مقایسۀ کارآیی الگوریتم‌های‌ ماشین‌ بردار پشتیبان و حداکثر احتمال در آشکارسازی تغییرات کاربری اراضی (مطالعۀ موردی: حوضۀ آبخیز سیمینه‌رود)

نوع مقاله : علمی - پژوهشی

نویسندگان

1 کارشناس ارشد مهندسی آبخیزداری، دانشکدۀ منابع طبیعی دانشگاه تربیت مدرس، نور

2 استادیار گروه اقتصاد محیط‌زیست، دانشگاه آزاد اسلامی، علوم و تحقیقات، تهران

چکیده

با توجه به اینکه الگوریتم‌های متنوعی برای طبقه‌بندی تصاویر ماهواره‌ای در سنجش از دور توسعه یافته‌اند، انتخاب الگوریتم مناسب طبقه‌بندی در دستیابی به نتایج صحیح نقش بسیاری ایفا می‌کند. به همین منظور در پژوهش حاضر، با مقایسۀ کارآیی صحت طبقه‌بندی دو الگوریتم حداکثر احتمال و ماشین‌های بردار پشتیبان، الگوریتم دقیق‌تر تعیین، و از آن برای بررسی روند تغییرات کاربری اراضی استفاده شد. تحقیق حاضر در حوزۀ آبخیز سیمینه‌رود و با استفاده از تصاویر سنجنده‌های TM، ETM+ و OLI انجام گرفت. نتایج تحقیق نشان داد که الگوریتم ماشین بردار پشتیبان، درمقایسه با الگوریتم حداکثر احتمال، تصاویر ماهواره‌ای را بهتر طبقه‌بندی کرده است و از میان کرنل‌های ماشین بردار، کرنل تابع پایۀ شعاعی (RBF) کارآیی بهتری داشته است. بنابراین، از الگوریتم ماشین بردار پشتیبان با کرنل تابع پایۀ شعاعی برای تهیۀ نقشۀ کاربری اراضی دوره‌های مورد بررسی و تغییرات کاربری استفاده شد. بررسی روند تغییرات کاربری اراضی، با استفاده از این کرنل، مشخص کرد که در طی دوره‌های بررسی‌شده، مساحت کاربری‌های زراعت آبی از 30.535 هکتار به 67.210 هکتار، زراعت دیم از 79.909 هکتار به 123.383 هکتار و مناطق مسکونی از 474 هکتار به 1934 هکتار افزایش یافته است درحالی‌که مراتع از 259.811 هکتار به 178.398هکتار، و منابع آب از 240 هکتار به 41 هکتار روند کاهشی دارند. 

کلیدواژه‌ها


عنوان مقاله [English]

Efficiency Comparison of Support Vector Machine and Maximum Likelihood Algorithms for Monitoring Land Use Changes

نویسندگان [English]

  • A Daneshi 1
  • M Panahi 2
1 M.Sc. of Watershed Management Engineering, Faculty of Natural Resources, Tarbiat Modares University, Nour
2 Assistant Prof., Science and Research Branch, Islamic Azad University, Tehran
چکیده [English]

Because the various algorithms have been developed for the land use classification by using remote sensing, the suitable algorithm selection plays an important role in achieving good results. For this purpose, by efficiency comparison of two algorithms classification i.e. support vector machines (SVM) and maximum likelihood (ML), the more precision method was determined and it was used for investigating land use changes trend. The present research was carried out using TM, ETM+ and OLI sensors images in Siminehroud watershed. The research results showed that SVM algorithm classified satellite images better than ML algorithm and radial basis function (RBF) kernel has the highest overall accuracy among the studied methods. Therefore, SVM algorithm with RBF kernel was used to derive land use maps and monitor land use changes in the studied periods. By analysis of land use changes trend using this kernel, it was found that during studied periods, irrigated farming from 30535ha to 67210ha, dry farming from 79909ha to 123387ha, residential from 474ha to 1934ha land uses have been increased but rangeland from 259811ha to 178397ha and water resources from 30535ha to 67210ha land uses are decreasing

کلیدواژه‌ها [English]

