姚尧 李林龙 孙振辉 寇世浩 程涛 关庆锋

Yao Yao, Li Linlong, Sun Zhenhui, Kou Shihao, Cheng Tao, Guan Qingfeng

关键词：城市交通；土地利用变化；矢量元胞自动机；城市模拟；连通性；可达性

Keywords：Urban Traffic; Land Use Change; Vector-based Cellular Automata（VCA）; Urban Simulation; Connectivity; Accessibility

摘要：

城市交通作为土地利用空间格局变化的重要驱动因素，在城市发展模拟研究中值得重视。如何有效挖掘城市交通因素并引入地块尺度城市土地利用模拟成为重要议题。本文提出一套基于矢量元胞自动机考虑交通因素的城市土地利用变化模拟框架（T-VCA）。该框架综合交通流、信息流、经济流等数据量化城市连通性因子，基于路网数据有效量化交通可达性因子，将其引入矢量元胞自动机模型，能够有效模拟微观地块尺度下的城市土地利用变化。以深圳市为研究区，本研究所提出的T-VCA 模型模拟精度最高（FoM=0.266），相较于最新的基于随机森林的矢量元胞自动机（RF-VCA）模型模拟精度提高了11.05%，景观指数相似度高达96.00%，表明考虑交通因素可以有效提高城市发展模拟精度。T-VCA 模型较仅考虑城市连通性的矢量元胞自动机（C-VCA）模型和仅考虑交通可达性的矢量元胞自动机（A-VCA）模型精度分别提高2.67% 和3.75%，表明城市连通性因素适用于挖掘新兴城区和远郊区的土地利用转化规则，而城市交通可达性因素适用于挖掘发展成熟的中心城区的土地利用转化规则。本研究可为城市规划人员在城市交通和土地利用管理方面提供参考。

Abstract：

As an essential driving factor of land use spatial pattern change, urban traffic deserves attention in urban development simulation studies. An important issue is how to effectively mine the urban traffic factors and introduce them into the fine-scale urban land use simulation. This paper proposes an urban land-use change simulation framework (T-VCA) based on vector-based cellular automata and considering traffic factors. The framework integrates traffic, information and economic flows to quantify urban connectivity. Based on the road network data, the traffic accessibility factor is effectively quantified. The framework introduces them into the vector-based cellular automata model and can effectively simulate urban land-use changes at the micro-plot scale. Taking Shenzhen as the study area, the T-VCA model achieves the highest accuracy (FoM=0.266), whose accuracy is 11.05% higher than the latest RF-VCA model. And the similarity of the landscape index is up to 96.00%. These indicate that considering traffic factors can effectively improve the accuracy of urban development simulation. Compared with C-VCA which is only considering urban connectivity and A-VCA only considering traffic accessibility, the accuracy of the T-VCA model increases by 2.67% and 3.75%, respectively. The study shows that the urban connectivity factor is suitable for mining the land use conversion rules in emerging urban areas and distant suburban areas. In contrast, the urban traffic accessibility factor is suitable in mature central urban areas. This study can provide references for urban planners in urban transportation and land use management.

姚尧（通信作者），博士，中国地质大学（武汉）地理与信息工程学院，教授，日本东京大学空间信息科学研究中心，研究员。yaoy@cug.edu.cn

李林龙，武汉大学资源与环境科学学院，硕士研究生。lilinlong@whu.edu.cn

孙振辉，华东师范大学地理科学学院，硕士研究生。51253901052@stu.ecnu.edu.cn

寇世浩，硕士，中国地质大学（武汉）地理与信息工程学院。sikoushao@163.com

程涛，同济大学测绘与地理信息学院，硕士研究生。chengtaoch@tongji.edu.cn

关庆锋，博士，中国地质大学（武汉）地理与信息工程学院，教授。guanqf@cug.edu.cn

• [1] YUAN Y, ZHAO T, WANG W, et al. Projection of the spatially explicit land use/cover changes in China, 2010-2100[J]. Advances in meteorology, 2013(2/3): 1-9.

  [2] ALMEIDA C M, GLERIANI J M, CASTEJON E F, et al. Using neural networks and cellular automata for modelling intra-urban land-use dynamics[J]. International journal of geographical information science: 2008, 22(9): 943-963.

  [3] DENG J S, WANG K, HONG Y, et al. Spatio-temporal dynamics and evolution of land use change and landscape pattern in response to rapid urbanization[J]. Landscape and urban planning, 2009, 92(3/4): 187-198.

  [4] DADASHPOOR H, AZIZI P, MOGHADASI M. Land use change, urbanization, and change in landscape pattern in a metropolitan area[J]. Science of the total environment, 2019, 655: 707-719.

