MONITORING LAND USE CHANGE BY MULTI-TEMPORAL LANDSAT REMOTE 
SENSING IMAGERY 
Tayyebi, A., M.R. Delavar, S. Saeedi, J. Aminiand H. Alinia 
Center of Excellence in Geomatics Eng. and Disaster Management, Dept, of Surveying and Geomatics Eng., College of 
Eng., University of Tehran, Tehran, Iran, 
amin.tayyebi@gmail.com, ssaidi@ut.ac.ir, mdelavar@ut.ac.ir, jamini@ut.ac.ir, alinia_202000@yahoo.com 
Commission VII, WG VII/5 
KEY WORDS: Land Use, Artificial-Intelligence, GIS, Remote Sensing, Change Detection 
ABSTRACT: 
This paper presents a methodology through utilizing remote sensing imagery, GIS-based neuro-fuzzy approach and variety of social 
and environmental factors for simulating land use change. Two historical Landsat imageries of Tehran Metropolitan Area with 
twenty year time interval and user-selected socio-economic and environmental variables have been employed in order to simulate 
land use change. All images were rectified and registered to Universal Transverse Mercator (UTM) WGS 1984 zone 39N. 
Supervised classification was used to classify the images to different land use categories. Four classes were identified: road, 
residential area, service centre, administrative area. This work introduces a simulation experiment on urban land use change in 
which a supervised back propagation neural network has been employed in the parameterization of the simulation model, while GIS 
is used to model and monitor land use change and perform spatial analysis on the results. This paper adapts land use change model 
which parameterized for Tehran Metropolitan Area and explores how factors such as road, slope, administrative space, service 
centre and residential area parameters can influence it. For each cell in the study area, the real change between the two time steps is 
determined and analyzed compared with the provided variables in order to produce a probability of land use change layer. Parts of 
two datasets were used to train the neural network while full datasets were utilized to predict land use change modelling. In addition, 
the impact of training and prediction period on land use is examined. The creation of the GIS based neuro-fuzzy land use change 
modelling is the major contribution of this paper. 
1. INTRODUCTION 
A serious problem for modelling urban land use change has 
been the lack of spatially detailed data. GIS and remote sensing 
have the potential to support such models, by providing data 
and analytical tools for the study of urban environments. The 
work emphasizes spatial relationships between various 
geospatial, land-use, and demographic variables characterizing 
fine zones across and around regions. Land use change is a 
complex process that encounters sophisticated parameters. The 
interpretation of aerial photography provides a variety of ways 
to develop digital land use information which is basis for land 
use planning. For this reason, government is planning to 
develop land use maps on a regular timetable and store and 
manage this information in a GIS. 
The proposed model in this paper relies on artificial neural 
network, GIS, fuzzy logic and remote sensing imageries from at 
least two time periods. Artificial neural networks arise as an 
alternative to assess such probabilities by means of non- 
parametric approaches. As stated by Fischer and Abrahart 
(2000), these mechanisms are able to learn from and make 
decisions based on incomplete, noisy and fuzzy information, 
and that is the reason why they can be suitable to handle spatial 
problems. This information is important for planners and 
resource managers in developing better decisions affecting the 
environment and local and regional economies. Land use 
change models attempt to project future changes in land use 
based on past trends and the drivers thought to determine 
conversions of land between different categories. The neuro- 
fuzzy approach was used to predict Tehran’s future land use. 
Li and Yeh (2001) conducted a simulation of land use change 
for a cluster of cities in southern China, using ANN embedded 
in a CA model upon a binary state basis (urban/non urban use). 
They further refined this model dealing with multiple regional 
land uses (Li and Yeh, 2002) and simulations for alternative 
development scenarios (Yeh and Li, 2003), however, their 
investigations did not ever scale down at the intra-urban level. 
A GIS-based Land Transformation Model (Pijanowski, et al., 
2000) was developed to forecast land use change over large 
regions. Liu (2000) adapted a new method to detect the change 
from non-urban to urban land use through using artificial neural 
network (ANN). In land use change, (Pijanowskia et al., 2002) 
integrate both the artificial neural network and geospatial 
information systems for the purpose of forecasting the change 
in land use. The model (Pijanowski et al. 2000, 2002) couples 
GIS, customized data handling routines, a variety of parameter 
files and Artificial Neural Network (ANN) software to forecast 
land use changes. 
The importance of accurate information describing the kind of 
land features for land use planning is increasing. Tehran 
Metropolitan Area exhibited accelerated rates of urban land use 
change over the last three decades. Being the capital city of Iran, 
Tehran has undertaken a great deal of economical and social 
developments in term of land use change and the rapid growth 
of infrastructure. The main objective of this paper is to 
implement the neuro-iuzzy concepts to create the land use