MODELING AND SIMULATING LAND USE/COVER CHANGE USING ARTIFICIAL NEURAL NETWORK FROM REMOTELY SENSING DATA

Cerne

Endereço:
Departamento de Ciências Florestais, Universidade Federal de Lavras, Caixa Postal 3037
Lavras / MG
0
Site: http://www.dcf.ufla.br/cerne
Telefone: (35) 3829-1706
ISSN: 1047760
Editor Chefe: Gilvano Ebling Brondani
Início Publicação: 31/05/1994
Periodicidade: Trimestral

MODELING AND SIMULATING LAND USE/COVER CHANGE USING ARTIFICIAL NEURAL NETWORK FROM REMOTELY SENSING DATA

Ano: 2019 | Volume: 25 | Número: 2
Autores: Ender Buğday, Seda Erkan Buğday
Autor Correspondente: Ender Buğday | enthere@gmail.com

Palavras-chave: Computational intelligence, Human population, Landscape Forecasting

Resumos Cadastrados

Resumo Inglês:

Increasing population, mobility and requirements of human beings have significant effects on the dynamics of land use and land cover. Today, these impacts need to be understood and analyzed for the applicability of decision support systems, which are an important tool in the management of natural resources, urban and rural areas. The aim of this study is to detect the temporal and spatial changes of land cover and human population, in northwest Turkey. For this purpose, using satellite images of 1997-2007 and 2017 years’ land cover was estimated for 2027 by ANN (Artificial Neural Network) approach. Kappa values are 93%, 87% and 95% for 1997, 2007 and 2017 respectively. As a result, learning success was 80.6%, and correctness validation value was 90.1% for 2027 simulation. In parallel, the spatial analysis of the population was conducted for 2000-2007-2017. Using the exponential rate of change; the population was predicted to increase by concentrating on the urban area and the rural areas surrounding the urban (with a rate of 2.019%) for 2027. According to the results; rural population, urban population, forest, and built-up areas is estimated to increase by 4.14%, 5.58%, 2.72%, and 0.77% respectively from 2017 to 2027, while the agricultural and water area is estimated to decrease by 3.47% and 0.02% respectively. Consequently, the observation of population movements and the use of the ANN approach in simulations could be suggested for the success of planning in forest and land management