Classification of quantitative attributes of Zagros forest using Landsat 8-OLI and Random Forest algorithm (Case study: protected area of Manesht forests)

Document Type : Scientific article

Authors

1 Phd student of Forestry, Faculty of Natural Resources, University of Guilan, Sowmeh Sara, I. R. Iran.

2 Professor, Department of Forestry, Faculty of Natural Resources, University of Guilan, Sowmeh Sara, I. R. Iran.

3 Asistant professor, Department of Photogrammetry and Remote Sensing, School of Surveying and Geospatial Engineering, Khajeh Nasir Toosi University of Technology, Tehran, I. R. Iran.

Abstract

Proper forest management needs quantitative and precise estimates of forest stands characteristics. Remotely sensed imageries, due to accurate and broad spatial information, has become a cost-effective tool in forest management. Classification of forest attributes and generation of thematic maps are among the common applications of remote sensing. The objective of this study was to optimize Random Forest algorithm for classification of quantitative attributes of Manesht forest in Ilam Province. Two parameters including mtry= 8, 8, 6 and ntree =300, 800, 200 were used as the optimum numbers to classify basal area, canopy cover and density, respectively. The results showed the more accurate classification in canopy cover (overall accuracy=83%, Kappa coefficient=0.73), basal area (overall accuracy=78%, Kappa coefficient=0.72) and density (overall accuracy=75%, Kappa coefficient=0.69), respectively. Furthermore, variable importance index indicated distance-based vegetation indices are more important for basal area and density classification. It is concluded that the Random Forest algorithm as a non-parametric method could classify basal area, canopy cover and density properly.

