(Ecole de Management et d’Innovation Technologique(EMIT), University of Fianarantsoa, Madagascar)(2) Aimé Richard Hajalalaina
(Ecole de Management et d’Innovation Technologique(EMIT), University of Fianarantso, Madagascar)(3) Hasina Rakotonirainy
(Ecole de Management et d’Innovation Technologique(EMIT), University of Fianarantso, Madagascar)(4) Reziky Zafimarina
(Higher Polytechnic School of Antananarivo, University of Antananarivo, Madagascar)*corresponding author
AbstractThis article aims to apply machine learning algorithms to the supervised classification of optical satellite images. Indeed, the latter is efficient in the study of land use. Despite the performance of machine learning in satellite image processing, this can change but depends on the nature of the satellite images used. Moreover, when we use the satellite, then the reliability of one classifier can be different from the others. In this paper, we examined the performance of DT, SVM, KNN, ANN, and RF. Analysis factors were used to investigate further their importance for Sentinel 2, Landsat 8, Terra Modis, and Spot 5 images. The results show that the KNN showed the most interesting accuracy during the analysis of medium and low-resolution images with spectral bands lower or equal to 4, with a higher accuracy of about 93%. The RF completely dominated the other analysis cases, where the higher accuracy was about 94%. The classification accuracy is more reliable with high-resolution images than with the other resolution categories. However, the processing times of high-resolution images are much higher. Moreover, higher accuracy was often achieved with more expensive processing times. Besides, almost all machine learning algorithms suffered from the Hugs phenomenon during the analyses. So, before the classification with machine learning, some preprocessing is needed.
KeywordsSatellite images optical,Machine learning,knowledge,land cover,reliability
|
DOIhttps://doi.org/10.26555/ijain.v8i3.803 |
Article metricsAbstract views : 754 | PDF views : 192 |
Cite |
Full Text Download
|
References
[1] J. Knorn, A. Rabe, V. C. Radeloff, T. Kuemmerle, J. Kozak, and P. Hostert, “Land cover mapping of large areas using chain classification of neighboring Landsat satellite images,” Remote Sens. Environ., vol. 113, no. 5, pp. 957–964, May 2009, doi: 10.1016/J.RSE.2009.01.010.
[2] A. E. Maxwell, T. A. Warner, and F. Fang, “Implementation of machine-learning classification in remote sensing: An applied review,” Int. J. Remote Sens., vol. 39, no. 9, pp. 2784–2817, May 2018, doi: 10.1080/01431161.2018.1433343.
[3] P. Thanh Noi and M. Kappas, “Comparison of Random Forest, k-Nearest Neighbor, and Support Vector Machine Classifiers for Land Cover Classification Using Sentinel-2 Imagery,” Sensors 2018, Vol. 18, Page 18, vol. 18, no. 1, p. 18, Dec. 2017, doi: 10.3390/S18010018.
[4] E. Tomppo and M. Katila, “Satellite image-based national forest inventory of Finland for publication in the IGARSS’91 digest,” Dig. - Int. Geosci. Remote Sens. Symp., vol. 3, pp. 1141–1144, 1991, doi: 10.1109/IGARSS.1991.579272.
[5] S. E. Sesnie, B. Finegan, P. E. Gessler, A. M. S. Smith, R. B. Zayra, and S. Thessler, “The multispectral separability of Costa Rican rainforest types with support vector machines and Random Forest decision trees,” http://dx.doi.org/10.1080/01431160903140803, vol. 31, no. 11, pp. 2885–2909, 2010, doi: 10.1080/01431160903140803.
[6] A. C. Lorena et al., “Comparing machine learning classifiers in potential distribution modelling,” Expert Syst. Appl., vol. 38, no. 5, pp. 5268–5275, May 2011, doi: 10.1016/J.ESWA.2010.10.031.
[7] M. Li, J. Im, and C. Beier, “Machine learning approaches for forest classification and change analysis using multi-temporal Landsat TM images over Huntington Wildlife Forest,” GIScience Remote Sens., vol. 50, no. 4, pp. 361–384, Aug. 2013, doi: 10.1080/15481603.2013.819161.
[8] X. Shang and L. A. Chisholm, “Classification of Australian native forest species using hyperspectral remote sensing and machine-learning classification algorithms,” IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens., vol. 7, no. 6, pp. 2481–2489, 2014, doi: 10.1109/JSTARS.2013.2282166.
[9] A.Ter-Sarkisov," Detection and segmentation of lesion areas in chest CT scans for the prediction of COVID-19," Sci. Inf. Tech. Lett., vol. 1, no. 2, pp. 92-99, Nov. 2020, doi: 10.31763/sitech.v1i2.202.
[10] A. Septiarini, H. Hamdani, M. S. Sauri, and J. A. Widians," Image processing for maturity classification of tomato using otsu and manhattan distance methods," J. Informatika, vol. 16, no. 3, pp. 118-126, Sept. 2022, doi: 10.26555/jifo.v16i1.a21985.
[11] M. Pal and P. M. Mather, “An assessment of the effectiveness of decision tree methods for land cover classification,” Remote Sens. Environ., vol. 86, no. 4, pp. 554–565, Aug. 2003, doi: 10.1016/S0034-4257(03)00132-9.
