توسعه و ارتقاء روش های طبقه بندی الگوریتم شبکه عصبی و شاخص پوشش جنگلی (FCD) در داده ماهواره ای با وضوح بالا GEOEYE. (مطالعه موردی: جنگل های هیرکانی رامسر-صفارود)
محورهای موضوعی :
منابع طبیعی
امین مهدوی سعیدی
1
,
ساسان بابایی کفاکی
2
,
اسداله متاجی
3
1 - دانشجو دکترای جنگلداری. دانشکده منابع طبیعی و محیط زیست، واحد علوم و تحقیقات، دانشگاه آزاد اسلامی، تهران، ایران.
2 - استاد گروه جنگلداری. دانشکده منابع طبیعی و محیط زیست، واحد علوم و تحقیقات، دانشگاه آزاد اسلامی، تهران، ایران. *(مسوول مکاتبات)
3 - استاد گروه جنگلداری. دانشکده منابع طبیعی و محیط زیست، واحد علوم و تحقیقات، دانشگاه آزاد اسلامی، تهران، ایران.
تاریخ دریافت : 1400/05/07
تاریخ پذیرش : 1400/08/26
تاریخ انتشار : 1401/09/01
کلید واژه:
مراحل تحولی,
داده وضوح بالا,
Density Slice,
FCD,
شبکه عصبی,
چکیده مقاله :
زمینه و هدف: با عنایت به وضوح مکانی بالای داده های Geoeye، به دلیل توزیع گسترده تر پیکسل ها، نقشه های خروجی در دو روش طبقه بندی الگوریتم شبکه عصبی و شاخص پوشش جنگلی (FCD)، حساس تر و با جزئیات پیکسلی بیشتر همراه هستند. با توجه به حجم زیاد اطلاعات در سنسورهای جدید، هدف این مطالعه توسعه و ارتقاء عملکرد الگوریتم های طبقه بندی پیچیده تر، برای تفسیر داده های ماهواره ای مدرن است.
روش بررسی: طبقه بندی مدل پایه FCDبراساس چهار شاخص اصلی، حساس به سایه، خاک بدون پوشش، شرایط و تراکم پوشش گیاهی، و بدون نیاز به نمونه تعلیمی، عمل می نماید. الگوریتم شبکه عصبی با حساسیت بالایی نسبت به باندهای تصویر اصلی و باندهای ایجاد شده و اضافه شده به تصویر و همچنین نمونه آموزشی معرفی شده، عمل می کند. نمونه های تعلیمی، تابستان 1395و 96 در سری 5 و 6 حوزه آبخیز 30 رامسر، بررسی گردیدند.
یافته ها: با استفاده از روش یاد شده دقت 5/24٪ برای روش FCD و 2/26٪ برای روش شبکه عصبی بدست آمده است. با توجه به اینکه داده های استفاده شده از وضوح بالایی برخوردارند، نقشه خروجی در این روش توسعه یافته، با تراکم بالای پولی گون ها همراه است.
بحث و نتیجه گیری: با توجه به دامنه ظهور پیکسل ها در نقشه های خروجی دو روش یاد شده، روش توسعه یافته ای برای تولید نقشه دقیق تر، با توجه به قدرت تفکیک مکانی زیاد سنجنده Geoeye، ارائه شده است. در این روش با طبقه بندی مجدد در محدوده حداکثر فراوانی پیکسل ها، مرزبندی پولی گون ها در ابعاد بسیار کوچکتر و دقیق تر قابل ملاحظه است.
چکیده انگلیسی:
Background and Objective: Due to the high spatial resolution of Geoeye data, due to the wider distribution of pixels, the output maps in Neural network algorithm and Forest cover index (FCD) classification methods are more sensitive and with more pixel detail. Considering the large amount of information in new sensors, the aim of this study is to develop and improve the performance of more complex classification algorithms for the interpretation of modern satellite data.
Material and Methodology: FCD model base classification is based on four main indicators: sensitive to shadow, uncovered soil, vegetation conditions and density, and without the need for a training sample. The Neural network algorithm operates with high sensitivity to the original image bands and the bands created and added to the image, as well as training samples. Training samples were determined in the summer of 2016-2017 from series 5 and 6 of 30 Ramsar watersheds.
Finding: Using this method, an accuracy of 24.5% was obtained for the FCD method and 26.2% for the Neural network method. Due to the high resolution of the data used, the output map developed in this method is associated with a high density of polygons.
Discussion & Conclusion: Due to the range of pixels in the output maps of the two methods, an extended method has been proposed to produce a more accurate map, due to the high spatial resolution of the Geoeye sensor. In this method, by reclassifying within the maximum frequency range of pixels, the demarcation of polygons in much smaller and more accurate dimensions is considerable.
