Sustainable GIS Based-ANN's Solution for Landfill Suitability Analysis

Abstract:

Sustainable suitability analysis for landfill sites is an important and necessary issue for authorities of solid waste planning in the fast growing zones, due to the increasing complexity coming from dealing with various disciplines and requirement and the needy of satisfaction. A combination of geographic information systems including spatial analysis, and artificial neural network ANNs were employed in this study for decision-makers in the sustainable suitability analysis problems in Malaysia and GIS was used to manipulate and present spatial data. The GIS analysis reveals three distinct groupings based on actual conditions of the case study area, environmental factors, economic factors and social factors which are reflection of different factors contributing to the sustainable development. The result shown that ANNs has good information extraction and evaluation functions of the suitability value based on the exact relationship between the input criteria and the output landfill site data with high coefficient of determination (R²) which help decision-makers to analysis sustainable suitability for landfill sites.

• Periodical: Applied Mechanics and Materials (Volume 802)
• Pages: 537-542
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.802.537
• Online since: October 2015
• Authors: Sohaib K.M. Abujayyab*, Mohd Sanusi S. Ahamad, Ahmad Shukri Yahya, Maher Elbayoumi, Mutasem Sh. Alkhasawneh
• Keywords: Artificial Neural Network (ANN), GIS, Landfill, Suitability Analysis, Sustainable Development

References

[1] M.I. Yesilnacar et al., Municipal solid waste landfill site selection for the city of Şanliurfa-Turkey: an example using MCDA integrated with GIS. International Journal of Digital Earth, 5(2) (2011) pp.147-164.

DOI: 10.1080/17538947.2011.583993

[2] M. Ghobadi, R. Babazadeh and V. Bagheri, Siting MSW landfills by combining AHP with GIS in Hamedan province, western Iran. Environmental Earth Sciences, 70(4) (2013) pp.1823-1840.

DOI: 10.1007/s12665-013-2271-9

[3] M. Uyan, MSW landfill site selection by combining AHP with GIS for Konya, Turkey. Environmental Earth Sciences, 71(4) (2014) pp.1629-1639.

DOI: 10.1007/s12665-013-2567-9

[4] M. Conforti et al., Evaluation of prediction capability of the artificial neural networks for mapping landslide susceptibility in the Turbolo River catchment (northern Calabria, Italy). CATENA, 113(0) (2014) pp.236-250.

DOI: 10.1016/j.catena.2013.08.006

[5] E.J. Chua, M. Sahid and Leong, Sustainable municipal solid waste management and GHG abatement in Malaysia. ST-4: Green & Energy Management, 04(02) (2011) pp.1-8.

[6] B. Lal, S.S. Tripathy, Prediction of dust concentration in open cast coal mine using artificial neural network. Atmospheric Pollution Research, 3(2) (2012).

DOI: 10.5094/apr.2012.023

[7] M. Elangasinghe et al., A simple semi-empirical technique for apportioning the impact of roadways on air quality in an urban neighbourhood. Atmospheric Environment, 83 (2014) pp.99-108.

DOI: 10.1016/j.atmosenv.2013.11.005

[8] N.N.A. Tukimat, S. Harun, The projection of future rainfall change over Kedah, Malaysia with the statistical downscaling model. Malays. J. Civ. Eng, 23 (2) (2011) pp.67-79.

[9] S. Song, X. Zheng and F. Li. Surface water quality forecasting based on ANN and GIS for the Chanzhi Reservoir, China. in Information Science and Engineering (ICISE), 2010 2nd International Conference on. 2010. IEEE.

DOI: 10.1109/icise.2010.5689328

[10] Y. Li et al., Rainfall and earthquake-induced landslide susceptibility assessment using GIS and Artificial Neural Network. Natural Hazards and Earth System Science, 12(8) (2012) pp.2719-2729.

DOI: 10.5194/nhess-12-2719-2012

[11] K. Kawaguchi, A multithreaded software model for Backpropagation Neural Network applications, Department of Electrical and Computer Engineering [Master ] 2000 2000 [cited Master Of Science Available from: http: /wwwold. ece. utep. edu/research/webfuzzy/docs/kk-thesis/kk-thesis-html/node22. html.