Arabian Journal of Geosciences

, Volume 8, Issue 11, pp 9763–9773 | Cite as

Comparative analysis of product-level fusion, support vector machine, and artificial neural network approaches for land cover mapping

Original Paper
First Online:
Received:
Accepted:

Abstract

Increasing the accuracy of thematic maps generated using satellite imagery is a crucial task in remote sensing. In this study, a product-level fusion (PLF) approach based on integration of different land-type maps generated using various satellite-derived indices including normalized difference water index (NDWI), normalized difference built-up index (NDBI), enhanced vegetation index (EVI), and normalized difference vegetation index (NDVI) is proposed to improve the accuracy of land cover mapping. The suitability of the proposed approach for land cover mapping is evaluated in comparison with two high-performance image classification techniques including support vector machine (SVM) and artificial neural network (ANN). The results show that the overall accuracy and kappa values of about 95.95 % and 0.95, 94.91 % and 0.94, and 85.32 % and 0.82 are achieved for the PLF, SVM, and ANN approaches, respectively. The results indicate superiority of the PLF approach than SVM and ANN techniques for land cover classification of Advanced Spaceborne Thermal Emission and Reflection Radiometer (ASTER) imagery, especially for the extraction of forest, rice, and citrus classes. However, SVM technique also provided reliable result for land cover mapping.

Keywords

ASTER Landsat Product-level fusion Land cover mapping 
This is a preview of subscription content, log in to check access.

Notes

Acknowledgments

The authors would like to acknowledge the support of Universiti Teknologi Malaysia (UTM) for providing the facilities for this investigation. We are also grateful to US Geological Survey server for providing the ASTER and Landsat data.