[12] C. E. Brodley and M. A. Friedl, “Decision tree classification of land cover from remotely sensed data,” Remote Sens. Environ., vol. 61, no. 3, pp. 399–409, Sep. 1997, doi: 10.1016/S0034-4257(97)00049-7.
[13] B. E. Boser, I. M. Guyon, and V. N. Vapnik, “Training algorithm for optimal margin classifiers,” Proc. Fifth Annu. ACM Work. Comput. Learn. Theory, pp. 144–152, 1992, doi: 10.1145/130385.130401.
[14] C. Cortes, V. Vapnik, and L. Saitta, “Support-vector networks,” Mach. Learn. 1995 203, vol. 20, no. 3, pp. 273–297, Sep. 1995, doi: 10.1007/BF00994018.
[15] V. N. Vapnik, “The Nature of Statistical Learning Theory,” Nat. Stat. Learn. Theory, 1995, doi: 10.1007/978-1-4757-2440-0.
[16] -Stéphane -CANU, “Apprentissage et noyaux : séparateur à vaste marge (SVM),” Rev. l’Electricité l’Electronique, vol., no. 07, p. 69, 2006, doi: 10.3845/REE.2006.062.
[17] F. Lauer et al., “Méthodes SVM pour l ’ identification To cite this version : HAL Id : hal-00110344 Méthodes SVM pour l ’ identification,” 2006 Available at : https://hal.archives-ouvertes.fr/hal-00110344.
[18] N. S. Altman, “An introduction to kernel and nearest-neighbor nonparametric regression,” Am. Stat., vol. 46, no. 3, pp. 175–185, 1992, doi: 10.1080/00031305.1992.10475879.
[19] R. E. McRoberts, M. D. Nelson, and D. G. Wendt, “Stratified estimation of forest area using satellite imagery, inventory data, and the k-Nearest Neighbors technique,” Remote Sens. Environ., vol. 82, no. 2–3, pp. 457–468, Oct. 2002, doi: 10.1016/S0034-4257(02)00064-0.
[20] H. Franco-Lopez, A. R. Ek, and M. E. Bauer, “Estimation and mapping of forest stand density, volume, and cover type using the k-nearest neighbors method,” Remote Sens. Environ., vol. 77, no. 3, pp. 251–274, Sep. 2001, doi: 10.1016/S0034-4257(01)00209-7.
[21] E. Tomppo and M. Halme, “Using coarse scale forest variables as ancillary information and weighting of variables in k-NN estimation: a genetic algorithm approach,” Remote Sens. Environ., vol. 92, no. 1, pp. 1–20, Jul. 2004, doi: 10.1016/J.RSE.2004.04.003.
[22] P. M. Atkinson and A. R. L. Tatnall, “Introduction Neural networks in remote sensing,” http://dx.doi.org/10.1080/014311697218700, vol. 18, no. 4, pp. 699–709, 2010, doi: 10.1080/014311697218700.
[23] A. A. Azmer, N. Hassan, S. H. Khaleefah, S. A. Mostafa, and A. A. Ramli, “Comparative analysis of classification techniques for leaves and land cover texture,” Int. J. Adv. Intell. Inform., vol. 7, no. 3, pp. 357–367, Nov. 2021, doi: 10.26555/ijain.v7i3.706.
[24] L. Breiman, “Random forests,” Mach. Learn., vol. 45, no. 1, pp. 5–32, Oct. 2001, doi: 10.1023/A:1010933404324.
[25] R. Haapanen, A. R. Ek, M. E. Bauer, and A. O. Finley, “Delineation of forest/nonforest land use classes using nearest neighbor methods,” Remote Sens. Environ., vol. 89, no. 3, pp. 265–271, Feb. 2004, doi: 10.1016/J.RSE.2003.10.002.
[26] T. Koukal, F. Suppan, and W. Schneider, “The impact of relative radiometric calibration on the accuracy of kNN-predictions of forest attributes,” Remote Sens. Environ., vol. 110, no. 4, pp. 431–437, Oct. 2007, doi: 10.1016/J.RSE.2006.08.016.
[27] A. A. Mehdawi and B. Bin Ahmad, “K-nearest neighbor method for classification of forest encroachment by using reflectance processing of remote sensing spectroradiometer data,” Res. J. Appl. Sci. Eng. Technol., vol. 6, no. 15, pp. 2881–2885, 2013, doi: 10.19026/RJASET.6.3799.
[28] Q. Meng, C. J. Cieszewski, M. Madden, and B. E. Borders, “K Nearest Neighbor Method for Forest Inventory Using Remote Sensing Data,” http://dx.doi.org/10.2747/1548-1603.44.2.149, vol. 44, no. 2, pp. 149–165, Apr. 2013, doi: 10.2747/1548-1603.44.2.149.
[29] A. E. Maxwell, T. A. Warner, and F. Fang, “Implementation of machine-learning classification in remote sensing: An applied review,” Int. J. Remote Sens., vol. 39, no. 9, pp. 2784–2817, May 2018, doi: 10.1080/01431161.2018.1433343.
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
___________________________________________________________
International Journal of Advances in Intelligent Informatics
ISSN 2442-6571 (print) | 2548-3161 (online)
Organized by UAD and ASCEE Computer Society
Published by Universitas Ahmad Dahlan
W: http://ijain.org
E: info@ijain.org (paper handling issues)
andri.pranolo.id@ieee.org (publication issues)
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0