Skip to main content

Advertisement

SpringerLink
Log in

Comparative analysis of unsupervised classification methods for mapping burned forest areas

  • Original Paper
  • Published:
Arabian Journal of Geosciences Aims and scope Submit manuscript

Abstract

Forest fires cause a lot of damage in Turkey, due to the geographical location, high temperatures, and low humidity levels. Accurate determination of burned forest areas is crucial for correct damage assessment studies, fire risk calculations, and review of the forest regeneration processes. In this study, we compare the performances of unsupervised classification methods (which have not been used to map burned areas before) of burned area extraction from medium resolution satellite images with K-means. In this regard, the areas affected by fire in the Kumluca and Adrasan regions in 2016, Alanya and Gümüldür regions in 2017 and Athens region in 2018 are determined using Landsat 8 images. For this purpose, Canopy, M-tree, a hierarchical clustering algorithm, and a learning vector quantization which are frequently used in the literature are applied to determine the burned area, and the results obtained are compared with the results obtained from K-means. The results show that unsupervised classification methods can be used to map burned areas. The hierarchical clustering and K-means algorithms provide the most accurate results in mapping burned areas in most of the regions used in the study.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10

Similar content being viewed by others

References

  • Benz UC, Hofmann P, Willhauck G, Lingenfelder I, Heynen M (2004) Multi-resolution, object-oriented fuzzy analysis of remote sensing data for GIS-ready information. ISPRS J Photogramm Remote Sens 58:239–258

    Article  Google Scholar 

  • Camia A, Libertá G, San-Miguel-Ayanz J (2017) Modeling the impacts of climate change on forest fire danger in Europe. EU JRC Tech Rep, pp 1-22

  • Celik T (2009) Unsupervised change detection in satellite images using principal component analysis and $ k $-means clustering. IEEE Geosci Remote Sens Lett 6:772–776

    Article  Google Scholar 

  • Chen W, Moriya K, Sakai T, Koyama L, Cao C (2016) Mapping a burned forest area from Landsat TM data by multiple methods. Geom Nat Haz Risk 7:384–402

    Article  Google Scholar 

  • Chuvieco E (2009) Earth observation of wildland fires in Mediterranean ecosystems. Springer, Dordrecht, pp 129–148

  • Ciaccia P, Patella M, Zezula P (1997) M-tree: an efficient access method for similarity search in metric spaces. In: Proceedings of the 23rd VLDB conference, Athens, Greece, pp 426–435

  • Çömert R, Matcı DK, Emir H, Avdan U (2017) Nesne Tabanlı Sınıflandırma ile Yanmış Orman Alanlarının Tespiti Afyon Kocatepe Üniversitesi Fen Ve Mühendislik Bilimleri Dergisi 17:27–34

  • Congalton RG, Green K (2008) Assessing the accuracy of remotely sensed data: principles and practices. CRC press, Boca Raton

  • Dai W, Yu C, Jiang Z (2016) An improved hybrid canopy-fuzzy C-means clustering algorithm based on apReduce model. J Comput Sci Eng 10:1–8

    Article  Google Scholar 

  • Earth G (2018) Google Earth. https://earth.google.com/web/@39.08764278,35.17776244,1254.97487337a,2309683.10527162d,35y,0h,0t,0r/data=ChMaEQoJL20vMDF6bmNfGAIgASgC. Accessed 16.8.2019 2019

  • Fernández-Manso A, Quintano C (2015) Evaluating Landsat ETM+ emissivity-enhanced spectral indices for burn severity discrimination in Mediterranean forest ecosystems. Remote Sens Lett 6:302–310

    Article  Google Scholar 

  • Fox D, Laaroussi Y, Malkinson L, Maselli F, Andrieu J, Bottai L, Wittenberg L (2016) POSTFIRE: a model to map forest fire burn scar and estimate runoff and soil erosion risks. Remote Sensing Applications: Society and Environment 4:83–91

    Article  Google Scholar 

  • Gitas I, Devereux B (2006) The role of topographic correction in mapping recently burned Mediterranean forest areas from LANDSAT TM images. Int J Remote Sens 27:41–54

    Article  Google Scholar 

  • Guha S, Govil H, Dey A, Gill N (2018) Analytical study of land surface temperature with NDVI and NDBI using Landsat 8 OLI and TIRS data in Florence and Naples city, Italy. European Journal of Remote Sensing 51:667–678

    Article  Google Scholar 

  • Guru D, Vasudev T, Chethan H, Kumar YS (2018) Proceedings of international conference on cognition and recognition. https://doi.org/10.1007/978-981-10-5146-3

  • Hawbaker TJ et al (2017) Mapping burned areas using dense time-series of Landsat data. Remote Sens Environ 198:504–522

    Article  Google Scholar 

  • Hudak A, Brockett B (2004) Mapping fire scars in a southern African savannah using Landsat imagery. Int J Remote Sens 25:3231–3243

    Article  Google Scholar 

  • Jarchow CJ, Nagler PL, Glenn EP (2017) Greenup and evapotranspiration following the minute 319 pulse flow to Mexico: an analysis using Landsat 8 normalized difference vegetation index (NDVI) data. Ecol Eng 106:776–783

    Article  Google Scholar 

  • Johnson SC (1967) Hierarchical clustering schemes. Psychometrika 32:241–254

    Article  Google Scholar 

  • Kanungo T, Mount DM, Netanyahu NS, Piatko CD, Silverman R, Wu AY (2002) An efficient k-means clustering algorithm: analysis and implementation. IEEE Trans Pattern Anal Mach Intell 24:881–892

