75 
DETECTION AND PREDICTION OF LAND USE CHANGE IN BEIJING BASED ON 
REMOTE SENSING AND GIS 
Wenli Huang 3 , Huiping Liu 3, *, Qingzu Luan 3 , Qingxiang Jiang b , Junping Liu c , Hua Liu c 
a School of Geography, Beijing Normal University, Beijing, P. R. China, 100875 - hwl208@yahoo.com.cn 
‘Cartographic Institute of Beijing Institute of Surveying and Mapping, No.15, Yang fang dian Road, Beijing, P. R. 
China, 100038 -jqx79@163.com 
c Beijing Research center of Agriculture Economic, Beijing, 100029 
YF 
KEY WORDS: Change Detection, Multi-temporal Data, Image Data Mining, Spatio-temporal Modelling, Expansion Simulation 
ABSTRACT: 
With the development of global changes, researchers from all over the world attach attention to land use changes increasingly, and 
large scale land use changes which have resulted from urban expansion catch people’s eyes. In this paper, urban expansion and their 
spatial and temporal variability of the Beijing city has been studied over a period of 21 years (1984-2005) via statistical classification 
approaches based on the remotely sensed images obtained from sensors both Landsat TM5 and SPOT4. The research method 
includes three parts: First, using multi-temporal images, land use/land cover change is detected by means of remote sensing. Then, 
based on result of classification images, the process of land use/land cover change and the model of urban expansion are analyzed by 
GIS technologies. It includes markov and transfer matrix, trajectories analysis, the spatial distribution rules of urban land and the 
spatial distribution rules of urban expansion intensity. Concretely, these include Markov and transitional probabilities matrix and the 
spatial distribution mles of urban land and urban expansion intensity. Finally, the relationship of population, GDP and urban land 
area are built up through a linear regression analysis. Research shows that: 1) Land use/land cover change detection using multi 
temporal images by means of remote sensing and ration research of model of urban expansion by GIS are good means of research of 
urban expansion. 2) Research of time sequence land use/ land cover change through analysis of urban expansion trajectories and 
index reveals of urban distribution rules in terms of spatial-temporal. 3) Combined the analysis of social economic data, the 
simulation of expansion urban land is given in amount. 
1. INTRODUCTION 
The land use change in large city area is a complicated process; 
several factors have influences on this process, including both 
physical aspects and human aspects. On the one hand, 
accelerated urban expansion is usually associated with and 
driven by the social-economic factors; on the other hand, the 
process of urbanization has a considerable impact on the 
economics of the society in that area (He, 2006; Mahesh, 2008). 
For substantial development, municipal authorities need tools to 
monitor how the land is currently used, assess future demand, 
and take steps to assure adequacy of future supply; for a better 
planning of future urban development, municipal authorities 
need to know situation of urban expansion and in what way it is 
likely to move in the years to come (Mahesh, 2008). So the 
detection of urban land change is important for officials and 
planner in the local government. 
Recent years, urbanization is a major trend in big city all around 
the world (Weber, 2003). The main change of landuse in these 
areas can be described as other type of landuse converting into 
urban land. Unfortunately, the conventional survey and 
mapping techniques are expensive and time consuming for the 
estimation of urban expansion and such information is not 
available for most of the urban centers, especially in developing 
countries. As a result, increased research interest is being 
directed to the monitoring of urban growth using GIS and 
remote sensing techniques (Epstein et al., 2002). Remote 
sensing is increasingly used for detection and analysis of urban 
expansion since it is cost effective and technologically efficient. 
The detection of landuse change using either an image-to-image 
comparison or a post-classification comparison (Liu, 1999). 
During the past ten years, extensive study efforts has been made 
for urban change detection using remotely sensed images (Yeh 
and Li, 2001; Liu and Zhou, 2004; Li et al., 2005; He et al., 
2005; Mahesh, 2008). Despite these efforts, further research is 
needed in order to reinforce the absolute and comparative 
relationship between the type and intensity of urban land use 
change and their causative factors (Mahesh, 2008). 
Many models for urban growth prediction, such as the cellular 
automata (CA) model and land conversion in the urban fringe 
area, have been developed (Wu, 1998; Li and Yeh, 2002; He et 
al., 2008). Among these models, Geographical Information 
System (GIS) based urban models have been widely used (Yeh 
and Li, 1998; He et al., 2005). In practice, however, the use of 
these models has been limited in urban growth analysis because 
of the difficulty in obtaining all of the required factors or 
enough data for the model. 
Therefore, in this paper, we take plain region of Beijing City as 
an example, based on remotely sensed data (Landsat TM and 
SPOT images) in seven years (1984, 1988, 1991, 1994, 1997, 
2001 and 2005), detecting Beijing’s land use/land cover change 
* Corresponding author. Tel: 861058807455-1625. Fax: 861058806955. 
Present address: School of Geography, Beijing Normal University, Beijing, P. R. China, 100875. 
E-mail address: hpliu@bnu.edu.cn