مقایسه الگوریتم‌های شبکه عصبی مصنوعی و حداکثر احتمال در آشکار‌سازی تغییرات جنگل

محورهای موضوعی : سیستم اطلاعات جغرافیایی

پروین باقری فر ¹ , رضا بصیری ² , شهرام یوسفی خانقاه ³ , حمیدرضا پورخباز ⁴

1 - دانش آموخته کارشناسی ارشد جنگلشناسی و اکولوژی جنگل دانشگاه صنعتی خاتم الانبیاء (ص) بهبهان، ایران. *(مسوول مکاتبات)
2 - دانشیار گروه جنگلداری دانشگاه صنعتی خاتم الانبیاء (ص) بهبهان، ایران.
3 - استادیار گروه مرتع و آبخیزداری دانشگاه صنعتی خاتم الانبیاء (ص) بهبهان، ایران.
4 - دانشیار گروه محیط زیست دانشگاه صنعتی خاتم الانبیاء (ص) بهبهان، ایران.

تاریخ دریافت : 1402/06/12 تاریخ پذیرش : 1402/07/20 تاریخ انتشار : 1402/08/01

کلید واژه: تصاویر لندست, باغ‌ملک, سنجش‌ازدور, طبقه‌بندی, خوزستان,

چکیده مقاله :

زمینه و هدف: فن آوری سنجش‌ازدور در دنیای پیشرفته امروزی به عنوان یکی از مهم ترین و عمده ترین منابع داده های مکانی و موضوعی قلمداد می شود. در این مقاله هدف مقایسه دو روش جهت آشکار سازی تغییرات جنگل با استفاده از تصاویر ماهواره لندست می باشد. بدین منظور از تصاویر سال 1369 سنجنده TM ماهواره لندست و هم چنین تصاویر سال 1390 سنجنده ETM+ این ماهواره استفاده‌ شده است. روش بررسی: در طبقه بندی تصاویر، از روش طبقه بندی نظارت‌شده و الگوریتم حداکثر احتمال و شبکه عصبی مصنوعی به شیوه پرسپترون چندلایه استفاده گردید. یافته ها: بر اساس نتایج به دست آمده الگوریتم شبکه عصبی مصنوعی در مقایسه با حداکثر احتمال صحت کلی و ضریب کاپای بالاتری در هر دو تصویر (TM و ETM+) نشان داده است. پس از طبقه بندی، نقشه های استخراج‌شده از تصاویر TM و ETM+ به منظور آشکارسازی تغییرات روی هم گذاری شدند و نقشه تغییرات به دست آمد. بحث و نتیجه گیری: نتیجه نهایی تحقیق نشان می‌دهد که استفاده از داده های لندست همراه با داده های حاصل از آماربرداری قابلیت تهیه نقشه تغییرات جنگل را در منطقه موردمطالعه دارا می باشند.

چکیده انگلیسی:

Background and Objective: Remote Sensing Technology is considered one of the most important sources of spatial and thematic data in the developed world of today. The objective of this work is a comparison of two different methods of change detection in forests using Landsat images. Therefore, sensor Landsat TM images of 1990 and 2011 (ETM+) satellite images have been used. Material and Methodology: In the classification of images, the maximum likelihood algorithm, and artificial neural network to multilayer perceptron method were used. Findings: Evaluated results showed that the algorithm approach, the maximum likelihood overall accuracy, and kappa coefficient maps classified in TM image, respectively, are 96.72 and 0.96 percent and image ETM+ 98.02 and 0.97 percent, and the method of artificial neural networks, overall accuracy and kappa coefficient map classified, TM image was 98.22 and 0.97% and ETM+ image was 98.34and 0.97 percent respectively. Following TM and ETM+ classification maps to detect the changes were marked and the map changes obtained. Discussion and conclusion: The results of this study showed that using Landsat data along with data from have inventory capabilities of forest change mapping

منابع و مأخذ:

1. Sagheb-Talebi, K. Sajedi, T. Yazdian, F. 2004. View to Iranian Forests. Research Institute of Forest and Rangelands, 29p. (In Persian)


2. Laurance, F. Laurance, S. Ferreira, L. Merona, J. Gascon, C. Lovejoy, T. 1997. Biomass Collapse in Amazonian Forest Fragments. Science. Vol. 278(5340), pp.1117-1128.


