Detect changes land cover and forest surfaces Mangrove in Gando protected area using maximum likelihood method and artificial neural network

Knowledge of changes in forest cover and environmental considerations has always been one of the most important actions in the world.Mangrove deforestation, forested shores land use changes to the facility also oil pollution and changing in the sea-shore hydrodynamics is the most important factors threatening the plant reserves. Gulf of Goutr in the extreme south-eastern Iran, and almost half of them belong to Pakistan. Satellite imagery and image processing techniques are very accurate tools for survey and assessment of changes in forest areas. This study aimed to detect changes in forest cover area is protected Gando .To gain this goal using the information and topographic maps, satellite imagery of 1972-1995 and 2015 tests are maximum likelihood, neural networks were used. The results show that artificial neural networks with general accuracy of 98/32% and kappa coefficient0/9781 and Maximum likelihood method with general accuracy of 92/45% and kappa coefficient is 90/01. The result is a more accurate method method artificial neural network to the maximum likelihood method in the preparation of the land cover map. According to remoteness and low population area was expected certain changes have not occurred in the area.After the investigation it was found dense forests and scattered Mangrove total surface area of 1972 sq km of 24/0 that the amount in 1995 to 4.1 sq km to 2.4 sq km and in 2015 reached.Therefore, any planning of coastal zone management and the management of wildlife and vegetation of the Gando protected natural area is should be based on and, nvironmental and natural considerations.So that to preserve the natural heritage of the region to exploit the maximum possibilities of the region to improve the livelihood of the inhabitants of this remote region of the country.