Advertisement

A comparison of different land-use classification techniques for accurate monitoring of degraded coal-mining areas

  • Shivesh Kishore Karan
  • Sukha Ranjan Samadder
Original Article
  • 42 Downloads

Abstract

Classification of different land features with similar spectral response is an enigmatical task for pixel-based classifiers, as most of these algorithms rely only on the spectral information of the satellite data. This study evaluated the performance of six major pixel-based land-use classification techniques (both common and advanced) for accurate classification of the heterogeneous land-use pattern of Jharia coalfield, India. WorldView-2 satellite data was used in the present study. The land-use classification results revealed that Maximum Likelihood classifier algorithm performed best out of the four common algorithms with an overall accuracy of about 84%. The advanced classifiers used in the study were Neural-Net and Support Vector Machine both of which gave excellent results with an overall accuracy of 91% and 95%, respectively. It was observed that use of very high-resolution data is not sufficient for obtaining high classification accuracy, selection of an appropriate classification algorithm is equally important to get better classification results. Advanced classifiers gave higher accuracy with minimal errors, hence, for critical planning and monitoring tasks these classifiers should be preferred.

Keywords

Accuracy assessment Classification algorithms Coal-mining areas Very high resolution Worldview-2 

Notes

Acknowledgements

The authors are thankful to the DigitalGlobe Foundation for providing WorldView-2 satellite imagery. The authors acknowledge the support provided by the Department of Environmental Science and Engineering, Indian Institute of Technology (Indian School of Mines), Dhanbad, India for carrying out the research work.

