Comparison of Random Forest and Support Vector Machine algorithms in urban land use and land cover classification

Nur Hakimah Asnawi, Lam Kuok Choy, Rosniza Aznie Che Rose

Abstract


A precise and up-to-date land use and land cover (LULC) map is crucial for sustainable development planning and monitoring environmental change. Various machine learning (ML) algorithms are widely used to classify remote sensing data for mapping the Earth’s surface, particularly Random Forest (RF) and Support Vector Machine (SVM). Although numerous comparative studies evaluating these two algorithms exist, their results remain inconsistent and vary across geographic regions and datasets. This study aims to evaluate the accuracy of ML algorithms of Random Forest (RF) and Support Vector Machine (SVM) for LULC classification in the Seremban and Port Dickson districts, Negeri Sembilan, Malaysia. LULC classification was conducted using the Google Earth Engine (GEE) platform, utilizing Landsat 5 TM imagery for the year 2010 and Landsat 8 OLI imagery for the year 2020. The findings revealed that the RF classifier outperformed the SVM classifier, achieving higher overall accuracy of 0.918 (2010) and 0.890 (2020) compared to 0.780 (2010) and 0.842 (2020) for SVM. RF also demonstrated a higher Kappa coefficient (0.8589 in 2010; 0.8093 in 2020) than SVM (0.6384 in 2010; 0.7318 in 2020). Based on the accuracy metrics, forest, agriculture and built-up areas exhibited lower classification accuracy due to mixed and complex LULC patterns, whereas water bodies were classified with high accuracy by both classifiers due to their distinct spectral characteristics. Overall, the RF algorithm demonstrates superior performance in mixed-class classification and more efficiently handles large volumes of medium-resolution images. Future research may explore hybrid models that combine RF with deep learning or other ML algorithms, alongside higher-resolution imagery and global datasets, to improve classification accuracy and broaden comparative perspectives.

 

Keywords: Google Earth Engine, kappa coefficient, Landsat satellite imagery, land use and land cover, Random Forest, Support Vector Machine

Keywords


Google Earth Engine, kappa coefficient, Landsat satellite imagery, land use and land cover, Random Forest, Support Vector Machine

Full Text:

PDF

References


Aburas, M. M., Ho, Y. M., Ramli, M. F., & Ash’aari, Z. H. (2018). Monitoring and assessment of urban growth patterns using spatio-temporal built-up area analysis. Environmental Monitoring and Assessment, 190(3), 156.

Adugna, T., Xu, W., & Fan, J. (2022). Comparison of Random Forest and Support Vector Machine classifiers for regional land cover mapping using coarse resolution FY-3C images. Remote Sensing, 14(3), 574.

Alam, A., Bhat, M. S., & Maheen, M. (2020). Using Landsat satellite data for assessing the land use and land cover change in Kashmir valley. GeoJournal, 85(6), 1529-1543.

Alshehri, B., Zhang, Z., & Liu, X. (2025). A review of Google Earth Engine for land use and land cover change analysis: Trends, applications, and challenges. ISPRS International Journal of Geo-Information, 14(11), 416.

Amani, M., Ghorbanian, A., Ahmadi, S. A., Kakooei, M., Moghimi, A., Mirmazloumi, S. M., Moghaddam, S. H. A., Mahdavi, S., Ghahremanloo, M., Parsian, S., Wu, Q., & Brisco, B. (2020). Google Earth Engine cloud computing platform for remote sensing big data applications: A comprehensive review. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 13, 5326-5350.

Amini, S., Saber, M., Rabiei-Dastjerdi, H., & Homayouni, S. (2022). Urban land use and land cover change analysis using Random Forest classification of Landsat time series. Remote Sensing, 14(11), 2654.

Amiren, M., Nazhifah, S. A., Rusdi, M., & Misbullah, A. (2024). Comparison of Support Vector Machine and Random Forest methods on Sentinel-2A Imagery for land cover identification in Banda Aceh City using Google Earth Engine. The Indonesian Journal of Computer Science, 13(6).

Atef, I., Ahmed, W., & Abdel-Maguid, R. H. (2023). Modelling of land use land cover changes using machine learning and GIS techniques: A case study in El-Fayoum Governorate, Egypt. Environmental Monitoring and Assessment, 195(6), 637.

