Volume 7, Issue 4 (2019)
ECOPERSIA 2019, 7(4): 183-193 |
Back to browse issues page
Download citation:
BibTeX | RIS | EndNote | Medlars | ProCite | Reference Manager | RefWorks
Send citation to:
BibTeX | RIS | EndNote | Medlars | ProCite | Reference Manager | RefWorks
Send citation to:
Hayatzadeh M, Fathzadeh A, Moosavi V. Improving the Accuracy of Land Use/Cover Maps using an
Optimization Technique. ECOPERSIA 2019; 7 (4) :183-193
URL: http://ecopersia.modares.ac.ir/article-24-31343-en.html
URL: http://ecopersia.modares.ac.ir/article-24-31343-en.html
1- Nature Engineering Department, Agriculture & Natural Resources Faculty, Ardakan University, Yazd, Iran , mhayatzadeh@ardakan.ac.ir
2- Nature Engineering Department, Agriculture & Natural Resources Faculty, Ardakan University, Yazd, Iran
3- Watershed Management Engineering Department, Natural Resources Faculty, Tarbiat Modares University, Tehran, Iran
2- Nature Engineering Department, Agriculture & Natural Resources Faculty, Ardakan University, Yazd, Iran
3- Watershed Management Engineering Department, Natural Resources Faculty, Tarbiat Modares University, Tehran, Iran
Abstract: (4160 Views)
Mapping of Land use/cover is important for many activities of planning and management, especially in arid areas. Nowadays, satellite imagery and remote sensing techniques, which provide timely and high capability data, are widely used in producing this kind of mapping. The main objective of this study is to produce an actual land use map using advanced pixel-based (MLP, SVM, and SOM) approaches. The most important challenge, in this case, is to determine the optimum structure of classification methods. The Taguchi method is used to optimize the structure of MLP, SVM, and SOM methods. Results show that the Taguchi method can be effectively used to cope with this problem. It significantly reduces the number of classification tests. We also showed that there are significant differences between the results of the SVM method with those of the MLP and SOM methods (χ2 more than 100) and that SVM model is more efficient than other methods. The accurate map produced by the optimized SVM approach (Overall accuracy of 0.93) showed that this method has a better performance.
Article Type: Original Research |
Subject:
Watershed Management
Received: 2019/03/15 | Accepted: 2019/09/14 | Published: 2019/12/21
Received: 2019/03/15 | Accepted: 2019/09/14 | Published: 2019/12/21
References
1. Groot R. Function-analysis and valuation as a tool to assess land use conflicts in planning for sustainable, multi-functional landscapes. Landsc Urban Plan. 2006;75(3-4):175-86. [Link] [DOI:10.1016/j.landurbplan.2005.02.016]
2. Jafarian Jeloudar Z, Shabanzadeh S, Kavian A, Shokri M. Spatial variability of soil features affected by landuse type using geostatistics. Ecopersia. 2014;2(3):667-79. [Link]
3. Parvizi Y, Heshmati M, Gheituri M. Intelligent approaches to analysing the importance of land use management in soil carbon stock in a semiarid ecosystem, west of Iran. Ecopersia. 2017;5(1):1699-709. [Link] [DOI:10.18869/modares.ecopersia.5.1.1699]
4. Farajollahi A, Asgari HR, Ownagh M, Mahboubi MR, Salman Mahini A. Socio-economic factors influencing land use changes in Maraveh Tappeh Region, Iran. Ecopersia. 2017;5(1):1683-97. [Link] [DOI:10.18869/modares.ecopersia.5.1.1683]
5. Ildoromi A, Safari Shad M. Land use change prediction using a hybrid (CA-Markov) model. Ecopersia. 2017;5(1):1631-40. [Link] [DOI:10.18869/modares.ecopersia.5.1.1631]
6. Demková L, Bobuľská L. Two centuries of land use changes influenced by intensive mining and smelting activities (Middle Spis, Slovakia). Ecopersia. 2018;6(3):147-53. [Link]
7. Afshari M, Hashemi SS, Attaeian B. Land use change effect on physical, chemical, and mineralogical properties of calcareous soils in western Iran. Ecopersia. 2019;7(1):47-57. [Link]
8. Gong P, Howarth PJ. The use of structural information for improving land-cover classification accuracies at the rural-urban fringe. Photogramm Eng Remote Sens. 1990;56(1):67-73. [Link]
