کاربرد تصاویر ماهواره‌ای لندست و الگوریتم شبکه عصب مصنوعی در بررسی تغییرات کاربری اراضی حوضه سد ایلام

نویسندگان

1 دانشگاه پیام نور

2 دانشگاه ساری

10.22052/deej.2018.7.19.25

چکیده

احداث سدهای بزرگ اثرات محیطی مهمی در محیط اطراف داشته و یکی از مهم­ترین آن­ها، تغییرات پوشش اراضی می‌باشد. از طرفی شناسایی تغییرات زمانی کاربری اراضی پایه‌گذار شناخت بهتری از روابط‌ و اثرات متقابل انسان و منابع اراضی به ما داده و موجب مدیریت و استفاده پایداری از این منابع می‌گردد. هدف از این مطالعه بررسی روند تغییرات کاربری اراضی حوضه سد ایلام که یکی از بزرگترین سدهای استان ایلام می‌باشد، در طی دو دوره قبل و بعد از احداث سد تاکنون است. در این مطالعه به منظور تشخیص تغییرات کاربری های حوضه سد ایلام ، ابتدا با استفاده از تصاویر ماهواره‌ای لندست و الگوریتم طبقه‌بندی شبکه عصب مصنوعی، نقشه کاربری اراضی حوضه در طی سال‌های 1368، 1379 و 1396 تهیه گردید. جهت طبقه‌بندی تصاویر ماهواره‌ای از الگوریتم شبکه عصب مصنوعی استفاده شد. در ساختار شبکه، نمونه‌های آموزشی از طریق لایه ورودی وارد شبکه می‌شوند و بعد از ضرب شدن در وزن‌های ارتباط دهنده نرون‌ها وارد لایه میانی می‌شوند. این عمل آن‌قدر تکرار می‌شود تا مقادیر وزن بهینه شده و میزان خطا به حداقل ممکن تعیین شده برسد. سپس با استفاده از روش مقایسه پس از طبقه‌بندی به تعیین روند تغییرات کاربری اراضی در طی دو دوره زمانی پرداخته شد. نتایج نشان داد که صحت نقشه‌های کاربری اراضی سال‌های مختلف بیش از 85 درصد است که نشان­دهنده قابل اعتماد بودن این نقشه‌هاست. همچنین مطابق نتایج در طی دو دوره زمانی مذکور و همچنین دوره کلی 28 ساله، سطح کاربری جنگل و اراضی بایر کاهش یافته و سطح کاربری­های دریاچه، مرتع، مسکونی، زراعت دیم و باغ افزایش یافته است.
 

کلیدواژه‌ها


عنوان مقاله [English]

Application of Landsat satellite images and artificial neural network algorithm in study of land use changes in Ilam dam basin

نویسندگان [English]

  • Adel Soltani 1
  • Milad Soltani 2
1
2
چکیده [English]

