Kentsel büyümenin vektör hücresel otomat yaklaşımı ile yüksek çözünürlüklü modellenmesi

Year 2025, Volume: 14 Issue: 2, 701 - 711, 15.04.2025

Ahmet Emir Yakup , İsmail Ercüment Ayazlı

Abstract

Bu çalışma, coğrafi veri madenciliği (CVM) ile bütünleşik çalışan, vektör hücresel otomat (V-HO) tabanlı kentsel büyüme simülasyon modeli (KBSM) geliştirmeyi amaçlamaktadır. Coğrafi nesnelerin gerçek geometrilerini daha doğru şekilde temsil eden V-HO modelinin KBSM çalışmalarında kullanımı giderek yaygınlaşmaktadır. Ancak raster tabanlı HO algoritmasına kıyasla, vektör veri yapısının karmaşıklığı ve düzensizliği, V-HO modellerinin uygulanmasını zorlaştırmaktadır. Bu nedenle esnek komşuluk ve hücresel işlerliğin sağlanmasındaki kısıtlılıkları aşmak amacıyla büyüme vektörleri (BV) yöntemi önerilmiştir. Modelde, arazi örtüsü/kullanımı değişimlerini etkileyen mekânsal ve zamansal dinamikler Rastgele Orman (RO) algoritması ile analiz edilmiştir. Çalışma alanı olarak İstanbul’un Sancaktepe ilçesi seçilmiş, parsel seviyesinde arazi örtüsü/kullanımı değişimleri simüle edilerek %86 doğruluk oranı elde edilmiştir. Bulgularımız, vektör veri yapısının esnekliğinden yararlanılarak daha verimli, dinamik, doğru ve yüksek çözünürlükte simülasyonlar oluşturulabileceğini göstermektedir. 2040 yılına ait simülasyon sonuçları, mevcut kentleşme eğilimlerinin devam etmesi durumunda tarım alanlarında %25, orman alanlarında %3 ve açık arazilerde %21 oranında kayıplar yaşanabileceğini ortaya koymaktadır.

Keywords

Vektör Hücresel Otomat, Simülasyon, Arazi Örtüsü/Kullanımı Değişimi, Coğrafi Bilgi Sistemleri

Supporting Institution

Sivas Cumhuriyet Üniversitesi ve TÜBİTAK

Project Number

M-2024-862 ve 124Y025

Thanks

Bu çalışma, ilk yazarın Sivas Cumhuriyet Üniversitesi Fen Bilimleri Enstitüsü Geomatik Mühendisliği Ana Bilim Dalında hazırlanan doktora tezinin bir kısmını içermektedir. Araştırma TÜBİTAK 124Y025 ve Sivas Cumhuriyet Üniversitesi Bilimsel Araştırma Projeleri Koordinatörlüğü tarafından M-2024-862 Nolu projeler kapsamında desteklenmiştir.

Modelling urban growth in high resolution employing vector cellular automata approach

Abstract

This paper aims to create a vector cellular automata (V-CA)-based urban growth simulation model (UGSM) integrated with geographic data mining (GDM). V-CA-based models, which more accurately represent the actual geometries of geographic objects, are becoming prevalent in UGSM studies. However, compared to the raster-CA algorithm, the complexity and irregularity of the vector data structure make implementing V-CA models difficult. Therefore, the growth vectors (GV) method suggests overcoming the limitations of flexible neighborhood and cellular operability. The model examines the spatio-temporal dynamics driving land cover/land use changes with the Random Forest (RF) algorithm. Istanbul's Sancaktepe district was selected as the study area, achieving an 86% accuracy rate in simulating land cover/use changes at the parcel level. Our findings demonstrate that vector data structure's flexibility allows more efficient, dynamic, accurate, and high-resolution UGSMs. Simulation results for 2040 indicate that if current urbanization trends continue, agricultural areas could lose 25%, forest areas 3%, and open lands 21%.

Keywords

Vector Cellular Automata, Simulation, Land Cover/Use Change, Geographical Information Systems

Project Number

M-2024-862 ve 124Y025

Thanks

Bu araştırma TÜBİTAK 124Y025 ve Sivas Cumhuriyet Üniversitesi Bilimsel Araştırma Projeleri Koordinatörlüğü tarafından M-2024-862 Nolu projeler kapsamında desteklenmiştir.