9. Gong P, Howarth PJ. An assessment of some factors influencing multispectral land-cover classification. Photogramm Eng Remote Sens. 1990;56(5):597-603. [Link]
10. Gong P, Howarth PJ. Frequency-based contextual classification and gray-level vector reduction for land-use identification. Photogramm Eng Remote Sens. 1992;58(4):423-37. [Link]
11. Deguchi C, Sugio S. Estimations for percentage of impervious area by the use of satellite remote sensing imagery. Water Sci Technol. 1994;29(1-2):135-44. [Link] [DOI:10.2166/wst.1994.0659]
12. Ridd MK. Exploring a V-I-S (vegetation-impervious surface-soil) model for urban ecosystem analysis through remote sensing: Comparative anatomy for cities. Int J Remote Sens. 1995;16(12):2165-85. [Link] [DOI:10.1080/01431169508954549]
13. Xu B, Gong P, Seto E, Spear R. Comparison of gray-level reduction and different texture spectrum encoding methods for land-use classification using a panchromatic IKONOS image. Photogramm Eng Remote Sens. 2003;69(5):529-36. [Link] [DOI:10.14358/PERS.69.5.529]
14. Moosavi V, Talebi A, Shirmohammadi B. Producing a landslide inventory map using pixel-based and object-oriented approaches optimized by Taguchi method. Geomorphology. 2014;204:646-56. [Link] [DOI:10.1016/j.geomorph.2013.09.012]
15. Breiman L. Random forests. Mach Learn. 2001;45(1):5-32. [Link] [DOI:10.1023/A:1010933404324]
16. Huang C, Davis LS, Townshend JRG. An assessment of support vector machines for land cover classification. Int J Remote Sens. 2002;23(4):725-49. [Link] [DOI:10.1080/01431160110040323]
17. Pal M. Random forest classifier for remote sensing classification. Int J Remote Sens. 2005;26(1):217-22. [Link] [DOI:10.1080/01431160412331269698]
18. Carreiras J, Pereira J, Campagnolo M, Shimabukuro YE. Assessing the extent of agriculture/pasture and secondary succession forest in the Brazilian Legal Amazon using SPOT VEGETATION data. Remote Sens Environ. 2006;101(3):283-98. [Link] [DOI:10.1016/j.rse.2005.12.017]
19. Gislason PO, Benediktsson JA, Sveinsson JR. Random forests for land cover classification. Pattern Recogn Lett. 2006;27(4):294-300. [Link] [DOI:10.1016/j.patrec.2005.08.011]
20. Brenning A. Benchmarking classifiers to optimally integrate terrain analysis and multispectral remote sensing in automatic rock glacier detection. Remote Sens Environ. 2009;113(1):239-47. [Link] [DOI:10.1016/j.rse.2008.09.005]
21. Otukei JR, Blaschke T. Land cover change assessment using decision trees, support vector machines and maximum likelihood classification algorithms. Int J Appl Earth Obs Geoinform. 2010;12(Suppl1):S27-31. [Link] [DOI:10.1016/j.jag.2009.11.002]
22. Oruc M, Marangoz M, Buyuksalih G. Comparison of pixel-based and object-oriented classification approaches using landsat-7 etm spectral bands. Int Archiv Photogrammetry Remote Sensing spatial Inf Sci. 2004;35:1118-22. [Link]
23. Pakhale GK, Gupta PK. Comparison of advanced pixel based (ANN and SVM) and object-oriented classification approaches using landsat-7 Etm+data. Int J Eng Technol. 2010;2(4):245-51. [Link]
24. Vapnik V. Statistical learning theory. 2nd Edition Berlin: Springer Science & Business Media; 1999. [Link]
25. Wang TY, Huang CY. Improving forecasting performance by employing the Taguchi method. Eur J Oper Res. 2007;176(2):1052-65. [Link] [DOI:10.1016/j.ejor.2005.08.020]
26. Chou ChS, Ho CY, Huang CI. The optimum conditions for comminution of magnetic particles driven by a rotating magnetic field using the Taguchi method. Adv Powder Technol. 2009;20(1):55-61. [Link] [DOI:10.1016/j.apt.2008.02.002]
27. Hayatzadeh M, Ekhtesasi M, Malekinezhad H, Fathzadeh A, Azimzadeh H. Simulation of Future Land use map of the catchment area, with the Integration of cellular automata and markov chain models based on selection of the best classification algorithm: A case study of Fakhrabad Basin of Mehriz, Yazd. Q J Environ Eros Res. 2017;6(24):1-22. [Persian] [Link]
28. Elachi Ch, Van Zyl JJ. Introduction to the physics and techniques of remote sensing. 2nd Edition. Hoboken: Wiley; 2006. [Link] [DOI:10.1002/0471783390]