Avcı, C., Budak, M., Yağmur, N., & Balçık, F. (2023). Comparison between Random Forest and Support Vector Machine algorithms for LULC classification. International Journal of Engineering and Geosciences, 8(1), 1-10.

Bogale, T., Degefa, S., Dalle, G., & Abebe, G. (2025). Machine learning-based analysis of land use and land cover trends in southeastern Ethiopia using Google Earth Engine. Discover Sustainability, 6(1), 878.

Cai, G., Ren, H., Yang, L., Zhang, N., Du, M., & Wu, C. (2019). Detailed urban land use land cover classification at the metropolitan scale using a three-layer classification scheme. Sensors, 19(14), 3120.

Dabija, A., Kluczek, M., Zagajewski, B., Raczko, E., Kycko, M., Al-Sulttani, A.H., Tardà, A., Pineda, L. and Corbera, J. (2021). Comparison of Support Vector Machines and Random Forests for corine land cover mapping. Remote Sensing, 13(4), 777.

Department of Statistics Malaysia (2024). Data catalogue.

Dewan, A. M., & Yamaguchi, Y. (2009). Land use and land cover change in Greater Dhaka, Bangladesh: Using remote sensing to promote sustainable urbanization. Applied Geography, 29(3), 390-401.

El-Raey, M., Nasr, S. M., El-Hattab, M. M., & Frihy, O. E. (1995). Change detection of Rosetta promontory over the last forty years. Remote Sensing, 16(5), 825-834.

Gautam, L., & Rai, R. (2022). Land use and land cover change analysis using Google Earth Engine in Manamati watershed of Kathmandu district, Nepal. The Third Pole Journal of Geography Education, 22, 49-60.

Guan, H., Yu, J., Li, J., & Luo, L. (2012). Random Forests-based feature selection for land-use classification using LiDAR data and orthoimagery. The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 39, 203-208.

Hasan, S. H., AL-Hameedawi, A. N., & Ismael, H. S. (2022). Supervised classification model using Google Earth Engine development environment for Wasit Governorate. IOP Conference Series: Earth and Environmental Science, 961(1), 012051.

Hayashi, T., Tamukoh, H., & Kubota, R. (2019). Modified hierarchical k-Nearest Neighbor method with application to land-cover classification. International Workshop on Advanced Image Technology (IWAIT), 11049, 746-749.

Jozdani, S. E., Johnson, B. A., & Chen, D. (2019). Comparing Deep Neural Networks, Ensemble Classifiers, and Support Vector Machine algorithms for object-based urban land use/land cover classification. Remote Sensing, 11(14), 1713.

Kavzoglu, T., Tonbul, H., Yildiz Erdemir, M., & Colkesen, I. (2018). Dimensionality reduction and classification of hyperspectral images using object-based image analysis. Journal of the Indian Society of Remote Sensing, 46(8), 1297-1306.

Kumar, M. D., Bhavani, Y. L., Sahithi, V. S., Kumar, K. A., & Cheepulla, H. (2024). Analysing the impact of training sample size in classification of satellite imagery. 5th International Conference on Data Intelligence and Cognitive Informatics (ICDICI).

Landis, J. R., & Koch, G. G. (1977). The measurement of observer agreement for categorical data. Biometrics, 159-174.

Liu, X., Hu, G., Chen, Y., Li, X., Xu, X., Li, S., Pei, F., & Wang, S. (2018). High-resolution multi-temporal mapping of global urban land using Landsat images based on the Google Earth Engine Platform. Remote Sensing of Environment, 209, 227-239.

Loukika, K. N., Keesara, V. R., & Sridhar, V. (2021). Analysis of land use and land cover using machine learning algorithms on Google Earth Engine for Munneru River Basin, India. Sustainability, 13(24), 13758.

Ma, H., Gao, X., & Gu, X. (2019). Random Forest classification of Landsat 8 imagery for the complex terrain area based on the combination of spectral, topographic and texture information. Journal of Geo-information Science, 21, 359-371.

Ma, T. Z., Teh, B. T., & Kho, M. Y. (2024). Land use change and ecological network in rapid urban growth region in Selangor region, Malaysia. Scientific Reports, 14(1), 16470.

