Land Management and Utilization

Research Article

Machine Learning Innovations in LULC Classification: A Comparative Study of SVM, Random Forest, and Decision Trees

Downloads

https://doi.org/10.54963/lmu.v2i1.2356
Volume 2 Issue 1 (2026): In Progress
Copyright (c) 2026 Berna Çalışkan
Creative Commons License

This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.

Copyright

The authors shall retain the copyright of their work but allow the Publisher to publish, copy, distribute, and convey the work.

License

Land Management and Utilization (LMU)  publishes accepted manuscripts under Creative Commons Attribution 4.0 International (CC BY 4.0). Authors who submit their papers for publication by Land Management and Utilization (LMU) agree to have the CC BY 4.0 license applied to their work, and that anyone is allowed to reuse the article or part of it free of charge for any purpose, including commercial use. As long as the author and original source is properly cited, anyone may copy, redistribute, reuse and transform the content.

Authors

  • Berna Çalışkan

    Civil Engineering Department, Istanbul Technical University, Istanbul 34467, Türkiye

Received: 27 August 2025; Revised: 14 November 2025; Accepted: 28 December 2025; Published: 26 March 2026

Classifying land use and land cover (LULC) is a fundamental process in remote sensing and geographical information systems (GIS) that is essential to many applications, including disaster assessment, urban planning, environmental monitoring, and natural resource management. Understanding the dynamics of landscapes and how they evolve over time requires accurate classification of land use and land cover groups. For this reason, straightforward classification methods like decision trees, artificial neural networks and maximum likelihood have historically been employed extensively. However, there has been an increasing interest in investigating machine learning techniques' potential to enhance the precision and effectiveness of LULC classification since their introduction. Computer vision, natural language processing, and remote sensing are just a few of the fields that have greatly benefited from the quick development of machine learning algorithms, especially deep learning approaches. Due to its capacity to automatically extract intricate patterns and features from massive datasets, machine learning-based techniques have become more and more popular in LULC classification jobs in recent years, potentially surpassing conventional approaches. This research paper aims to conduct a Land use classification by using machine learning based (ML) models (Support Vector Machine (SVM) model, Random Forest (RF) and Decision Trees (DT) models) with the use of open-sourced Python modules (Rasterio, Numpy, and Scikit-learn). The comparative analysis demonstrates that the SVM model achieved the highest performance with an Overall Accuracy (OA) of 97.30%, followed by Random Forest at 94.59%, and Decision Tree at 89.19%.

Keywords:

LULC Classification Machine Learning Algorithms Visual Interpretation

References

  1. Bogale, T.; Degefa, S.; Dalle, G.; et al. Machine learning-based analysis of land use and land cover trends in southeastern Ethiopia using Google Earth Engine. Discov. Sustain. 2025, 6, 878. DOI: https://doi.org/10.1007/s43621-025-01709-5
  2. Rawat, K.S.; Kumar, S.; Garg, N. Statistical Comparison of Simple and Machine Learning Based Land Use and Land Cover Classification Algorithms: A Case Study. J. Water Manag. Model. 2024. DOI: https://doi.org/10.14796/JWMM.H524
  3. Xie, G. Machine Learning Methods and Land Use/Land Cover (LULC) in the Coastal Pays de Brest. PhD Thesis, Université de Bretagne Occidentale–Brest, Brest, France, 2023.
  4. Hermosilla, T.; Wulder, M.A.; White, J.C.; et al. Land cover classification in an era of big and open data: Optimizing localized implementation and training data selection to improve mapping outcomes. Remote Sens. Environ. 2022, 268, 112780. DOI: https://doi.org/10.1016/j.rse.2021.112780
  5. Amin, G.; Imtiaz, I.; Haroon, E.; et al. Assessment of Machine Learning Algorithms for Land Cover Classification in a Complex Mountainous Landscape. J. Geovis. Spat. Anal. 2024, 8, 34. DOI: https://doi.org/10.1007/s41651-024-00195-z
  6. Taati, A.; Sarmadian, F.; Mousavi, A.; et al. Land Use Classification using Support Vector Machine and Maximum Likelihood Algorithms by Landsat 5 TM Images. Walailak J. Sci. Technol. 2014, 12, 681–687. DOI: https://doi.org/10.14456/wjst.2015.33
  7. Singh, A.R.; Sharma, R. Prevailing Trends and Innovations in Machine Learning Techniques and Applications. Int. J. Sci. Technol. 2025, 16, 1–10. Available online: https://www.ijsat.org/papers/2025/2/6316.pdf
  8. Ahmad, H.; Abdallah, M.; Jose, F.; et al. Evaluation and mapping of predicted future land use changes using hybrid models in a coastal area. Ecol. Inform. 2023, 78, 102324. DOI: https://doi.org/10.1016/j.ecoinf.2023.102324
  9. Dapke, P.; Syed, A.; Nagare, S.; et al. A Comparative Analysis of Machine Learning Techniques for LULC Classification Using Landsat-8 Satellite Imagery. Int. J. Eng. Geosci. 2025, 10, 1–10. DOI: https://doi.org/10.26833/ijeg.1503104
  10. Phiri, D.; Simwanda, M.; Nyirenda, V.; et al. Decision Tree Algorithms for Developing Rulesets for Object-Based Land Cover Classification. ISPRS Int. J. Geo-Inf. 2020, 9, 329. DOI: https://doi.org/10.3390/ijgi9050329
  11. Alshari, E.A.; Gawali, B.W. Development of classification system for LULC using remote sensing and GIS. Glob. Transit. Proc. 2021, 2, 8–17. DOI: https://doi.org/10.1016/j.gltp.2021.01.002
  12. Talukdar, S.; Singha, P.; Mahato, S.; et al. Land-Use Land-Cover Classification by Machine Learning Classifiers for Satellite Observations—A Review. Remote Sens. 2020, 12, 1135. DOI: https://doi.org/10.3390/rs12071135
  13. Basheer, S.; Wang, X.; Farooque, A.A.; et al. Comparison of Land Use Land Cover Classifiers Using Different Satellite Imagery and Machine Learning Techniques. Remote Sens. 2022, 14, 4978. DOI: https://doi.org/10.3390/rs14194978
  14. Mahmoud, R.; Hassanin, M.; Al Feel, H.; et al. Machine Learning-Based Land Use and Land Cover Mapping Using Multi-Spectral Satellite Imagery: A Case Study in Egypt. Sustainability 2023, 15, 9467. DOI: https://doi.org/10.3390/su15129467
  15. Waleed, M. Mastering Machine Learning Based Land Use Classification with Python: A Comprehensive Guide! Available online: https://waleedgeo.medium.com/lulc-py-78cb954673d (accessed on 26 May 2025).
  16. Lu, D.; Weng, Q. Use of impervious surface in urban land-use classification. Remote Sens. Environ. 2006, 102, 146–160. DOI: https://doi.org/10.1016/j.rse.2006.02.010
  17. Deval, K.; Joshi, P.K. Vegetation type and land cover mapping in a semi-arid heterogeneous forested wetland of India: Comparing image classification algorithms. Environ. Dev. Sustain. 2022, 24, 3947–3966. DOI: https://doi.org/10.1007/s10668-021-01596-6
  18. Codecademy Team. Scikit-Learn Tutorial: Python Machine Learning Model Building. Available online: https://www.codecademy.com/article/scikit-learn-tutorial (accessed on 26 May 2025).
  19. Dennis, T. Confusion Matrix Visualization. Available online: https://medium.com/@dtuk81/confusion-matrix-visualization-fc31e3f30fea (accessed on 26 May 2025).
  20. Waleedgeo/lulc_py. Available online: https://github.com/waleedgeo/lulc_py/tree/main/materials/results (accessed on 26 May 2025).
  21. Bhat, R. Extracting Metadata from TIFF Images Using Python. Available online: https://ra-bhat2002.medium.com/extracting-metadata-from-tiff-images-using-python-c1f3b38ab5ce (accessed on 26 May 2025).
  22. Rasterio. Available online: https://github.com/rasterio/rasterio (accessed on 26 May 2025).
  23. Yang, J.; Xu, J.; Lv, Y.; et al. Deep learning-based automated terrain classification using high-resolution DEM data. Int. J. Appl. Earth Obs. Geoinf. 2023, 118, 103249. DOI: https://doi.org/10.1016/j.jag.2023.103249
  24. Rasterio. Available online: https://geog-510.gishub.org/book/geospatial/rasterio.html (accessed on 26 May 2025).
  25. Chachondhia, P.; Shakya, A.; Kumar, G. Performance evaluation of machine learning algorithms using optical and microwave data for LULC classification. Remote Sens. Appl. Soc. Environ. 2021, 23, 100599. DOI: https://doi.org/10.1016/j.rsase.2021.100599
  26. Jansen, L.J.M.; Badea, A.; Milenov, P.; et al. The Use of the Land-Cover Classification System in Eastern European Countries: Experiences, Lessons Learnt and the Way Forward. In Land Use and Land Cover Mapping in Europe; Springer: Dordrecht, The Netherlands, 2014; pp. 297–314.