References

• I.E. Ayazli, Monitoring of urban growth with improved model accuracy by statistical methods, Sustainability 11 (2019) 5579. https://doi.org/10.3390/su11205579.
• M. Batty, Cities and complexity: understanding cities with cellular automata, agent-based models, and fractals, The MIT press, 2007. https://doi.org/10.5555/1543541.
• R. White, G. Engelen, Cellular Automata and Fractal Urban Form: A Cellular Modelling Approach to the Evolution of Urban Land-Use Patterns, Environment and Planning A: Economy and Space 25 (1993) 1175–1199. https://doi.org/10.1068/a251175.
• Y. Yao, L. Li, Z. Liang, T. Cheng, Z. Sun, P. Luo, Q. Guan, Y. Zhai, S. Kou, Y. Cai, L. Li, X. Ye, UrbanVCA: a vector-based cellular automata framework to simulate the urban land-use change at the land-parcel level, (2021). https://doi.org/10.48550/arXiv.2103.08538.
• N. Moreno, F. Wang, D.J. Marceau, Implementation of a dynamic neighborhood in a land-use vector-based cellular automata model, Computers, Environment and Urban Systems 33 (2009) 44–54. https://doi.org/10.1016/j.compenvurbsys.2008.09.008.
• A.G.-O. Yeh, X. Li, Errors and uncertainties in urban cellular automata, Computers, Environment and Urban Systems 30 (2006) 10–28. https://doi.org/10.1016/j.compenvurbsys.2004.05.007.
• P. Barreira-González, M. Gómez-Delgado, F. Aguilera-Benavente, From raster to vector cellular automata models: A new approach to simulate urban growth with the help of graph theory, Computers, Environment and Urban Systems 54 (2015) 119–131. https://doi.org/10.1016/j.compenvurbsys.2015.07.004.
• N. Moreno, A. Ménard, D.J. Marceau, VecGCA: A Vector-Based Geographic Cellular Automata Model Allowing Geometric Transformations of Objects, Environ Plann B Plann Des 35 (2008) 647–665. https://doi.org/10.1068/b33093.
• Y. Lu, M. Cao, L. Zhang, A vector-based Cellular Automata model for simulating urban land use change, Chin. Geogr. Sci. 25 (2015) 74–84. https://doi.org/10.1007/s11769-014-0719-9.
• S. Abolhasani, M. Taleai, M. Karimi, A. Rezaee Node, Simulating urban growth under planning policies through parcel-based cellular automata (ParCA) model, International Journal of Geographical Information Science 30 (2016) 2276–2301. https://doi.org/10.1080/13658816.2016.1184271.
• Y. Lu, S. Laffan, C. Pettit, M. Cao, Land use change simulation and analysis using a vector cellular automata (CA) model: A case study of Ipswich City, Queensland, Australia, Environment and Planning B: Urban Analytics and City Science 47 (2020) 1605–1621. https://doi.org/10.1177/2399808319830971.
• Y. Yao, K. Zhou, C. Liu, Z. Sun, D. Chen, L. Li, T. Cheng, Q. Guan, Temporal-VCA: Simulating urban land use change using coupled temporal data and vector cellular automata, Cities 149 (2024) 104975. https://doi.org/10.1016/j.cities.2024.104975.
• H. Zhuang, X. Liu, Y. Yan, D. Zhang, J. He, J. He, X. Zhang, H. Zhang, M. Li, Integrating a deep forest algorithm with vector-based cellular automata for urban land change simulation, Transactions in GIS 26 (2022) 2056–2080. https://doi.org/10.1111/tgis.12935.
• W. Shi, M.Y.C. Pang, Development of Voronoi-based cellular automata -an integrated dynamic model for Geographical Information Systems, International Journal of Geographical Information Science 14 (2000) 455–474. https://doi.org/10.1080/13658810050057597.
• F. Semboloni, The Growth of an Urban Cluster into a Dynamic Self-Modifying Spatial Pattern, Environ Plann B Plann Des 27 (2000) 549–564. https://doi.org/10.1068/b2673.
