Assessment of Land Cover Dynamics in Cox’s Bazar, Bangladesh: An Integrated Machine Learning and Remote Sensing Approach

Md Mahfuzur Rahman

Undegraduate Student and Research Assistant, Department of Environmental Science, Stamford University Bangladesh (SUB).

Mahazuza Islam

Undegraduate Student, Department of Environmental Science, Stamford University Bangladesh (SUB).

Corresponding author: mahfujr199@gmail.com (Md Mahfuzur Rahman)

Keywords: Rohingya Refugee Crisis, Google Earth Engine, Random Forest, Forest Loss, Protected Area.  

PDF: Full Article

DOI: https://doi.org/10.66268/jrse.2026.05.774134

Published: 31 March 2026

Abstract

This study aims to assess the land cover dynamics using machine learning and remote sensing techniques in the Google Earth Engine (GEE) over the period 2016-2024 in Cox’s Bazar, Bangladesh, which is hosting a million Rohingya refugees. Here, the Land Use Land Cover (LULC) changes show the decline in forest cover from 66,024 ha (26.46%) in 2016 to 42,865 ha (17.13%) in 2024. The built-up areas expanded dramatically from 3,746 ha (1.5%) to 15,036 ha (6.02%), linked to the rapid growth of Rohingya refugee settlements. Besides, the shrubland and water-bodies showed strong inter-annual fluctuations influenced by both environmental conditions and human activities. Furthermore, the Normalized Difference Vegetation Index (NDVI) analysis reflects the highest vegetation loss in Ukhiya upazila, where the largest refugee camps are located. The analysis of the study showed that the camps are extended to the protected areas. The accuracy of the LULC analysis confirmed accepted classifications with overall accuracy of 76-96% and Kappa values of 0.70-0.95. The rapid LULC changes driven by the refugee influx require the need for continuous monitoring and sustainable land management to prevent the expansion of camps into the protected areas, as evidenced by this study.

References

Abdullah, A. Y. M., Masrur, A., Adnan, M. S. G., Baky, M. A. A., Hassan, Q. K., Dewan, A. (2019). Spatio-temporal patterns of land use/land cover change in the heterogeneous coastal region of Bangladesh between 1990 and 2017. Remote Sensing, 11(7), 790. https://doi.org/10.3390/rs11070790

ACAPS. (2017). Review Rohingya influx since 1978: Thematic report. ACAPS NPM Analysis Hub.

Ahmed, B., Rahman, M. S., Sammonds, P., Islam, R., Uddin, K. (2020). Application of geospatial technologies in developing a dynamic landslide early warning system in a humanitarian context: the Rohingya refugee crisis in Cox's Bazar, Bangladesh. Geomatics, Natural Hazards and Risk, 11(1), 446–468. https://doi.org/10.1080/19475705.2020.1730988

Ahsan, K., Habib, M. A., Alam, M. F., Talukder, A. (2017). Geological report on Cox's Bazar-Teknaf Coastal Area, Bangladesh (Records of the Geological Survey of Bangladesh, Vol. 14, Part 4). Geological Survey of Bangladesh.

Altman, N. S. (1992). An introduction to kernel and nearest-neighbor nonparametric regression. The American Statistician, 46(3), 175–185. https://doi.org/10.2307/2685209

Anderson, J. R., Hardy, E. E., Roach, J. T., Witmer, R. E. (1976). A land use and land cover classification system for use with remote sensor data (U.S. Geological Survey Professional Paper 964) [Report]. U.S. Geological Survey. https://pubs.usgs.gov/pp/0964/report.pdf

Arfa, A., Minaei, M. (2024). Utilizing multitemporal indices and spectral bands of Sentinel-2 to enhance land use and land cover classification with random forest and support vector machine. Advances in Space Research, 74, 5580–5590. https://doi.org/10.1016/j.asr.2024.08.062

Babaremu, K., Taiwo, O., Ajayi, D. (2024). Impacts of land use and land cover changes on hydrological response: a review of current understanding and implications for watershed and water resources management. TWIST, 19(1), 256–267. https://doi.org/10.5281/zenodo.10049652#89

Belgiu, M., Drăguţ, L. (2016). Random forest in remote sensing: A review of applications and future directions. ISPRS Journal of Photogrammetry and Remote Sensing, 114, 24–31. https://doi.org/10.1016/j.isprsjprs.2016.01.017

Breiman, L. (2001). Random forests. Machine Learning, 45(1), 5–32.

