نوع مقاله : مقاله پژوهشی

نویسندگان

1 دانشجوی دکتری شهرسازی، دانشکده هنر و معماری، واحد علوم و تحقیقات، دانشگاه آزاد اسلامی، تهران، ایران.

2 استادیار گروه شهرسازی، دانشگاه آزاد اسلامی، زنجان،ایران

3 دانشیار گروه شهرسازی، دانشکده هنر و معماری، واحد علوم و تحقیقات، دانشگاه آزاد اسلامی، تهران، ایران.

10.34785/J011.2021.998

چکیده

یکی از مهم‌ترین دغدغه‌های برنامه‌ریزان و مدیران شهری، نحوه توزیع و تخصیص منابع و خدمات شهری به‌ صورت عادلانه در سطح مناطق مختلف شهر برحسب نیازهای جامعه شهری است. تخصیص بهینه خدمات، ارتباط مستقیمی با برنامه‌ریزی کاربری اراضی دارد. موفقیت درعرصه برنامه‌ریزی کاربری اراضی شهری نیز وابسته به وجود قوانین مناسب در زمینه نحوه استفاده از زمین و همچنین استفاده از روش‌های کارآمد در تهیه واجرای طرح‌های شهری و برنامه کاربری زمین است. این مقاله با هدف ارائه‌ مدلی بر مبنای روش‌های بهینه‌سازی چند هدفه انجام گرفته است تا تخصیص کاربری‌های شهری را از منظر عدالت فضایی در سطح پلاک شهری و در طبقات هر قطعه زمین مدل­سازی کند. به این منظور از الگوریتم ژنتیک رتبه­بندی نامغلوب و یــک کــد کامپیوتری در نــرم­افــزار Matlab R2018a استفاده شده است. مدل بر مبنای پنج تابع هدف شامل بیشینه­سازی سازگاری، وابستگی، دسترسی به خدمات، تنوع و تناسب فیزیکی، در طبقات و در همجواری‌ها‌ و نیز تعداد مشخصی شرایط مورد نیاز پیکربندی شده است. از میان نتایج حاصل از پیاده­سازی الگوریتم که مجموعه‌ای از راه‌حل‌های بهینه پارتو است، یک جبهه جواب انتخاب و سپس برای انتخاب مناسبت‌ترین چینش کاربری‌ها از میان این راه‌حل‌های بهینه، روش تحلیل فرایند سلسله مراتبی، برای تعیین وزن هر یک از اهداف تخصیص کاربری زمین به کار رفته است. وزن حاصل در مقادیر برازش اهداف ضرب شده و پس از اعمال روش مجموع وزن­دار جوابی که بیشترین وزن را در جبهه جواب‌های بهینه به دست آورده، به نقشه‌ کاربری زمین تبدیل شده و به عنوان چینش پیشنهادی ارائه گردیده است. ارزیابی کمی نتایج حاصل از تخصیص نشان داد که کاربری­های تجاری، آموزشی ، درمانی، ورزشی و فرهنگی هم از نظر سرانه و هم از نظر توزیع در سطح محلات و ناحیه‌ مورد مطالعه به خوبی تخصیص داده شده‌اند و سطح برخورداری محلات را در محدوده مطالعه افزایش داده‌اند.

کلیدواژه‌ها

موضوعات

عنوان مقاله [English]

Modeling Urban Land Use Allocation using Spatial Justice Approach Based on the Multi-Objective Optimization Methods

نویسندگان [English]

  • parvaneh jalerajabi 1
  • reza ahmadian 2
  • Zahra sadat saiedeh Zarabadi 3

1 Department of urban development, science and research branch,Islamic Azad University, Tehran,Iran

2 Department of urban development, Islamic Azad University, Zanjan. ,Iran

3 Associated Professor, Faculty of Art and Architecture, Islamic Azad University, Science and Research Branch, Tehran, Iran

چکیده [English]