Keywords

References

- Abdollahi, H., J. S. Shataee, A. Sepehri & H. Zanganeh, 2010. Comparing investigation on Landsat-ETM+ and IRS-P6-LISS IV data for canopy cover mapping of Zagros forests (Case study, Javanroud forests), Journal of Wood & Forest Science and Technology, 17(3): 1-18 (In Persian).
- Abedi, R. & A. E. Bonyad, 2015. Estimation and Mapping Forest Attributes Using" k Nearest Neighbor" Method on IRS-P6 LISS III Satellite Image Data, Ecologia Balkanica, 7(1): 93-102.
- Bannari, A., D. Morin, F. Bonn & A. R. Huete, 1995. A review of vegetation indices, Remote Sensing Reviews, 13(1-2): 95-120.
- Breiman, L., 2001. Random forests, Machine learning, 45(1): 5-32.
- Clevers, J. G. P. W., 1989, Application of a weighted infrared-red vegetation index for estimating leaf area index by correcting for soil moisture, Remote Sensing of Environment, 29(1): 25-37.
- Erfanifard, S. Y., M. Zobeyri, J. Feghhi & M. Namiranian, 2007. Estimation of crown cover on aerial photographs using shadow index (case study: Zagros forests, Iran), Iranian Journal of Forest and Poplar Research, 3(29): 278-288 (In Persian).
- Fawcett, T., 2006. An introduction to ROC analysis, Pattern Recognition Letters, 27(8):861-874.
- Golino, H. F. & C. M. A. Gomes, 2014. Visualizing Random Forest’s prediction results, Psychology, 5(19): 2084.
- Jafari, M., 2007. Environmental image of the protected area of ​​Manesht and Qalarang, Publications of the Environmental Protection Agency of the province Ilam, Ilam.
- Kuhn, M., 2015. A Short Introduction to the caret Package. R Found Stat Comput: 1-10.
- LeMay, V. & H. Temesgen, 2005. Comparison of nearest neighbor methods for estimating basal area and stems per hectare using aerial auxiliary variables, Forest Science, 51(2): 109-119.
- LeMay, V., J. Maedel & N. C. Coops, 2008. Estimating stand structural details using nearest neighbor analyses to link ground data, forest cover maps, and Landsat imagery, Remote Sensing of Environment, 112(5): 2578-2591.
- Li, C., J. Wang, L. Wang, L. Hu & P. Gong, 2014. Comparison of classification algorithms and training sample sizes in urban land classification with Landsat Thematic Mapper Imagery, Remote Sensing, 6(2): 964-983.
- Liaw, A. & M. Wiener, 2002. Classification and regression by random Forest, R news, 2(3): 18-22.
- Lillesand, T., R. W. Kiefer & J. Chipman, 2004. Remote sensing and image interpretation. John Wiley & Sons Ltd Press, 812.
- Loeb, N. G., S. Kato, W. Su, T. Wong, F. G. Rose, D. R. Doelling, J. R. Norris & X. Huang, 2012. Advances in understanding top of atmosphere radiation variability from satellite observations, Surveys in Geophysics, 33(3-4): 359-385.
- Memarian, H., S. K. Balasundram, J. B. Talib, C. T. B. Sung, A. M. Sood, K. Abbaspour, 2012. Validation of CA-Markov for Simulation of Land Use and Cover Change in the Langat Basin, Malaysia, Journal of Geographic Information System, 4(6): 542-554
- Meyer, D. & F. T. Wien, 2015. Support vector machines, The Interface to libsvm in package e1071.
- Modaberi, A. & J. Mirzaei, 2017. Study of decline effect on structure of central Zagros forests, Journal of Forest Research and Development, 2(4): 325-336 (In Persian).
- Mohammadi, J. & S. Shataee, 2007. Forest stand density mapping using Landsat ETM+ data, Loveh forests, North of Iran. Proceedings of the 28th Asian association on remote sensing ACRS, Nov, pp. 12-16.
- Mohammadi, J., S. Shataee, M. Namiranian & E. Næsset, 2017. Modeling biophysical properties of broad-leaved stands in the hyrcanian forests of Iran using fused airborne laser scanner data and ultra Cam-D images, International Journal of Applied Earth Observation and Geoinformation, 61: 32-45.
- Naghavi, H., A. Fallah, S. Shataee, H. Latifi, J. Soosani, H. Ramezani & C. Conrad, 2014. Canopy cover estimation across semi-Mediterranean woodlands: application of high-resolution earth observation data, Journal of Applied Remote Sensing, 8(1): 083524-083524.
- Naseri, F., 2003. Classification of forest types and estimation of their quantitative parameters in arid and semi-arid regions using satellite data (case study: National Park of Khabr-Kerman province). PhD. Thesis. Faculty of Natural Resources. University of Tehran, Tehran, Iran, 202 p. (In Persian)
- Ng, W. T., M. Meroni, M. Immitzer, S. Böck, U. Leonardi, F. Rembold, H. Gadain & C. Atzberger, 2016. Different methods and temporal imagery selection for Hargeisa, Somaliland, International Journal of Applied Earth Observation and Geoinformation, 53: 76-89.
- Nguyen, T. T. H., 2010. Applying different methods for prediction of stand volume using SPOT 5 data. Proceeding of The 31th Asian conference remote sensing ACRS, TS02-4. Nov. pp. 1-5.
- Ok, A. O., O. Akar & O. Gungor, 2012. Evaluation of random forest method for agricultural crop classification, European Journal of Remote Sensing, 45(1):421-432.
- Pal, M., 2005. Random Forest classifier for remote sensing classification, International Journal of Remote Sensing, 26(1): 217-222.
- Perry Jr, C. R. & L. F. Lautenschlager, 1984. Functional equivalence of spectral vegetation indices, Remote Sensing of Environment, 14(1-3): 169-182.
- Pesta, F., S. Bhatta, D. Helder & N. Mishra, 2015. Radiometric non-uniformity characterization and correction of Landsat 8 OLI using earth imagery-based techniques, Remote Sensing, 7(1): 430-446.
- Poursanidis, D., N. Chrysoulakis & Z. Mitraka, 2015. Ladnsat 8 vs. Landsat 5: A comparison based on urban and peri-urban land cover mapping, International Journal of Applied Earth Observation and Geoinformation, 35: 259-269.
- Prasad, A. M., L. R. Iverson & A. Liaw, 2006. Newer classification and regression tree techniques: Bagging and random forests for ecological prediction, Ecosystems, 9(2):181-199.
- Qi, J., A. Chehbouni, A. R. Huete, Y. H. Kerr & S. Sorooshian, 1994. A modified soil adjusted vegetation index, Remote Sensing of Environment, 48(2): 119-126.
- Rahdari, V., A. Soffianian, S. J. Khajaldin & N. S. Maleki, 2014. Identification of Sattelite Image Ability for Vegetation Cover Crown Percentage Mapping in Arid and Semi Arid Region (Case Study: Mouteh Wild Life Sanctuary), Environmental Science and Technology, 4(59): 43-54 (In Persian).
- Ren, H. & G. Zhou, 2014. Determination of green above-ground biomass in desert steppe using litter-soil-adjusted vegetation index, European Journal of Remote Sensing, 47(1): 611-625
- Richardson, A. J. & C. L. Wiegand, 1977. Distinguishing vegetation from soil background Information, photogrammetric engineering and remote sensing, 43(12): 1541-1552.
- Roujean, J. L. & F. M. Breon, 1995. Estimating PAR absorbed by vegetation from bidirectional reflectance measurements, Remote Sensing of Environment, 51(3):375-384.
- Rouse, J. W., R. H. Haas, J. A. Schell, D. W. Deering & J. C. Harlan, 1974. Monitoring the vernal advancement of retrogradation of natural vegetation, NASA/GSFC, Type I II, Final Report, Greenbelt, MD, 371 p.
- Sagheb Talebi, Kh., T. Sajedi & F. Yazdanian, 2004. A look at the forests of Iran. Research Institute of Forests and Rangelands, Tehran, 56 p. (In Persian)
- Samaniego, L., A. Bárdossy & K. Schulz, 2008. Supervised classification of remotely sensed imagery using a modified k-NN technique, IEEE Transactions on Geoscience and Remote Sensing, 46(7): 2112-2125.
- Sarouei, S., 1999. An Investigation on possibility of forest density classification in Zagros forests, using satellite data. MSc thesis. Faculty of Natural Resources, University of Tehran, Tehran, Iran, 122 p. (In Persian)
- Sivanpillai, R., C. T. Smith, R. Srinivasan, M. G. Messina & X. B. Wu, 2006. Estimation of managed loblolly pine stand age and density with Landsat ETM+ data, Forest Ecology and Management, 223(1-3): 247-254.
Forest Research and Development
Volume 4, Issue 4
March 2019
Pages 415-434

Files

Share

How to cite

Statistics