Introduction: Population growth has increased the pressure on natural environment, and unsustainable exploitation and the land use changes have damaged ecosystems. Consequently the need for food and water has led humans to devote more land to cultivate and use it under his control. Indeed, remote sensing satellites are the most common source of data for identifying, quantifying and mapping for patterns of land use change. Therefore, detecting land use changes using remote sensing data in the GIS environment can provide a good understanding of how land use changes are made, and present appropriate solutions in management. In the meantime, Landsat satellite imagery has the potential to detect land-use changes, land cover and modeling due to the proper location resolution and long-term archiving of images. There are several methods for discovering variations that in the meantime, the past classification comparison method is highly common. This method was first used by Gordon (1980).
Materials and methods: So far, many studies have been conducted on land use monitoring using different data, methods and algorithms. The aim of this study is discover the land use change trend during the two periods before and after the dam construction. So, in this study, in order to identify the dam construction effects in changing the dam basin, Ilam dam which is one of the largest dams in Ilam province, has been investigated. First by using Landsat satellite imagery and Artificial Neural Network classification algorithm, the land use map of the basin was prepared in the years of 1989, 2000, and 2017. Satellite data can play an effective role in providing land cover mapping, because of its specific features including wide coverage, repeatability, multi-spectrum, diversity and land cover, and continuous upgrading. Landsat satellite imagery has the high potential to identify land cover, land-use changes and modeling due to the strong archive and high temporal resolution. In this study, for providing land use change for different years have used of TM sensor images on 14/5/1989 and 28/5/2000, as well as OLI sensor on the 11/5/2017. In order to discover land use changes due to the construction of the dam, using the past classification comparison method, land use changes were determined during two periods. 7 species land use including lake, forest, pasture, dry land farming, garden, residential and barren lands were used for classification by surveying the study area. Gathering data about the changes required the use of techniques and tools that can scan large areas at a cost effective and short-term. Change detection is one of the major applications of remote sensing. Accordingly, various digital methods have been developed for change detecting in land covers. The main factors for the successful implementation of change detecting are selecting the appropriate dates for image acquisition and the use of accurate detection methods. In the changes detection to eliminate the effects of external sources such as the angle of the sun and the seasonal and geological differences, the spectral reflection of the data should be similar. The data used should be at a similar time interval (in terms of season and month), and on the other hand, be in the appropriate seasons. Because of the difference in weather conditions in two different times, the difference between the calibrations of the sensors, the humidity and exposure conditions can affect the numbers and the digital image of two different times. For this purpose, the images used in this study were selected in late of May and early of June. As Mather (2005) states, atmospheric corrections in remote sensing surveys is necessary; especially in cases where the goal is to determine variations in different periods. Because the effects of the atmosphere reduce the contrast between objects and reduce the contrast of the image, and it actually causes the problem of extraction of information. For this reason COST method was used to reduce atmospheric effects.
 Result: The results of this study showed that the forests have decreased by about 10354.79 ha during a 28-year period; In other words, during this period, about 49% of the forest area in the studied area was lost, which represents an annual degradation of about 369.82 hectares, equivalent to a degradation rate of about 1.75%.
Discussion and Conclusion: The results showed that the accuracy of land use maps of different years is more than 85%, which indicates the reliability of these maps. Also, according to the results during the two mentioned periods, as well as the general period of 28 years, the area of forest land and barren lands has decreased and the level of lake use, rangeland, residential, dry farming and garden has increased. The results of this study are consistent with Rahmani et al. (2013), Arokhi and Niazi (2013) and Saghafian et al. (2007). According to the FAO statistics for the years 1990 to 2000, the annual degradation level of forest land has been estimated at 0.2% per annum worldwide. The most important reason for decreasing the area of forests in the studied area is the development of the phenomenon of oak decline. This phenomenon, which has strongly affected the forests of the west of the country during the last decade, is considered one of the most important environmental problems in the country and has destroyed thousands of hectares of western forests in the country. One of the provinces that is heavily exposed is Ilam province (Karami et al., 2018).

کلیدواژه‌ها [English]

