Skip to main content

Combining Landsat-8 spectral bands with ancillary variables for land cover classification in mountainous terrains of northern Pakistan

Abstract

Landsat-8 spectral values have been used to map the earth’s surface information for decades. However, forest types and other land-use/land-cover (LULC) in the mountain terrains exist on different altitudes and climatic conditions. Hence, spectral information alone cannot be sufficient to accurately classify the forest types and other LULC, especially in high mountain complex. In this study, the suitability of Landsat-8 spectral bands and ancillary variables to discriminate forest types, and other LULC, using random forest (RF) classification algorithm for the Hindu Kush mountain ranges of northern Pakistan, was discussed. After prior-examination (multicollinearity) of spectral bands and ancillary variables, three out of six spectral bands and five out of eight ancillary variables were selected with threshold correlation coefficients r2<0.7. The selected datasets were stepwise stacked together and six Input Datasets (ID) were created. The first ID-1 includes only the Surface Reflectance (SR) of spectral bands, and then in each ID, the extra one ancillary variable including Normalized Difference Vegetation Index (NDVI), Normalized Difference Water Index (NDWI), Normalized Difference Snow Index (NDSI), Land Surface Temperature (LST), and Digital Elevation Model (DEM) was added. We found an overall accuracy (OA) = 72.8% and kappa coefficient (KC) =61.9% for the classification of forest types, and other LULC classes by using the only SR bands of Landsat-8. The OA = 81.5% and KC=73.7% was improved by the addition of NDVI, NDWI, and NDSI to the spectral bands of Landsat-8. However, the addition of LST and DEM further increased the OA, and Kappa coefficient (KC) by 87.5% and 82.6%, respectively. This indicates that ancillary variables play an important role in the classification, especially in the mountain terrain, and should be adopted in addition to spectral bands. The output of the study will be useful for the protection and conservation, analysis, climate change research, and other mountains forest-related management information.

This is a preview of subscription content, access via your institution.

References

  1. Barsi JA, Barker JL, Schott JR (2003) An atmospheric correction parameter calculator for a single thermal band earth-sensing instrument. In: IGARSS 2003. 2003 IEEE Int Geosci Remote Sens Symposium. Proceedings (IEEE Cat. No. 03CH37477). IEEE, pp 3014–3016

  2. Berk A, Conforti P, Kennett R, et al. (2014) ® 6: A major upgrade of the MODTRAN® radiative transfer code. In: 2014 6th Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sens (WHISPERS). IEEE, pp 1–4.

  3. Bivand R (2015) OGR shapefile encoding. pp 1–6. Available online at: https://OGR_shape_encoding.pdf (r-project.org) (Accessed on 16-Jan-2020)

  4. Bobrowski M, Bechtel B, Böhner J, et al. (2018) Application of thermal and phenological land surface parameters for improving ecological niche models of Betula utilis in the Himalayan Region. Remote Sens 10(6): 1–19. https://doi.org/10.3390/rs10060814

    Article  Google Scholar 

  5. Bouzekri S, Lasbet AA, Lachehab A (2015) A new spectral index for extraction of built-up area using Landsat-8 data. J Ind Soc Remote Sens 43: 867–873. https://doi.org/10.1007/s12524-015-0460-6

    Article  Google Scholar 

  6. Breiman L (2001a) Random forests. Mach Learn 45: 5–32. https://doi.org/10.1023/A:1010933404324

    Article  Google Scholar 

  7. Breiman L (2001b) ST4_Method_Random_Forest. Machine Learning 45(1): 5–32. https://doi.org/10.1017/CBO9781107415324.004

    Article  Google Scholar 

  8. Chiang SH, Valdez M, Chen CF (2016) Forest tree species distribution mapping using Landsat satellite imagery and topographic variables with the Maximum Entropy method in Mongolia. Int Archives of the Photogramm, Remote Sens and Spat Inf Sci — ISPRS Archives 41 (July): 593–596. https://doi.org/10.5194/isprsarchives-XLI-B8-593-2016

    Article  Google Scholar 

  9. Demircioglu N, Kaplan GJ, Avdan ZY, et al. (2018) Urban Heat Island Analysis Using the Landsat 8 Satellite Data: A case study in FETHIYE, Turkey. 7 th Global Conference on Global Warming (August), Izmir, Turkey. pp 2005–2008

  10. Deng Y, Wu C, Li M, et al.l (2015) A ratio normalized difference soil index for remote sensing of urban/suburban environments. Int J Appl Earth Obs Geoinf 39: 40–48. https://doi.org/10.1016/j.jag.2015.02.010

