Comparison between random forest and support vector machine algorithms for LULC classification

Yıl 2023, , 1 - 10, 15.02.2023

Cengiz Avcı , Muhammed Budak , Nur Yağmur , Filiz Balçık

https://doi.org/10.26833/ijeg.987605

Cited By: 45

Öz

Nowadays, machine learning (ML) algorithms have been widely chosen for classifying satellite images for mapping Earth's surface. Support Vector Machine (SVM) and Random Forest (RF) stand out among these algorithms with their accurate results in the literature. The aim of this study is to analyze the performances of these algorithms on land use and land cover (LULC) classification, especially wetlands which have significant ecological functions. For this purpose, Sentinel-2 satellite image, which is freely provided by European Space Agency (ESA), was used to monitor not only the open surface water body but also around Marmara Lake. The performance evaluation was made with the increasing number of the training dataset. 3 different training datasets having 10, 15, and 20 areas of interest (AOI) per class, respectively were used for the classification of the satellite images acquired in 2015 and 2020. The most accurate results were obtained from the classification with RF algorithm and 20 AOIs. According to obtained results, the change detection analysis of Marmara Lake was investigated for possible reasons. Whereas the water body and wetland have decreased more than 50% between 2015 and 2020, crop sites have increased approximately 50%.  

Anahtar Kelimeler

Remote Sensing, Supervised Classification, Random Forest, Support Vector Machine, Wetland