منابع و مأخذ:
Desclée, B., Bogaert, P. and Defourny, P. (2006). Forest change detection by statistical object-based Remote Sensing of Environment, 102(1-2), 1-11.
Chen, G., Hay, G.J., Carvalho, L.M., Wulder, M.A. (2012). Object-based change detection. International Journal of Remote Sensing, 33(14), 4434-4457.
Kavzoglu, T., Colkesen, I. and Yomralioglu, T. (2015). Object-based classification with rotation forest ensemble learning algorithm using very-high-resolution WorldView-2 image. Remote Sensing Letters, 6(11), 834-843.
Bulut, S., Günlü, A. and Keleş, S. (2019). Estimation of forest development stage and crown closure using different classification methods and satellite images: A case study from Turkey. Journal of Forest Science, 65(1), 18-26.
Al-Doski, J., Mansorl, S.B. and Shafri, H.Z.M. (2013). Image classification in remote sensing. Department of Civil Engineering, Faculty of Engineering, University Putra, Malaysia. Journal of Environment and Earth Science,3(10), 141-148.
Morales, R.M. (2012). Using Remotely Sensed Imagery for Forest Resource Assessment and Inventory. FOREST ECOSYSTEMS–MORE THAN JUST TREES, p.165.
Osio, A., Lefèvre, S., Ogao, P. and Ayugi, S. (2018). OBIA-based Monitoring of Riparian Vegetation Applied to the Identification of Degraded Acacia Xanthophloea along Lake Nakuru, Kenya. Espace pour le développement (ESPACE DEV); Société T.E.T.I.S,.GEOBIA'2018–Montpellier, 18-22 June 2018. https://hal.univreunion.fr/hal-01960341.
Xue, J. and Su, B. 2017. Significant remote sensing vegetation indices: A review of developments and applications. Journal of Sensors, https://doi.org/10.1155/2017/1353691.
R.H and Running.S.W. "Forest Ecosystems: Analysis at Multiple Scales". Academic Press.1988.
10. Shataee, S., Kalbi, S., Fallah, A. and Pelz, D. (2012). Forest attribute imputation using machine-learning methods and ASTER data: comparison of k-NN, SVR and random forest regression algorithms. International journal of remote sensing, 33(19), 6254-6280.
11. Aronoff.S. "Remote Sensing for GIS Managers" . Esri Press.2005.
12. Math(z)er.P.M . "Computer Processing of Remotely-Sensed Images". 1996.
Vina, A, Gitelson, A, Robertson, A, Peng, Y, 2011, Comparison of different vegetation indices for the remote assessment of green leaf area index of corps, Remote sensing of Environment. https://doi.org/10.1016/j.rse.2011.08.010.
Mataji, A., Sagheb-Talebi, K. and Eshaghi-Rad, J.(2014) Deadwood assessment in different developmental stages of beech (Fagus orientalis Lipsky) stands in Caspian forest International Journal of Environmental Science and Technology, 11(5): 1215-1222.
15. Stoffels, J, Hill, J, Sachtleber, T, Mader, S, Buddenbaum, H, Stern, O, 2015, Satellite based derivation of high resolution forest information layers for operational forest management. Forests. Vol6. iss6. https://doi.org/10.3390/f6061982.
Hill, J.; Diemer, C.; Udelhoven, T. 2003. A Local Correlation approach for the fusion of image bands with different spatial resolutions. Bull. Soc. Fr. Photogramm. Télédétect. 2003, 169.
H. Multi-spectral classification. Multi-satellite remote sensing based on decision-making integration. Master's Degree Electronic Thesis. Tarbiyat Modares University 2002.
H. Processing and interpreting remote sensing images. Malek ashtar Industrial University Press. 2013. ISBN 978-600-5665-51-2.
F, Babaei Khafaki, Sasan, Metaji, Asadullah, 2009. A survey on the capability of ETM+ sensor digital data in separating forest types (Case study of Lefebvre Savadkou region), Journal of Forest and Poplar Research, No. 1, 88. 63_51 p.
20. Crowson et al. 2018. A comparison of satellite remote sensing data fusion methods to map peat swamp forest loss in Sumatra, Indonesia. Remote Sensing in Ecology and Conservation published by John Wiley & Sons. DOI: 10.1002/rse2.102.
M.A, S, Salyanian. A, Khajeeddin. Seyyedmalamdin, 2009, Preparation of Arak Landslide Survey Map Using Artificial Neural Network Classification Methods and Maximum Likelihood, Natural Geography Research, No. 69, 88. 98_83 p.
Z, Zahiri.J, Jalili.S, Ansari.M.R, Taghizadeh.A, 2016 Remote Sensing and Artificial Neural Network Application in Estimation of Suspended Sediment in River (Case Study of Karun River), Journal of Water and Soil Science No. 2, year 97. 259_249 p.