References

  1. Aguilar MA, Saldaña MM, Aguilar FJ (2013) GeoEye-1 and WorldView-2 pan-sharpened imagery for object-based classification in urban environments. Int J Remote Sens 34:2583–2606.  https://doi.org/10.1080/01431161.2012.747018 CrossRefGoogle Scholar
  2. Anderson JR (1976) A land-use and land cover classification system for use with remote sensor data, vol 964. US Government Printing OfficeGoogle Scholar
  3. Andréfouët S, Kramer P, Torres-Pulliza D, Joyce KE et al (2003) Multi-site evaluation of IKONOS data for classification of tropical coral reef environments. Remote Sens Environ 88:128–143.  https://doi.org/10.1016/j.rse.2003.04.005 CrossRefGoogle Scholar
  4. Bagnardi M, González PJ, Hooper A (2016) High-resolution digital elevation model from tri-stereo Pleiades-1 satellite imagery for lava flow volume estimates at Fogo Volcano. Geophys Res Lett 43:6267–6275.  https://doi.org/10.1002/2016GL069457 CrossRefGoogle Scholar
  5. Belgiu M, Dragut L, Strobl J (2014) Quantitative evaluation of variations in rule-based classifications of land cover in urban neighbourhoods using WorldView-2 imagery. ISPRS J Photogramm Remote Sens 87:205–215.  https://doi.org/10.1016/j.isprsjprs.2013.11.007 CrossRefGoogle Scholar
  6. Bhaskaran S, Paramananda S, Ramnarayan M (2010) Per-pixel and object-oriented classification methods for mapping urban features using Ikonos satellite data. Appl Geogr 30:650–665.  https://doi.org/10.1016/j.apgeog.2010.01.009 CrossRefGoogle Scholar
  7. Bolognesi M, Vrieling A, Rembold F, Gadain H (2015) Rapid mapping and impact estimation of illegal charcoal production in southern Somalia based on WorldView-1 imagery. Energy Sustain Dev 25:40–49.  https://doi.org/10.1016/j.esd.2014.12.008 CrossRefGoogle Scholar
  8. Boser BE, Guyon I, Vapnik V (1992) A training algorithm for optimal margin classifiers. In: proceedings of the fifth annual workshop on computational learning theory, ACM Press, pp 144–152Google Scholar
  9. Bsaibes A, Courault D, Baret F, Weiss M et al (2009) Albedo and LAI estimates from FORMOSAT-2 data for crop monitoring. Remote Sens Environ 113:716–729.  https://doi.org/10.1016/j.rse.2008.11.014 CrossRefGoogle Scholar
  10. Campbell J (2007) Introduction to remote sensing, 4th edn. The Guilford Press, New YorkGoogle Scholar
  11. Congalton RG (1991) A review of assessing the accuracy of classifications of remotely sensed data. Remote Sens Environ 37:35–46.  https://doi.org/10.1016/0034-4257(91)90048-B CrossRefGoogle Scholar
  12. Cortes C, Vapnik V (1995) Support-vector networks. Mach Learn 20:273–297.  https://doi.org/10.1007/BF00994018 CrossRefGoogle Scholar
  13. Dyke G, Gill S, Davies R, Betorz F et al (2011) Dream project: applications of earth observations to disaster risk management. Acta Astronaut 68:301–315.  https://doi.org/10.1016/j.actaastro.2010.06.018 CrossRefGoogle Scholar
  14. Fisher PF (1997) The pixel: a snare and a delusion. Int J Remote Sens 18:679–685.  https://doi.org/10.1080/014311697219015 CrossRefGoogle Scholar
  15. Foody GM, Mathur A (2004) A relative evaluation of multiclass image classification by support vector machines. IEEE T Geosci Remote Sens 45:1335–1343.  https://doi.org/10.1109/TGRS.2004.827257 CrossRefGoogle Scholar
  16. Ghosh A, Joshi PK (2014) A comparison of selected classification algorithms for mapping bamboo patches in lower Gangetic plains using very high-resolution WorldView 2 imagery. Int J Appl Earth Obs Geoinf 26:298–311.  https://doi.org/10.1016/j.jag.2013.08.011 CrossRefGoogle Scholar