Ma, Y., Jiang, Q., Meng, Z., Li, Y., Wang, D., & Liu, H. (2016). Classification of land use in farming area based on Random Forest algorithm. Transactions of the Chinese Society for Agricultural Machinery, 47(1), 297-303.

Manandhar, R., Odeh, I. O., & Ancev, T. (2009). Improving the accuracy of land use and land cover classification of Landsat data using post-classification enhancement. Remote Sensing, 1(3), 330-344.

Maxwell, A. E., & Warner, T. A. (2020). Thematic classification accuracy assessment with inherently uncertain boundaries: An argument for center-weighted accuracy assessment metrics. Remote Sensing, 12(12), 1905.

Mellor, A., Haywood, A., Stone, C., & Jones, S. (2013). The performance of Random Forests in an operational setting for large area sclerophyll forest classification. Remote Sensing, 5(6), 2838-2856.

Ming, D., Zhou, T., Wang, M., & Tan, T. (2016). Land cover classification using Random Forest with genetic algorithm-based parameter optimization. Journal of Applied Remote Sensing, 10(3), 035021-035021.

Mirjalalov, N., Teshaev, N., Safarov, E., Gerts, J., Mominov, A., & Pardaboyev, A. (2025). Comparative analysis of Random Forest and Support Vector Machine for LULC classification in Tashkent Region using Landsat-8 imagery. InterCarto InterGIS, 31(1), 519.

Nadzri, I. F. M., Khalid, N., Wahab, W. A., & Hashim, N. (2023). Analyzing the effectiveness of Support Vector Machine and Random Forest classifiers in delineating the green area. IOP Conference Series: Earth and Environmental Science, 1217(1), 012032.

Nimbalkar, P., Jarocinska, A., & Zagajewski, B. (2018). Optimal band configuration for the roof surface characterization using hyperspectral and LiDAR imaging. Journal of Spectroscopy, 2018(1), 6460518.

Nuissl, H., & Siedentop, S. (2021). Urbanisation and land use change. Sustainable Land Management in a European Context, 8, 75-99.

Olokeogun, O. S., Iyiola, K., & Iyiola, O. F. (2014). Application of remote sensing and GIS in land use/land cover mapping and change detection in Shasha forest reserve, Nigeria. The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 40, 613-616.

Othman, A. G., Ali, K. H., Yin, I., Tan, M. L., & Jizan, N. H. M. (2021). Urbanization and land use changes in rural town: Guar Cempedak, Kedah. Planning Malaysia, 19(19).

Ouma, Y. O., Keitsile, A., Nkwae, B., Odirile, P., Moalafhi, D., & Qi, J. (2023). Urban land-use classification using machine learning classifiers: Comparative evaluation and post-classification multi-feature fusion approach. European Journal of Remote Sensing, 56(1), 2173659.

Panuju, D. R., Paull, D. J., & Griffin, A. L. (2020). Change detection techniques based on multispectral images for investigating land cover dynamics. Remote Sensing, 12(11), 1781.

PLANMalaysia. (2021). Rancangan Fizikal Negara Keempat.

Rane, N. L., Achari, A., Choudhary, S. P., & Giduturi, M. (2023). Effectiveness and capability of remote sensing (RS) and geographic information systems (GIS): A powerful tool for land use and land cover (LULC) change and accuracy assessment. International Journal of Innovative Science and Research Technology, 8(4), 4375-4392.

Samardžić‐Petrović, M., Dragićević, S., Kovačević, M., & Bajat, B. (2016). Modeling urban land use changes using support vector machines. Transactions in GIS, 20(5), 718-734.

Samardžić-Petrović, M., Kovačević, M., Bajat, B., & Dragićević, S. (2017). Machine learning techniques for modelling short term land-use change. ISPRS International Journal of Geo-information, 6(12), 387.

Shang, K., Li, P., & Cheng, T. (2011). Land cover classification of hyperspectral data using composite kernel support vector machines. Acta Scientiarum Naturalium Universitatis Pekinensis, 47(1), 109-114.

Shapla, T., Park, J., Hongo, C., & Kuze, H. (2015). Agricultural land cover change in Gazipur, Bangladesh, in relation to local economy studied using Landsat images. Advances in Remote Sensing, 4(3), 214-223.