Hilbert, D.W., Muyzenberg, J.V.D. Using an artificial neural network to characterize the relative suitability of environments for forest types in a complex tropical vegetation mosaic. Diversity and Distributions 5(6): 263-274., 1999.
Himayah, S, Hartono, Danoedoro, P, 2016. The Utilization of Landsat 8 Multitemporal Imagery and Forest Canopy Density (FCD) Model for Forest Reclamation Priority of Natural Disaster Areas at Kelud Mountain, East Java. 2nd International Conference of Indonesian Society for Remote Sensing (ICOIRS) 2016. https://www.researchgate.net/publication/312190068 https://doi.org/10.1029/2005GL023647.
Pak-khesal.E, Baniyad.A, 2013. Canopy cover canopy classification by using FCD model (Case study of Shafarood Gilan Basin), Journal of Forest and Poplar Research, No.1. 92,114_99 p.
Xiao, X., He, L., Salas, W., Li, C., Moore, B., Zhao, R., et al. (2002). Quantitative relationships between field-measured leaf area index and vegetation index derived from vegetation images for paddy rice fields. International Journal of Remote Sensing, 23, 3595–3604. http://www.tandf.co.uk/journals.
Viña, A., Gitelson, A.A.(2005). New developments in the remote estimation of the fraction of absorbed photosynthetically active radiation in crops. Geophysical ResearchLetters,32,L17403.
Congalton, R.G. and Green, K. (1999). Assessing the accuracy of remotely sensed data: principles and practices", Boca Raton: Lewis Publications. Second Edition (Mapping Science) 2nd Edition.183 pp.
Kempeneers, P.; Sedano, F.; Seebach, L.; Strobl, P.; San‑Miguel‑Ayanz, J. 2011. Data fusion of different spatial resolution remote sensing images applied to forest‑type mapping. IEEE T. Geosci. Remote , 49, 4977–4986. lucia.seebach@jrc.ec, Digital Object Identifier 10.1109/TGRS.2011.2158548.
Vohland, M.; Stoffels, J.; Hau, C.; Schüler, G.2007. Remote sensing techniques for forest parameter assessment: Multispectral classification and linear spectral mixture analysis. Silva Fenn, 41, 441–456. http://www.metla.fi/silvafennica/full/sf41/sf413441.pdf.
_||_
Desclée, B., Bogaert, P. and Defourny, P. (2006). Forest change detection by statistical object-based Remote Sensing of Environment, 102(1-2), 1-11.
Chen, G., Hay, G.J., Carvalho, L.M., Wulder, M.A. (2012). Object-based change detection. International Journal of Remote Sensing, 33(14), 4434-4457.
Kavzoglu, T., Colkesen, I. and Yomralioglu, T. (2015). Object-based classification with rotation forest ensemble learning algorithm using very-high-resolution WorldView-2 image. Remote Sensing Letters, 6(11), 834-843.
Bulut, S., Günlü, A. and Keleş, S. (2019). Estimation of forest development stage and crown closure using different classification methods and satellite images: A case study from Turkey. Journal of Forest Science, 65(1), 18-26.
Al-Doski, J., Mansorl, S.B. and Shafri, H.Z.M. (2013). Image classification in remote sensing. Department of Civil Engineering, Faculty of Engineering, University Putra, Malaysia. Journal of Environment and Earth Science,3(10), 141-148.
Morales, R.M. (2012). Using Remotely Sensed Imagery for Forest Resource Assessment and Inventory. FOREST ECOSYSTEMS–MORE THAN JUST TREES, p.165.
Osio, A., Lefèvre, S., Ogao, P. and Ayugi, S. (2018). OBIA-based Monitoring of Riparian Vegetation Applied to the Identification of Degraded Acacia Xanthophloea along Lake Nakuru, Kenya. Espace pour le développement (ESPACE DEV); Société T.E.T.I.S,.GEOBIA'2018–Montpellier, 18-22 June 2018. https://hal.univreunion.fr/hal-01960341.
Xue, J. and Su, B. 2017. Significant remote sensing vegetation indices: A review of developments and applications. Journal of Sensors, https://doi.org/10.1155/2017/1353691.
R.H and Running.S.W. "Forest Ecosystems: Analysis at Multiple Scales". Academic Press.1988.
10. Shataee, S., Kalbi, S., Fallah, A. and Pelz, D. (2012). Forest attribute imputation using machine-learning methods and ASTER data: comparison of k-NN, SVR and random forest regression algorithms. International journal of remote sensing, 33(19), 6254-6280.
