• P-ISSN 0974-6846 E-ISSN 0974-5645

Indian Journal of Science and Technology


Indian Journal of Science and Technology

Year: 2024, Volume: 17, Issue: 8, Pages: 713-722

Original Article

A Comparative Analysis of Random Forest and Support Vector Machines for Classifying Irrigated Cropping Areas in The Upper-Comoé Basin, Burkina Faso

Received Date:10 January 2024, Accepted Date:08 February 2024, Published Date:14 February 2024


Objectives: This study investigates the performance of two machine-learning algorithms in classifying land areas across the Upper-Comoé basin in Burkina Faso. Methods: Within the Google Earth Engine data processing environment, Support Vector Machine (SVM) and the Random Forest (RF) algorithms were applied to a Landsat-8 OLI image of March 2019, to discriminate agricultural land areas, with an emphasis on irrigated areas. Findings: The results indicated good to excellent classification performance, with overall accuracies and Kappa coefficients between 71% and 99%, and 0.66 and 0.99, respectively. The RF method outperformed the SVM in terms of mapping "accuracy", but in terms of spatial distribution of classes, the SVM method provided a mapping close to reality, due to the density of the classes generated. Novelty: Our findings suggest that remote sensing can constitute a tool fully adapted to the needs of services in charge of agricultural water management in Burkina Faso.

Keywords: Irrigation, Random Forest, Support Vector Machine, Google Earth Engine, Burkina Faso


