implemented in the Markov-cellular automata model through a multi-objective land allocation (MOLA) procedure. Using the normalised transition probabilities, the Markov-cellular automata model simulated future land use/cover changes (up to 2030) under the 2000 calibration scenario, predicting a continuing downward trend in woodland areas and an upward trend in bareland areas. Future land use/cover simulations indicated that if the current land use/cover trends continue in the study area without holistic sustainable development measures, severe land degradation will ensue.     

Spatially-explicit sensitivity analysis of an agent-based model of land use change

The complexity of land use and land cover (LULC) change models is often attributed to spatial heterogeneity of the phenomena they try to emulate. The associated outcome uncertainty stems from a combination of model unknowns. Contrarily to the widely shared consensus on the importance of evaluating outcome uncertainty, little attention has been given to the role a well-structured spatially explicit sensitivity analysis (SSA) of LULC models can play in corroborating model results. In this article, I propose a methodology for SSA that employs sensitivity indices (SIs), which decompose outcome uncertainty and allocate it to various combinations of inputs. Using an agent-based model of residential development, I explore the utility of the methodology in explaining the uncertainty of simulated land use change. Model sensitivity is analyzed using two approaches. The first is spatially inexplicit in that it applies SI to scalar outputs, where outcome land use maps are lumped into spatial statistics. The second approach, which is spatially explicit, employs the maps directly in SI calculations. It generates sensitivity maps that allow for identifying regions of factor influence, that is, areas where a particular input contributes most to the clusters of residential development uncertainty. I demonstrate that these two approaches are complementary, but at the same time can lead to different decisions regarding input factor prioritization.     

中国表层土壤全氮的空间模拟分析

基于第二次全国土壤普查5336个典型土壤剖面数据,分析表土全氮(A层)与环境因素的相关关系,利用多元回归模型和HASM模型结合的方法模拟中国国家尺度上表层土壤全氮的空间分布格局。结果表明:对350个检验点模拟结果的平均绝对误差和平均相对误差为0.67g·kg^-1和61.06%,与普通克里格法相比分别降低了0.05g·kg^-1和17.53%;对样点分布较少的西北地区的模拟结果也更符合实际情况。多元回归模型和HASM模型结合的方法考虑了环境因素的影响,可作为目前模拟大尺度土壤性质空间分布相对有效的方法。