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

Publish Year: 1400
نوع سند: مقاله کنفرانسی
زبان: English
View: 257

This Paper With 11 Page And PDF Format Ready To Download

  • Certificate
  • من نویسنده این مقاله هستم

این Paper در بخشهای موضوعی زیر دسته بندی شده است:

استخراج به نرم افزارهای پژوهشی:

لینک ثابت به این Paper:

شناسه ملی سند علمی:

ICSDA05_219

تاریخ نمایه سازی: 4 مهر 1400

Abstract:

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.

Authors

Mohammad Esmaeili

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,