Comparing Maximum Likelihood and Fuzzy Classification Methods for Mapping Land Cover (Case Study: Behshahr urban Catchment)
Subject Areas : landuseKebriya jafari 1 , marziyeh alikhah-asl 2 , Yahya Kooch 3
1 - M.S. student, Environmental field (trend: assessment and land use planning), Payame Noor university, Tehran, Iran.
2 - Assistant professor, Department of Agriculture and Natural Resources, Payame Noor University, Tehran, Iran. *(Corresponding Author)
3 - Assistant professor of forestry, Natural resources faculty, Tarbiat Modares university, Noor, Iran.
Keywords: Behshahr, Maximum likelihood, Fuzzy, Remote Sensing.,
Abstract :
Background and Objective: Land use maps are one of the most important maps for land use planning which is being prepared using satellite images. Land use classification of satellite images is one of remote sensing utilities and Now days, different classification methods have been expanded for mapping land cover that have different accuracies. The aim of this research is to Compare Maximum Likelihood and Fuzzy Classification Methods for mapping land use in Behshar urban catchment located in Mazandaran province.
Material and Methodology: First OLI image for the year 2015 was prepared and after geometric and elevation corrections, image was classified using maximum likelihood and Fuzzy methods in Erdas Imagine software. Kappa and overall accuracy indexes were used to calculate classification accuracy. Findings: Based on results, in both methods Broad-leaved tree area involve most part of the area while urban area is the lowest. Also results showed Maximum likelihood method with kappa 0.87 and overall accuracy 89.52% in comparison with Fuzzy method with kappa 0.86 and overall accuracy 88.57% has better classification accuracy.
Discussion and Conclusion: Results show despite high capability of Landsat images in mapping land use, it is necessary to land mapping using the best classification method resulted from comparing different classification accuracies.
1. Khosrovani, Z., Khajeddin, S.J., Safyanian, A., Mohebbi. M., Parsamahr, A. 2012. Landslide Land Use Using IRS-P6 Satellite, Journal of Science and Technology of Agriculture and Natural Resources, Water and Soil Science, Year 16, Number 59, P 233-244. (In Persian)
2. Ghorbani, M., Nazari-Samani, A.A., Kohanbani, H.R., Akbari, F., Jalili-Parvaneh, Z. 2010. Evaluation of land use change trend in Taleghan watershed, The 4th International Congress of Geographers of the Islamic World. (In Persian)
3. Taghizadeh- Ghalejoghi, S., Masomi, M. 2012. Study of land use changes in Naghade County using remote sensing and geographic information system (RS & GIS), Sepehr Journal, Volume 21, Issue 84, P 59-65. (In Persian)
4. Sarmad Dashti, Latif., Nur Alyaa Binti, Hazrin., Chai Hoon, Koo., Jing Lin, Ng., Barkha, Chaplot., Yuk Feng, Huang., Ahmed, El-Shafie., Ali Najah, Ahmed. 2023. Assessing rainfall prediction models: Exploring the advantages of machine learning and remote sensing approaches. Alexandria Engineering Journal, vol.82, pp.16-25.
5. Kate Altemus, Cullen., 2023. A review of applications of remote sensing for drought studies in the Andes region. Journal of Hydrology: Regional Studies. Vol.49, pp101483.
6. Ghorbani, R., Taghipor, A.A., Mahmodzadeh, H. 2012. Evaluation and analysis of land use changes in the area of the international wetlands Alla Gol, Alma Gholagh AJ Gol Turkmen Sahra using multi-temporal satellite imagery, Geography and Environmental Planning, Year 23, Series 48, Number 4. P 168-186. (In Persian)
7. Mazaheri. M.R., Esfandiyari, M., Masihabadi, M.H., Kamali, A. 2014. Monitoring of Land Use Time Changes Using Remote Sensing Techniques and Geographic Information Systems (Case Study: Jiroft, Kerman Province). Remote Sensing Application and GIS in Natural Resources Science, 4 (2): p 25-39. (In Persian)
8. Uosefi, S., Tazeh, M., Mirzai, S., Moradi, H.R., Tavangar, SH. 2011. Comparison of Different Satellite Image Categorization Algorithms in Land Use Mapping (Case Study: Noor City). Application of Remote Sensing and GIS in Natural Resources Science, No. 2, P 15-25. (In Persian)
9. Alikhah-Asl, M., Forotan, E. 2013. Using Fuzzy Classification Method for Land Use Mapping (Case Study: Hablehrood Watershed Basin). Human and Environment Quarterly, No. 24, Spring 2013. (In Persian)
10. Alikhah-Asl, M., Naseri, D. 2022. Preparing Ghoorichay Catchment Land Cover Map Using Satellite Image Analysis, Human and Environment, No. 60, pp. 93-104 (In Persian).
