Journal of Marine Science and Technology

Journal of Marine Science and Technology

utilization of neural network and Maximum Likelihood Algorithms in classification of satellite images to extract land cover bahmanshir and arvand coastal zone

Document Type : Original Manuscript

Authors
ziba batvandi 1
Ramin Alaie Ruozbahani 2
1 Department of general and basic science, Faculty of marine economy and management, khorrammshar university of marine science and technology.
2 Department of Environmental Planning, Faculty of Environment, University of Tehran
10.22113/jmst.2017.50789
Abstract
The main purpose of satellite image processing is preparing thematic and efficient maps, so choosing appropriate classification algorithm has important role in this case. In parametric methods such as maximum likelihood main problem is their dependence on the statistical distribution of input data. Artificial neural network is nonparametric classification method which is not dependent on any particular distribution and extract desired functions from within data. This study aimed to compare the efficiency of neural network and maximum likelihood to classify land cover Using Landsat Satellite Images. Determine classes and samples to classify land cover Using field operations, topographic maps, aerial photographs and maps were made and using the above information four classes vegetation cover, building, water and outdoor were selected. After applying two algorithms, the neural network and maximum likelihood on the Landsat 8 satellite image with OLI sensors, land cover map of the arvand coastal area was prepared. Multi-layer perceptron network neural network structure consists of three input neurons, seven intermediate neurons, and four output neurons. For network training, a back propagation algorithm has been used. with Kappa coefficient, the accuracy of the classification methods was evaluated. Based on the results, Artificial neural network method with kappa coefficient of 0.92 in comparison to maximum probability algorithm with kappa coefficient of 0.79 has a better performance in providing land cover map of the arvand coastal area which is due to Neural network is nonparametric and nonlinear.
Keywords
Land cover
Maximum Likelihood
Neural Network
Castal zone
Alaie roozbahani R. 2005. Evaluation of Neural Network and maximum likelihood Classification algorithms  for dryland cultivation using IRS satellite imagery. MS.Thesis. Faculty of  earth Science. Shaid chamran university, Iran.
Arkhi S. 2014. Preparation of land use map of Ilam Plain using artificial neural network, Backup vector machine and maximum likelihood. Commodore journal. 1(2): 30-43.
Brian W.S. and Michael B. 2011. Comparison of classification techniques to support land cover and land use analysis in tropical coastal  zones. Applied  geography. 31:525-532.
Darvishsefat A. 1998. Estimated accuracy of GIS database thematic maps. The 5th GIS Conference. Tehran.
Mas  J.F.  2003.  A artificial neural networks approach to map land use/cover using  landsat  imagery  and ancillary data .  Proceedings of the international geoscience and remote sensing symposium IEE IGARSS..vol5.
Mirzaiezadeh V, Niknejhad M, Mahdavi A. 2014. Comparison of two classification methods maximum likelihood and mahalanubis distance in Preparing a Forest Map. Fourth International Conference on Ecological and Botanical Tree. Sari.
Mountrakis G.I. and  Ogole.C. 2011. Support vector machines in remote sensing: a review. ISPRS journal of photogramemetry and remote sensing. 13:247-259.
 Murthy  C.S., Raju P. and  Brdrinath K.. 2003. Classification of wheat  crop with multi-temporal  images: performance of  maximum likelihood and artificial neural networks. Remote sensing. 24(23): 4871-4890.
Niazi Y., Ekhtesasi M., Malekinejhad H. and Hoseini Z.2010. Comparison of two classification methods maximum likelihood and artificial neural network in land use exploitation in Ilam dam area. Geography and development. 20: 119-132.
Lillesand T.M. and Kiefer R.W. 1994. Rmote sensing and image interpretation. Jhon weily and sons inc. new York, p749.
 Lizarazo I.  2006. Urban land cover and land use classification using high spatial resolution images and spatial metrics. Proceeding of 2nd workshop of the earsel  sig on land cover and land use.
 Paola  J. D. and  Schowengerdt R. A. 1997. The Effect of Neural- Network Structure on a Multispectral Land-Use/ Land-Cover Classification.
Rahdari V, Maleki najafababdi S, Rahnama M. 2011. Comparison of satellite image categorization methods for mapping and vegetation cover in arid and semi-arid regions. Geomatics conference. Tehran.
Turner,M. 1988. Change in landscape patterns in Georgia. Landscape Ecology,1(4):421-435.
Yousefi S., Tazeh M. and Mirzaie S. 2014. Comparison of Different Classification Algorithms in Preparation of Land Use Map. Remote Sensing and Geographic Information Systems in Natural Resources. 5(3): 67-76. 
Yuan F., Sawaya K.E., Loeffelholz B.C. and Bbauer M.E. 2005. Landcover classification and change analysis of twin cities metropolitan area by multitemporal landsat remote sensing. Remote sensing of  environment. 98(2):317-328.
Zahedifard KH., Jalalian N. and Jamalaldin A. 2004. Application of digital data of TIM sensor in preparation of land use map in bazoft river  Basin. Journal of Agricultural and natural resources  Science and Technology.8(2).

  • Receive Date 18 December 2016
  • Revise Date 03 October 2017
  • Accept Date 08 October 2017
  • Publish Date 20 April 2020