3. Rasouli, A.A. 2008. Principles of Applied Remote Sensing with Emphasis on Satellite Images processing. Published by Tabriz University, Tabriz: 703p. (In Persian)


4. Jensen, J. R. 2005. Introductory Digital Image Processing: A RemoteSensing Perspective, Upper Saddle River, Prentice & Hall Pub. USA.


5. Boyd, D. S. Foody, G. M. Ripple, W. J. 2002. Evaluation of approaches for forest cover estimation in the Pacific Northwest, USA, using remote sensing. Applied Geography. Vol. 22, pp.375-392.


6. Sivanpillai, R. Smith, C.T. Srinivasan, R. Messina, M.G. Ben Wu, X. 2006. Estimation of managed loblolly pine stand age and density with Landsat ETM⁺ For. Ecol. and Manage, vol. 223, pp. 247-254.


7. Naseri, M.H. Shataee, S. and Habashi, H. 2022. Zoning of leaf burn percentage of tree canopy using UAV and Sentinel 2 images in Deland Forest Park, Golestan provinceAbstract. Journal of Wood and Forest Science and Technology, 29(4), pp.75-92. (In Persian) 22069/JWFST.2023.20939.2001


8. Naseri, F. 2002. Classification of forest type and estimation of their quantities parameters in arid and semiarid region using satellite data (case study: national park of Khabr – Kerman province), PH.D. university of Tehran, Faculty of Natural Resources, 202 p. (In Persian)


9. Pettrolli, N. Vik, J. Gaillard, J. 2005. Using the satellite- derive NDVI to assess ecological responses to environmental change. Journal of Trends in Ecology and Evolution.vol. 20 (9), pp.503-510.


10. Amiri, A. Chavooshi, S.H. Amini, J. 2007. Comparison of Three Satellite Image Classification Fuzzy, Neural Network and Minimum Distance. Geomatic Conference, National Cartographic Center, Tehran, pp. 21-37. 21-22 May.


11. Azizi Ghalati, S. 2015. Application of Artificial Neural Network and Ordinary least square regression in modeling land use change. Iranian Journal of Forest and Wooden products. Vol. 68 (1), pp. 16-1. (In Persian)


12. Sudhaker, S. Sridevi, G. Ramana, I. V. Venkateswara Rac, V. Raha, A. 1999. Thechniques of Classification for Landuse/Landcover with Special Reference to Forest Type Mapping in Jaldpara Wildlife Sanctuary, Jaldpaiguri District, West Bengal – a Case Study. Journal of the Indian Society of Remote Sensing. 27(4), pp.218-224.


13. Torahi, A. Chand Rai, S. 2011. Land cover classification and forest change analysis, using satellite imagingery (case study in Dehdez area of Zagros Mountain in Iran). Journal of geographical information system.vol. 3, pp.1-11.


14. Khoi, D.D. Murayama, Y. 2010. Forecasting areas vulnerable to forest conversion in the Tam Dao National Park Region, Vietnam. Remote Sensing.vol. 2 (5), 1249– 1272.


15. Niyaze, Y. Ekhtesase, M. R. Maleke nejad, H. Hosseini, S. Z. 2010. Comparison of twain method Maximum likelihood classification and Artificial Neural Networks in extraction Land use map (Case study: Ilam dam sphere). Iranian Journal of Geography and Development.vol. 8(20), pp.119-132. (In Persian)


16. Naseri, M.H. Shataee Jouibari, S. Mohammadi, J. and Ahmadi, S. 2019. Capability of Rapid Eye Satellite Imagery to Map the Distribution of Canopy Trees in Dashtebarm Forest Area of Fars Province. Ecology of Iranian Forest, 7(14), pp.58-69. (In Persian) 29252/ifej.7.14.58


17. Moradi, H. and Rezaei, V. 2021. Comparison of Land Use Type Classification Algorithms in the Land use Mappreparation Inzenouzchai Watershed. Degradation and Rehabilitation of Natural Land, 1(2), pp.80-88. (In Persian)


18. S. Niyazi, Y. Ebrahemi, H. 2013. Comparing efficiency algorithms classification artificial neural network and decision tree in land use layer Preparation using data ETM⁺ (Case study: Daresher Catchment, Ilam Province). Iranian Journal Geographical Space.vol. 13(44), pp. 47-72. (In Persian)


19. Zobeiri, M. Majd, R. 2011. An introduction to Remote Sensing Technology and its Application in of Natural Resources. 9 th Edition, University of Tehran Press, Tehran, 316p. (In Persian)


20. Feizizadeh, B. Helali, H. 2010. Comparison pixel-based, object oriented methods and effective parameters in Classification Land cover/ land use of west province Azerbaijan. Iranian Journal of physical of Geography Research.vol. 42 (71), pp.73-84. (In Persian)


21. Laliberte, A.S. Browning, D.M. & Rango, A. 2012. A comparison of three feature selection methods for object-based classification of sub-decimeter resolution UltraCam-L imagery. International Journal of Applied Earth Observation and Geoinformation, 15: 70–78.