References

  1. Agam N, Kustas WP, Anderson MC, Li F, Neale CM (2007) A vegetation index based technique for spatial sharpening of thermal imagery. Remote Sens Environ 107:545–558. doi: 10.1016/j.rse.2006.1010.1006 CrossRefGoogle Scholar
  2. Agarwal S, Vailshery LS, Jaganmohan M, Nagendra H (2013) Mapping urban tree species using very high resolution satellite imagery: comparing pixel-based and object-based approaches. ISPRS Int J Geo-Inf 2:220–236. doi: 10.3390/ijgi2010220 CrossRefGoogle Scholar
  3. Ahmed EA, Adam ME-N (2013) Estimate of global solar radiation by using artificial neural network in Qena, Upper Egypt. J Clean Technol 1:168–150. doi: 10.7763/JOCET.2013.V7761.7735 Google Scholar
  4. Arekhi S, Jafarzadeh A (2014) Forecasting areas vulnerable to forest conversion using artificial neural network and GIS (case study: northern Ilam forests, Ilam province, Iran). Arab J Geosci 7:1073–1085. doi: 10.1007/s12517-012-0785-1 CrossRefGoogle Scholar
  5. Badreldin N, Goossens R (2013) Monitoring land use/land cover change using multi-temporal Landsat satellite images in an arid environment: a case study of El-Arish, Egypt. Arab J Geosci 7:1671–1681. doi: 10.1007/s12517-12013-10916-12513 CrossRefGoogle Scholar
  6. Bandaru V, West TO, Ricciuto DM, César Izaurralde R (2013) Estimating crop net primary production using national inventory data and MODIS-derived parameters. ISPRS J Photogramm Remote Sens 80:61–71. doi: 10.1016/j.isprsjprs.2013.03.005 CrossRefGoogle Scholar
  7. Bolton DK, Friedl MA (2013) Forecasting crop yield using remotely sensed vegetation indices and crop phenology metrics. Agric For Meteorol 173:74–84. doi: 10.1016/j.agrformet.2013.01.007 CrossRefGoogle Scholar
  8. Breckling B, Laue H, Pehlke H (2011) Remote sensing as a data source to analyse regional implications of genetically modified plants in agriculture—oilseed rape (Brassica napus) in Northern Germany. Ecol Indic 11:942–950. doi: 10.1016/j.ecolind.2009.03.003 CrossRefGoogle Scholar
  9. Bridhikitti A, Overcamp TJ (2012) Estimation of Southeast Asian rice paddy areas with different ecosystems from moderate-resolution satellite imagery. Agr Ecosyst Environ 146:113–120. doi: 10.1016/j.agee.2011.1010.1016 CrossRefGoogle Scholar
  10. Bulley HNN, Bishop MP, Shroder JF, Haritashya UK (2013) Integration of classification tree analyses and spatial metrics to assess changes in supraglacial lakes in the Karakoram Himalaya. Int J Remote Sens 34:387–411. doi: 10.1080/01431161.01432012.01705915 CrossRefGoogle Scholar
  11. Chust G, Ducrot D, Pretus JL (2004) Land cover mapping with patch-derived landscape indices. Landsc Urban Plan 69:437–449. doi: 10.1016/j.landurbplan.2003.12.002 CrossRefGoogle Scholar
  12. Deng JS, Qiu LF, Wang K, Yang H, Shi YY (2011) An integrated analysis of urbanization-triggered cropland loss trajectory and implications for sustainable land management. Cities 28:127–137. doi: 10.1016/j.cities.2010.09.005 CrossRefGoogle Scholar
  13. Dixon B, Candade N (2007) Multispectral landuse classification using neural networks and support vector machines: one or the other, or both? Int J Remote Sens 29:1185–1206. doi: 10.1080/01431160701294661 CrossRefGoogle Scholar
  14. Dong J, Xiao X, Chen B, Torbick N, Jin C, Zhang G, Biradar C (2013) Mapping deciduous rubber plantations through integration of PALSAR and multi-temporal Landsat imagery. Remote Sens Environ 134:392–402. doi: 10.1016/j.rse.2013.03.014 CrossRefGoogle Scholar
  15. Duda R, Hart P, Stork DG (2002) Pattern Classification. Wiley, New YorkGoogle Scholar
  16. Elatawneh A, Kalaitzidis C, Petropoulos GP, Schneider T (2012) Evaluation of diverse classification approaches for land use/cover mapping in a Mediterranean region utilizing Hyperion data. Int J Digital Earth 7:194–216. doi: 10.1080/17538947.17532012.17671378 CrossRefGoogle Scholar
  17. Gardi C, Panagos P, Van Liedekerke M, Bosco C, De Brogniez D (2014) Land take and food security: assessment of land take on the agricultural production in Europe. J Environ Plann Manag 58:898–912. doi: 10.1080/09640568.09642014.09899490 CrossRefGoogle Scholar