    Article  Google Scholar 

  11. Dorren LKA, Maier B, Seijmonsbergen AC (2003) Improved Landsat-based forest mapping in steep mountainous terrain using object-based classification. For Ecol Manag 183 (1–3): 31–46. https://doi.org/10.1016/S0378-1127(03)00113-0

    Article  Google Scholar 

  12. Dozier J (1989) Spectral signature of alpine snow cover from the landsat thematic mapper. Remote Sens Environ 28(C): 9–22. https://doi.org/10.1016/0034-4257(89)90101-6

    Article  Google Scholar 

  13. Du Z, Li W, Zhou D, et al. (2014) Analysis of Landsat-8 OLI imagery for land surface water mapping. Remote Sens Lett 5(7): 672–681. https://doi.org/10.1080/2150704X.2014.960606

    Article  Google Scholar 

  14. Engman ET, Gurney RJ (1991) Remote Sens Hydrology. Chapman and Hall Ltd, London.

    Book  Google Scholar 

  15. Fox J, Weisberg S, Adler D, et al. (2007) Package ‘car’. R foundation for statistical computing. Available online at: https://cran.r-project.org/web/packages/car/index.html (Accessed on 28-Jan-2020)

  16. García-Santos V, Cuxart J, Martínez-Villagrasa D, et al. (2018) Comparison of three methods for estimating land surface temperature from Landsat 8-TIRS Sensor Data. Remote Sens 10(9): 1450. https://doi.org/10.3390/rs10091450

    Article  Google Scholar 

  17. Ge Y, Thomasson JA, Sui R (2011) Remote sensing of soil properties in precision agriculture: A review. Front Earth Sci 5(3): 229–238. https://doi.org/10.1007/s11707-011-0175-0

    Google Scholar 

  18. George R, Padalia H, Kushwaha SPS (2014) Forest tree species discrimination in western Himalaya using EO-1 Hyperion. Int J Appl Earth Obs Geoinf 28(1): 140–149. https://doi.org/10.1016/j.jag.2013.11.011

    Article  Google Scholar 

  19. Hall DK, Riggs GA (2011) Normalized-difference snow index (Ndsi). Encyclopedia of Earth Sci Series Part 3: 779–780. https://doi.org/10.1007/978-90-481-2642-2_376

    Article  Google Scholar 

  20. Hijmans RJ (2017) Introduction to the ‘Raster’Package (version 2.6–7). Available online at: https://mran.microsoft.com/snapshot/2018-04-14/web/packages/raster/vignettes/Raster.pdf (Accessed on 28-Jan-2020)

  21. Iqbal MF, Khan IA (2014) Spatiotemporal Land Use Land Cover change analysis and erosion risk mapping of Azad Jammu and Kashmir, Pakistan. Egypt J Remote Sens Space Sci 17(2): 209–229. https://doi.org/10.1016/j.ejrs.2014.09.004

    Google Scholar 

  22. Jimenez-Munoz JC, Sobrino JA, Skokovic D, et al. (2014) Land surface temperature retrieval methods from landsat-8 thermal infrared sensor data. IEEE Geosci Remote Sens Lett 11(10): 1840–1843. https://doi.org/10.1109/LGRS.2014.2312032

    Article  Google Scholar 

  23. Kalnay E, Kanamitsu M, Kistler R, et al. (1996) The NCEP/NCAR 40-Year Reanalysis Project. Bull Am Meteorol Soc 77(3): 437–471. https://doi.org/10.1175/1520-0477(1996)077<0437:tnyrp>2.0.co;2

    Article  Google Scholar 

  24. Khan AA, ul Hassan SN, Baig S, et al. (2019) The response of land surface temperature to the changing land-use land-cover in a mountainous landscape under the influence of urbanization: Gilgit City as a case study in the Hindu Kush Himalayan Region of Pakistan. Int J Econ Environ Geol 10(3): 40–49. https://doi.org/10.46660/ijeeg.Vol10.Iss3.2019.307

    Google Scholar 

  25. Kuhn M (2005) A short introduction to the caret package.pp 1–10. Available online at: https://download(psu.edu) (Accessed on 28-Jan-2020)

  26. Kuhn M, Johnson K (2013) Applied Predictive Modeling. Springer. ISBN 978-1-4614-6849-3. https://doi.org/10.1007/978-1-4614-6849-3

  27. Lõhmus K, Oja T, Lasn R (1989) Specific root area: A soil characteristic. Plant and Soil 119(2): 245–249. https://doi.org/10.1007/BF02370415