22. Walker, R.T. Perz, S. Caldas, M. & Texeira da silva, L. G. 2002. Land use and Land cover change in Forest Frontire: The Role of Hosuehold Life Cycles. International Regional Science Review. Vol. 25(2), pp. 169–199.


23. Wright, G.G. Morrice, J.G. 1997. Landsat TM spectral information to enhance the landcover of Scotland, dataset. Int. J. Remote Sensing, 18(18), pp.1997 – 3834.


24. Soffianian, A. R. Mohamadi Towfigh, E. Khodakarami, L. Amiri, F. 2011. Land use mapping using artificial neural network (Case study: Kaboudarahang, Razan and Khonjin- Talkhab catchment in Hamedan province). Journal Iranian of Applied Remote Sensing & GIS Techniques in Natural Resource Science.vol. 2(1), pp. 1-13. (In Persian)


25. Alizadeh Rabiei, H. 1999. Remote Sensing, Principles and Applications. Published by Tehran Press, Tehran: 302p. (In Persian)


26. Mas, J.F. 2003. An Artificial Neural Networks Approach to Map Land Use/cover Using Landsat Imagery and Ancillary Data. Proceedings of the International Geosciences and Remote Sensing Symposium IEEE IGARSS 2003. Vol.10 (3), pp. 3498-3500.


27. Akbari, E. Ebrahemi, M. Amir ahmadi, A. 2013. Land use mapping of Sabzevar city using Maximum likelihood techniques and Artificial Multilayer Perceptron Neural Network. Journal of environment preparation.vol. 23, pp. 128-148. (In Persian)


28. Abd El-Kawy, O.R. Rod, J.K. Ismail, H.A. Suliman, A.S. 2011. Land use and land cover change detection in the western Nile delta of Egypt using remote sensing data. Applied Geography.vol. 31(2), pp. 483-494.


29. Amini, M.R. Shataee joubary, SH. Ghazanfari, KH, Mo’ayyeri, M.H. 2008. Assessment of changes in the scope of Zagros forests using aerial photographs and satellite images in Armardeh. Baneh. Journal of Agricultural Sciences and Natural Resources.vol. 15 (2), pp. 10-20. (In Persian)


30. Soosani, J. Zobeiri, M. Feghhi, J. 2009. Application of aerial photographs and satellite images for visualization of forest cover changes (Case study: Zagros forests, Iran). Iranian Journal of Forest and Poplar Research. Vol. 17(2), pp. 236-249. (In Persian)


31. Gholamalifard, M. Joorabian Shoushtari, S. Hosseini Kahnuj, H. Mirzaei, M. 2012. Modeling of land use changes in coastal areas of Mazandaran province using the LCM model in GIS. Environment Ecology.vol. 38, pp. 124-109. (In Persian)


32. Fauzi, Hussin, Y.A. Weir, M. A Comparison between Neural Networks and Maximum Likelihood Remotely Sensed Data Classifiers to Detect Tropical Rain Logged-cover Forest in Indonesia. Asian Conference on Remote Sensing, November 2001, Singapore, Singapore.


33. Neshat, A. 2002. Analysis and evaluation land use and land -cover changes using remote sensing data and geographic information systems in Golestan province, a master's thesis, Tarbiat Modares University: 115p. (In Persian)


34. Haghighi, M. 2003. Survey of changes in low land forest stands change in west of Guilan using satellite image, a master's thesis, Department of Forestry, Guilan University, Guilan, Iran. 98p. (In Persian)


35. Najjarlou, S. 2005. Investigation on Forest Expanse Change Detection, G Using Aerial Photos, Topography Maps, IRS-1D and ETM+ Data, a master's thesis, Gorgan University of Agriculture Sciences and Natural Resources, faculty of natural resources, 124 p. (In Persian)


36. Darvishi Boloorani, A. Rashidian, A. Jokar, J, 2012. Applications of remote sensing and GIS sciences and technologies in health system (Part I). Hakim Medical Journal.vol. 15(2), pp. 87-100. (In Persian)