  18. Gebrehiwot T (2008) Rural food security in Tigray. Policy Impact Evaluation. Dissertation, University of Twente, EthiopiaGoogle Scholar
  19. Ghobadi Y, Pradhan B, Shafri H, Kabiri K (2013) Assessment of spatial relationship between land surface temperature and landuse/cover retrieval from multi-temporal remote sensing data in South Karkheh Sub-basin, Iran. Arab J Geosci 8:525–537. doi: 10.1007/s12517-013-1244-3 CrossRefGoogle Scholar
  20. Golafshani MB, Shahnazari A, Ahmadi MZ, Aghajani G (2012) Compare the parameters of the water balance in traditional and land levening paddy fields in Qaemshahr City. J Soil Water 26:1010–1017Google Scholar
  21. Gumma MK, Nelson A, Thenkabail PS, Singh AN (2011) Mapping rice areas of South Asia using MODIS multitemporal data. J Appl Remote Sens 5:0535471–05354726. doi: 10.1117/1.3619838 CrossRefGoogle Scholar
  22. Huang S, Liu H, Dahal D, Jin S, Welp LR, Liu J, Liu S (2013) Modeling spatially explicit fire impact on gross primary production in interior Alaska using satellite images coupled with eddy covariance. Remote Sens Environ 135:178–188. doi: 10.1016/j.rse.2013.04.003 CrossRefGoogle Scholar
  23. Iran Meteorological Organization (2012) Meteorological Information and Statistic. Tehran, IranGoogle Scholar
  24. Iran Statistic Center P (2011) Iran Population and Housing Census. Tehran, IranGoogle Scholar
  25. Jiang Z, Huete AR, Didan K, Miura T (2008) Development of a two-band enhanced vegetation index without a blue band. Remote Sens Environ 112:3833–3845. doi: 10.1016/j.rse.2008.3806.3006 CrossRefGoogle Scholar
  26. Joshi PC (2011) Performance evaluation of vegetation indices using remotely sensed data. Int J Geomat Geosci 2:231–240CrossRefGoogle Scholar
  27. Karwariya S, Tripathi S (2012) Landuse/landcover mapping of Achanakmar Amarkantak Biosphere Reserve, India using unsupervised classification technique. Int J Comput Eng Res 2:1302–1307Google Scholar
  28. Kelarestaghi A, Jafarian Jeloudar Z (2011) Land use/cover change and driving force analyses in parts of northern Iran using RS and GIS techniques. Arab J Geosci 4:401–411. doi: 10.1007/s12517-009-0078-5 CrossRefGoogle Scholar
  29. Kia M, Pirasteh S, Pradhan B, Mahmud A, Sulaiman W, Moradi A (2012) An artificial neural network model for flood simulation using GIS: Johor River Basin, Malaysia. Environ Earth Sci 67:251–264. doi: 10.1007/s12665-011-1504-z CrossRefGoogle Scholar
  30. Kolios S, Stylios CD (2013) Identification of land cover/land use changes in the greater area of the Preveza peninsula in Greece using Landsat satellite data. Appl Geogr 40:150–160. doi: 10.1016/j.apgeog.2013.02.005 CrossRefGoogle Scholar
  31. Kustas WP, Norman JM, Anderson MC, French AN (2003) Estimating subpixel surface temperatures and energy fluxes from the vegetation index–radiometric temperature relationship. Remote Sens Environ 85:429–440. doi: 10.1016/S0034-4257(1003)00036-00031 CrossRefGoogle Scholar
  32. Laliberte A, Browning D, Rango A (2012) A comparison of three feature selection methods for object-based classification of sub-decimeter resolution UltraCam-L imagery. Int J Appl Earth Obs Geoinf 15:70–78. doi: 10.1016/j.jag.2011.1005.1011 CrossRefGoogle Scholar
  33. Liu HQ, Huete A (1995) A feedback based modification of the NDVI to minimize canopy background and atmospheric noise. IEEE Trans Geosci Remote Sens 33:457–465. doi: 10.1109/1136.377946 CrossRefGoogle Scholar
  34. Liu Y, Zhang B, Wang L-m, Wang N (2013) A self-trained semisupervised SVM approach to the remote sensing land cover classification. Comput Geosci 59:98–107. doi: 10.1016/j.cageo.2013.1003.1024 CrossRefGoogle Scholar
  35. Mantero P, Moser G, Serpico SB (2005) Partially supervised classification of remote sensing images through SVM-based probability density estimation. Geosci Remote Sens IEEE Trans 43:559–570. doi: 10.1109/TGRS.2004.842022 CrossRefGoogle Scholar
