Performance Assessment of Maximum Likelihood, Random Forest and Support Vector Machines Classifier for Urban Land Use Classification: A Case Study of Dhaka Metropolitan City, Bangladesh

Ha-mim Ebne Alam; Md. Nizam Uddin; Kazi Tawkir Ahmed; Md. Jahidul Hasan; Md. Yeasir Arafat; Md. Enamul Hoque

doi:10.22146/jgise.73283

Performance Assessment of Maximum Likelihood, Random Forest and Support Vector Machines Classifier for Urban Land Use Classification: A Case Study of Dhaka Metropolitan City, Bangladesh

https://doi.org/10.22146/jgise.73283

Ha-mim Ebne Alam^(1*), Md. Nizam Uddin⁽²⁾, Kazi Tawkir Ahmed⁽³⁾, Md. Jahidul Hasan⁽⁴⁾, Md. Yeasir Arafat⁽⁵⁾, Md. Enamul Hoque⁽⁶⁾

(1) Department of Oceanography, University of Chittagong, Chittagong-4331, Bangladesh
(2) Department of Oceanography, University of Chittagong, Chittagong-4331.
(3) Department of Oceanography, University of Chittagong, Chittagong-4331.
(4) Institute of Marine Sciences, University of Chittagong
(5) Department of Oceanography, University of Chittagong, Chittagong-4331.
(6) Department of Oceanography, University of Chittagong, Chittagong-4331.
(*) Corresponding Author

Abstract

Segmentation of remotely sensed satellite images is obligatory for multifarious earth observation studies, including land use and land cover (LULC) analysis. It is also inherent in environment, ecosystem, and urban development in analytical perspectives and complex inputs for modeling urban planning and disaster management. Assessment of LULC pattern uses different segmentation methods for assigning specific given classes to pixels of bands containing an image of natural color composite to define land use land cover classes such as water body, vegetation, bare soil, and built-up areas. The process of assigning classes to pixels varies from one to another, and thus, different accuracy levels are obtained. The accuracy of frequently used methods for LULC classification was assessed in this study, where the Dhaka metropolitan area has been taken as a sample to observe the LULC. The classification was conducted by using three methods where the Support vector machines classification (SVMC) produced the best accuracy results of 83.2% overall accuracy and overall kappa coefficient value of 0.74 than both random forest classification (RFC) and maximum likelihood classification (MLC) methods with 86.34% and 83% spatial similarity rate respectively. Besides, RFC and MLC are roughly equivalent in kappa and overall accuracy values, though MLC revealed less capability at classifying vegetation. However, MLC showed a high spatial similarity with RFC and dissimilarity with SVMC. This study on segmentation methods in classifying LULC will help users make an informed choice in selecting the best method for relevant studies.

Keywords

Land Cover Classification, Urban GIS, Remote Sensing, Land Cover Classification Accuracy

Full Text:

PDF

References

Abdi, A. M. (2020). Land cover and land use classification performance of machine learning algorithms in a boreal landscape using Sentinel-2 data. GIScience & Remote Sensing, 57(1), 1–20. https://doi.org/10.1080/15481603.2019.1650447

Ahmed, B., & Ahmed, R. (2012). Modeling Urban Land Cover Growth Dynamics Using Multi‑Temporal Satellite Images: A Case Study of Dhaka, Bangladesh. ISPRS International Journal of Geo-Information, 1(1), 3–31. https://doi.org/10.3390/ijgi1010003

Ahmed, B., Kamruzzaman, Md., Zhu, X., Rahman, Md., & Choi, K. (2013). Simulating Land Cover Changes and Their Impacts on Land Surface Temperature in Dhaka, Bangladesh. Remote Sensing, 5(11), 5969–5998. https://doi.org/10.3390/rs5115969

Alshari, E. A., & Gawali, B. W. (2021). Development of classification system for LULC using remote sensing and GIS. Global Transitions Proceedings, 2(1), 8–17. https://doi.org/10.1016/j.gltp.2021.01.002

BBS. (1998). Statistical Year Book. Bangladesh Bureau of Statistics (BBS), Statistics and Informatics Division (SID), Ministry of Planning, Government of the People’s Republic of Bangladesh.

Boser, B. E., Guyon, I. M., & Vapnik, V. N. (1992). A training algorithm for optimal margin classifiers. The Fifth Annual Workshop on Computational Learning Theory, 144–152.

Breiman, L. (2001). Random forests. Machine Learning, 45(1), 5–22.

Congalton, R. G. (1991). A review of assessing the accuracy of classifications of remotely sensed data. Remote Sensing of Environment, 37(1), 35–46.

Congalton, R. G., Oderwald, R. G., & Mead, R. A. (1983). Assessing Landsat classification accuracy using discrete multivariate analysis statistical techniques. Photogrammetric Engineering and Remote Sensing (USA), 49(12), 1671–1678.