29. Mather P, Tso B. Classification methods for remotely sensed data. 2nd Edition. Boca Raton: CRC Press; 2009. p. 367. [Link]
30. Frizzelle BG, Moody A. Mapping continuous distributions of land cover: A comparison of maximum-likelihood estimation and artificial neural networks. Photogramm Eng Remote Sens. 2001;67(6):693-706. [Link]
31. Hopfield JJ. Neural networks and physical systems with emergent collective computational abilities. Proc Natl Acad Sci U S A. 1982;79(8):2554-8. [Link] [DOI:10.1073/pnas.79.8.2554]
32. Richards JA, Jia X. Remote Sensing Digital Image Analysis. Berlin: Springer-Verlag; 2006. [Link]
33. Kohonen T. Self-organized formation of topologically correct feature maps. Biol Cybern. 1982;43(1):59-69. [Link] [DOI:10.1007/BF00337288]
34. Sathya R, Abraham A. Comparison of supervised and unsupervised learning algorithms for pattern classification. Int J Adv Res Artif Intell. 2013;2(2):34-8. [Link] [DOI:10.14569/IJARAI.2013.020206]
35. Shrivastava P, Singh P, Shrivastava G. Image classification using SOM and SVM feature extraction. Int J Comput Sci Inf Technol. 2014;5(1):264-71. [Link]
36. Hsu CW, Chang CC, Lin CJ. A practical guide to support vector classification [Internet]. Taipei: National Taiwan University; 2013 [cited 2018 Apr]. Available from: URL link: https://www.csie.ntu.edu.tw/~cjlin/papers/guide/guide.pdf. [Link]
37. Belousov AI, Verzakov SA, Von Frese J. Applicational aspects of support vector machines. J Chemom. 2002;16(8‐10):482-9. [Link] [DOI:10.1002/cem.744]
38. Marjanović M, Kovačević M, Bajat B, Voženílek V. Landslide susceptibility assessment using SVM machine learning algorithm. Eng Geol. 2011;123(3):225-34. [Link] [DOI:10.1016/j.enggeo.2011.09.006]
39. Laliberte AS, Rango A, Havstad KM, Paris JF, Beck RF, McNeely R, et al. Object-oriented image analysis for mapping shrub encroachment from 1937 to 2003 in southern New Mexico. Remote Sens Environ. 2004;93(1-2):198-210. [Link] [DOI:10.1016/j.rse.2004.07.011]
40. Barlow J, Franklin S, Martin Y. High spatial resolution satellite imagery, DEM derivatives, and image segmentation for the detection of mass wasting processes. Photogramm Eng Remote Sens. 2006;72(6):687-92. [Link] [DOI:10.14358/PERS.72.6.687]
41. Dragut L, Blaschke T. Automated classification of landform elements using object-based image analysis. Geomorphology. 2006;81(3-4):330-44. [Link] [DOI:10.1016/j.geomorph.2006.04.013]
42. Kerle N, de Leeuw J. Reviving legacy population maps with object-oriented image processing techniques. IEEE Trans Geosci Remote Sens. 2009;47(7):2392-402. [Link] [DOI:10.1109/TGRS.2008.2010853]
43. Espindola GM, Câmara G, Reis IA, Bins LS, Monteiro AM. Parameter selection for region‐growing image segmentation algorithms using spatial autocorrelation. Int J Remote Sens. 2006;27(14):3035-40. [Link] [DOI:10.1080/01431160600617194]
44. Foody GM. Thematic map comparison: Evaluating the statistical significance of differences in classification accuracy. Photogramm Eng Remote Sens. 2004;70(5):627-33. [Link] [DOI:10.14358/PERS.70.5.627]
45. Zar JH. Biostatistical analysis. 5th Edition. London: Pearson; 2009. [Link]
46. Bradley JV. Distribution-free statistical tests. Upper Saddle River: Prentice-Hall; 1968. [Link]
47. Masoudi M, Jahantigh H, Jokar P. Land use planning using a quantitative model and geographic information system (GIS) in Sistan region, Iran. Ecopersia. 2017;5(2):1745-59. [Link]
48. Zanaty EA. Support vector machines (SVMs) versus multilayer perception (MLP) in data classification. Egypt Inform J. 2012;13(3):177-83. [Link] [DOI:10.1016/j.eij.2012.08.002]
49. Bagan H, Wang Q, Watanabe M, Kameyama S, Bao Y. Land-cover classification using ASTER multi-band combinations based on wavelet fusion and SOM neural network. Photogramm Eng Remote Sens. 2008;74(3):333-42. [Link] [DOI:10.14358/PERS.74.3.333]
Send email to the article author
| Rights and permissions | |
 |
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License. |