11. Aronoff.S. "Remote Sensing for GIS Managers" . Esri Press.2005.
12. Math(z)er.P.M . "Computer Processing of Remotely-Sensed Images". 1996.
Vina, A, Gitelson, A, Robertson, A, Peng, Y, 2011, Comparison of different vegetation indices for the remote assessment of green leaf area index of corps, Remote sensing of Environment. https://doi.org/10.1016/j.rse.2011.08.010.
Mataji, A., Sagheb-Talebi, K. and Eshaghi-Rad, J.(2014) Deadwood assessment in different developmental stages of beech (Fagus orientalis Lipsky) stands in Caspian forest International Journal of Environmental Science and Technology, 11(5): 1215-1222.
15. Stoffels, J, Hill, J, Sachtleber, T, Mader, S, Buddenbaum, H, Stern, O, 2015, Satellite based derivation of high resolution forest information layers for operational forest management. Forests. Vol6. iss6. https://doi.org/10.3390/f6061982.
Hill, J.; Diemer, C.; Udelhoven, T. 2003. A Local Correlation approach for the fusion of image bands with different spatial resolutions. Bull. Soc. Fr. Photogramm. Télédétect. 2003, 169.
H. Multi-spectral classification. Multi-satellite remote sensing based on decision-making integration. Master's Degree Electronic Thesis. Tarbiyat Modares University 2002.
H. Processing and interpreting remote sensing images. Malek ashtar Industrial University Press. 2013. ISBN 978-600-5665-51-2.
F, Babaei Khafaki, Sasan, Metaji, Asadullah, 2009. A survey on the capability of ETM+ sensor digital data in separating forest types (Case study of Lefebvre Savadkou region), Journal of Forest and Poplar Research, No. 1, 88. 63_51 p.
20. Crowson et al. 2018. A comparison of satellite remote sensing data fusion methods to map peat swamp forest loss in Sumatra, Indonesia. Remote Sensing in Ecology and Conservation published by John Wiley & Sons. DOI: 10.1002/rse2.102.
M.A, S, Salyanian. A, Khajeeddin. Seyyedmalamdin, 2009, Preparation of Arak Landslide Survey Map Using Artificial Neural Network Classification Methods and Maximum Likelihood, Natural Geography Research, No. 69, 88. 98_83 p.
Z, Zahiri.J, Jalili.S, Ansari.M.R, Taghizadeh.A, 2016 Remote Sensing and Artificial Neural Network Application in Estimation of Suspended Sediment in River (Case Study of Karun River), Journal of Water and Soil Science No. 2, year 97. 259_249 p.
Hilbert, D.W., Muyzenberg, J.V.D. Using an artificial neural network to characterize the relative suitability of environments for forest types in a complex tropical vegetation mosaic. Diversity and Distributions 5(6): 263-274., 1999.
Himayah, S, Hartono, Danoedoro, P, 2016. The Utilization of Landsat 8 Multitemporal Imagery and Forest Canopy Density (FCD) Model for Forest Reclamation Priority of Natural Disaster Areas at Kelud Mountain, East Java. 2nd International Conference of Indonesian Society for Remote Sensing (ICOIRS) 2016. https://www.researchgate.net/publication/312190068 https://doi.org/10.1029/2005GL023647.
Pak-khesal.E, Baniyad.A, 2013. Canopy cover canopy classification by using FCD model (Case study of Shafarood Gilan Basin), Journal of Forest and Poplar Research, No.1. 92,114_99 p.
Xiao, X., He, L., Salas, W., Li, C., Moore, B., Zhao, R., et al. (2002). Quantitative relationships between field-measured leaf area index and vegetation index derived from vegetation images for paddy rice fields. International Journal of Remote Sensing, 23, 3595–3604. http://www.tandf.co.uk/journals.
Viña, A., Gitelson, A.A.(2005). New developments in the remote estimation of the fraction of absorbed photosynthetically active radiation in crops. Geophysical ResearchLetters,32,L17403.
Congalton, R.G. and Green, K. (1999). Assessing the accuracy of remotely sensed data: principles and practices", Boca Raton: Lewis Publications. Second Edition (Mapping Science) 2nd Edition.183 pp.
Kempeneers, P.; Sedano, F.; Seebach, L.; Strobl, P.; San‑Miguel‑Ayanz, J. 2011. Data fusion of different spatial resolution remote sensing images applied to forest‑type mapping. IEEE T. Geosci. Remote , 49, 4977–4986. lucia.seebach@jrc.ec, Digital Object Identifier 10.1109/TGRS.2011.2158548.
Vohland, M.; Stoffels, J.; Hau, C.; Schüler, G.2007. Remote sensing techniques for forest parameter assessment: Multispectral classification and linear spectral mixture analysis. Silva Fenn, 41, 441–456. http://www.metla.fi/silvafennica/full/sf41/sf413441.pdf.