Performance comparison of land change modeling techniques for land use projection of arid watersheds

• Main Authors: S.M. Tajbakhsh, H. Memarian, K. Moradi, A.H. Aghakhani Afshar
• Format: Article
• Language: English
• Published: GJESM Publisher 2018-07-01
• Series: Global Journal of Environmental Science and Management
• Subjects: Artificial neural network-multi layer perceptron (ANN-MLP); CA-Markov; Fuzzy-analytic hierarchy process (Fuzzy-AHP); Land use change; simulation
• Online Access: http://www.gjesm.net/article_31528_5b726f6ce9789ee06ae721ba73469d0b.pdf

The change of land use/land cover has been known as an imperative force in environmental alteration, especially in arid and semi-arid areas. This research was mainly aimed to assess the validity of two major types of land change modeling techniques via a three dimensional approach in Birjand urban watershed located in an arid climatic region of Iran. Thus, a Markovian approach based on two suitability and transition potential mappers, i.e. fuzzy analytic hierarchy process and artificial neural network-multi layer perceptron was used to simulate land use map. Validation metrics, quantity disagreement, allocation disagreement and figure of merit in a three-dimensional space were used to perform model validation. Utilizing the fuzzy-analytic hierarchy processsimulation of total landscape in the target point 2015, quantity error, the figure of merit and allocation error were 2%, 18.5% and 8%, respectively. However, Artificial neural network-multi layer perceptron simulation led to a marginal improvement in figure of merit, i.e. 3.25%.