Cortes, C., & Vapnik, V. (1995). Support-vector networks. Machine Learning, 20(3), 273–297.

Cracknell, A. P. (1998). Review article Synergy in remote sensing-what’s in a pixel? International Journal of Remote Sensing, 19(11), 2025–2047. https://doi.org/10.1080/014311698214848

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.

Dewan, A. M., Kabir, Md. H., Nahar, K., & Rahman, Md. Z. (2012). Urbanisation and environmental degradation in Dhaka Metropolitan Area of Bangladesh. International Journal of Environment and Sustainable Development, 11(2), 118. https://doi.org/10.1504/IJESD.2012.049178

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.

Dhaka, Bangladesh Metro Area Population 1950–2021. (n.d.). MacroTrends. Retrieved June 17, 2021, from https://www.macrotrends.net/cities/20119/dhaka/population

Fauvel, M., Tarabalka, Y., Benediktsson, J. A., Chanussot, J., & Tilton, J. C. (2013). Advances in Spectral-Spatial Classification of Hyperspectral Images. Proceedings of the IEEE, 101(3), 652–675. https://doi.org/10.1109/JPROC.2012.2197589

Fenstermaker, L. K. (1994). Remote sensing thematic accuracy assessment.

Fisher, P. (1997). The pixel: A snare and a delusion. International Journal of Remote Sensing, 18(3), 679–685. https://doi.org/10.1080/014311697219015

Foody, G. M. (2002). Status of land cover classification accuracy assessment. Remote Sensing of Environment, 80(1), 185–201.

Foody, G. M., & Mathur, A. (2004). A relative evaluation of multiclass image classification by support vector machines. IEEE Transactions on Geoscience and Remote Sensing, 42(6), 1335–1343.

Ghamisi, P., Maggiori, E., Li, S., Souza, R., Tarablaka, Y., Moser, G., De Giorgi, A., Fang, L., Chen, Y., Chi, M., Serpico, S. B., & Benediktsson, J. A. (2018). New Frontiers in Spectral-Spatial Hyperspectral Image Classification: The Latest Advances Based on Mathematical Morphology, Markov Random Fields, Segmentation, Sparse Representation, and Deep Learning. IEEE Geoscience and Remote Sensing Magazine, 6(3), 10–43. https://doi.org/10.1109/MGRS.2018.2854840

Gislason, P. O., Benediktsson, J. A., & Sveinsson, J. R. (2006). Random forests for land cover classification. Pattern Recognition Letters, 27(4), 294–300.

Guidici, D., & Clark, M. L. (2017). One-Dimensional convolutional neural network land-cover classification of multi-seasonal hyperspectral imagery in the San Francisco Bay Area, California. Remote Sensing, 9(6), 629.

Hall, F. G., Townshend, J. R., & Engman, E. T. (1995). Status of remote sensing algorithms for estimation of land surface state parameters. Remote Sensing of Environment, 51(1), 138–156.

Huang, C., Davis, L., & Townshend, J. (2002). An assessment of support vector machines for land cover classification. International Journal of Remote Sensing, 23(4), 725–749.

Ishtiaque, A., Mahmud, M. S., & Rafi, M. H. (2014). Encroachment of Canals of Dhaka City,Bangladesh: An Investigative Approach. GeoScape, 8(2), 48–64. https://doi.org/10.2478/geosc-2014-0006

Islam, M. S., & Ahmed, R. (2011). Land use change prediction in Dhaka city using GIS aided Markov chain modeling. Journal of Life and Earth Science, 6, 81–89.

Jeon, B., & Landgrebe, D. A. (1990). Spatio-temporal contextual classification of remotely sensed multispectral data. 1990 IEEE International Conference on Systems, Man, and Cybernetics Conference Proceedings, 342–344. https://doi.org/10.1109/ICSMC.1990.142124

Jin, J. (2012). A random forest based method for urban land cover classification using LiDAR data and aerial imagery.

Kavzoglu, T. (2017). Object-oriented random forest for high resolution land cover mapping using quickbird-2 imagery. In Handbook of neural computation (pp. 607–619). Elsevier.

Kavzoglu, T., & Colkesen, I. (2009). A kernel functions analysis for support vector machines for land cover classification. International Journal of Applied Earth Observation and Geoinformation, 11(5), 352–359.

Kavzoglu, T., & Reis, S. (2008). Performance analysis of maximum likelihood and artificial neural network classifiers for training sets with mixed pixels. GIScience & Remote Sensing, 45(3), 330–342.

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.

Kranjcic, N., Medak, D., Zupan, R., & Rezo, M. (2019). Machine learning methods for classification of the green infrastructure in city areas. IOP Conference Series: Earth and Environmental Science, 362, 012079. https://doi.org/10.1088/1755-1315/362/1/012079

Landis, J. R., & Koch, G. G. (1977). The Measurement of Observer Agreement for Categorical Data. Biometrics, 33(1). https://doi.org/10.2307/2529310

Lu, D., & Weng, Q. (2007). A survey of image classification methods and techniques for improving classification performance. International Journal of Remote Sensing, 28(5), 823–870.

