Performance Assessment of CA-ANN Consolidated Model in Urban Growth Modelling (A Case Study of Tehran Metropolitan Area)

جغرافیاوتوسعه ناحیه ای

Article 10, Volume 16, Issue 1 - Serial Number 30, September 2018, Pages 257-278   

Document Type: scientific-research article

DOI: 10.22067/geography.v16i1.72248

Authors

Hatef al-Rahman Salehi Asfichi^* ; Jalal Karami; Sayyed Ali Alavi

Tarbiat Modarres University

Abstract

Extended Abstract

Introduction

Nowadays, investigations and analysis of changes in land use through local and national scales have been taken into consideration more than ever, the major purpose of which is to optimize land use as well as its limited finite resources.
During the past few years, the rapid growth in population along with urbanization have intensified the significance of land use, resulting in extensive changes regarding the usage of lands in the cities. In general, it has been indicated that natural forces as well as human activities are the two major factors in changing land use and ground cover through scales ranging from local to national.
Although the development of cities in western countries have taken a rather slow pace of progress currently, yet, statistics show a rapid, considerable growth in Asia. Similarly, our country have also witnessed such an increasing, accelerated progress, especially during the past 40 years; in most cases, however, the growth has taken place in outskirts of cities and locations with fewer facilities and features.
Among various changes in land use brought about by humans, urban growth and development is of utmost importance concerning the high values of lands; as a result, the position of modelling and predicting the changes in land use in the future have also gained significance for urban management, environment, and other authorities and researchers involved.
In many studies concerning the modelling of changes in land use, multi-temporal satellite images are presented as the most important type of data to be used. Consequently, the examination on how to utilize their various capabilities as to achieve desirable results is of special importance.
Tehran metropolitan area, as the political and economic capital of the country, has been subject to a rapid influx of population along with inconvenient and unbalanced development. The emergence of an entangled, polluted and overcrowded environment in Tehran have revealed the necessity of an optimized management of natural resources as well as proper use of lands in this city, more than before. It is evident that in this regard, urban designers and environment experts would draw a set of strategies in order to accomplish the aforementioned purposes.
The main goal of the present study is to investigate and analyze the effective factors in the development process of Tehran metropolitan area since 1990 until 2010, as to develop and present a model through which urban development can be predicted; such predictions would provide the basis for implementation and execution of urban planning policies.

Theoretical Framework

The high urban population growth rate and the lack of basic infrastructure, on the one hand, and the increasing trend of land-use disparate changes, on the other hand, clearly reveal the need for the analysis of these changes. In this regard, urban designers and environmental experts are considering strategies for the optimal management of natural resources as well as the proper use of land valuable in urban areas.

Methodology

The main purpose of this study is the consolidated employment of a mixed model of automatic cells and neural network algorithm based on spatial information system in order to create a model of urban development with regards to Tehran metropolitan area during time intervals of 1990, 2000, 2010, as well as comparing the accuracy of modelling in this algorithm with common models of automatic cells.
A set of parameters including the distance from urban areas, roads, streets and parks along with the slope and altitude of lands, have been considered as the effective parameters on urban development and growth. The results showed that the consolidated employment of automatic cells model and neural network algorithm can offer improvements to the calibration process of rules regarding the transfer of automatic cells.
Satellite images used in this study have been taken in 1990, 2000, and 2010. Furthermore, the required layers of information such as the maps of elevation, slopes, and land use layer of Tehran metropolitan area have been used in a shapefile format in ArcGIS 10 software. The entire processes of satellite images have been carried out in ENVI 7.4 software.
The Thematic Mapper (TM) image in 1990 and the Enhanced Thematic Mapper Plus (ETM+) images in 2000 and 2010, which would form the input and output of the models in both consecutive periods, have been classified into urban, arid, parks and farmlands, lakes and road regions using Support Vector Machine (SVM) algorithm. Then, by extracting binary image of developed regions (urban, non-urban), the spatial objects related to such regions are obtained.
In the next step, these objects are transferred to cellular space via an inverse conversion of vector space so that they could be used in the model structure while maintaining their unique identifiers. Moreover, a Cellular Automata (CA) model based on artificial neural network optimization algorithm is implemented in order to obtain the likelihood of development (transformation from non-urban to urban mode) for each cell. The model for calculating such possibility is based on mixed automatic pattern.
It is worth mentioning that the Kappa statistical index and the overall accuracy are used to assess the results and compare them to the ground truth. Furthermore, in order to validate the results, a statistical test based on variance to measure the meaningfulness of the results is utilized.

Results and Discussion

Considering the limitations in common cellular patterns and vectors of automatics, the present study offers a mixed automatic pattern as a combination of cellular computing structure as well as optimal features of vector patterns. The major problem with conventional models of automatic cells entail a sensitivity to scale along with being far from the reality of ground objects. Although object-based vector models have lessened such deficiencies to some extent, yet their implementation and calculations still face a number of complexities and challenges.
In a mixed model, space is defined as a set of arranged cells, yet spatial objects derived from ground truth is also used along with them. In order to avoid employing a trial and error approach in determining the proper weights regarding the model’s components, an artificial neural network optimization method have been used to calculate the possibility of extension based on the distance from developmental factors such as the distance from roads or important central regions of the city. A statistical comparison of the ground truth of Tehran in 2010 via the simulations obtained from mixed model along with common cellular pattern shows the higher accuracy of the proposed model relative to cellular model.
The result of the study showed that the consolidated employment of automatic cell models as well as artificial neural network optimization algorithm can offer improvements to the calibration process of the rules concerning the transfer of automatic cells. A statistical comparison of the ground truth of Tehran in 2010 using simulated images taken from the mixed model and also, the common model of automatic raster cells indicate the higher accuracy of the proposed model, in a way that according to the results of modelling based on two images, the kappa index and overall accuracy for the mixed model have been estimated as 76% and 90.96%, and for the common raster model, they have been 70.47% and 87.85%, respectively. Furthermore, according to modelling based on three images, the kappa index and the overall accuracy for mixed model and also the common raster model have been estimated as 69.18%, 84.88%, 63.37% and 82.98%, respectively.