• Q. Guan, J. Li, Y. Zhai, X. Liang, Y. Yao, HashGAT-VCA: A vector cellular automata model with hash function and graph attention network for urban land-use change simulation, Landscape and Urban Planning 250 (2024) 105145. https://doi.org/10.1016/j.landurbplan.2024.105145.
• Y. Long, Z. Shen, V-BUDEM: A Vector-Based Beijing Urban Development Model for Simulating Urban Growth, in: Y. Long, Z. Shen (Eds.), Geospatial Analysis to Support Urban Planning in Beijing, Springer International Publishing, Cham, 2015: pp. 91–112. https://doi.org/10.1007/978-3-319-19342-7_5.
• J. Yang, X. Zhu, W. Chen, Y. Sun, J. Zhu, Modeling land-use change using partitioned vector cellular automata while considering urban spatial structure, Environment and Planning B: Urban Analytics and City Science (2023) 239980832311528. https://doi.org/10.1177/23998083231152887.
• Y. Chen, X. Liu, X. Li, Calibrating a Land Parcel Cellular Automaton (LP-CA) for urban growth simulation based on ensemble learning, International Journal of Geographical Information Science 31 (2017) 2480–2504. https://doi.org/10.1080/13658816.2017.1367004.
• I.E. Ayazli, Investigating the interactions between spatiotemporal land use/land cover dynamics and private land ownership, Land Use Policy 141 (2024) 107165. https://doi.org/10.1016/j.landusepol.2024.107165.
• D. Ozturk, N. Uzel-Gunini, Investigation of the effects of hybrid modeling approaches, factor standardization, and categorical mapping on the performance of landslide susceptibility mapping in Van, Turkey, Natural Hazards 114 (2022) 2571–2604. https://doi.org/10.1007/s11069-022-05480-y.
• A. Tayyebi, B.C. Pijanowski, M. Linderman, C. Gratton, Comparing three global parametric and local non-parametric models to simulate land use change in diverse areas of the world, Environmental Modelling & Software 59 (2014) 202–221. https://doi.org/10.1016/j.envsoft.2014.05.022.
• R. White, G. Engelen, Cellular automata as the basis of integrated dynamic regional modelling, Environ. Plann. B 24 (1997) 235–246. https://doi.org/10.1068/b240235.
• S. Wolfram, Cellular automata as models of complexity, Nature 311 (1984) 419–424. https://doi.org/10.1038/311419a0.
• N.N. Pinto, A.P. Antunes, A Cellular Automata Model Based on Irregular Cells: Application to Small Urban Areas, Environ Plann B Plann Des 37 (2010) 1095–1114. https://doi.org/10.1068/b36033.
• J.I. Barredo, L. Demicheli, C. Lavalle, M. Kasanko, N. McCormick, Modelling Future Urban Scenarios in Developing Countries: An Application Case Study in Lagos, Nigeria, Environ Plann B Plann Des 31 (2004) 65–84. https://doi.org/10.1068/b29103.
• M. Batty, Y. Xie, Z. Sun, Modeling urban dynamics through GIS-based cellular automata, Computers, Environment and Urban Systems 23 (1999) 205–233. https://doi.org/10.1016/S0198-9715(99)00015-0.
• K. Krishnamoorthy, Handbook of statistical distributions with applications, Chapman and Hall/CRC, 2006. https://www.taylorfrancis.com/books/mono/10.1201/9781420011371/handbook-statistical-distributions-applications-krishnamoorthy, Accessed August 31, 2024.
• F.J. Massey, The Kolmogorov-Smirnov Test for Goodness of Fit, Journal of the American Statistical Association 46 (1951) 68–78. https://doi.org/10.1080/01621459.1951.10500769.
• J.D. Gibbons, S. Chakraborti, Nonparametric statistical inference: revised and expanded, CRC press, 2014. https://doi.org/10.4324/9780203911563, Accessed August 31, 2024.
