Development and Improvement of Neural network algorithm and forest cover index (FCD) classification methods in GEOEYE high resolution satellite data. (Case study: Ramsar-Safarood Hyrcanian forests)

Subject Areas : natural resorces

Amin Mahdavi Saeidi ¹ , Sasan Babaie Kafaki ² , Asadollah Mattaji ³

1 - PhD Student. Department of Forestry, Faculty of Natural Resources and Environment, Science and Research Branch, Islamic Azad University, Tehran, Iran.
2 - Professor. Department of Forestry, Faculty of Natural Resources and Environment, Science and Research Branch, Islamic Azad University, Tehran, Iran. *(Corresponding Author)
3 - Professor. Department of Forestry, Faculty of Natural Resources and Environment, Science and Research Branch, Islamic Azad University, Tehran, Iran.

Received: 2021-07-29 Accepted : 2021-11-17 Published : 2022-11-22

Keywords: Development Stages, Density Slice, FCD, High Resolution Data, Neural Network,

Abstract :

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.

References:

1. Desclée, B., Bogaert, P. and Defourny, P. (2006). Forest change detection by statistical object-based Remote Sensing of Environment, 102(1-2), 1-11.


2. 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.


3. 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.


4. 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.


5. 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.


6. Morales, R.M. (2012). Using Remotely Sensed Imagery for Forest Resource Assessment and Inventory. FOREST ECOSYSTEMS–MORE THAN JUST TREES, p.165.


7. 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.


8. 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.


9. 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.

13. 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.


14. 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.

16. 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.


17. H. Multi-spectral classification. Multi-satellite remote sensing based on decision-making integration. Master's Degree Electronic Thesis. Tarbiyat Modares University 2002.


18. H. Processing and interpreting remote sensing images. Malek ashtar Industrial University Press. 2013. ISBN 978-600-5665-51-2.


19. 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.

21. 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.


22. 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.


23. 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.


24. 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.


25. 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.


26. 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.


27. 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.


28. 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.


29. 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. [e-mail], Digital Object Identifier 10.1109/TGRS.2011.2158548.


30. 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.