  • Satellite images
  • Support vector machines algorithm
  • Maximum likelihood
  • Land sue
  1. Al-Ahmadi, F.S., Hames S.A., 2009, Comparison of Four Classification Methods to Extract Land Use and Land Cover from Raw Satellite Images for Some Remote Arid Areas, Kingdom of Saudi Arabia, JKAU, Earth Science, Vol. 20, No. 1, PP. 167-191.
  2. Alavipanah, S.K., 2003, Application of Remote Sensing in Geosciences, Tehran University Press.
  3. Arekhi, S., Adibnejad, M., 2011, Efficiency Assessment of the of Support Vector Machines for Land Use Classification Using Landsat ETM+ Data (Case Study: Ilam Dam Catchment) (In Persian), Iranian Journal of Range and Desert Reseach, Vol. 18, No. 3, PP. 420-440.
  4. Barkhordary, J., Zare Mehrjuei, M., Khosroshahi, M., 2005. Assessment of Land Cover Change in Minab Esteghlal Dam's Watershed Using GIS and RS (In Persian), Soil Conservation and Watershed Management, Vol. 1, No. 2, PP. 59-64.
  5. Billah, M., gazi, R., 2004, Land Cover Mapping Khulna City Applying Remote Sensing Technique, proc., 12 Conf. on Geoinformation Research,Bridging the Pocific and Atlantic, Univesity of Gavel, Swen ,7-9 june 2004.
  6. Bonyad, A.A. & Hajighaderi, T., 2007, Producing Natural Forest Maps of the Zanjan by Using ETM+ Data of Landsat 7 Satellite (In Persian), Science and Technology of Agriculture and Natural Resource, Water and Soil Science, Vol. 11, No. 42, PP. 627-638.
  7. Chen, J., Gong, P., He, C., Pu, R. & Shi, P., 2003, Land-Use/Land-Cover Change Detection Using Improved Change-Vector Analysis, Photogrammetric Engineering and Remote Sensing, Vol. 69, No. 4, PP. 369-380.
  8. Congcong, L., Jie, W., Lei, W., Luanyun, H. & Peng, G., 2014, Comparison of Classification Algorithms and Training Sample Sizes in Urban Land Classification with Landsat Thematic Mapper Imagery, Remote Sens., Vol. 6, No. 2, PP. 964-983.
  9. Dixon, B. & Candade, N., 2008, Multispectral Land Use Classification Using Neural Networks and Support Vectormachines: One or the other, or Both?, International Journal of Remote Sensing, Vol. 29, Issue 4, PP. 1185–1206.
  10. Feyzizadeh, B., Azizi, H. & Valizadeh, K.KH., 2007, Extraction Land Uses Malekan City Using Satellite Images ETM+ (In Persian), Amayesh, Vol. 2, No. 3, PP. 1-10.
  11. Goudarzimehr, S., Abbaspour, R.A., Ahadnejhad, V. & Khakbaz, B., 2012, Comparison of SVM with ANN and Maximum Likelihood Methods for Identification of Lithology (In Persian), Iranian Journal of Geology, Vol. 6, No. 22, PP. 75-92.
  12. Gualtieri, J.A. & Cromp, R.F., 1998, Support Vector Machines for Hyperspectral Remote Sensing Classification, In: Proceedings of the 27th AIPR Workshop: Advances in Computer Assisted Recognition, Washington, DC, 27 October, SPIE, Washington, DC, PP. 221-232.
  13. Huang, C., Davis, L.S. & Townshend, J.R.G., 2002, An Assessment of Support Vectormachines for Land Cover Classification, International Journal of Remote Sensing, Vol. 23, Issue 4, PP. 725-749.
  14. Hussaina, M., Chen, D., Cheng, A., Wei, H. & Stenley, D., 2013, Change Detection from Remotely Sensed Images: From Pixel-Based to Object-Based Approaches, ISPRS Journal of Photogrammetry and Remote Sensing, Vol. 80, PP. 91-106.
  15. Keshavarz, A. & Ghassemian, H., 2005, Hierar-chical classification of hyperspectral images by using SVMs and same class neighborhood property, in proc. of IEEE International Geoscience and Remote Sensing Symposicm IGRSS 2005, pp.3219-3222, Jul, 2005.
