Investigation on the capability of Landsat-8 and Sentinel-2 data for mapping forest type in the Kojur watershed of Hyrcanian forests

Document Type : Complete scientific research article

Authors

1 Department of Forestry, Faculty of Natural Resources, University of Tehran

2 Land Affairs Organization of Alborz Province

Abstract

Investigation on the capability of Landsat-8 and Sentinel-2 data for mapping forest type in the Kojur watershed of Hyrcanian forests
Abstract

Background and Objectives: Information on forest types and their spatial distribution are valuable for sustainable forest management and planning. The use of remote sensing technology and geographic information system for providing such fundamental information specially in mountainous and remote areas, has been considered by many researchers and forest managers. The current study aims to investigate the capability of Landsat-8 and Sentinel-2 satellite data to generate forest type map in the Kojur watershed of Hyrcanian forests. The performance of some parametric and non-parametric classification methods was also compared.
Materials and Methods: Following quality assessment, some preprocessing techniques including vegetation indices (VI) extraction, tasseled cap transformation (TCT), principal component analysis (PCA) and fusion were applied on the satellite imagery. Field information collected in September 2018 plus available field data from September 2013 and May 2014, in total 60 sample plots, were used to produce a ground truth map. Forest type was determined through Gorji Bahri approach in each plot. Based on forest types separability, six types were identified (pure beech, mixed beech, beech-hornbeam, mixed hornbeam, pure eastern hornbeam, and eastern hornbeam-Persian oak) to be classified using satellite data. The performance of some classifiers like support vector machine (SVM), random forest (RF), artificial neural network (ANN) and maximum likelihood (ML) was analyzed using two different training datasets.
Results: The results indicated that the sentinel-2 dataset performed better than Landsat-8 for producing forest type map specially when the number of classes increases. It was also found that image fusion methods on sentinel-2 and landsat-8, appropriately improved the result of classifications. This research confirms the effectiveness of number of training samples on the performance of classifiers. Respecting the accuracy assessment criterion, the SVM and RF algorithms showed better result while only 22% of field data was used as training samples. By increasing the number of training samples to 50% of field measurements, the highest accuracy was obtained using RF algorithm applying on all datasets from two satellites.
Conclusion: The Landsat-8 and Sentinel-2 satellite data have moderate capability (overall accuracy around 75% for four-class classification) for mapping forest types in the Hyrcanian forest. The SVM and RF produced more stable and accurate results in comparison with two other algorithms, ANN and ML. Complementary studies are recommended in different forest sites while considering phenology of species and topographic attributes.

Keywords

References

  1. 1.Alimohammadi, A., Matkan, A., Ziaeean, P., and Tabatabaie, H. 2009. Comparison of pixel-based and object-based classification and decision tree for forest type mapping using remote sensing data (case study: Astara forest). J. of geographical sciences. 10: 13. 7-26.

    2.Baatuuwie, N.B., and Van Leeuwen, L. 2011. Evaluation of three classifiers in mapping forest stand types using medium resolution imagery: a case study in the Offinso Forest District, Ghana. African J. of Environmental Science and Technology. 5: 1. 25-36.

    3.Breiman, L. 2001. Random forests. Machine learning. 45: 1. 5-32.‏4.Darvishsefat, A.A., Arjhangi Choobar, R., Bonyad, A.E., and Ronoud, G. 2016. Mapping the poplar plantations using Landsat-8 data (Case Study: Talesh and Sumehsara region, Guilan province). Iranian J. of Forest. 8: 3. 315-326.(In Persian)

    5.Darvishsefat, A.A., Abbasi, M., and Marvi Mohajer, M.R. 2009. Investigation on the possibility of beech forest type mapping using Landsat ETM+ data (Case study: Kheyrood forest). Iranian J. of Forest. 1: 2. 105-113. (In Persian)

    6.Fallah, A., Kalbi, S., Shataee Joibari, Sh., and Karami, O. 2015. Determination of ASTER data capability for forest type mapping using classification and regression tree and random forest Algorithms. J. of Forest and Wood Product. 67: 4. 573-584. (In Persian)

    7.Foody, G.M., Mcculloch, M.B., and Yates, W.B. 1995. The effect of training set size and composition on artificial neural network classification. International J. of Remote Sensing. 16: 9. 1707-1723.