Kaynakça

• DeFries, R. S., Foley, J. A., & Asner, G. P. (2004). Land‐use choices: Balancing human needs and ecosystem function. Frontiers in Ecology and the Environment, 2(5), 249-257.
• Kavzoglu, T., Tonbul, H., Erdemir, M. Y., & 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.
• Ekumah, B., Armah, F. A., Afrifa, E. K., Aheto, D. W., Odoi, J. O., & Afitiri, A. R. (2020). Assessing land use and land cover change in coastal urban wetlands of international importance in Ghana using Intensity Analysis. Wetlands Ecology and Management, 28(2), 271-284.
• Basu, T., Das, A., Pham, Q. B., Al-Ansari, N., Linh, N. T. T., & Lagerwall, G. (2021). Development of an integrated peri-urban wetland degradation assessment approach for the Chatra Wetland in eastern India. Scientific reports, 11(1), 1-22.
• Jamal, S., & Ahmad, W. S. (2020). Assessing land use land cover dynamics of wetland ecosystems using Landsat satellite data. SN Applied Sciences, 2(11), 1-24.
• Hochreuther, P., Neckel, N., Reimann, N., Humbert, A., & Braun, M. (2021). Fully Automated Detection of Supraglacial Lake Area for Northeast Greenland Using Sentinel-2 Time-Series. Remote Sens. 2021, 13, 205.
• Shih, H. C., Stow, D. A., & Tsai, Y. H. (2019). Guidance on and comparison of machine learning classifiers for Landsat-based land cover and land use mapping. International Journal of Remote Sensing, 40(4), 1248-1274.
• Bangira, T., Alfieri, S. M., Menenti, M., & Van Niekerk, A. (2019). Comparing thresholding with machine learning classifiers for mapping complex water. Remote Sensing, 11(11), 1351.
• Gislason, P. O., Benediktsson, J. A., & Sveinsson, J. R. (2006). Random forests for land cover classification. Pattern recognition letters, 27(4), 294-300.
• Gorelick, N., Hancher, M., Dixon, M., Ilyushchenko, S., Thau, D., & Moore, R. (2017). Google Earth Engine: Planetary-scale geospatial analysis for everyone. Remote sensing of Environment, 202, 18-27.
• Wang, Y., Ma, J., Xiao, X., Wang, X., Dai, S., & Zhao, B. (2019). Long-term dynamic of poyang lake surface water: a mapping work based on the Google earth engine cloud platform. Remote Sensing, 11(3), 313.
• Wang, C., Jia, M., Chen, N., & Wang, W. (2018). Long-term surface water dynamics analysis based on Landsat imagery and the Google Earth Engine platform: A case study in the middle Yangtze River Basin. Remote Sensing, 10(10), 1635.
• Amani, M., Mahdavi, S., Afshar, M., Brisco, B., Huang, W., Mohammad Javad Mirzadeh, S., ... & Hopkinson, C. (2019). Canadian wetland inventory using google earth engine: The first map and preliminary results. Remote Sensing, 11(7), 842.
• MoAF (Ministry of Agriculture and Forestry) (2018). Wetland Managemant Plan of Marmara Lake. Ankara.
• Breiman, L. (1999). Random forests. UC Berkeley TR567.
• Berhane, T. M, Lane, C. R., Wu, Q, Autrey, B. C., Anenkhonov, O. A., Chepinoga, V. V., & Liu, H. (2018). Decision-tree, rule-based, and random forest classification of high-resolution multispectral imagery for wetland mapping and inventory. Remote sensing, 10(4), 580.
• Dubeau, P., King, D. J., Unbushe, D. G., & Rebelo, L. M. (2017). Mapping the Dabus wetlands, Ethiopia, using random forest classification of Landsat, PALSAR and topographic data. Remote Sensing, 9(10), 1056.
• Jagannath, V. (2020). “Random Forest Template for TIBCO Spotfire® - Wiki Page TIBCO Community.” https://community.tibco.com/wiki/random-forest-template-tibco-spotfire
• Vapnik, V. (1998). The support vector method of function estimation. In Nonlinear modeling (pp. 55-85). Springer, Boston, MA.
• Qian, Y., Zhou, W., Yan, J., Li, W., & Han, L. (2015). Comparing machine learning classifiers for object-based land cover classification using very high resolution imagery. Remote Sensing, 7(1), 153-168.
• Han, X., Pan, J., & Devlin, A. T. (2018). Remote sensing study of wetlands in the Pearl River Delta during 1995–2015 with the support vector machine method. Frontiers of Earth Science, 12(3), 521-531.
• Pretorius, L., Brown, L. R., Bredenkamp, G. J. & van Huyssteen, C. W. (2016). The ecology and classification of wetland vegetation in the Maputaland Coastal Plain, South Africa. Phytocoenologia, 46(2), 125-139.
• Burges, C. J. (1998). A tutorial on support vector machines for pattern recognition. Data mining and knowledge discovery, 2(2), 121-167.
• Canty, M. J. (2014). Image analysis, classification and change detection in remote sensing: with algorithms for ENVI/IDL and Python. Crc Press.
• Colditz, R. R. (2015). An evaluation of different training sample allocation schemes for discrete and continuous land cover classification using decision tree-based algorithms. Remote Sensing, 7(8), 9655-9681.
• Mellor, A., Boukir, S., Haywood, A., & Jones, S. (2015). Exploring issues of training data imbalance and mislabelling on random forest performance for large area land cover classification using the ensemble margin. ISPRS Journal of Photogrammetry and Remote Sensing, 105, 155-168.
• Thanh, Noi, P., & Kappas, M. (2018). Comparison of random forest, k-nearest neighbor, and support vector machine classifiers for land cover classification using Sentinel-2 imagery. Sensors, 18(1), 18.
• Story, M., & Congalton, R. G. (1986). Accuracy assessment: a user’s perspective. Photogrammetric Engineering and remote sensing, 52(3), 397-399.
• Tubitak MAM (2013). Preparation Project of Basin Protection Action Plans, Gediz Basin. Project Report, Kocaeli.
• TUIK, 2020. https://www.tuik.gov.tr/
• Korbalta, H. (2019) Marmara Gölü Neden Kuruyor? Kent Akademisi, 12(3), 441-459.
• MGM (2020). Analysis of meteorological parameters for Turkey. Accessed from: https://www.mgm.gov.tr/veridegerlendirme/il-ve ilceleristatistik.aspx?k=parametrelerinTurkiyeAnalizi.