Land cover map is important for many urban planning and management activities. In this study, in order to produce land cover map of Arak city, digital image of LISS-III scanner acquired on 16 June 2006 were employed. First of all, geometric correction with RMSe 0.58 pixel was applied. Considering the mountainous condition of the study area, topographic correction was applied to the image. In support of image classification, two different methods namely, supervised classification with Maximum Likelihood classifier algorithm and a three-layer perceptron neural network with and without using slope map were used. Finally, land cover map of the study region was classified into four classes: urban areas, vegetated areas, barren lands, and rocks. In order to sort out the rocks precisely from other classes, classified slope map of the study area was introduce to neural network model as an input layer. To assess the classified land cover map precision, it was controlled for ground truths with a GPS and the overall accuracies were 92.6, 92.7 and 94.6% for maximum likelihood classification, neural network classifier with and without the usage of classified slope map, respectively. The results confirm that the neural network classifier is capable to generate land cover maps with high accuracy.
Ahmadi Naddoshan, M., Soffianian, A., & Khajedin, S. (2010). Land Cover Mapping of Arak City Using Artificial Neural Network and Maximum Likelihood Classifiers. Physical Geography Research, 41(69), -.
MLA
M Ahmadi Naddoshan; A Soffianian; S.J Khajedin. "Land Cover Mapping of Arak City Using Artificial Neural Network and Maximum Likelihood Classifiers", Physical Geography Research, 41, 69, 2010, -.
HARVARD
Ahmadi Naddoshan, M., Soffianian, A., Khajedin, S. (2010). 'Land Cover Mapping of Arak City Using Artificial Neural Network and Maximum Likelihood Classifiers', Physical Geography Research, 41(69), pp. -.
VANCOUVER
Ahmadi Naddoshan, M., Soffianian, A., Khajedin, S. Land Cover Mapping of Arak City Using Artificial Neural Network and Maximum Likelihood Classifiers. Physical Geography Research, 2010; 41(69): -.
)