  16. Lausch, A. & Herzog, F., 2002, Applicability of Landscape Metrics for the Monitoring of Landscape Change: Issues of Scale, Resolution and Interpretability, Ecological Indicators, Vol. 2, PP. 3-15.
  17. Mohaggeg, M.H., 2002, Reducing on the Water Level of Urmia Lake, Future View and Recomondations, Urmia Lake and its Potentials to Development, Urmia University Publishing.
  18. Mountrakis, G., Im, J. & Ogole, C., 2011, Support Vector Mmachines in Remote Sensing: A Review, ISPRS Journal of Photogrammetry and Remote Sensing, Vol. 66, Issue 3, PP. 247-259.
  19. Omidipour, R., Moradi, H.R. & Arekhi, S., 2014, Comparison of Pixel-Based and Object-Oriented Classification Methods in Land Use Mapping Using Satellite Data (In Persian), RS & GIS Iran, Vol. 5, No. 3, PP. 99-110. (In Persian)
  20. Petropoulos, G.P., Kalaitzidis, C. & Vadrevu, K.P., 2012, Support Vector Machines and Object-Based Classification for Obtaining Land-Use/Cover Cartography from Hyperion Hyperspectral Imagery, Computers & Geosciences, Vol. 41, PP. 99-107.
  21. Rahdari, V., Maleki Najafabadi, S. & Rahnema, M., 2008, Comparison of Supervised and un supervised Satiate Image Classification Methods in Producing Land Use and Land Cover Maps of Arid and Semi-Arid (In Persian), National Conference of Geomatic 88, Tehran.
  22. Rasouli, A.A., 2008, Principles of Applied Remote Sensing with Emphasis on Satellite Image Processing (In Persian), Tabriz University Press.
  23. Reger, B., Otte, A. & Waldhardt, R., 2007, Identifying Patterns of Land-Cover Change and their Physical Attributes in a Marginal European Landscape, Landscape and Urban Planning, Vol. 81, No. 1-2, PP. 104- 113.
  24. Rezaei Zaman, M., Morid, S. & Delavar, M., 2014, Impact of Climate Change on Water Resources on Simineh Rud Basin and its Inflows to Lake Urmia (In Persian), Journal of Water and Soil, Vol. 27, No. 6, PP. 1247-1259.
  25. Serra, P., Pons, X. & Sauri, D., 2008, Land-Cover and Land-Use Change in a Mediterranean Landscape: A Spatial Analysis of Driving Forces Integrating Biophysical and Human Factors, Applied Geography, Vol. 28, No. 3, PP. 189- 209.
  26. Shalaby, A. & Tateishi, R., 2007, Remote Sensing and GIS for Mapping and Monitoring Land Cover and Land-Use Changes in the Northwestern Coastal Zone of Egypt, Applied Geography, Vol. 27, No. 1, PP. 28-41.
  27. Shetaee, Sh. & Abdi, O., 2007, Land Cover Mapping in Mountainous Lands of Zagros Using ETM+ Data Case Stady: Sorkhab Watershed (In Persian), Lorestan Province, Agricultural Science and Natural Resource, Vol. 14, No. 1, PP. 129-138.
  28. Sonmez, N.K. & Sari, M., 2007, Monitoring Land Use Change in the West Mediterranean Region of Turkey: A Case Study on Antalya-Turkey Coast, Fresenius Environmental Bulletin, Vol. 16, No. 1A, PP. 1325-1330.
  29. Van, Oort, P.A.J., 2007, Interpreting the Change Detection Error Matrix, Remote Sensing of Environment, Vol. 108, No. 1, PP. 1-8.
  30. Yang, X. & Lo, C., 2002, Using a Time Series of Satellite Imagery to Detect Land Use and Land Cover Changes in the Atlanta, Georgia Metropolitan Area, International Journal of Remote Sensing, Vol. 23, Issue 9, PP. 1775-1798.
  31. Yao, X., Tham, L.g. & Dai, F.C., 2008, Landslide Susceptibility Mapping Based on Support Vector Machine: A Case Study on Natural Slopes of Hong Kong, China, Geomor-phology, Vol. 101, PP. 572-582.