This research was conducted mainly to provide a method based on artificial intelligence algorithms in order to obtain optimal urban land use allocation, subjected to mathematical modeling from the perspective of spatial justice using multi-criteria decision analysis concepts, both parcel-based and floor-based. For that purpose, objective functions were considered for land use allocation, including mixed use, suitability, dependency, compatibility, and access to services, in terms of both floors and neighbors.
For achievement of the main purpose, parameters effective on urban land use planning were examined to optimize urban land use allocation from the spatial justice perspective. This led to a presentation and classification of the spatial parameters effective on land use allocation based on sustainability and, more specifically, spatial justice concerns.
The main part of the research, named “land use allocation modeling with NSGA-II” focused on development of a land use allocation model and its optimization. The main stage in the modeling procedure was to adapt multi-objective optimization algorithms to land use allocation and, then, to define it as desired. The adaptation of the multi-objective optimization algorithm involved the definition of the solution structure, objective functions, and problem constraints and their calculation for use in the second version of the Non-dominant Genetic Ranking Algorithm (NSGA-II). The objective functions were defined based on criteria and indexes extracted in the second part of the research, including maximization of accessibility to the facilities, of service efficiency (compatibility), of mixed uses, of land suitability, and of spatial dependency. Moreover, seven constraints were introduced for land use allocation, including avoidance of allocating wasteland to the first floor of the parcel, allocation of a land use to the third floor provided that the second one already has a defined land use, possibility of land use allocation to various floors of the same parcel, consideration of maximum and minimum land parceling, avoidance of exceeding the per capita standards in neighborhoods and districts, and, finally, allocation of the necessary land uses to each of the neighborhoods.
The models were then implemented, where the main purpose was to optimize urban land use allocation according to all the criteria and constraints. In other words, these criteria had to be defined in terms of the model objectives and with an extensive search space (many of the possible land use allocations) at the same time. Therefore, a set of solutions, which included Pareto front, i.e. optimal, solutions, was obtained rather than a single solution to the problem. As decision-makers prefer to examine the corresponding scenarios after introducing their own decision priorities, the AHP method was used finally after the optimal Pareto solutions were obtained for selection of one of the four possible land use allocations and its presentation in a land use plan given spatial justice concerns. For that purpose, weights were assigned to the objective functions based on spatial justice. Once the objective function values were normalized, the desired weights were multiplied by the normal values. After the calculation of total weight, the solutions corresponding to the objective functions being addressed were converted to land use plans in ArcGIS. The results of land use allocation in floors were compared to the actual conditions.
It could be stated in general that the most important achievement of the study involved the introduction and presentation of an efficient model that was appropriate for addressing multi-criteria decision-making problems for allocation of urban land use. The presented model performs simultaneous optimization, and helps decision makers to select one desired solution from among multiple optimized ones according to their priorities, although it is in contradiction with some of the objective functions. The results of the model designed for land use allocation given spatial justice concerns improved the spatial distribution of facilities at the level of the area under study. Moreover, a quantitative evaluation of the allocation results demonstrated that the commercial, academic, health, sport, and cultural land uses were allocated properly per capita, increasing the level of enjoyment in neighborhoods across the area under investigation.

Land use allocation, Spatial justice, Multi-objective optimization method, NSGA-II.

کلیدواژه‌ها [English]