• L. Breiman, Random Forests, Machine Learning 45 (2001) 5–32. https://doi.org/10.1023/A:1010933404324.
• S. Amini, M. Saber, H. Rabiei-Dastjerdi, S. Homayouni, Urban land use and land cover change analysis using random forest classification of landsat time series, Remote Sensing 14 (2022) 2654. https://doi.org/10.3390/rs14112654.
• L.A. Guzman, R. Camacho, A.R. Herrera, C. Beltrán, Modeling population density guided by land use-cover change model: a case study of Bogotá, Popul Environ 43 (2022) 553–575. https://doi.org/10.1007/s11111-022-00400-5.
• C. Kamusoko, J. Gamba, Simulating urban growth using a random forest-cellular automata (RF-CA) model, ISPRS International Journal of Geo-Information 4 (2015) 447–470. https://doi.org/10.3390/ijgi4020447.
• J. Lv, Y. Wang, X. Liang, Y. Yao, T. Ma, Q. Guan, Simulating urban expansion by incorporating an integrated gravitational field model into a demand-driven random forest-cellular automata model, Cities 109 (2021) 103044. https://doi.org/10.1016/j.cities.2020.103044.
• A. Rienow, A. Mustafa, L. Krelaus, C. Lindner, Modeling urban regions: Comparing random forest and support vector machines for cellular automata, Transactions in GIS 25 (2021) 1625–1645. https://doi.org/10.1111/tgis.12756.
• İ.E. Ayazlı, F. Gul, A.E. Yakup, D. Kotay, Extracting an Urban Growth Model’s Land Cover Layer from Spatio-Temporal Cadastral Database and Simulation Application, Polish Journal of Environmental Studies 28 (2019). https://doi.org/10.15244/pjoes/89506.
• TÜİK, Adrese Dayalı Nüfus Kayıt Sistemi Sonuçları, Adrese Dayalı Nüfus Kayıt Sistemi Sonuçları (2025). https://data.tuik.gov.tr/Bulten/Index?p=Adrese-Dayali-Nufus-Kayit-Sistemi-Sonuclari-2022-49685, Accessed January 26, 2025.
• A.E. Yakup, İ.E. Ayazlı, Investigating changes in land cover in high-density settlement areas by protected scenario, International Journal of Engineering and Geosciences 7 (2022) 1–8. https://doi.org/10.26833/ijeg.850247.
• A.S. Kubat, H.S. Kaya, F. Sarı, G. Güler, Ö. Özer, The Effects of Proposed Bridges on Urban Macroform of Istanbul, in: 6th International Space Syntax Symposium. Istanbul: Istanbul Technical University, 2007. https://www.academia.edu/download/90993985/papers_5Clongpapers_5C003_20-_20Kubat_20Kaya_20G_C3_BCler_20Sari_20Ozer.pdf, Accessed August 17, 2024.
• Y. Ye, C. Jia, S. Winter, Measuring Perceived Walkability at the City Scale Using Open Data, Land 13 (2024) 261. https://doi.org/10.3390/land13020261.
• Kaufman, J, Steudler, D, Kadastro 2014: Gelecekteki Kadastral Sistem İçin Bir Vizyon, International Federation of Surveyors, Brighton, 1998.
• I. Horňanskỳ, E. Ondrejička, M. Fojtl, From Cadastre 2014 to Cadastre 2034, in: Permanent Committee on Cadastre in the EU, Plenary Meeting & Conference, Greece, 2014: pp. 45–51.
• M. Lemmens, Towards cadastre 2034 (Part II), GIM International: The Worldwide Magazine for Geomatics 24 (2010) 37–45.
• X. Liu, C. Andersson, Assessing the impact of temporal dynamics on land-use change modeling, Computers, Environment and Urban Systems 28 (2004) 107–124.
• K.C. Clarke, S. Hoppen, L. Gaydos, Methods and techniques for rigorous calibration of a cellular automaton model of urban growth, in: Third International Conference/Workshop on Integrating GIS and Environmental Modeling, Citeseer, 1996: pp. 21–25. https://citeseerx.ist.psu.edu/document?repid=rep1&type=pdf&doi=5d755c433ff52d36e08a235689c69c7db127bd59, Accessed March 22, 2024.