Camps-Valls, G., Tuia, D., Bruzzone, L., & Benediktsson, J. A. (2013). Advances in hyperspectral image classification: Earth monitoring with statistical learning methods. ArXiv. https://doi.org/10.1109/MSP.2013.2279179

Corner, R. J., Dewan, A. M., Chakma, S. (2022). Monitoring and prediction of land-use and land-cover (LULC) change. In S. K. Sarkar, S. S. Roy, & K. K. Mondal (Eds.), Remote Sensing, Environmental Management and Education (pp. 95–119). Springer.

Dampha, N. K., Salemi, C., Polasky, S. (2022). Rohingya refugee camps and forest loss in Cox's Bazar, Bangladesh: An inquiry using remote sensing and econometric approaches (Policy Research Working Paper No. 9948). World Bank Group.

Das, D., Prodhan, F. A., Hoque, M. Z., Haque, M. E., Kabir, M. H. (2025). Monitoring and future prediction of land use land cover dynamics in northern Bangladesh using remote sensing and CA-ANN model. Earth, 6(3), 73. https://doi.org/10.3390/earth6030073

DIVA-GIS. (2024). Global spatial data (administrative boundaries, roads, land cover, etc.) [Data set]. https://diva-gis.org/data.html

Drusch, M., Del Bello, U., Carlier, S., Colin, O., Fernandez, V., Gascon, F., Hoersch, B., Isola, C., Laberinti, P., Martimort, P., Meygret, A., Spoto, F., Sy, O., Marchese, F., Bargellini, P. (2012). Sentinel-2: ESA's optical high-resolution mission for GMES operational services. Remote Sensing of Environment, 120, 25–36. https://doi.org/10.1016/j.rse.2011.11.026

European Space Agency. (2015). Sentinel 2 User Handbook (Issue 1, Rev. 2, 24 July 2015). https://sentinels.copernicus.eu/documents/247904/685211/Sentinel-User_Handbook

Friedman, J. H. (2001). Greedy function approximation: a gradient boosting machine. The Annals of Statistics, 29(5), 1189–1232. https://doi.org/10.1214/aos/1013203451

Gao, B. (1996). NDWI—A normalized difference water index for remote sensing of vegetation liquid water from space. Remote Sensing of Environment, 58(3), 257-266. https://doi.org/10.1016/S0034-4257(96)00067-3

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. https://doi.org/10.1016/j.rse.2017.06.031

Hasan, M. E., Mahmood, R., Zhang, L., Dewan, A. (2020). Spatiotemporal pattern of forest degradation and loss of ecosystem function associated with Rohingya influx: A geospatial approach. Land Degradation & Development, 32(3), 1184–1195. https://doi.org/10.1002/ldr.3821

Hassan, M. M., Smith, A. C., Walker, K., Rahman, M. K., Southworth, J. (2018). Rohingya refugee crisis and forest cover change in Teknaf, Bangladesh. Remote Sensing, 10(5), 667. https://doi.org/10.3390/rs10050667

Haykin, S. (1999) Neural Networks: A Comprehensive Foundation. 2nd Edition, Prentice- Hall, Englewood Cliffs, NJ.

Hossain, F., Moniruzzaman, M. (2021). Environmental change detection through remote sensing technique: A study of Rohingya refugee camp area (Ukhia and Teknaf sub-district), Cox's Bazar, Bangladesh. Environmental Challenges, 2, 100024. https://doi.org/10.1016/j.envc.2021.100024

Huang, C., Davis, L. S., Townshend, J. R. G. (2002). An assessment of support vector machines for land cover classification. International Journal of Remote Sensing, 23(4), 725–749. https://doi.org/10.1080/01431160110040323

HRRC (Human Rights Research Center). (2025, July 23). Crisis within a crisis: Environmental degradation in the Rohingya refugee settlement in Bangladesh. Human Rights Research Center.https://www.humanrightsresearch.org/post/crisis-within-a-crisis-environmental-degradation-in-the-rohingya-refugee-settlement-in-bangladesh#:~:text=Environmental%20Impacts,De%20La%20Portilla%2C%202021).