  • Land use allocation
  • Spatial justice
  • Multi-objective optimization method
  • NSGA-II
Alaei Moghadam, S.,  Karimi , M.,   & Mohammadzadeh, A. (2015). Modeling of Urban Land Use Allocation Using Reference-Point-Nondominated Sorting Genetic Algorithm II, Journal of Geomatics Science and Technology, Volume:4 Issue: 4,47-66. [in Persian]
Aminzadeh,B & Roshan, M. (2015). Evaluation of Spatial Justice Measurement Methods in Urban Land-Use Distribution, Case Study: Qazvin , Journal of Architect, Urban Design & Urban Planning, Volume:7 Issue: 13, 243-258. [in Persian]
Cao, K., Batty, M., Huang, B., Liu, Y., Yu, L., & Chen, J. (2011). Spatial multi-objective land use optimization: extensions to the non-dominated sorting genetic algorithm-II. International Journal of Geographical Information Science25(12), 1949-1969.
Cao, K., Huang, B., Wang, S., & Lin, H. (2012). Sustainable land use optimization using Boundary-based Fast Genetic Algorithm. Computers, Environment and Urban Systems36(3), 257-269.
Coello, C. A. C., Lamont, G. B., & Van Veldhuizen, D. A. (2007). Evolutionary algorithms for solving multi-objective problems (Vol. 5). New York: Springer.
Dadashpoor, H. & Rostami, F. (2012). Investigation and analysis of urban public services distribution from the perspective of spatial equity: The case of Yasuj City, Journal Of Geography and Regional Development Reseach Journal, Volume:9 Issue: 16, 171-198. [in Persian]
Dadashpoor, H . , Rostami, F. & Alizadeh, B. (2014).  Analysis of Justice Distribution of Urban Services and the their Spatial Distribution Pattern in Hamadan City, Journal Of Urban Studies, Volume: 3, Issue: 12, 5-18. [in Persian]
Dadashpoor, H . , Alizadeh, B. & Rostami, F. (2015a).  Spatial justice dialectic in city. Azarkhsh: Tehran. [in Persian]
Dadashpoor, H . , Alizadeh, B. & Rostami, F. (2015b).  Determination of Conceptual Framework from Spatial Justice in Urban Planning with Focus on the Justice Concept in Islamic School, Naqshejahan- Basic studies and New Technologies of Architecture and Planning, Volume:5 Issue: 1 . 75-84.[in Persian]
Dadashpoor, H . , Rostami, F. & Alizadeh, B.  (2015c).  Status of Spatial Justice in System of Iran,s Urban Planning, Development Strategy, Issue: 43 . 181-206.[in Persian]
Dadashpoor, H. & Alvandipour, N. (2017). Spatial Justice in Urban Scale in Iran; Meta- Study of Selected Articles’ Theoretical Famework, Honarhaie ziba, Volume: 21, Issue: 3, 67-80. [in Persian]
Dai, W., & Ratick, S. J. (2014). Integrating a Raster Geographical Information System with Multi‐Objective Land Allocation Optimization for Conservation Reserve Design. Transactions in GIS18(6), 936-949.
Datta, D., Deb, K., Fonseca, C. M., Lobo, F., Condado, P., & Seixas, J. (2007). Multi-objective evolutionary algorithm for land-use management problem. International Journal of Computational Intelligence Research3(4), 371-384.
Deb, K., Pratap, A., Agarwal, S., & Meyarivan, T. A. M. T. (2002). A fast and elitist multiobjective genetic algorithm: NSGA-II. IEEE transactions on evolutionary computation6(2), 182-197.
Delaviz, Y., Karami, J., & Shaygan, M. (2016). Using NSGA-II for Multi-Objective Optimization Allocation of Urban Land Use in Order to Reduce Earthquake Vulnerability. Journal of Geomatics Science and Technology5(3), 247-264.
Haque, A., & Asami, Y. (2011). Optimizing urban land-use allocation: case study of Dhanmondi Residential Area, Dhaka, Bangladesh. Environment and Planning B: Planning and Design38(3), 388-410.
Haque, A., & Asami, Y. (2014). Optimizing Urban Land Use Allocation for Planners and Real Estate Developers. International Journal of Computers, Environment and Urban Systems, 46, 57-69.
 Hataminejad , H.,  Vahedian Beiki, L. &   Parnoon, Z. (2014). The spatial distribution pattern of urban services Measurement in fifth region Of Tehran using Entropy and Williamson models, Geographical Research, Volume:29 Issue: 3, 17 – 28. [in Persian]
Huang, B., Fery, P., Xue, L., & Wang, Y. (2008). Seeking the Pareto front for multiobjective spatial optimization problems. International Journal of Geographical Information Science22(5), 507-526.