  • Dam
  • change detection
  • land use
  • Artificial Neural Network
  • Ilam
1. Abd El-Kawy, O.R., Rod, J.K., Ismail, H.A. and Suliman, A.S. 2011. Land use and land cover change detection in the western Nile delta of Egypt using remote sensing data. Applied Geography, 31(2): 483-494. 2. Ahmed, B. and Ahmed. R. 2012. Modeling urban land cover growth dynamics using multi-temporal satellite images: A case study of Dhaka, Bangladesh. ISPRS Int. J. Geo-Inf., 1: 3-31; doi:10.3390/ijgi1010003. 3. Arkhi, S. and niazi, Y. 2010. Evaluation of different remote sensing methods for monitoring land use change (Case study of Valley of Shahr-Ilam Province). Journal of Rangeland and Desert Researches of Iran, 17 (1): 74-93. 4. Chavez, P.S. 1996. An improved dark – object subtraction technique for atmospheric scattering of multispectral data, remote sensing of Environment, 24: 459 – 479. 5. Chuanga, W.C., Lina, C.Y., Chiena, C.H. and Choub, W.C. 2011. Application of Markov-chain model for vegetation restoration assessment at landslide areas caused by a catastrophic earthquake in Central Taiwan. Ecological Modelling, 222: 835- 845. 6. DeWitta, J.D., Chiricoa, P.G., Bergstresserb, S.E. and Warner, T.A. 2017. Multi-scale 46-year remote sensing change detection of diamond mining and land cover in a conflict and post-conflict setting. Remote Sensing Applications: Society and Environment, 8: 126–139. 7. Duke, J.R., White, J.D., Prochnow, Sh.J., Zygo, L., Allen, P.M. and Muttiah, R.S. 2007. The use of remote sensing and modelling to detect small-dam influences on land-use changes along downstream riparian zones. Journal of Ecohydrology and Hydrobiology, 7 (1): 23-35. 8. Fatemi, S.B. And Rezaei, Y. 2011. The basics of remote sensing. Omid Institute, Azadeh Tehran Publishing center. 268 p. 9. Karami, O. 2017. Monitoring and modeling the decline of Zagros oak forests using satellite images with high spatial resolution. Department of Forestry, Faculty of Natural Resources, University of Agricultural Sciences and Natural Resources, Sari, 126 p. 10. Karami, O., Fallah, A., Shtaeii, Sh. and latifi, H. 2017. Investigating the Possibility of Preparation of Zagros Oak Forests Dehumidification Map Using Worldview-2 Satellite Data (Case Study: Ilam Dam Forest). Journal of Forest and Poplar Researches of Iran, 25 (3): 452-462. 11. Kolehmainen, K. and Ban. Y. 2008. Multi Temporal SPOT images for urban land cover change detection over Stockholm Between 1986 and 2004, The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences. Vol. XXXVII. Part B6b. 12. Kotsiantis, S.B. 2007. Supervised Machine Learning: A Review of Classification Techniques. Informatica, 31: 249-268. 13. Lee S, Ryu J-H, Lee M-J, Won J-S. 2006. The application of artificial neural networks to landslide susceptibility mapping at Janghung, Korea. Mathematical Geology, 38(2): 199- 220. 14. Lu, D. and Weng, Q. 2007. A survey of image classification methods and techniques for improving classification performance. International Journal of Remote Sensing, 28 (5): 823–870. 15. Matakan, A.A., Saeidi, Kh., Shakiba, A.R. and Hosseiniasl., A. 2010. Evaluation of Land Cover Changes in Connection with Taleghan Dam Construction Using Remote Sensing Techniques. Journal of Applied Research of Geographic Sciences, 16 (19): 45-64. 16. Mazaheri, M.R., Esfandiari, M., Massihabadi, M.H. and Kamali, A. 2014. Monitoring of Land Use Time Changes Using Remote Sensing Techniques and Geographic Information Systems (Case Study: Jiroft, Kerman Province). Journal of Remote Sensing Applications and GIS in Natural Resources Science, 4 (2): 25-39. 17. Mendoza, M.E., Lopez, E., Geneletti, D., Pérez-Salicrup, D.R. and Salinas, V. 2011, Analyzing land cover and land use change processes at watershed level: A multitemporal study in the Lake Cuitzeo Watershed, Mexico (1975-2003), Applied Geography, 31 (1): 237-250. 18. Pal, M. and Mather, P.M. 2003. An assessment of the effectiveness of decision tree methods for land cover classification. Remote Sensing of Environment, 86: 554–565. 19. Parker, D.C., Manson, S.M., Janssen, M.A., Hoffmann, M.J. and Deadman, P. 2003. Malti agent systems for the simulation of land use and land cover change: a Review. Annals of the Association of American eographers, 93(2): 314-337. 