  36. Martínez-López J, Carreño M, Martínez-Fernández J, Esteve M (2014) Wetland and landscape indices for assessing the condition of semiarid Mediterranean saline wetlands under agricultural hydrological pressures. Ecol Indic 36:400–408. doi: 10.1016/j.ecolind.2013.1008.1007 CrossRefGoogle Scholar
  37. Mas JF, Flores JJ (2007) The application of artificial neural networks to the analysis of remotely sensed data. Int J Remote Sens 29:617–663. doi: 10.1080/01431160701352154 CrossRefGoogle Scholar
  38. Matinfar H, Alavi Panah S, Zand F, Khodaei K (2013) Detection of soil salinity changes and mapping land cover types based upon remotely sensed data. Arab J Geosci 6:913–919. doi: 10.1007/s12517-011-0384-6 CrossRefGoogle Scholar
  39. Maxwell SK, Nuckols JR, Ward MH, Hoffer RM (2004) An automated approach to mapping corn from Landsat imagery. Comput Electron Agr 43:43–54. doi: 10.1016/j.compag.2003.09.001 CrossRefGoogle Scholar
  40. McFeeters S (1996) The use of the normalized difference water Index (NDWI) in the delineation of open water features. Int J Remote Sens 17:1425–1432. doi: 10.1080/01431169608948714 CrossRefGoogle Scholar
  41. Mirik M, Ansley RJ, Price JA, Workneh F, Rush CM (2013) Remote monitoring of wheat streak mosaic progression using sub-pixel classification of Landsat 5 TM imagery for site specific disease management in winter wheat. Adv Remote Sens 2:16–28. doi: 10.4236/ars.2013.21003 CrossRefGoogle Scholar
  42. Mishra VN, Rai PK, Mohan K (2014) Prediction of land use changes based on land change modeler (LCM) using remote sensing: a case study of Muzaffarpur (Bihar), India. J Geogr Inst Jovan Cvijic 64:111–127. doi: 10.2298/IJGI1401111M CrossRefGoogle Scholar
  43. Mountrakis G, Im J, Ogole C (2011) Support vector machines in remote sensing: a review. ISPRS J Photogramm 66:247–259. doi: 10.1016/j.isprsjprs.2010.1011.1001 CrossRefGoogle Scholar
  44. Ninomiya Y (2003) A stabilized vegetation index and several mineralogic indices defined for ASTER VNIR and SWIR data. International Geoscience and Remote Sensing Symposium (IGARSS), 2003. IEEE, pp 1552–1554Google Scholar
  45. Pan HJ, Li XX, Wang GW, Qi CS (2013) Mariculture zones extraction using NDWI and NDVI. Adv Mat Res 659:153–155. doi: 10.4028/AMR.4659.4153 CrossRefGoogle Scholar
  46. Pohl C, van Genderen J (2013) Remote sensing image fusion: an update in the context of Digital Earth. Int J Digital Earth 7:158–172. doi: 10.1080/17538947.2013.869266 CrossRefGoogle Scholar
  47. Pournamdari M, Hashim M (2014) Detection of chromite bearing mineralized zones in Abdasht ophiolite complex using ASTER and ETM+ remote sensing data. Arab J Geosci 7:1973–1983. doi: 10.1007/s12517-12013-10927-12510 CrossRefGoogle Scholar
  48. Pradhan B (2013) A comparative study on the predictive ability of the decision tree, support vector machine and neuro-fuzzy models in landslide susceptibility mapping using GIS. Comput Geosci 51:350–365. doi: 10.1016/j.cageo.2012.08.023 CrossRefGoogle Scholar
  49. Rahman AF, Dragoni D, Didan K, Barreto-Munoz A, Hutabarat JA (2013) Detecting large scale conversion of mangroves to aquaculture with change point and mixed-pixel analyses of high-fidelity MODIS data. Remote Sens Environ 130:96–107. doi: 10.1016/j.rse.2012.11.014 CrossRefGoogle Scholar
  50. Rokni K, Hashim M, Hazini S (2011a) Fusion of Aster and Radarsat Sar data using different transforming algorithms of wavelet resolution merge. Aust J Basic Appl Sci 5:991–998Google Scholar
  51. Rokni K, Marghany M, Hashim M, Hazini S (2011) Performance evaluation of global and absolute DEMs generated from ASTER stereo imagery. RF and Microwave Conference (RFM), Serembam, Malaysia, 2011b. IEEE, pp 266–269Google Scholar
  52. Rokni K, Ahmad A, Selamat A, Hazini S (2014) Water feature extraction and change detection using multitemporal Landsat imagery. Remote Sens 6:4173–4189. doi: 10.3390/rs6054173 CrossRefGoogle Scholar
  53. Rokni K, Ahmad A, Solaimani K, Hazini S (2015) A new approach for surface water change detection: integration of pixel level image fusion and image classification techniques. Int J Appl Earth Obs Geoinf 34:226–234. doi: 10.1016/j.jag.2014.08.014 CrossRefGoogle Scholar