  [5] GU W, GUO J, FAN K, et al. Dynamic land use change and sustainable urban development in a third-tier city within Yangtze Delta[J]. Procedia environmental sciences, 2016, 36: 98-105.

  [6] 王家丰, 王蓉, 冯永玖, 等. 顾及轨道交通影响的浙中城市群土地利用多情景模拟与分析[J]. 地球信息科学学报, 2020, 22(3): 605-615.

  [7] BATTY M. Urban evolution on the desktop: simulation with the use of extended cellular automata[J]. Environment and planning a, 1998, 30(11): 1943-1967.

  [8] LI X, CHEN Y, LIU X, et al. Experiences and issues of using cellular automata for assisting urban and regional planning in China[J]. International journal of geographical information science, 2017, 31(8): 1606-1629.

  [9] LI X, YEH A G. Neural-network-based cellular automata for simulating multiple land use changes using GIS[J]. International journal of geographical information science, 2002, 16(4): 323-343.

  [10] LIU X, MA L, LI X, et al. Simulating urban growth by integrating landscape expansion index (LEI) and cellular automata[J]. International journal of geographical information science, 2014, 28(1): 148-163.

  [11] LIU X, LIANG X, LI X, et al. A future land use simulation model (FLUS) for simulating multiple land use scenarios by coupling human and natural effects[J]. Landscape and urban planning, 2017, 168: 94-116.

  [12] BARREIRA-GONZáLEZ P, GóMEZ-DELGADO M, AGUILERABENAVENTE F. From raster to vector cellular automata models: a newapproach to simulate urban growth with the help of graph theory[J]. Computers, environment and urban systems, 2015, 54: 119-131.

  [13] STEVENS D, DRAGI?EVI? S. A GIS-based irregular cellular automata model of land-use change[J]. Environment and planning b: planning and design, 2007, 34(4): 708-724.

  [14] O’SULLIVAN D. Exploring spatial process dynamics using irregular cellular automaton models[J]. Geographical analysis, 2001, 33(1): 1-18.

  [15] MORENO N, MéNARD A, MARCEAU D J. VecGCA: a vector-based geographic cellular automata model allowing geometric transformations of objects[J]. Environment and planning b: planning and design, 2008, 35(4): 647-665.

  [16] SEMBOLONI F. The growth of an urban cluster into a dynamic selfmodifying spatial pattern[J]. Environment and planning b, planning and design, 2000, 27(4): 549-564.

  [17] NORTE PINTO N, PAIS ANTUNES A. A cellular automata model based on irregular cells: application to small urban areas[J]. Environment and planning b: planning and design, 2010, 37(6): 1095-1114.

  [18] YAO Y, LIU X, LI X, et al. Simulating urban land-use changes at a large scale by integrating dynamic land parcel subdivision and vector-based cellular automata[J]. International journal of geographical information science, 2017, 31(12): 2452-2479.

  [19] JJUMBA A, DRAGI?EVI? S. High resolution urban land-use change modeling: Agent iCity approach[J]. Applied spatial analysis and policy, 2012, 5(4): 291-315.

  [20] 于茜, 白建军, 张晶言, 等. 路网通达性与城镇空间扩展的耦合关系——以西安市为例[J]. 经济地理, 2016, 36(10): 69-75.

  [21] HE L, LIU Y, H Q, et al. Simulating urban cooperative expansion in a single-core metropolitan region based on improved CA model integrated information flow: case study of Wuhan urban agglomeration in China[J]. Journal of urban planning and development, 2018, 144(2): 05018002.

  [22] YU Y, HE J, TANG W, et al. Modeling urban collaborative growth dynamics using a multiscale simulation model for the Wuhan urban agglomeration area, China[J]. ISPRS international journal of geo-information, 2018, 7(5): 176.

  [23] FOTHERINGHAM A S. Spatial structure and distance-decay parameters[J]. Annals of the Association of American Geographers, 1981, 71(3): 425-436.

  [24] 张童, 姚士谋, 胡伟平, 等. 基于交通可达性的广佛都市区城市扩展的模拟与分析[J]. 地理科学, 2018, 38(5): 737-746.

  [25] ZHU J, ZHENG J, DI S, et al. Cellular automata based land-use change simulation considering spatio-temporal influence heterogeneity of light rail transit construction: a case in Nanjing, China[J]. ISPRS international journal of geo-information, 2021, 10(5): 308.

  [26] ALJOUFIE M, ZUIDGEEST M, BRUSSEL M, et al. A cellular automatabased land use and transport interaction model applied to Jeddah, Saudi Arabia[J]. Landscape and urban planning, 2013, 112: 89-99.