    Article  Google Scholar 

  28. Manandhar R, Odehi IOA, Ancevt T (2009) Improving the accuracy of land use and land cover classification of landsat data using postclassification enhancement. Remote Sens 1(3): 330–344. https://doi.org/10.3390/rs1030330

    Article  Google Scholar 

  29. McFeeters SK (1996) The use of the Normalized Difference Water Index (NDWI) in the delineation of open water features. Int J Remote Sens 17(7): 1425–1432. https://doi.org/10.1080/01431169608948714

    Article  Google Scholar 

  30. Mohajane M, Essahlaoui A, Oudija F, et al. (2018) Land Use/Land Cover (LULC) Using Landsat Data Series (MSS, TM, ETM+ and OLI) in Azrou Forest, in the Central Middle Atlas of Morocco. Environ 5(12): 131. https://doi.org/10.3390/environments5120131

    Google Scholar 

  31. Pal M (2005) Random forest classifier for remote sensing classification. Int J Remote Sens 26(1): 217–222. https://doi.org/10.1080/01431160412331269698

    Article  Google Scholar 

  32. Pal M, Mather PM (2005) Support vector machines for classification in remote sensing. Int J Remote Sens 26(5): 1007–1011. https://doi.org/10.1080/01431160512331314083

    Article  Google Scholar 

  33. Pimple U, Sitthi A, Simonetti D, et al. (2017) Topographic correction of Landsat TM-5 and Landsat OLI-8 imagery to improve the performance of forest classification in the mountainous terrain of Northeast Thailand. Sustainability (Switzerland) 9(2): 1–26. https://doi.org/10.3390/su9020258

    Google Scholar 

  34. Qamer FM, Shehzad K, Abbas S, et al. (2016) Mapping deforestation and forest degradation patterns in Western Himalaya, Pakistan. Remote Sens 8(5): 385. https://doi.org/10.3390/rs8050385

    Article  Google Scholar 

  35. Qasim M, Hubacek K, Termansen M, et al. (2011) Spatial and temporal dynamics of land use pattern in District Swat, Hindu Kush Himalayan region of Pakistan. Appl Geogr 31(2): 820–828. https://doi.org/10.1016/j.apgeog.2010.08.008

    Article  Google Scholar 

  36. Rehman AUR, Ullah S, Liu Q, et al. (2021) Comparing different spaceborne sensors and methods for the retrieval of land surface temperature. Earth Sci Inform 14: 985–995. https://doi.org/10.1007/s12145-021-00578-6

    Article  Google Scholar 

  37. Rodriguez-Galiano VF, Chica-Olmo M, Abarca-Hernandez F, et al. (2012) Random Forest classification of Mediterranean land cover using multi-seasonal imagery and multi-seasonal texture. Remote Sens Environ 121: 93–107. https://doi.org/10.1016/j.rse.2011.12.003

    Article  Google Scholar 

  38. Sadiq Khan M, Ullah S, Sun T, et al. (2020) Land-Use/Land-Cover Changes and its contribution to urban heat island: A case study of Islamabad, Pakistan. Sustainability 12(9): 3861. https://doi.org/10.3390/su12093861

    Article  Google Scholar 

  39. Salomonson VV, Appel I (2004) Estimating fractional snow cover from MODIS using the normalized difference snow index. Remote Sens Environ 89(3): 351–360. https://doi.org/10.1016/j.rse.2003.10.016

    Article  Google Scholar 

  40. Sayler K (2018) EROS Science Processing Architecture On Demand Interface User Guide. U.S. Geological Survey. https://www.usgs.gov/media/files/eros-science-processing-architecture-demand-interface-user-guide (Accessed on 5-May-2020)

  41. Sheeren D, Fauvel M, Josipovíc V, et al. (2016) Tree species classification in temperate forests using Formosat-2 satellite image time series. Remote Sens 8(9): 1–29. https://doi.org/10.3390/rs8090734

    Article  Google Scholar 

  42. Shehzad K, Qamer FM, Murthy MSR, et al. (2014) Deforestation trends and spatial modelling of its drivers in the dry temperate forests of northern Pakistan — A case study of Chitral. J Mt Sci 11(5): 1192–1207. https://doi.org/10.1007/s11629-013-2932-x

    Article  Google Scholar 

  43. Slater JA, Garvey G, Johnston C, et al. (2006) The SRTM data “finishing” process and products. Photogramm Eng Remote Sens 72(3): 237–247. https://doi.org/10.14358/PERS.72.3.237