Mansaray, L. R., Wang, F., Huang, J., Yang, L., & Kanu, A. S. (2020). Accuracies of support vector machine and random forest in rice mapping with Sentinel-1A, Landsat-8 and Sentinel-2A datasets. Geocarto International, 35(10), 1088–1108.

Mondal, A., Kundu, S., Chandniha, S. K., Shukla, R., & Mishra, P. (2012). Comparison of support vector machine and maximum likelihood classification technique using satellite imagery. International Journal of Remote Sensing and GIS, 1(2), 116–123.

Mustapha, M. R., Lim, H. S., & Mat Jafri, M. Z. (2010). Comparison of Neural Network and Maximum Likelihood Approaches in Image Classification. Journal of Applied Sciences, 10(22), 2847–2854. https://doi.org/10.3923/jas.2010.2847.2854

Naguib, A., Abd Elwahab, M., Farag, M., Yahia, M., & Ramadan, H. (2009). Comparative Study Between Support Vector Machines and Neural Networks for Lithological Discrimination Using Hyper spectral Data. Egyptian Journal of Remote Sensing and Space Sciences, 12.

Oommen, T., Misra, D., Twarakavi, N. K., Prakash, A., Sahoo, B., & Bandopadhyay, S. (2008). An objective analysis of support vector machine based classification for remote sensing. Mathematical Geosciences, 40(4), 409–424.

Pal, M., & Mather, P. (2005). Support vector machines for classification in remote sensing. International Journal of Remote Sensing, 26(5), 1007–1011.

Pranckevičius, T., & Marcinkevičius, V. (2017). Comparison of naive bayes, random forest, decision tree, support vector machines, and logistic regression classifiers for text reviews classification. Baltic Journal of Modern Computing, 5(2), 221.

Rai, R., Zhang, Y., Paudel, B., Li, S., & Khanal, N. (2017). A Synthesis of Studies on Land Use and Land Cover Dynamics during 1930–2015 in Bangladesh. Sustainability, 9(10), 1866. https://doi.org/10.3390/su9101866

Rosenfeld, A., & Banerjee, S. (1992). Maximum-likelihood edge detection in digital signals. CVGIP: Image Understanding, 55(1), 1–13. https://doi.org/10.1016/1049-9660(92)90002-K

Santosa, P. B. (2016). Evaluation of satellite image correction methods caused by differential terrain illumination. Jurnal Forum Geografi. Vol. 30, No. 1 (2016). https://doi.org/10.23917/forgeo.v30i1.1768

Scott, A. J., & Symons, M. J. (1971). Clustering methods based on likelihood ratio criteria. Biometrics, 387–397.

Shi, D., & Yang, X. (2015). Support Vector Machines for Land Cover Mapping from Remote Sensor Imagery. In J. Li & X. Yang (Eds.), Monitoring and Modeling of Global Changes: A Geomatics Perspective (pp. 265–279). Springer Netherlands. https://doi.org/10.1007/978-94-017-9813-6_13

Sisodia, P. S., Tiwari, V., & Kumar, A. (2014). Analysis of supervised maximum likelihood classification for remote sensing image. 1–4.

Szuster, B. W., Chen, Q., & Borger, M. (2011). A comparison of classification techniques to support land cover and land use analysis in tropical coastal zones. Applied Geography, 31(2), 525–532. https://doi.org/10.1016/j.apgeog.2010.11.007

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.

Townshend, J. G. (1992). Land cover. International Journal of Remote Sensing, 13(6–7), 1319–1328.

UN. (2014). 2014 Revision of the World Urbanization Prospects. Department of Economics and Social Affairs United Nations.

Vapnik, V. N. (1995). The nature of statistical learning Theory. Springer-Verlag. Springer-Verlag, New York.

Varma, M. K. S., Rao, N. K. K., Raju, K. K., & Varma, G. P. S. (2016). Pixel-Based Classification Using Support Vector Machine Classifier. 2016 IEEE 6th International Conference on Advanced Computing (IACC), 51–55. https://doi.org/10.1109/IACC.2016.20

Wright, M. N., & König, I. R. (2019). Splitting on categorical predictors in random forests. PeerJ, 7, e6339. https://doi.org/10.7717/peerj.6339

Zhang, Y., Ren, J., & Jiang, J. (2015). Combining MLC and SVM Classifiers for Learning Based Decision Making: Analysis and Evaluations. Computational Intelligence and Neuroscience, 2015, 1–8. https://doi.org/10.1155/2015/423581

DOI: https://doi.org/10.22146/jgise.73283