Sharma, V., Singh, A., Prasad, Y., Gupta, S., Choudhury, T., & Kotecha, K. (2023). Land Use and Land Cover Classification for Temporal Analysis on Ganjam District Region, Odisha Using Remote Sensing and Google Earth Engine. IEEE International Conference on ICT in Business Industry & Government (ICTBIG).

Shetty, S., Gupta, P. K., Belgiu, M., & Srivastav, S. K. (2021). Assessing the effect of training sampling design on the performance of machine learning classifiers for land cover mapping using multi-temporal remote sensing data and Google Earth Engine. Remote Sensing, 13(8), 1433.

Singh, P., Singh, N., Singh, K. K., & Singh, A. (2021). Diagnosing of disease using machine learning. In. K. K. Singh, M. Elhoseny, A, Singh, & A. A. Elngar (Eds.), Machine learning and the internet of medical things in healthcare (pp. 89-111). Academic Press.

Tamiminia, H., Salehi, B., Mahdianpari, M., Quackenbush, L., Adeli, S., & Brisco, B. (2020). Google Earth Engine for geo-big data applications: A meta-analysis and systematic review. ISPRS Journal of Photogrammetry and Remote Sensing, 164, 152-170.

Tesfaye, W., Elias, E., Warkineh, B., Tekalign, M., & Abebe, G. (2024). Modeling of land use and land cover changes using Google Earth Engine and machine learning approach: Implications for landscape management. Environmental Systems Research, 13(1), 31.

Thanh Noi, P., & Kappas, M. (2017). Comparison of random forest, k-nearest neighbor, and Support Vector Machine classifiers for land cover classification using Sentinel-2 imagery. Sensors, 18(1), 18.

Thiyagarajan, G., & Vijayalakshmi, V. (2024). Classification of land cover using machine learning models in Landsat satellite data. 15th International Conference on Computing Communication and Networking Technologies (ICCCNT).

Tokar, O., Havryliuk, S., Korol, M., Vovk, O., & Kolyasa, L. (2018). Using Multitemporal and Multisensoral Images for Land Cover Interpretation with Random Forest Algorithm in the Prykarpattya Region of Ukraine. In Conference on Computer Science and Information Technologies (pp. 48-64). Springer International Publishing.

Ustuner, M., Sanli, F. B., & Dixon, B. (2015). Application of support vector machines for land use classification using high-resolution rapid eye images: A sensitivity analysis. European Journal of Remote Sensing, 48(1), 403-422.

Wickham, J., Stehman, S. V., Gass, L., Dewitz, J. A., Sorenson, D. G., Granneman, B. J., Poss, R.V., & Baer, L. A. (2017). Thematic accuracy assessment of the 2011 national land cover database (NLCD). Remote Sensing of Environment, 191, 328-341.

Wu, Y., Zhang, X., & Shen, L. (2011). The impact of urbanization policy on land use change: A scenario analysis. Cities, 28(2), 147-159.

Xu, J., Chen, C., Zhou, S., Hu, W., & Zhang, W. (2024). Land use classification in mine-agriculture compound area based on multi-feature random forest: A case study of Peixian. Frontiers in Sustainable Food Systems, 7, 1335292.

Yuh, Y. G., Tracz, W., Matthews, H. D., & Turner, S. E. (2023). Application of machine learning approaches for land cover monitoring in northern Cameroon. Ecological Informatics, 74, 101955.

Zafar, Z., Zubair, M., Zha, Y., Fahd, S., & Nadeem, A. A. (2024). Performance assessment of machine learning algorithms for mapping of land use/land cover using remote sensing data. The Egyptian Journal of Remote Sensing and Space Sciences, 27(2), 216-226.

Zare, M., Behnia, N., & Gabriels, D. (2019). Assessment of land cover changes using Taguchi-based optimized SVM classification approach. Journal of the Indian Society of Remote Sensing, 47(1), 45-52.

Zerrouki, N., Harrou, F., Sun, Y., & Hocini, L. (2019). A machine learning-based approach for land cover change detection using remote sensing and radiometric measurements. IEEE Sensors Journal, 19(14), 5843-5850.

Zhao, Y. (2013). Chapter 4—Decision Trees and Random Forest. In. Zhao, Y (Eds.), R and data mining (pp. 27-40). Cambridge, MA, USA, Academic Press.


Refbacks

  • There are currently no refbacks.