    Article  Google Scholar 

  • Kohonen T, Kangas J, Laaksonen J, Torkkola K (1992) LVQ PAK: a software package for the correct application of learning vector quantization algorithms. In: Proc. IJCNN, Vol. 92, pp 725–730

  • Koonsanit K, Jaruskulchai C, Eiumnoh A (2012) Parameter-free K-means clustering algorithm for satellite imagery application. In: 2012 International Conference on Information Science and Applications. IEEE, pp 1–6

  • Kriegel H-P, Schubert E, Zimek A (2017) The (black) art of runtime evaluation: are we comparing algorithms or implementations? Knowl Inf Syst 52:341–378

    Article  Google Scholar 

  • Kumar A, Kiran M, Prathap B (2013) Verification and validation of mapreduce program model for parallel k-means algorithm on hadoop cluster. In: 2013 Fourth International Conference on Computing, Communications and Networking Technologies (ICCCNT). IEEE, pp 1–8

  • KumlucaBelediyesi (2019) COĞRAFYA. http://www.kumluca-bld.gov.tr/19/COGRAFYA.html. Accessed 26.8.2019 2019

  • Kwon Y, Lee H, Lee H (2018) Implication of the cluster analysis using greenhouse gas emissions of Asian countries to climate change mitigation. Mitig Adapt Strateg Glob Chang 23:1225–1249

    Article  Google Scholar 

  • Leckie DG, Walsworth N, Dechka J, Wulder M (2002) An investigation of two date unsupervised classification in the context of a national program for Landsat based forest change mapping. In: IEEE International Geoscience and Remote Sensing Symposium. IEEE, Vol. 3, pp 1307–1311

  • Lillesand T, Kiefer RW, Chipman J (2014) Remote sensing and image interpretation. John Wiley & Sons, Hoboken

  • Liu JG, Mason PJ (2013) Essential image processing and GIS for remote sensing. John Wiley & Sons, Hoboken

  • Long T et al (2019) 30 m resolution global annual burned area mapping based on Landsat images and Google Earth engine. Remote Sens 11:489

    Article  Google Scholar 

  • Mallinis G, Koutsias N (2012) Comparing ten classification methods for burned area mapping in a Mediterranean environment using Landsat TM satellite data. Int J Remote Sens 33:4408–4433

    Article  Google Scholar 

  • Matcı DK, Avdan U (2019) Optimization of remote sensing image attributes to improve classification accuracy. International Journal of Environment and Geoinformatics 6:50–56

    Article  Google Scholar 

  • McCallum A, Nigam K, Ungar LH (2000) Efficient clustering of high-dimensional data sets with application to reference matching. In: Proceedings of the sixth ACM SIGKDD international conference on Knowledge discovery and data mining, pp 169–178

  • Mihaescu MC, Burdescu DD (2012) Using m tree data structure as unsupervised classification method. Informatica 36(2)

  • Miller JD, Yool SR (2002) Mapping forest post-fire canopy consumption in several overstory types using multi-temporal Landsat TM and ETM data. Remote Sens Environ 82:481–496

    Article  Google Scholar 

  • OGM (2017) Orman İstatistikleri. Yayın

  • Polychronaki A, Gitas IZ (2012) Burned area mapping in Greece using SPOT-4 HRVIR images and object-based image analysis. Remote Sens 4:424–438

    Article  Google Scholar 

  • Rogan J, Yool S (2001) Mapping fire-induced vegetation depletion in the Peloncillo Mountains, Arizona and New Mexico. Int J Remote Sens 22:3101–3121

    Article  Google Scholar 

  • Roux M (2015) A comparative study of divisive hierarchical clustering algorithms. arXiv preprint arXiv:1506.08977

  • Sedano F, Kempeneers P, San Miguel J, Strobl P, Vogt P (2013) Towards a pan-European burnt scar mapping methodology based on single date medium resolution optical remote sensing data. Int J Appl Earth Obs Geoinf 20:52–59

    Article  Google Scholar 

  • Tucker CJ, Townshend JRG, Goff TE (1985) African land-cover classification using satellite data. Science 227:369–375

    Article  Google Scholar 

  • Usman B (2013) Satellite imagery land cover classification using k-means clustering algorithm computer vision for environmental information extraction. Elixir Computer Science and Engineering 63:18671–18675

    Google Scholar 

Download references

Acknowledgements

This study was produced from a PHD thesis conducted by Dilek Küçük Matcı under the supervision of Assoc. Prof Uğur Avdan.

Author information

Authors and Affiliations

  1. Institute of Earth and Space Sciences, Eskisehir Technical University, Iki Eylul Campus, 26470, Eskisehir, Turkey

    Dilek Küçük Matcı & Uğur Avdan

Authors
  1. Dilek Küçük Matcı
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Uğur Avdan
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Dilek Küçük Matcı.

Additional information

Responsible Editor: Biswajeet Pradhan

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Küçük Matcı, D., Avdan, U. Comparative analysis of unsupervised classification methods for mapping burned forest areas. Arab J Geosci 13, 711 (2020). https://doi.org/10.1007/s12517-020-05670-7

Download citation

  • Received:

  • Accepted:

  • Published:

  • DOI: https://doi.org/10.1007/s12517-020-05670-7

Keywords

Search

Navigation