11. Salimi, Kh., Ahmadi Sani, N., Jalilnejad, N. 2019. Mapping Soil Salinity Using Remote Sensing Technology (Case Study: South Lands of West Azarbaijan province), Danesh Water and Soil Science, Vol. 29, pp. 115 – 128. (In Persian).
12. Moghani Rahimi, F., Mazidi, A., Ghafarian Malamiri, H.M. 2022. An investigation of urban development and land cover changes in abarkoh city combining bands from landsat 7 and 8 satellite images, geographical Data (sepehr), vo.31, N0.121, pp.127-141 (In Persian)
13. Zhao, Y., Duole, F., Le, Y., Xiaoyi, W., Yanlei, C., Yuqi, B., Hernández, J., Galleguillos, M., Estades, C., Biging, G., Radke, J., Peng, G., 2016, Detailed dynamic land cover mapping of Chile: Accuracy improvement by integrating multi-temporal data, Remote Sensing of Environment, Remote Sensing of Environment 183 (2016), Pp 170–185.
14. Aghaloo, K., Ali, T., Chiu, Y., Sharifi, A, 2023. Optimal site selection for the solar-wind hybrid renewable energy systems in Bangladesh using an integrated GIS-based BWM-fuzzy logic method, Energy Conversion and Management, Vol. 283.
15. Department of Natural Resources and Watershed of Mazandaran Province, Department of Engineering and Studies, Spring Access Date 2016. (In Persian)
16. Waseem, M., Paul, H., Jeffrey, G., Boshra, H., Salem, B., 2015. Land use/land cover change detection and prediction in the north-western coastal desert of Egypt using Markov-CA.
Applied Geography, 63 (2015), Pp 101-112.
17. Aslami, F., Ghorbani, A., Sobhani, B., Panahandeh, M. 2015. Comparison of artificial neural network, supporting and object-oriented vector machines in land use and land cover from Landsat 8, Application of Remote Sensing and GIS in Natural Resources Science, 6 (3): P 1-14. (In Persian)
18. Kun, J., Shunlin, L., Ning, Zh., Xiangqin, W., Xingfa, G., Xiang, Zh., Yunjun, Y., Xianhong, X. ,2014. Land cover classification of finer resolution remote sensing data integrating temporal features from time series coarser resolution data. ISPRS Journal of Photogrammetry and Remote Sensing, 93 (2014), Pp 49–55.
19. Tolaii, S and Haji-Norozi, N. 2006. Preparing the mapping of Pakdasht lands using RS and GIS, Geospatial Journal, vol. 5, p. 6 and 7: pp. 27-40 (In Persian).
20. Yuan, F.K.E., Sawaya, B.C., Loeffelholz, M. E., 2005. Land cover classification and change analysis of the Twin (Minnesota) Metropolitan Area by multi temporal Landsat remote sensing. Remote sensing of Environment, 95: 317-328.
21. Alavipanah, S.K., Valdani, M. 2010. Remote Sensing and GIS, Tehran University Press, Iran, 149-153 (In Persian).
22. ERDAS. 2007, Erdas Field Guide, Volume Tow, pp.138-139.
23. Xiao, T.Y., Huiping, L.X., 2015. Land cover changed object detection in remote sensing data with medium spatial resolution. International Journal of Applied Earth Observation and Geo information, 38, (2015), Pp 129–137.
24. Mathers, P. 2005, Computer Processing of Remotely- Sensed Images. John Wiley & Sons, 345 pp.