  17. Grossman S (2015) A comparison of directed search target detection versus in-scene target detection in Worldview-2 datasets. In: Proc. SPIE 9472, algorithms and technologies for multispectral, hyperspectral, and ultraspectral imagery XXI, 94721H (21 May 2015).  https://doi.org/10.1117/12.2177283
  18. Hagolle O, Huc M, Pascual DV, Dedieu G (2010) A multi-temporal method for cloud detection, applied to FORMOSAT-2, VENµS, LANDSAT and SENTINEL-2 images. Remote Sens Environ 114:1747–1755.  https://doi.org/10.1016/j.rse.2010.03.002 CrossRefGoogle Scholar
  19. Hsu CW, Chang CC, Lin CJL (2010) Practical guide to support vector classification. Available at: http://www.csie.ntu.edu.tw/-cjlin. Accessed 26 May 2015
  20. Hyde P, Dubayah R, Walker W, Blair JB, Hofton M, Hunsaker C (2006) Mapping forest structure for wildlife habitat analysis using multi-sensor (LiDAR, SAR/InSAR, ETM+, Quickbird) synergy. Remote Sens Environ 102:63–73.  https://doi.org/10.1016/j.rse.2006.01.021 CrossRefGoogle Scholar
  21. Jawak SD, Luis AJ (2013) A spectral index ratio-based Antarctic land-cover mapping using hyperspatial 8-band WorldView-2 imagery. Polar Sci 7:18–38.  https://doi.org/10.1016/j.polar.2012.12.002 CrossRefGoogle Scholar
  22. Karan SK, Samadder SR (2016a) Accuracy of land use change detection using support vector machine and maximum likelihood techniques for open-cast coal mining areas. Environ Monit Assess 188:486.  https://doi.org/10.1007/s10661-016-5494-x CrossRefGoogle Scholar
  23. Karan SK, Samadder SR (2016b) Reduction of spatial distribution of risk factors for transportation of contaminants released by coal mining activities. J Environ Manag 180:280–290.  https://doi.org/10.1016/j.jenvman.2016.05.042 CrossRefGoogle Scholar
  24. Karan SK, Samadder SR (2017) Dual-tree complex wavelet transform-based image enhancement for accurate long-term change assessment in coal mining areas. Geocarto Int.  https://doi.org/10.1080/10106049.2017.1333534 CrossRefGoogle Scholar
  25. Karan SK, Samadder SR (2018) Improving accuracy of long-term land-use change in coal mining areas using wavelets and support vector machines. Int J Remote Sens 39:84–100.  https://doi.org/10.1080/01431161.2017.1381355 CrossRefGoogle Scholar
  26. Karan SK, Samadder SR, Singh V (2018) Groundwater vulnerability assessment in degraded coal mining areas using the AHP-Modified DRASTIC model. Land Degrad Dev.  https://doi.org/10.1002/ldr.2990 CrossRefGoogle Scholar
  27. Kopsiaftis G, Karantzalos K (2015) Vehicle detection and traffic density monitoring from very high-resolution satellite video data, 2015. In: IEEE International geoscience and remote sensing symposium (IGARSS), Milan, pp 1881–1884.  https://doi.org/10.1109/IGARSS.2015.7326160
  28. Kruse FA, Perry SL (2013) Mineral mapping using simulated Worldview-3 short-wave-infrared imagery. Remote Sens 5:2688–2703.  https://doi.org/10.3390/rs5062688 CrossRefGoogle Scholar
  29. Kruse FA, Lefkoff AB, Boardman JW, Heidebrecht KB, Shapiro AT, Barloon PJ, Goetz AFH (1993) The spectral image processing system (SIPS)—interactive visualization and analysis of imaging spectrometer data. Remote Sens Environ 44:145–163.  https://doi.org/10.1016/0034-4257(93)90013-N CrossRefGoogle Scholar
  30. Lee KR, Kim AM, Olsen RC, Kruse FA (2011) Using WorldView-2 to determine bottom-type and bathymetry. In: Proc. SPIE 8030, ocean sensing and monitoring III, 80300D, 4 May 2011.  https://doi.org/10.1117/12.883578
  31. Li W, Niu Z, Liang X, Li Z et al (2015) Geostatistical modeling using LiDAR-derived prior knowledge with SPOT-6 data to estimate temperate forest canopy cover and above-ground biomass via stratified random sampling. Int J Appl Earth Obs Geoinf 41:88–98.  https://doi.org/10.1016/j.jag.2015.04.020 CrossRefGoogle Scholar