  [27] HE C, ZHAO Y, TIAN J, et al. Modeling the urban landscape dynamics in a megalopolitan cluster area by incorporating a gravitational field model with cellular automata[J]. Landscape and urban planning, 2013, 113: 78-89.

  [28] LIANG S. Research on the urban inf luence domains in China[J]. International journal of geographical information science, 2009, 23(12): 1527-1539.

  [29] JINGHU P, WEISHENG L. Quantitative delimitation of urban influential hinterland in China[J]. Journal of urban planning and development, 2015, 141(4): 04014033.

  [30] LV J, WANG Y, LIANG X, et al. Simulating urban expansion by incorporating an integrated gravitational field model into a demand-driven random forest-cellular automata model[J]. Cities, 2021, 109: 103044.

  [31] XIAO Y, WANG F, LIU Y, et al. Reconstructing gravitational attractions of major cities in China from air passenger flow data, 2001-2008: a particle swarm optimization approach[J]. The professional geographer, 2013, 65(2): 265-282.

  [32] WOLD S, ESBENSEN K, GELADI P. Principal component analysis[J]. Chemometrics and intelligent laboratory systems, 1987, 2(1/3): 37-52.

  [33] STOICA I, TULLA A F, ZAMFIR D, et al. Exploring the urban strength of small towns in Romania[J]. Social indicators research, 2020, 152(3): 843-875.

  [34] TOBLER W R. A computer movie simulating urban growth in the Detroit region[J]. Economic geography, 1970, 46(Supplement 1): 234-240.

  [35] PINTO N, ANTUNES A O N P, ROCA J. A cellular automata model for integrated simulation of land use and transport interactions[J]. ISPRS international journal of geo-information, 2021, 10(3): 149.

  [36] NAVARRO CERRILLO R M, PALACIOS RODR I GUEZ G, CLAVERO RUMBAO I, et al. Modeling major rural land-use changes using the GISbased cellular automata metronamica model: the case of Andalusia (Southern Spain)[J]. ISPRS international journal of geo-information, 2020, 9(7): 458.

  [37] ZHAO L, SHEN L. The impacts of rail transit on future urban land use development: a case study in Wuhan, China[J]. Transport policy, 2019, 81: 396-405.

  [38] PONTIUS R G, BOERSMA W, CASTELLA J, et al. Comparing the input, output, and validation maps for several models of land change[J]. The annals of regional science, 2008, 42(1): 11-37.

  [39] ZHUANG H, LIU X, YAN Y, et al. Integrating a deep forest algorithm with vector-based cellular automata for urban land change simulation[J]. Transactions in GIS, 26, 2056-2080. https://doi.org/10.1111/tgis.12935.

  [40] ZHAI Y, YAO Y, GUAN Q, et al. Simulating urban land use change by integrating a convolutional neural network with vector-based cellular automata[J]. International journal of geographical information science, 2020, 34(7): 1475-1499.

  [41] HEUVELINK G B. Error propagation in environmental modelling with GIS[M]. New York: CRC Press, 1998.

  [42] FENG Y, TONG X. A new cellular automata framework of urban growth modeling by incorporating statistical and heuristic methods[J]. International journal of geographical information science, 2020, 34(1): 74-97.

  [43] YAO Y, LI X, LIU X, et al. Sensing spatial distribution of urban land use by integrating points-of-interest and Google Word2Vec model[J]. International journal of geographical information science, 2016, 31(4): 825-848.

  [44] YAO Y, LIU X, LI X, et al. Simulating urban land-use changes at a large scale by integrating dynamic land parcel subdivision and vector-based cellular automata[J]. International journal of geographical information science, 2017, 31(12): 2452-2479.

  [45] CHEN J, CHANG K, KARACSONYI D, et al. Comparing urban land expansion and its driving factors in Shenzhen and Dongguan, China[J]. Habitat international, 2014, 43: 61-71.

  [46] WAND M P, JONES M C. Kernel smoothing[M]. New York: CRC Press,1994.

  [47] YUAN J, ZHENG Y, XIE X. Discovering regions of different functions in a city using human mobility and POIs(DRoF)[C] // The 18th SIGKDD conference on knowledge discovery and data mining. ACM, 2012.

  [48] LI S, ZHUANG C, TAN Z, et al. Inferring the trip purposes and uncovering spatio-temporal activity patterns from dockless shared bike dataset in Shenzhen, China[J]. Journal of transport geography, 2021, 91: 102974.

  [49] LIU Y, WANG F, KANG C, et al. Analyzing relatedness by Toponym Co-Occurrences on web pages[J]. Transactions in GIS, 2014, 18(1): 89-107.

  
  

• 收起