Modeling the diversity of tree species in circular forest forests using GeoEye images (Case study: Sari Gardeshi Series)

Document Type : Research Paper

Authors

1 FORESTERI، FACULTI NATIONAL RESORCES،UNIVERCITY SAYENCE AGRICULTUR AND NATIONAL RESORCES SARI ، IRAN

2 Boushehr

Abstract

Background: Identifying the relationship between conservation of biodiversity and ecosystem processes is one of the main topics in ecological research. Forests are one of the valuable natural resources of the planet, which plays an important role in the ecological balance and the lives of human societies. Diversity of tree species is one of the key parameters for describing forest ecosystems in the management of nature. Modeling and preparing a map of tree diversity is a useful tool for conservation and management of forests. In terms of tree diversity, the Caspian forests are the richest forests in Iran that have undergone severe changes in recent years. One of the most important and most effective ways to learn about tree diversity is the use of satellite imagery. The aim of this study was to determine the capability of GeoEye images in monitoring of tree diversity in circular forest forests in Mazandaran province.
Materials and Methods: For this purpose, 150 landfills of 30 to 30 meters in length were used for field surveying. Then, the Shannon-Weiner, Simpson and Simpson indexes were calculated for each sample piece. Pre-processing and necessary processing, such as principal component decomposition, making vegetation indices and texture analysis were performed on the images. For modeling, classification and regression tree methods, random forest, different variants of the nearest neighbor and different kernels of backup machine were used. Of the 70% of the teaching samples used for modeling. Then the best bands were selected for modeling. Models were evaluated using 30% of the samples. Then the best models were specified for each part.
Results: The results showed that the indices produced, the infrared band and the resulting bands were identified as the best band for modeling. The RBF kernel has the best result from a backup machine with a 58% explanatory factor and a root mean square error of 46% for modeling the Shannon Wiener Diversity Index among the above models. Also, the method of random forest with the coefficient of explanation of 54 and 57 percent, and the root mean square error margin of about 48 and 14 percent, respectively, for the Simpson and Simpson images have the best results.
Conclusion: The results showed that GeoEye satellite data has a relatively good ability to estimate tree diversity in circular forest forests. The models used by the random forest method for two modes and the RBF kernel were the best-performing vector-path vector technique in one state. Overall, the results showed that these data can be used for management, conservation and monitoring of tree diversity in the northern forests of the country.