20. Philpott, D. 2011. A Guide to Federal Terms and Acronyms. Government Institutes, 196 p. 21. Pullanikkatil, D., Palamuleni, L. and Ruhiiga, T. 2016. Assessment of land use change in Likangala River catchment, Malawi: A remote sensing and DPSIR approach. Applied Geography, 71: 9-23. 22. Quirós, E., Felicísimo Á.M. and Cuartero, A. 2009. Testing Multivariate Adaptive Regression Splines (MARS) as a Method of Land Cover Classification of TERRA-ASTER Satellite Images. Sensors, 9: 9011-9028; doi:10.3390/s91109011. 23. Rafiei, R., Mahini, A. and Khorasani, N. 2011. Determination of land use by comparison method after classification of Landsat and IRS images. Journal of Remote Sensing and GIS in Natural Resources, 1 (3): 62- 53. 24. Rahmani, N., Shahedi, K., Soleimani. K. and Miryaghoobzadeh, M.H. 2012. Investigation of Land use Change in Kasilian Watershed Using Multi-Temporal Images. Journal of Range and Watershed Management, Iranian Journal of Natural Resources65 (1): 35-47. 25. Rakeei, B., Khamechian, M., Abdolmaleki, P. and Giahchi, P. 2006. The application of artificial neural networks to landslide susceptibility mapping (case study: Sefidar-Gale region-Semnan province). Journal of Tehran university sciences, 33 (1): 57-68. 26. Ramankutty, N. and Foley, J.A. 1999. Estimating historical changes in global land cover: croplands from 1700 to 1992. Global Biogeochemical Cycles, 13(4): 997–1028. 27. Saghafian, B., Farazjoo, H., Sepehri, A. and Najafi Nejad, A. 2006. Effect of land use change on flood plain of Golestan dam. Iran Water Resources Research, 2 (1): 18-28. 28. Sala, O.E., Chapin, F.S., Armesto, J.J., Berlow, R., Bloomfield, J., Dirzo, R., Huber-Sanwald, E., Huenneke, L.F., Jackson, R.B., Kinzig, A., Leemans, R., Lodge, D., Mooney, H.A., Oesterheld, M., Poff, N.L., Sykes, M.T., Walker, B.H., Walker, M. and Wall, D.H. 2000. Global Biodiversity Scenarios for the Year 2100, Science, 287 p: 1770-1774. 29. Sanhouse-Garcia, A.J., Bustos-Terrones, Y., Rangel-Peraza, J.G., Quevedo-Castro, A. and Pacheco, C. 2016. Multi-temporal analysis for land use and land cover changes in an agricultural region using open source tools. Remote Sensing Applications: Society and Environment, http://dx.doi.org/10.1016/j.rsase.2016.11.002. 30. Shataei, Sh. and Abdi, O. 2008. Preparation of land use map in Zagros Mountains using ETM + data (Case study: Sorkh-e-Khoramabad Lorestan Province). Journal of Agricultural Sciences and Natural Resources. 14 (1): 1-10. 31. Shiraishi, T. Motohka, T. Thapa, R.B. Watanabe, M. and Shimada, M. 2014. Comparative assessment of supervised classifiers for land use–land cover classification in a tropical region using time-series palsar mosaic data. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 7 (4): 1186-1199. 32. Singh, A. 1989. Digital change detection techniques using remotely sensed data. International Journal of Remote Sensing, 10: 989–1003. 33. Talebi, A. and Niazi, Y. 2011. Investigating the Capability of the Physical-Hydrological Model for Surface Surface Surfacing in the Natural Slopes (Case Study: Ilam Dam Watershed). Quarterly Journal of Range and Watershed Management, 64 (3): 323-337. 34. Tripathi, D.K. and Kumar, M. 2012. Remote Sensing based analysis of land Use/land cover dynamics in Takula Block, Almora district (Uttarakhand). Journal of Human Ecology, 38 (3): 207-212. 35. United national population Revision: World Urbanization Prospects: The 2000 Revision. 36. Van Rompaey, A.J., Govers, G. and Puttemans, C. 2002. Modelling land use changes and their impact on soil erosion and sediment supply to rivers. Earth surface processes and landforms, 27 (5): 481-494. 37. Wang, F. and Jun Xu, Y. 2010. Comparison of remote sensing change detection techniques for assessing hurricane damage to forests. Environmental Monitoring and Assessment, 162: 311-326. 38. Wu, Q., Li, H.Q., Wang, R.S., Paulussen, J., He, Y., Wang, M., Wang, B.H. and Wang, Z., 2006. Monitoring and predicting land use change in Beijing using remote sensing and GIS. Landscape and urban planning, 78 (4): 322-333. 39. Zare, M., Nazari Samani, AA, Khalighi Sigaroodi, S., Bazrfshan, J. and Jori., M.H. 2017. Forecasting of Land Use Land Use Change Process in Kasaliyan Basin Using Automatic Markov Model. Pasture and Watershed Management, Iranian Journal of Natural Resources. 70 (2): 273-283.