  32. Licciardi GA, Villa A, Dalla Mura M, Bruzzone L, Chanussot J, Benediktsson JA (2012) Retrieval of the height of buildings from WorldView-2 multi-angular imagery using attribute filters and geometric invariant moments. IEEE J Sel Top Appl Earth Obs Remote Sens 5:71–79.  https://doi.org/10.1109/JSTARS.2012.2184269 CrossRefGoogle Scholar
  33. Lin AYM, Novo A, Har-Noy S, Ricklin ND, Stamatiou K (2011) Combining GeoEye-1 satellite remote sensing, UAV aerial imaging, and geophysical surveys in anomaly detection applied to archaeology. IEEE J Sel Top Appl Earth Obs Remote Sens 4:870–876.  https://doi.org/10.1109/JSTARS.2011.2143696 CrossRefGoogle Scholar
  34. Liu CC (2006) Processing of FORMOSAT-2 daily revisit imagery for site surveillance. IEEE T Geosci Remote Sens 44:3206–3214.  https://doi.org/10.1109/TGRS.2006.880625 CrossRefGoogle Scholar
  35. Liu JG, Mason PJ (2013) Essential image processing and GIS for remote sensing. Wiley, New YorkGoogle Scholar
  36. Lynch HJ, White R, Naveen R, Black A, Meixler MS, Fagan WF (2016) In stark contrast to widespread declines along the Scotia Arc, a survey of the South Sandwich Islands finds a robust seabird community. Polar Biol 39:1615–1625.  https://doi.org/10.1007/s00300-015-1886-6 CrossRefGoogle Scholar
  37. Mahalanobis PC (1936) On the generalized distance in statistics. Proc Nat Inst Sci (Calcutta) 2:49–55Google Scholar
  38. Mallinis G, Koutsias N, Tsakiri-Strati M, Karteris M (2008) Object-based classification using quickbird imagery for delineating forest vegetation polygons in a Mediterranean test site. ISPRS J Photogramm Remote Sens 63:237–250.  https://doi.org/10.1016/j.isprsjprs.2007.08.007 CrossRefGoogle Scholar
  39. Mather PM (2004) Computer processing of remotely sensed images: an introduction. Wiley, West SussexGoogle Scholar
  40. Mesev V (2010) Classification of urban areas: inferring land use from the interpretation of land cover. In: Remote sensing of urban and suburban areas. Springer, Dordrecht, pp 141–164.  https://doi.org/10.1007/978-1-4020-4385-7_8 CrossRefGoogle Scholar
  41. Michel P, Jean-Philippe C, Claire T, Delphine F (2013) Potential of pleiades VHR data for mapping applications, 2013. In: IEEE international geoscience and remote sensing symposium, IGARSS, Melbourne VIC, 2013, pp. 4313–4316.  https://doi.org/10.1109/IGARSS.2013.6723788
  42. Mishra D, Narumalani S, Rundquist D, Lawson M (2006) Benthic habitat mapping in tropical marine environments using QuickBird multispectral data. Photogramm Eng Rem Sens 72:1037–1048.  https://doi.org/10.14358/PERS.72.9.1037 CrossRefGoogle Scholar
  43. Momeni R, Aplin P, Boyd DS (2016) Mapping complex urban land cover from spaceborne imagery: the influence of spatial resolution, spectral band set and classification approach. Remote Sens 8:88.  https://doi.org/10.3390/rs8020088 CrossRefGoogle Scholar
  44. Mumby PJ, Edwards AJ (2002) Mapping marine environments with IKONOS imagery: enhanced spatial resolution can deliver greater thematic accuracy. Remote Sens Environ 82:248–257.  https://doi.org/10.1016/S0034-4257(02)00041-X CrossRefGoogle Scholar
  45. Murthy K, Shearn M, Smiley BD, Chau AH, Levine J, Robinson D (2014) SkySat-1: very high-resolution imagery from a small satellite. In: Proc. SPIE 9241, sensors, systems, and next-generation satellites XVIII, 92411E, 7 Oct 2014.  https://doi.org/10.1117/12.2074163
  46. Mutanga O, Adam E, Cho MA (2012) High density biomass estimation for wetland vegetation using WorldView-2 imagery and random forest regression algorithm. Int J Appl Earth Obs Geoinf 18:399–406.  https://doi.org/10.1016/j.jag.2012.03.012 CrossRefGoogle Scholar