    Article  Google Scholar 

  44. Sobhan I (2007) Species discrimination from a hyperspectral perspective. Available online at: https://Species discrimination from a hyperspectral perspective (wur.nl) (Accessed on 29-Aug-2020)

  45. Soe Thwal N, Ishikawa T, Watanabe H (2019) Land cover classification and change detection analysis of multispectral satellite images using machine learning. SPIE Remote Sens. https://doi.org/10.1117/12.2532988

  46. Soleimannejad L, Ullah S, Abedi R, et al. (2019) Evaluating the potential of sentinel-2, landsat-8, and irs satellite images in tree species classification of hyrcanian forest of iran using random forest. J Sustain For 38(7): 615–628. https://doi.org/10.1080/10549811.2019.1598443

    Article  Google Scholar 

  47. Stonex (2019) STONEX S500 GNSS RECEIVER, User Manual. June 2019 — Ver. 1 — Rev. o. Available online at: https://s12c0efdbda467d84.jimcontent.com/download/version/1561441665/module/15462156424/name/S500_UserManualENG_v1_revo.pdf (Accessed on 29-Aug-2020)

  48. Thenkabail A, Lyon P, Huete J, et al. (2011) Characterization of soil properties using reflectance spectroscopy. Hyperspectral Remote Sens Veg (October 2011): 513–558. https://doi.org/10.1201/b11222-31

  49. Torahi AA, Rai SC (2011) Land cover classificaiton and forest change analysis, using satellite imagery — A case study in Dehdez area of Zagros Mountain in Iran. J Geogr Inf Syst 3: 1–11. https://doi.org/10.1436/jgis.2011.31001

    Google Scholar 

  50. Ullah S, Farooq M, Shafique M, et al. (2016) Spatial assessment of forest cover and land-use changes in the Hindu-Kush mountain ranges of northern Pakistan. J Mt Sci 13(7): 1229–1237. https://doi.org/10.1007/s11629-015-3456-3

    Article  Google Scholar 

  51. Ullah S, Shafique M, Farooq M, et al. (2017) Evaluating the impact of classification algorithms and spatial resolution on the accuracy of land cover mapping in a mountain environment in Pakistan. Arab J Geosci 10(3). https://doi.org/10.1007/s12517-017-2859-6

  52. Xu H (2006) Modification of normalised difference water index (NDWI) to enhance open water features in remotely sensed imagery. Int J Remote Sens 27(14): 3025–3033. https://doi.org/10.1080/01431160600589179

    Article  Google Scholar 

  53. Zha Y, Gao J, Ni S (2003) Use of normalized difference built-up index in automatically mapping urban areas from TM imagery. Int J Remote Sens 24(3): 583–594. https://doi.org/10.1080/01431160304987

    Article  Google Scholar 

  54. Zhou J, Li J, Zhang L, et al. (2012) Intercomparison of methods for estimating land surface temperature from a Landsat-5 TM image in an arid region with low water vapour in the atmosphere. Int J Remote Sens 33(8): 2582–2602. https://doi.org/10.1080/01431161.2011.617396

    Article  Google Scholar 

  55. Zhu X, Liu D (2014) Accurate mapping of forest types using dense seasonal landsat time-series. ISPRS J Photogramm Remote Sens 96: 1–11. https://doi.org/10.1016/j.isprsjprs.2014.06.012

    Article  Google Scholar 

  56. Zhu Z, Woodcock CE, Rogan J, et al. (2012) Assessment of spectral, polarimetric, temporal, and spatial dimensions for urban and periurban land cover classification using Landsat and SAR data. Remote Sens Environ 117: 72–82. https://doi.org/10.1016/j.rse.2011.07.020

    Article  Google Scholar 

  57. Zuur AF, Ieno EN, Elphick CS (2010) A protocol for data exploration to avoid common statistical problems. Methods Ecol Evol 1(1): 3–14. https://doi.org/10.1111/j.2041-210X.2009.00001.x

    Article  Google Scholar 

Download references

Author information

Affiliations

Authors

Corresponding author

Correspondence to Qi-jing Liu.

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Ur Rehman, A., Ullah, S., Shafique, M. et al. Combining Landsat-8 spectral bands with ancillary variables for land cover classification in mountainous terrains of northern Pakistan. J. Mt. Sci. 18, 2388–2401 (2021). https://doi.org/10.1007/s11629-020-6548-7

Download citation

Keywords

  • Forest types
  • Landuse Landcover
  • Landsat-8
  • Random forest
  • Ancillary variables
  • Mountain environment