Keywords: tree diversity, Shannon Wiener, Simpson and Circulation Series

Keywords

Main Subjects

References

1.Agbelade, A.D., Onyekwelu, J.C., and Oyun, M.B. 2017. Tree species richness, diversity, and vegetation index for federal capital territory, abuja, nigeria. Inter. J. Forest. Res. 1: 1-12.
2.Akbari, H., and Kalbi, S. 2016. Determining pleiades satellite data capability for tree diversity modeling. Biogeosciences and Forestry 10: 1. 1-5.
3.Ardekani, M.R. 2004. Ecology. Tehran University Press. 340p. (In Persian)
4.Bawa, K., Rose, J., Ganeshaiah, K.N., Barve, N., Kiran, M.C., and Umashaanker, R. 2002. Assessing biodiversity from space: an example from the Western Ghats India. Conservation Ecology. 6: 2. 1-7.
5.Breiman, L. 2001. Random forests. Mach. Learn. 45: 5-32.
6.Dye, M., Mutanga, O., and Ismail, R. 2012. Combining spectral and textural remote sensing variables using random forests: Predicting the age of pinus patula forests in Kwazulu-Natal, South Africa. J. Spat. Sci. 57: 193-211.
7.Gillepsi, T.W., Saatchi, S., Pau, U., Bohlman, S., Giorgi, A.P., and Lewis, S. 2008. Towards quantifying tropical tree species richness in tropical forests. Inter. J. Rem. Sens. 30: 6. 1629-1634.
8.Gillespie, T.W., Moody, G.M., Rocchini, D., Giorgi, A.P., and Saatchi, S.2008. Progress in Physical Geography, 32: 2. 203-
9.Gillespie, T.W., Saatchi, S., Pau, U., Bohlman, S., Giorgi, A.P., and Lewis, S. 2009. Towards quantifying tropical tree species richness in tropical forests, Inter. J. Rem. Sens. 30: 6. 1629-1634.
10.Hosseini, S.M. 2000. Determination of ecological capability of native habitats of Iran. Doctoral dissertation, Tarbiat Modarres University. 160p. (In Persian)
11.Immitzer, M., Atzberger, C., and Koukal, T. 2012. Tree species classification with random forest using very high spatial resolution 8-band worldview-2 satellite data. Remote Sens. 4: 2661-2693.
12.Lopes, M., Fauvel, M., Ouin, A., and Girard, S. 2017. Potential of Sentinel-2 and SPOT5 (Take5) time series for the estimation of grasslands biodiversity indices. MultiTemp 2017 - 9th In-ternational workshop on the analysis of multitemporal remote sensing images, Jun 2017, Bruges, Belgium. Pp: 1-4.
13.McRoberts, R.E., and Tomppo, E.O. 2007. Remote sensing support for national forest inventories. Remote Sens. Environ. 
14.Meng, J., Li, S., Wang, W., Liu, Q., Xie, S., and Ma, W. 2016. Estimation of forest structural diversity using the spectral and textural information derived from SPOT-5 satellite images. Remote Sens. 8: 125. 1-24.
15.Mohammadi, J., and Shataee, S. 2007. Forest stand density mapping using Landsat-ETM+ data, Loveh’s forest, north of Iran. In: Proceedings of the “28th Asian Conferences of Remote Sensing”. Malaysia, 12-16 Nov 2007, pp. 10-27. Naeemi B. 1378. Evaluation and preparation of map of diversity and richness of plant species of Golestan National Park using TM data, Master's thesis, Tarbiat Modarres University, 95p. (In Persian)
16.Nagendra, H., Rocchini, D., Ghate, R., Sharma, B., and Pareeth, S. 2010. Assessing plant diversity in a dry tropical forest: Comparing the utility of Landsat and Ikonos satellite images. Rem. Sens. 2: 478-496.
17.Peng, Y., Fan, M., Song, J., Cui, T., and Li, R. 2018. Assessment of plant species diversity based on hyper spectral indices at a fine scale. Scientific Reports, 8: 47-76.
18.Pourbabaei, H. 1998. Biological diversity of wood species in the forests of Guilan province. PhD thesis, Tarbiat Modarres University. 367p. (In Persian)
19.Rocchini, D., Ricotta, C., and Chiarucci, A. 2007. Using satellite imagery to assess plant species richness: The role
of multispectral systems. Applied Vegetation Science, 10: 3. 325-331.
20.Saarinen, N., Vastaranta, M., Näsi R., Rosnell, T., Hakala T., Honkavaara, E., Wulder, M.A., Luoma, V., Tommaselli A.M.G., Imai, N.N.,  Ribeiro, E.A.W., Guimarães, R.B., Holopainen M., and Hyyppä, J. 2018. Assessing biodiversity in Boreal forests with UAV-based photogrammetric point clouds and hyperspectral imaging. Remote Sens. 10: 338. 1-24.
21.Safari, A., Shaabanian, N., Erfanifard, S.Y., Hassan Heidari, R., and Pourreza M. 2010. Investigation of spatial distribution pattern of bane species (Case study: Bayangan forest in Kermanshah province). Iran. For. J.2: 2. 177-185. (In Persian)
22.Shataee, Sh., and Darvish Sefat, A.A.S. 2007. Comparison of base object method and base pixel of satellite images in jungle type classification. J. Natur. Resour. Facul. 869: 13-881.(In Persian)
23.Shataee, Sh., Kalbi, S., and Fallah, A. 2012. Forest attributes imputation using machine-learning methods and ASTER data: Comparison of k-NN, SVR and random forest regression algorithms. Inter. J. Rem. Sens. 33: 19. 6254-6280.
24.St-Louis, V., Pidgeon, A.M., Radeloff, V.C., Hawbaker, T.J., and Clayton, M.K. 2006. High-resolution image texture asa predictor of bird species richness. Rem. Sens. Environ. 105: 299-312.
25.Walker, R.E., Stoms, D.M., Estes, J.E., and Cayocca, K.D. 1992. Relationships between biological diversity and multi-temporal vegetation index data in California. ASPRS ACSM held in Albuquerque, New Mexico. American Society for Photogrammetry and Remote Sensing, 15: 562-571.
26.Wolter, P.T., Townsend, P.A., and Sturtevant, B.R. 2009. Estimation of forest structural parameters using 5 and 10 mSPOT-5 satellite data. Rem. Sens. Environ. 113: 2019-2036.
27.Wood, E.M., Pidgeon, A.M., Radeloff, V.C., and Keuler, N.S. 2013. Image texture predicts avian density and species richness. PLOS ONE, 8: 5. 1-23.
Journal of Wood and Forest Science and Technology
Volume 26, Issue 2 - Serial Number 2
September 2019
Pages 51-62

Files

Share

How to cite

Statistics