    8.Gorji Bahri, Y. 2000. Investigation of typology classifications and forest planning in Vaz forest. PhD. Thesis. University of Tehran. 138p. (In Persian)

    9.Isuhuaylas, L.A.V., Hirata, Y., Ventura Santos, L., and Serrudo Torobeo, N. 2018. Natural forest mapping in the Andes (Peru): A comparison of the performance of machine-learning algorithms. Remote Sensing. 10: 782. 1-20.

    1. Klonus, S., and Ehlers, M. 2009. Performance of evaluation methods in image fusion. 12th International Conference on Information Fusion. IEEE. Pp: 1409-1416.

    11.Liu, Y., Gong, W., Hu, X., and Gong, J. 2018. Forest type identification with random forest using Sentinel-1A, Sentinel-2A, multi-temporal Landsat-8 and DEM data. Remote Sensing.10: 946. 1-25.

    12.Lohrabi, Y. 2017. Feasibility of using tree hyperspectral reflectance library physiographic and satellite data in typology map development of Chartagh forest reserve. M.Sc. Thesis. Shahrekord University. 88p. (In Persian)

    13.Marvi Mohajer, M.R. 2011. Silviculture. TehranUniv. Press. 418p. (In Persian) 14.Mirończuk, A., and Hościło, A. 2017. Mapping tree cover with Sentinel-2 data using the Support Vector Machine (SVM). Geoinformation. 1: 9. 27-38.

    15.Nikolakopoulos, K.G. 2008. Comparison of nine fusion techniques for very high resolution data. Photogrammetric Engineering & Remote Sensing. 74: 5. 647-659.

    16.Parma, R., Shataee Joybari, Sh., Khodakarami, Y., and Habashi, H. 2010. Evaluation of Landsat-ETM+ and IRS-LISS III satellite data for forest type mapping in Zagros forests (Case study: Ghalajeh forest, Kermanshah province), Iranian J. of Forest and Poplar Research, 17: 4. 594-606.

    17.Raczko, E., and Zagajewski, B. 2017. Comparison of support vector machine, random forest and neural network classifiers for tree species classification on airborne hyperspectral APEX images. European J. of Remote Sensing, 50: 1. 144-154.

    18.Rajabpour Rahmati, M. 2015. Estimation of forest canopy height using ICESat GLAS data (Case Study: Kojour forests). PhD. Thesis. University of Tehran. 160p. (In Persian)

    19.Shataee Joibari, SH. 2003. Investigation of the possibility of forest type mapping using satellite data (Case Study: Kheyrood Forest). PhD. Thesis. University of Tehran. 158p. (In Persian)

    20.Valderrama-Landeros, L., Flores-de-Santiago, F., Kovacs, J.M., and Flores-Verdugo, F. 2018. An assessment of commonly employed satellite-based remote sensors for mapping mangrove species in Mexico using an NDVI-based classification scheme. Environmental Monitoring and Assessment. 190: 23. 1-13.

    21.Wessel, M., Brandmeier, M., and Tiede, D. 2018. Evaluation of different machine learning algorithms for scalable classification of tree types and tree species based on Sentinel-2 data. Remote Sensing. 10: 1419. 1-21.

    1. Xie, Z., Chen, Y., Lu, D., Li, G., and Chen, E. 2019. Classification of land cover, forest, and tree species classes with ZiYuan-3 multispectral and stereo data. Remote Sensing. 11: 164. 1-27.
Journal of Wood and Forest Science and Technology
Volume 27, Issue 2
September 2020
Pages 79-98

Files

Share

How to cite

Statistics