  47. Myint SW, Gober P, Brazel A, Grossman-Clarke S, Weng Q (2011) Per-pixel vs. object-based classification of urban land cover extraction using high spatial resolution imagery. Remote Sens Environ 115:1145–1161.  https://doi.org/10.1016/j.rse.2010.12.017 CrossRefGoogle Scholar
  48. Nagai H, Watanabe M, Tomii N (2016) Preliminary remote sensing assessment of the catastrophic avalanche in Langtang Valley induced by the 2015 Gorkha earthquake, Nepal. In: EGU general assembly conference abstracts, vol 18, pp 3737Google Scholar
  49. Ni N, Chen N, Chen J, Liu M (2016) Integrating WorldView-2 imagery and terrestrial LiDAR point clouds to extract dyke swarm geometry: implications for magma emplacement mechanisms. J Volcanol Geoth Res 310:1–11.  https://doi.org/10.1016/j.jvolgeores.2015.11.020 CrossRefGoogle Scholar
  50. Otukei JR, Blaschke T (2010) Land cover change assessment using decision trees, support vector machines and maximum likelihood classification algorithms. Int J Appl Earth Obs Geoinf 12:S27–S31.  https://doi.org/10.1016/j.jag.2009.11.002 CrossRefGoogle Scholar
  51. Ozdemir I, Karnieli A (2011) Predicting forest structural parameters using the image texture derived from WorldView-2 multispectral imagery in a dryland forest, Israel. Int J Appl Earth Obs Geoinf 13:701–710.  https://doi.org/10.1016/j.jag.2011.05.006 CrossRefGoogle Scholar
  52. Petropoulos GP, Vadrevu KP, Xanthopoulos G, Karantounias G, Scholze M (2010) A comparison of spectral angle mapper and artificial neural network classifiers combined with Landsat TM imagery analysis for obtaining burnt area mapping. Sensors 10:1967–1985.  https://doi.org/10.3390/s100301967 CrossRefGoogle Scholar
  53. Ramoelo A, Cho MA, Mathieu R, Madonsela S, Van De Kerchove R, Kaszta Z, Wolff E (2015) Monitoring grass nutrients and biomass as indicators of rangeland quality and quantity using random forest modelling and WorldView-2 data. Int J Appl Earth Obs Geoinf 43:43–54.  https://doi.org/10.1016/j.jag.2014.12.010 CrossRefGoogle Scholar
  54. Richards JA (1999) Remote sensing digital image analysis, vol 3. Springer, BerlinCrossRefGoogle Scholar
  55. Richards JA, Jia X (2006) Remote sensing digital image analysis-hardback. Springer, BerlinGoogle Scholar
  56. Santoro F, Tarantino E, Figorito B, Gualano S, D’Onghia AM (2013) A tree counting algorithm for precision agriculture tasks. Int J Digit Earth 6:94–102.  https://doi.org/10.1080/17538947.2011.642902 CrossRefGoogle Scholar
  57. Schowengerdt RA (2006) Remote sensing: models and methods for image processing. Academic press, DublinGoogle Scholar
  58. Shankar U, Boral L, Pandey HN, Tripathi RS (1993) Degradation of land due to coal mining and its natural recovery pattern. Curr Sci 65:680–687Google Scholar
  59. Shao Y, Lunetta RS (2012) Comparison of support vector machine, neural network, and CART algorithms for the land-cover classification using limited training data points. ISPRS J Photogramm Remote Sens 70:78–87.  https://doi.org/10.1016/j.isprsjprs.2012.04.001 CrossRefGoogle Scholar
  60. Singh SK, Srivastava PK, Gupta M, Thakur JK, Mukherjee S (2013) Appraisal of land use/land cover of mangrove forest ecosystem using support vector machine. Environ Earth Sci 71:2245–2255.  https://doi.org/10.1007/s12665-013-2628-0 CrossRefGoogle Scholar
  61. Sonka M, Hlavac V, Boyle R (2014) Image processing, analysis, and machine vision. Cengage Learning, BostonGoogle Scholar
  62. Stumpf A, Malet JP, Allemand P, Ulrich P (2014) Surface reconstruction and landslide displacement measurements with Pléiades satellite images. ISPRS J Photogramm Remote Sens 95:1–12.  https://doi.org/10.1016/j.isprsjprs.2014.05.008 CrossRefGoogle Scholar
