Application of Neural Network in Urban Land Use Suitability Evaluation

Abstract:

Article Preview

Urban land use suitability evaluation is the basic work of urban land use planning and management. The evaluation method is a core in urban land use suitability evaluation. Traditional urban land use suitability evaluation methods are GIS-based methods which often can not get satisfactory results for the complex nonlinear urban land use system. Artificial neural network is a frontier theory of complex non-linearity scientific and artificial intelligence science. It is a new method to evaluate urban land use suitability. This paper took the land use suitability evaluation of Hefei city as an example, building a back propagation neural network with 8 neurous of input layer, 5 neurons of hide layer and 3 neurons of output layer. The analysis shows: the high suitability area is 682.27 km2 in Hefei city, being about 8.73% of the total study area; the middle suitability area is 5965.76 km2, or about 76.33% of the total area and the low suitability area is 1167.35 km2, or about 14.94% of the total area. The results reflect the actual situation in Hefei city. The study shows that the back propagation neural network model can overcome the shortcomings of traditional evaluation methods. It means that artificial neural network is suitable for urban land use suitability evaluation. This reflects that artificial neural network has great academic value and application prospect in urban land use suitability evaluation. It also reflects that this study can provide a new idea and method for urban land use suitability evaluation.

Info:

Periodical:

Key Engineering Materials (Volumes 474-476)

Edited by:

Garry Zhu

Pages:

681-686

Citation:

X. R. Zhang and G. Chen, "Application of Neural Network in Urban Land Use Suitability Evaluation", Key Engineering Materials, Vols. 474-476, pp. 681-686, 2011

Online since:

April 2011

Export:

Price:

$38.00

[1] J. Cheng, X. T. Li and J. B. Chen: Evaluation of land suitability based on GIS in Zhangzhou city. Journal of Fujian Teachers University (Natural Science). Vol. 17 (2001), pp.98-101.

[2] R. H. Huang: A land suitability study for town development by means of GIS—case study of huacheng. Acta Scientiarum Naturalum Universitatis Sunyatsen. Vol. 36 (1997), pp.108-113.

[3] I. L. Mcharg: Design with Nature (Natural History Press, U.S. 1969).

[4] S. J. Carver: Integrating multi-criteria evaluation with geographical information systems. International Journal of Geographical Information Systems. Vol. 5 (1991), pp.321-339.

DOI: https://doi.org/10.1080/02693799108927858

[5] J. A. Anderson: An Introduction to Neural Network (MIT Press, U.K. 1995).

[6] X. G. Chen and X. D. Pei: Technology and Application of Artificial Neural Network (China Electric Power Press, China 2003).

[7] L. Zhang and B. Zhang: Theory and Applications of Artificial Neural Networks (Zhejing Science and Technology Publishing House, China 1997).

[8] L. J. Zhang, J. Cao and S. Z. Jiang: Neural Network Utility Tutorial (Machinery Industry Press, China 2008).

[9] P. F. Yan and S. C. Zhang: Artificial Neural Network and Evolutionary Computation (Tsinghua University Press, China 2000).

[10] D. P. Mandic and J. A. Chambers: Recurrent Neural Networks for Prediction (Wiley Press, U.K. 2001).

[11] Q. Fu and X. Y. Zhao: Principle and Application of Projection Pursuit Model (Science Press, China 2006).

[12] X. Q. Cao and F. H. Tang: Systems Engineering and Information Technology of Urban Planning (China Railway Publishing House, China 2005).

Fetching data from Crossref.
This may take some time to load.