Modelling land-cover changes using Multi-layer Perceptron Neural Network and Cellular Automata

سال انتشار: 1400
محل انتشار: پنجمین کنگره بین المللی توسعه کشاورزی، منابع طبیعی، محیط زیست و گردشگری ایران
کد COI اختصاصی: ICSDA05_219
زبان مقاله: انگلیسی
تعداد مشاهده: 370

نویسندگان

GIS MSc Student at School of Surveying and Geospatial Engineering, College of Engineering, University of Tehran, Tehran, Iran,

Parham Pahlavani

Assistant Prof. at School of Surveying and Geospatial Engineering, College of Engineering,University of Tehran, Tehran, Iran,

چکیده

Land use change monitoring is an essential factor in performing sustainable land development. In this paper, land-use changes have been modeled using spatial techniques, starting with Landsat satellite imagery to predict major changes in land cover in Victoria state, Australia. Implementing time series methodology on land cover maps and performing a combination of multilayer neural network and Markov chain in order to find changes in every pixel of the map, is the main approach of this paper. Therefore, land sate images in three periods of ۱۹۸۵, ۲۰۰۰, and ۲۰۱۵ have been formed, with two images for training the model and the last one for validation. Using the support vector machine (SVM) algorithm for producing land cover maps and classifying into ۱۸ classes of different land cover and then generating a potential transition map with a multi-layer perceptron, showing the intention of changing for each pixel of the map. The Markov chain model has been used to predict the ۲۰۱۵ land cover map and validating the actual ۲۰۱۵ land cover for calculating accuracy of the model, which recorded the value of kappa with ۸۲.۱۸% which determines a highly reliable model. At last, the ۲۰۳۰ land cover map with the performed model for land cover changes in Victoria state, Australia was predicted which showed a ۱۴% reduction in pasture and grassland land cover, ۲۱% growth in urban areas and ۲۳% increase in agricultural lands in ۲۰۳۰ proportion to ۱۹۸۵ land cover areas. Results showed that human activities have changed the natural environment in the Victoria state thus, monitoring and forming future plans for reaching a sustainable land use is essential.

کلیدواژه ها

Land-Use Change Prediction, Multi-layer Perceptron, Markov Chain, Cellular Automata

مقالات مرتبط جدید

اطلاعات بیشتر در مورد COI

COI مخفف عبارت CIVILICA Object Identifier به معنی شناسه سیویلیکا برای اسناد است. COI کدی است که مطابق محل انتشار، به مقالات کنفرانسها و ژورنالهای داخل کشور به هنگام نمایه سازی بر روی پایگاه استنادی سیویلیکا اختصاص می یابد.

کد COI به مفهوم کد ملی اسناد نمایه شده در سیویلیکا است و کدی یکتا و ثابت است و به همین دلیل همواره قابلیت استناد و پیگیری دارد.