Huang, K., Liu, X., Li, X., Liang, J., & He, S. (2013). An improved artificial immune system for seeking the Pareto front of land-use allocation problem in large areas. International Journal of Geographical Information Science27(5), 922-946.
Janssen, R., van Herwijnen, M., Stewart, T. J., & Aerts, J. C. (2008). Multiobjective decision support for land-use planning. Environment and Planning B: Planning and Design35(4), 740-756.
Kaim, A., Cord, A. F., & Volk, M. (2018). A review of multi-criteria optimization techniques for agricultural land use allocation. Environmental Modelling & Software105, 79-93.
Li, X., & Parrott, L. (2016). An improved Genetic Algorithm for spatial optimization of multi-objective and multi-site land use allocation. Computers, Environment and urban systems59, 184-194.
Ligmann-Zielinska, A. (2016). Spatial Optimization. The International Encyclopedia of Geography: 1–6. http://onlinelibrary.wiley.com/doi/10.1002/9781118786352.wbieg0156/ abstract;jsessionid=BB7FA4B38B8D8FB2234B607D22178806.f04t02
Liu, X., Ou, J., Li, X., & Ai, B. (2013). Combining system dynamics and hybrid particle swarm optimization for land use allocation. Ecological Modelling257, 11-24.
Liu, Y. L., Tang, D. W., Kong, X. S., Liu, Y. F., & Ai, T. H. (2014). A land-use spatial allocation model based on modified ant colony optimization. International Journal of Environmental Research8(4), 1115-1126.
Liu, Y., Peng, J., Jiao, L., & Liu, Y. (2016). PSOLA: A heuristic land-use allocation model using patch-level operations and knowledge-informed rules. PloS one11(6), e0157728.
Ma, S., He, J., & Yu, Y. (2010). Model of urban land-use spatial optimization based on particle swarm optimization algorithm. Transactions of the Chinese Society of Agricultural Engineering26(9), 321-326.
Ma, S., He, J., Liu, F., & Yu, Y. (2011). Land-use spatial optimization based on PSO algorithm. Geo-spatial Information Science14(1), 54-61.
Malczewski, J., & Rinner, C. (2015). Multicriteria decision analysis in geographic information science. Springer.
Masoomi, Z., Mesgari, M. S., & Hamrah, M. (2013). Allocation of urban land uses by Multi-Objective Particle Swarm Optimization algorithm. International Journal of Geographical Information Science27(3), 542-566.
Memmah, M. M., Lescourret, F., Yao, X., & Lavigne, C. (2015). Metaheuristics for agricultural land use optimization. A review. Agronomy for sustainable development35(3), 975-998.
Mohammadi, M., Nastaran, M., & Sahebgharani, A. (2015). Sustainable spatial land use optimization through non-dominated sorting Genetic Algorithm-II (NSGA-II):(Case Study: Baboldasht District of Isfahan). Indian Journal of Science and Technology8(S3), 118-129.
Nazmfar, H., Eshghi chaharpar, A. & Ghasemi, M. (2014). Analysis of social justice in urban spatial structure ( case study : maragheh city ),Journal of Geography and Environmental Studies,  Issue: 11,91-112. [in Persian]
Porta, J., Parapar, J., Doallo, R., Rivera, F. F., Santé, I., & Crecente, R. (2013). High performance genetic algorithm for land use planning. Computers, Environment and Urban Systems37, 45-58.
Saeedi Rezvani, H. (2014). The transition to a fair city in the theories of  urban planningand the teachings of Islam,the Sustainable City, No: 1,135 - 163. [in Persian]
Shaygan, M., Alimohammadi, A., Mansourian, A., Govara, Z. S., & Kalami, S. M. (2013). Spatial multi-objective optimization approach for land use allocation using NSGA-II. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing7(3), 906-916.
Stewart, T. J., Janssen, R., & Herwijnen, M. V. (2004). A genetic algorithm approach to multiobjective land use planning. Computers and Operation Research, 31(14), 2293-2213.
Yang, L., Sun, X., Peng, L., Shao, J., & Chi, T. (2015). An improved artificial bee colony algorithm for optimal land-use allocation. International Journal of Geographical Information Science29(8), 1470-1489.
Yao, J., Zhang, X., & Murray, A. T. (2018). Spatial Optimization for Land-use Allocation: Accounting for Sustainability Concerns. International Regional Science Review, 0160017617728551.
Yoon, E. J., Kim, B., & Lee, D. K. (2019). Multi-objective planning model for urban greening based on optimization algorithms. Urban Forestry & Urban Greening40, 183-194.