  54. Rouse J, Haas R, Schell J, Deering D, Harlan J (1974) Monitoring the vernal advancement and retrogradation (greenwave effect) of natural vegetation. Texas A & M University, TexasGoogle Scholar
  55. Sener S, Sener E, Karagüzel R (2011) Solid waste disposal site selection with GIS and AHP methodology: a case study in Senirkent–Uluborlu (Isparta) Basin, Turkey. Environ Monit Assess 173:533–554. doi: 10.1007/s10661-10010-11403-x CrossRefGoogle Scholar
  56. Sharma R, Ghosh A, Joshi P (2013) Analysing spatio-temporal footprints of urbanization on environment of Surat city using satellite-derived bio-physical parameters. Geocarto Int 28:420–438. doi: 10.1080/10106049.10102012.10715208 CrossRefGoogle Scholar
  57. Shen L, Li C (2010) Water body extraction from Landsat ETM+ imagery using adaboost algorithm. 18th International Conference on Geoinformatics, Beijing, China, 2010. IEEE, pp 1–4Google Scholar
  58. Sun Q, Wu Z, Tan J (2012) The relationship between land surface temperature and land use/land cover in Guangzhou, China. Environ Earth Sci 65:1687–1694. doi: 10.1007/s12665-12011-11145-12662 CrossRefGoogle Scholar
  59. Tehrany MS, Pradhan B, Jebur MN (2014) Flood susceptibility mapping using a novel ensemble weights-of-evidence and support vector machine models in GIS. J Hydrol 512:332–343. doi: 10.1016/j.jhydrol.2014.1003.1008 CrossRefGoogle Scholar
  60. Thome K, Palluconi F, Takashima T, Masuda K (1998) Atmospheric correction of ASTER. IEEE Trans Geosci Remote Sens 36:1199–1211. doi: 10.1109/1136.701026 CrossRefGoogle Scholar
  61. Tien Bui D, Pradhan B, Lofman O, Revhaug I, Dick OB (2012) Landslide susceptibility assessment in the Hoa Binh province of Vietnam: a comparison of the Levenberg–Marquardt and Bayesian regularized neural networks. Geomorphology 171:12–29. doi: 10.1016/j.geomorph.2012.1004.1023 CrossRefGoogle Scholar
  62. Van Den Bergh F, Wessels KJ, Miteff S, Van Zyl TL, Gazendam AD, Bachoo AK (2012) HiTempo: a platform for time-series analysis of remote-sensing satellite data in a high-performance computing environment. Int J Remote Sens 33:4720–4740. doi: 10.1080/01431161.01432011.01638339 CrossRefGoogle Scholar
  63. Vapnik V (2000) The nature of statistical learning theory. Springer-Verlag, New YorkCrossRefGoogle Scholar
  64. Varshney A, Rajesh E (2014) A comparative study of built-up index approaches for automated extraction of built-up regions from remote sensing data. J Indian Soc Remote 42:659–663. doi: 10.1007/s12524-12013-10333-12529 CrossRefGoogle Scholar
  65. Xiu L-n, Liu X-n (2003) Current status and future direction of the study on artificial neural network classification processing in remote sensing. Remote Sens Tech App 18:339–345Google Scholar
  66. Yang G, Pu R, Zhao C, Huang W, Wang J (2011) Estimation of subpixel land surface temperature using an endmember index based technique: a case examination on ASTER and MODIS temperature products over a heterogeneous area. Remote Sens Environ 115:1202–1219. doi: 10.1016/j.rse.2011.1201.1004 CrossRefGoogle Scholar
  67. Yongzhu X, Zhengdong Z, Feng C (2010) Comparison of artificial neural network and support vector machine methods for urban land use/cover classifications from remote sensing images a case study of Guangzhou, South China. International Conference on Computer Application and System Modeling (ICCASM), Taiyuan, China, 2010. IEEE, pp V13-52Google Scholar
  68. 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 24:583–594. doi: 10.1080/01431160304987 CrossRefGoogle Scholar
  69. Zhai S, Jiang T (2014) A novel particle swarm optimization trained support vector machine for automatic sense-through-foliage target recognition system. Knowl-Based Syst 65:50–59. doi: 10.1016/j.knosys.2014.1004.1005 CrossRefGoogle Scholar

Copyright information

© Saudi Society for Geosciences 2015

Authors and Affiliations

  1. 1.Institute of Geospatial Science & Technology (INSTeG), Faculty of Geoinformation and Real StateUniversiti Teknologi MalaysiaSkudaiMalaysia

Personalised recommendations