Conclusion and Suggestions

The results of the study are briefly summarized in the following:

Investigation of the procedure regarding the spatial-temporal changes of phenomena such as the development of cities, require employing dynamic patterns in time. In this regard, due to their simple, yet dynamic structures as well as having strong spatial features, cellular automata have been used extensively in these types of modellings.
The proposed model of mixed automata simultaneously utilizes the optimal concept and features of the vector pattern along with the simple structure and calculations of cellular pattern. Having a proper accuracy in simulations, the present model involves low sensitivity to scale and does not require complex calculations and implementation, making it an appropriate, applicable pattern in modelling of urban development.
Neural network algorithm can be used as a proper method for optimal indication of the intensity regarding the participation of various factors in regulating structures of cellular automata, rather than employing a deficient, time-consuming method such as trial and error.

Keywords

Tehran Metropolitan Area; Urban growth; cellular automata; Artificial neural network; the kappa index

References

1. اصلانی مقدم، ا. (1388). بررسی مدل برداری به منظور پیش‎بینی تغییرات کاربری اراضی. (پایان‌نامة منتشرنشدة کارشناسی ارشد سنجش از دور)، دانشگاه تهران، ایران. ‎

2. ربانی، ا. (1390). ارزیابی تصاویر ماهواره‌ای با تفکیک‌پذیری چندگانه در مدل‎سازی رشد شهرها به کمک خودکاره‌های سلولی. (پایان‌نامة منتشرنشدة کارشناسی ارشد سنجش از دور)، دانشگاه تهران، ایران.

3. طیبی، 1. (1388). پیش‌بینی و ارزیابی تغییر کاربری اراضی شهری. (پایان‌نامة منتشرنشدة کارشناسی ارشد سنجش از دور)، دانشگاه تهران، ایران.

4. کاظم، ا. ح.، حسینعلی، ف. و آل‎شیخ، ع. ا. (1394). مدل‎سازی رشد شهری با استفاده از تصاویر ماهواره‎ای متوسط‌مقیاس و مبتنی بر روش خودکاره‎های سلولی (مطالعة موردی: شهر تهران). فصل‌نامة علمی- پژوهشی اطلاعات جغرافیایی، 24 (94)، 58-45.

5. Al-Kheder, S. (2007). Urban growth modelling with artificial intelligence techniques (Unpublished doctoral dissertation). Purdue University, USA.

6. Almeida, C., Monteiro, A. M. V., Camara, G., Soares-Filho, B. S. Cerqueira, G. C., & Pennachin, C. L. (2002). Modelling urban land use dynamics through Bayesian probabilistic methods in a cellular automaton environment. In C. Tamayo (Ed.), Proceedings of the 29th International Symposium on Remote Sensing of the Environment (pp. 1-5). Buenos Aires, Argentina, 8–12 April.

7. Batty, M. (1970). An activity allocation model for the Nottinghamshire-Derbyshire sub-region. Regional Studies, 4, 307-332.

8. Clarke, K. C., Hoppen, S., & Gaydos, L. (1997). A self-modifying cellular automaton model of historical urbanization in the San Francisco Bay area. Environment and Planning B, 24(2), 247-262.

9. Congalton, R.G., & Green K. (2009). Assessing the accuracy of remotely sensed data-principles and practices. International Journal of Applied Earth Observation and Geo-information, 11(6), 448-449.

10. Dietzel, C., & Clarke, K.C. (2004). Spatial differences in multi-resolution urban automata modeling. Transactions in GIS, 8(4), 479-492.

11. Feng, Y., Liu, Y., Tong, X., Liu, M., & Deng, S. (2011). Modelling dynamic urban growth using cellular automata and particle swarm optimization rules. International Journal of Landscape and Urban Planning, 102(3), 188-196.

12. Hegde, N.P., Muralikrishna, I. V., & Chalapatirao, K. V. (2008). Settlement growth prediction using neural network and cellular automata. Journal of Theoretical and Applied Information Technology, 4(5), 419-428.

13. Houghton, R.A. (1994). The world-wide extent of land-use change. Bioscience, 44(5), 305-313.

14. Landis, J. D. (1994). The California urban futures model: A new generation of metropolitan simulation models. Environment and Planning B: Planning and Design, 21, 399-420.

15. Li, X., & Yeh, A. G. O. (2000). Modelling sustainable urban development by the integration of constrained cellular automata and GIS. International Journal of Geographical Information Science, 14(2), 131-152.

16. Li, X., & Yeh, A. G. O. (2003). Simulation of development alternatives using neural networks, cellular automata, and GIS for urban planning. Photogrammetric Engineering and Remote Sensing, 69, 1043-1052.

17. Menard, A., & Marceau, D. (2005). Exploration of spatial scale sensitivity in geographic cellular automata. Environment and Planning B: Planning and Design, 32(5), 693-714.

18. Olson, J.M., Alagarswamy, G., Andresen, J.A., Campbell, D.J., Davis, A.Y., Ge, J.,... Wang, J., (2007). Integrating diverse methods to understand climate-land interactions in east Africa. Geoforum, 39, 898-911.

19. Openshaw, S. (1998). Neural network, genetic, and fuzzy logic models of spatial interaction. Environment and Planning, 30, 1857–1872.

20. Small, C., & Miller, R.B. (1999). Monitoring the urban environment from space. Columbia University, Palisades, NY, USA: Lamont Doherty Earth Observatory.