Autor(es): Sahalu, Atalel Getu
Data: 2014
Identificador Persistente: http://hdl.handle.net/10362/11553
Origem: Repositório Institucional da UNL
Assunto(s): Bahir Dar; Change detection; Geographical Information system; Image classification; Land Change Modeler; Land use and land cover change; Remote sensing
Dissertation submitted in partial fulfillment of the requirements for the Degree of Master of Science in Geospatial Technologies
The high rate of urbanization coupled with population growth has caused changes in land use and land cover in Bahir Dar, Ethiopia. Therefore, understanding and quantifying the spatio- temporal dynamics of urban land use and land cover changes and its driving factors is essential to put forward the right policies and monitoring mechanisms on urban growth for decision making. Thus, the objective of this study was to analyze land use and land cover changes in Bahir Dar area, Ethiopia by applying geospatial and land use change modeling tools. In order to achieve this, satellite data of Landsat TM for 1986 and ETM for 2001 and 2010 have been obtained and preprocessed using ArcGIS. The Maximum Liklihood Algorithm of Supervised Classification has been used to generate land use and land cover maps. For the accuracy of classified land use and land cover maps, a confusion matrix was used to derive overall accuracy and results were above the minimum and acceptable threshold level. The generated land cover maps have been run with Land Change Modeler for quantifying land use and land cover changes, to examine land use transitions between land cover classes, to identify gain and losses of built up areas in relation to other land cover classes and to asses spatial trend of built up areas. Finally, Land Change Modeler has been run to model land use and land cover changes in Bahir Dar area and to predict future urban land use changes. To achieve this, four model variables that explain urban growth and six land cover transitions were incorporated in the modeling process. Multi-layer perceptron neural network was used to model the transition potential maps and achieved an accuracy of 61%. This result was acceptable to make actual prediction using Markov chain analysis for year 2010. Validation results showed that the model (Land Change Modeler) had a lower accuracy in simulating changes for the year 2010. Generally, the results of this study have shown that there was an increased expansion of built up areas in the last 25 years from 1.5% in 1986 to 4.1 % in 2001 and 9.4% in 2010 at the expense of agricultural areas. The spatial trend of built up areas also showed that there was a growing trend in the western part of Bahir Dar relative to other directions. Therefore, the findings of this study could provide as decision making for urban planning.