  1. Palé S, Wellens J, Traoré F, Roncoli C, Sallah AHM, Zangré BVCA, et al. Testing an open app-based water management information system and its uptake among stakeholders in the Upper-Comoé river basin (Burkina Faso) Water International. 2021;46(3):417–431. Available from: https://doi.org/10.1080/02508060.2021.1897382
  2. Zida WA, Traoré F, Bationo BA, Waaub JP. Dynamics of woody plant cover in the Sahelian agroecosystems of the northern region of Burkina Faso since the 1970s–1980s droughts. Canadian Journal of Forest Research. 2020;50(7):659–669. Available from: https://doi.org/10.1139/cjfr-2019-0247
  3. Sawadogo A, Kouadio L, Traoré F, Zwart SJ, Hessels T, Gündoğdu KS. Spatiotemporal Assessment of Irrigation Performance of the Kou Valley Irrigation Scheme in Burkina Faso Using Satellite Remote Sensing-Derived Indicators. ISPRS International Journal of Geo-Information. 2020;9(8):1–23. Available from: https://doi.org/10.3390/ijgi9080484
  4. Traoré F, Bonkoungou J, Compaoré J, Kouadio L, Wellens J, Hallot E, et al. Using Multi-Temporal Landsat Images and Support Vector Machine to Assess the Changes in Agricultural Irrigated Areas in the Mogtedo Region, Burkina Faso. Remote Sensing. 2019;11(12):1–18. Available from: https://doi.org/10.3390/rs11121442
  5. Sawadogo A, Dossou-Yovo ER, Kouadio L, Zwart SJ, Traoré F, Gündoğdu KS. Assessing the biophysical factors affecting irrigation performance in rice cultivation using remote sensing derived information. Agricultural Water Management. 2023;278:1–12. Available from: https://doi.org/10.1016/j.agwat.2022.108124
  6. Zuo W, Mao J, Lu J, Zheng Z, Han Q, Xue R, et al. Mapping Irrigated Areas Based on Remotely Sensed Crop Phenology and Soil Moisture. Agronomy. 2023;13(6):1–19. Available from: https://doi.org/10.3390/agronomy13061556
  7. Weitkamp T, Veldwisch GJ, Karimi P, Fraiture Cd. Mapping irrigated agriculture in fragmented landscapes of sub-Saharan Africa: An examination of algorithm and composite length effectiveness. International Journal of Applied Earth Observation and Geoinformation. 2023;122:1–23. Available from: https://doi.org/10.1016/j.jag.2023.103418
  8. Bastiaanssen WGM, Molden DJ, Makin IW. Remote sensing for irrigated agriculture: examples from research and possible applications. Agricultural Water Management. 2000;46(2):137–155. Available from: https://doi.org/10.1016/S0378-3774(00)00080-9
  9. Shinozuka M, Mansouri B. Synthetic aperture radar and remote sensing technologies for structural health monitoring of civil infrastructure systems. Structural Health Monitoring of Civil Infrastructure Systems. 2009;p. 113–151. Available from: https://doi.org/10.1533/9781845696825.1.114
  10. Wu Q. GIS and Remote Sensing Applications in Wetland Mapping and Monitoring. Comprehensive Geographic Information Systems. 2018;p. 140–157. Available from: https://doi.org/10.1016/B978-0-12-409548-9.10460-9
  11. Li M, Zang S, Zhang B, Li S, Wu C. A Review of Remote Sensing Image Classification Techniques: the Role of Spatio-contextual Information. European Journal of Remote Sensing. 2014;47(1):389–411. Available from: https://doi.org/10.5721/EuJRS20144723
  12. Analyse et diagnostic de l'état des lieux des ressources en eau du bassin. Bobo-Dioulasso, Burkina Faso. VREO Project. 2010.
  13. Rodriguez-Galiano VF, Ghimire B, Rogan J, Chica-Olmo M, Rigol-Sanchez JP. An assessment of the effectiveness of a random forest classifier for land-cover classification. ISPRS Journal of Photogrammetry and Remote Sensing. 2012;67:93–104. Available from: https://doi.org/10.1016/j.isprsjprs.2011.11.002
  14. Ustuner M, Sanli FB, Dixon B. Application of Support Vector Machines for Landuse Classification Using High-Resolution RapidEye Images: A Sensitivity Analysis. European Journal of Remote Sensing. 2015;48(1):403–422. Available from: https://doi.org/10.5721/EuJRS20154823
  15. Mountrakis G, Im J, Ogole C. Support vector machines in remote sensing: A review. ISPRS Journal of Photogrammetry and Remote Sensing. 2011;66(3):247–259. Available from: https://doi.org/10.1016/j.isprsjprs.2010.11.001
  16. Vapnik VN. The Nature of Statistical Learning Theory, Information Science and Statistics (2). (p. XX, 314) New York, NY, USA. Springer. 2000.
  17. Hsu CW, Chang CC, Lin CJ. A Practical Guide to Support Vector Classification. (pp. 1-16) Taipei, Taiwan. National Taiwan University. 2003.
  18. Foody GM, Mathur A. A relative evaluation of multiclass image classification by support vector machines. IEEE Transactions on Geoscience and Remote Sensing. 2004;42(6):1335–1343. Available from: https://doi.org/10.1109/TGRS.2004.827257
  19. Wu TF, Lin CJ, Weng RC. Probability Estimates for Multi-class Classification by Pairwise Coupling. Journal of Machine Learning Research. 2004;5:975–1005. Available from: https://www.csie.ntu.edu.tw/~cjlin/papers/svmprob/svmprob.pdf
  20. Breiman L. Random Forests. Machine Learning. 2001;45(1):5–32. Available from: https://doi.org/10.1023/A:1010933404324
  21. Tumer K, Ghosh J. Analysis of decision boundaries in linearly combined neural classifiers. Pattern Recognition. 1996;29(2):341–348. Available from: https://doi.org/10.1016/0031-3203(95)00085-2
  22. Inglada J, Vincent A, Arias M, Tardy B, Morin D, Rodes I. Operational High Resolution Land Cover Map Production at the Country Scale Using Satellite Image Time Series. Remote Sensing. 2017;9(1):1–35. Available from: https://doi.org/10.3390/rs9010095
  23. Gislason PO, Benediktsson JA, Sveinsson JR. Random Forests for land cover classification. Pattern Recognition Letters. 2006;27(4):294–300. Available from: https://doi.org/10.1016/j.patrec.2005.08.011
  24. Pal M. Random forest classifier for remote sensing classification. International Journal of Remote Sensing. 2005;26(1):217–222. Available from: https://doi.org/10.1080/01431160412331269698
  25. Belgiu M, Drăguţ L. Random forest in remote sensing: A review of applications and future directions. ISPRS Journal of Photogrammetry and Remote Sensing. 2016;114:24–31. Available from: https://doi.org/10.1016/j.isprsjprs.2016.01.011
  26. Lassalle P, Inglada J, Michel J, Grizonnet M, Malik J. A Scalable Tile-Based Framework for Region-Merging Segmentation. IEEE Transactions on Geoscience and Remote Sensing. 2015;53(10):5473–5485. Available from: https://doi.org/10.1109/TGRS.2015.2422848
  27. Landis JR, Koch GG. The Measurement of Observer Agreement for Categorical Data. Biometrics. 1977;33(1):159–174. Available from: https://doi.org/10.2307/2529310
  28. Foody GM. Status of land cover classification accuracy assessment. Remote Sensing of Environment. 2002;80(1):185–201. Available from: https://doi.org/10.1016/S0034-4257(01)00295-4
  29. Streiner DL, Norman GR, Cairney J. Health Measurement Scales: A Practical Guide to Their Development and Use (5). USA. Oxford University Press. 2014.
  30. Congalton RG, Green K. Assessing the Accuracy of Remotely Sensed Data: Principles and Practices (2). (pp. 1-200) Boca Raton. CRC Press. 2008.
  31. Xie Z, Chen Y, Lu D, Li G, Chen E. Classification of Land Cover, Forest, and Tree Species Classes with ZiYuan-3 Multispectral and Stereo Data. Remote Sensing. 2019;11(2):1–27. Available from: https://doi.org/10.3390/rs11020164
  32. Avci C, Budak M, Yağmur N, Balçik FB. Comparison between random forest and support vector machine algorithms for LULC classification. International Journal of Engineering and Geosciences. 2023;8(1):1–10. Available from: https://dergipark.org.tr/en/download/article-file/1943956


© 2024 Traoré et al. This is an open-access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited. Published By Indian Society for Education and Environment (iSee)


Subscribe now for latest articles and news.