Humanitarian Data Exchange. (2025). Bangladesh water courses [Data set]. OCHA. https://data.humdata.org/dataset/bangladesh-water-courses

Humanitarian Data Exchange. (2025). Outline of camps/sites of Rohingya refugees in Cox’s Bazar, Bangladesh [Data set]. OCHA. https://data.humdata.org/dataset/outline-of-camps-sites-of-rohingya-refugees-in-cox-s-bazar-bangladesh

Karmakar, S., Rahman, M., Meng, L. (2025). Land Cover Changes and Land Surface Temperature Dynamics in the Rohingya Refugee Area, Cox Bazar, Bangladesh: An Analysis from 2013 to 2024. Atmosphere, 16(3), 250. https://doi.org/10.3390/atmos16030250

Kauth, R. J., & Thomas, G. S. (1976). The Tasselled Cap—A graphic description of the spectral-temporal development of agricultural crops as seen by LANDSAT. In Symposium on Machine Processing of Remotely Sensed Data (pp. 4B-4B). The Laboratory for Applications of Remote Sensing, Purdue University.

Maruf, J. K., Ara, S. (2023). Examining the Spatio-temporal changes of Ecosystem Service Value Due to LULC changes: A Case Study on Cox's Bazar, Bangladesh. Research Square. https://doi.org/10.21203/rs.3.rs-2500133/v1 

McFeeters, S. K. (1996). The use of the Normalized Difference Water Index (NDWI) in the delineation of open water features. International Journal of Remote Sensing, 17(7), 1425–1432. https://doi.org/10.1080/01431169608948714

Miah, M. D., Hossain, M. A., Ali, Y. (2024). Assessment of the degradation of Teknaf Wildlife Sanctuary, Bangladesh: Use of Remote Sensing and Geographic Information System Techniques. Forestist, 74(3), 354–364. https://doi.org/10.5152/forestist.2024.24002

Mutale, B., Withanage, N. C., Mishra, P. K., Shen, J., Abdelrahman, K., Fnais, M. S. (2024). A performance evaluation of random forest, artificial neural network, and support vector machine learning algorithms to predict spatio-temporal land use–land cover dynamics: a case from lusaka and colombo. Frontiers in Environmental Science, 12, 1431645. https://doi.org/10.3389/fenvs.2024.1431645 

RRRC (Relief and Repatriation Commissioner). Office of the Refugee, Government of Bangladesh (GOB). (2025). Rohingya refugee population factsheet (February 28, 2025)

Pal, M., Mather, P. M. (2003). An assessment of the effectiveness of decision tree methods for land cover classification. Remote Sensing of Environment, 86(4), 554–565. https://doi.org/10.1016/S0034-4257(03)00132-1 

Pal, M., Mather, P. M. (2005). Support vector machines for classification in remote sensing. International Journal of Remote Sensing, 26(5), 1007–1011. https://doi.org/10.1080/01431160412331291837

Phan, T. N., Kuch, V., Lehnert, L. W. (2020). Land Cover Classification using Google Earth Engine and Random Forest Classifier—The Role of Image Composition. Remote Sensing, 12(15), 2411. 

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. https://doi.org/10.3390/rs70100153

Rahim, M. A. (2025). Geological field report on Cox's Bazar town and surrounding areas focusing on geomorphology, geology, georesources and geohazards (Technical Report). Department of Geology, University of Dhaka. 