  63. Szuster BW, Chen Q, Borger M (2011) A comparison of classification techniques to support land cover and land use analysis in tropical coastal zones. Appl Geogr 31:525–532.  https://doi.org/10.1016/j.apgeog.2010.11.007 CrossRefGoogle Scholar
  64. Van Coillie FM, Verbeke LP, De Wulf RR (2007) Feature selection by genetic algorithms in object-based classification of IKONOS imagery for forest mapping in Flanders, Belgium. Remote Sens Environ 110:476–487.  https://doi.org/10.1016/j.rse.2007.03.020 CrossRefGoogle Scholar
  65. Van der Sande CJ, De Jong SM, De Roo APJ (2003) A segmentation and classification approach of IKONOS-2 imagery for land cover mapping to assist flood risk and flood damage assessment. Int J Appl Earth Obs Geoinf 4:217–229.  https://doi.org/10.1016/S0303-2434(03)00003-5 CrossRefGoogle Scholar
  66. Vapnik VN (1998) Statistical learning theory. Wiley, New YorkGoogle Scholar
  67. Wang G, Weng Q (2013) Remote sensing of natural resources. CRC Press, Boca RatonCrossRefGoogle Scholar
  68. Wang L, Sousa WP, Gong P, Biging GS (2004) Comparison of IKONOS and QuickBird images for mapping mangrove species on the Caribbean coast of Panama. Remote Sens Environ 91:432–440.  https://doi.org/10.1016/j.rse.2004.04.005 CrossRefGoogle Scholar
  69. Wang T, Zhang H, Lin H, Fang C (2015a) Textural–spectral feature-based species classification of mangroves in Mai Po nature reserve from Worldview-3 imagery. Remote Sens 8:24.  https://doi.org/10.3390/rs8010024 CrossRefGoogle Scholar
  70. Wang A, Chen J, Jing C, Ye G, Wu J, Huang Z, Zhou C (2015b) Monitoring the invasion of Spartina alterniflora from 1993 to 2014 with Landsat TM and SPOT 6 satellite data in Yueqing bay, China. PLoS One 10:e0135538.  https://doi.org/10.1371/journal.pone.0135538 CrossRefGoogle Scholar
  71. Welch R (1982) Spatial resolution requirements for urban studies. Int J Remote Sens 3:139–146.  https://doi.org/10.1080/01431168208948387 CrossRefGoogle Scholar
  72. Wu Z, Middleton B, Hetzler R, Vogel J, Dye D (2015) Vegetation burn severity mapping using Landsat-8 and WorldView-2. Photogramm Eng Remote Sens 81:143–154.  https://doi.org/10.14358/PERS.81.2.143 CrossRefGoogle Scholar
  73. Yamazaki F, Yano Y, Matsuoka M (2005) Visual damage interpretation of buildings in bam city using quickbird images following the 2003 bam, Iran, earthquake. Earthquake Spectra 21:329–336.  https://doi.org/10.1193/1.2101807 CrossRefGoogle Scholar
  74. Yang J, Gong P, Fu R, Zhang M et al (2013) The role of satellite remote sensing in climate change studies. Nat Clim Chang 3:875–883.  https://doi.org/10.1038/nclimate1908 CrossRefGoogle Scholar
  75. Yang T, Wang X, Yao B, Li J, Zhang Y, He Z, Duan W (2016) Small moving vehicle detection in a satellite video of an urban area. Sensors 16:1528.  https://doi.org/10.3390/s16091528 CrossRefGoogle Scholar
  76. Yates HW (1977) Measurement of the earth radiation balance as an instrument design problem. Appl Opt 16:297–299.  https://doi.org/10.1364/AO.16.000297 CrossRefGoogle Scholar
  77. Yavaşlı DD, Tucker CJ, Melocik KA (2015) Change in the glacier extent in Turkey during the Landsat Era. Remote Sens Environ 163:32–41.  https://doi.org/10.1016/j.rse.2015.03.002 CrossRefGoogle Scholar

Copyright information

© Springer-Verlag GmbH Germany, part of Springer Nature 2018

Authors and Affiliations

  1. 1.Department of Environmental Science and EngineeringIndian Institute of Technology (Indian School of Mines), DhanbadDhanbadIndia

Personalised recommendations