Rouse, J. W., Jr., Haas, R. H., Schell, J. A., Deering, D. W. (1973). Monitoring Vegetation Systems in the Great Plains with ERTS. In Symposium on Significant Results Obtained from the Earth Resources Technology Satellite-1 (ERTS-1) (NASA SP-327) (Vol. 1, pp. 309–317). National Aeronautics and Space Administration

Roy, B. (2021). A machine learning approach to monitoring and forecasting spatio-temporal dynamics of land cover in Cox's Bazar district, Bangladesh from 2001 to 2019. Environmental Challenges, 5, 100237. https://doi.org/10.1016/j.envc.2021.100237

Sakamoto, M., Ullah, S. M. A., Tani, M. (2021). Land cover changes after the massive Rohingya refugee influx in Bangladesh: Neo-classic unsupervised approach. Remote Sensing, 13(24), 5056. https://doi.org/10.3390/rs13245056

Sarkar, S. K., Saroar, M. M., Chakraborty, T. (2022). Cost of ecosystem service value due to Rohingya refugee influx in Bangladesh. Disaster Medicine and Public Health Preparedness. https://doi.org/10.1017/dmp.2022.125

Siddeqa, M., Islam, M. T., Hasan, M. F., Islam, R., Rasheduzzaman, M. (2023). Land use and land cover change detection of Teknaf Upazila due to Rohingya crisis by using GIS, and RS techniques. Asian Journal of Social Sciences and Legal Studies, 5(6), 246–252. https://doi.org/10.34104/ajssls.023.02460252

Sourav, A. P. (2025). Geological field report on the geology and coastal dynamics of Cox's Bazar (Technical Report). Department of Geology and Mining, University of Barishal. 

Sun, J., Ongsomwang, S. (2023). Optimal parameters of random forest for land cover classification with suitable data type and dataset on Google Earth Engine. Frontiers in Earth Science, 11, 1188093. https://doi.org/10.3389/feart.2023.1188093

Talukdar, S., Singha, P., Mahato, S., Shahfahad, Pal, S., Liou, Y. A., Rahman, A. (2020). Land-use land-cover classification by machine learning classifiers for satellite observations-A review. Remote Sensing, 12(7), 1135. https://doi.org/10.3390/rs12071135 

UNHCR Population Map. (2025). UNHCR, Bangladesh, Cox’s Bazar. UNHCR. Retrieved 16 August, 2025, from https://data2.unhcr.org/en/documents/details/70839

UNEP-WCMC, & IUCN. (2025). Protected Planet: The World Database on Protected Areas (WDPA) and the World Database on Other Effective Area-based Conservation Measures (WD-OECM) (December 2025 release). UNEP-WCMC and IUCN. https://www.protectedplanet.net

USGS (United States Geological Survey). (2018, July 16). USGS EROS archive – Sentinel-2: Mission overview and band specifications. https://www.usgs.gov/centers/eros/science/usgs-eros-archive-sentinel-2

Valdivieso-Ros, C., Alonso-Sarria, F., Gomariz-Castillo, F. (2021). Effect of different atmospheric correction algorithms on Sentinel-2 imagery classification accuracy in a semiarid Mediterranean area. Remote Sensing, 13(9), 1770. https://doi.org/10.3390/rs13091770

Xu, H. (2006). Modification of normalised difference water index (NDWI) to enhance open water features in remotely sensed imagery. International Journal of Remote Sensing, 27(14), 3025–3033. https://doi.org/10.1080/01431160600589179

Xue, J., Su, B. (2017). Significant remote sensing vegetation indices: A review of developments and applications. Journal of Sensors, 2017, 1353691. https://doi.org/10.1155/2017/1353691

Zha, Y., Gao, J., Ni, S. (2003). Use of normalized difference built-up index in automatically mapping urban areas from TM imagery. International Journal of Remote Sensing, 24(3), 583–594. https://doi.org/10.1080/01431160304987

Zhang, Z., Wei, M., Pu, D., He, G., Wang, G., Long, T. (2021). Assessment of annual composite images obtained by google earth engine for urban areas mapping using random forest. Remote Sensing, 13(4), 748. https://doi.org/10.3390/rs13040748

How to cite: 

Rahman, M.M., Islam, M. (2026). Assessment of Land Cover Dynamics in Cox’s Bazar, Bangladesh: An Integrated Machine Learning and Remote Sensing Approach. Journal of Remote Sensing and Environment, 5, 20250504. https://doi.org/10.66268/jrse.2026.05.774134

License: This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License. This allows anyone to copy, share, distribute, and modify the work for non-commercial purposes, where the original work and source should be properly cited.