|
Land Cover Classification Based on Machine Learning and Deep Learning Methods Using Sentinel-2 Satellite Images: A Case Study of the Urban Area in West Tehran
|
Dana Saeedi   , Ehsan Khankeshizadeh , Tayebe Managhebi * , Mohammad Karimi , Ali Mohammadzadeh |
|
|
|
Abstract: (297 Views) |
The production of land cover maps (LCM) provides essential information about land types and their characteristics, playing a significant role in updating urban maps, managing natural resources, environmental protection, and sustainable development. In this context, the use of image processing techniques and free remote sensing data is considered an optimal method for generating land cover maps (LCM). In this study, various artificial intelligence approaches, including machine learning (ML) and deep learning (DL) algorithms, were used to produce the LCM. The ML approach includes two stages: feature extraction and classification. In the feature extraction stage, texture features extracted from the gray-level co-occurrence matrix (GLCM), including mean, variance, homogeneity, contrast, and entropy, were used. For classification, the logistic regression (LR), decision tree (DT), random forest (RF), and support vector machine (SVM) algorithms were employed. In the DL approach, deep learning semantic segmentation models, including U-Net, U-Net++, ResU-Net, and MRU-Net, were used. To evaluate the accuracy of the ML and DL algorithms in producing the land cover map, Sentinel-2 images from two areas located in the west of Tehran were utilized. The results of this study were examined in three different sections: ML, DL, and their comparison. In the ML section, the RF model, which used a combination of the image's primary bands and texture features, performed better than other models with an overall accuracy of 95.21% and a Kappa coefficient of 92.62%. In the DL section, the MRU-Net model produced the most optimal LCM with an overall accuracy of 95.33% and a Kappa coefficient of 92.73% compared to other deep models. The MRU-Net model, without using texture features, improved overall accuracy and the Kappa coefficient by 0.53% and 0.82%, respectively, compared to the RF model using a combination of primary image bands. Furthermore, compared to the RF model, which used a combination of primary bands and texture features, the MRU-Net model's overall accuracy and Kappa coefficient were 0.12% and 0.11% higher, respectively. |
Article number: 4 |
| Keywords: Land Cover Classification, Machine Learning, Deep Learning, U-Net |
|
|
Full-Text [PDF 4818 kb]
(164 Downloads)
|
Type of Study: Research |
Subject:
Photo&RS
Received: 2024/05/20
|
|
|
|
|
|
|
| References |
1. H. Waghela, S. Patel, P. Sudesan, S. Raorane, and R. Borgalli, "Land Use Land Cover Classification using Machine Learning," in 2022 International Conference on Automation, Computing and Renewable Systems (ICACRS), Pudukkottai, India: IEEE, Dec. 2022, pp. 708-711. doi: 10.1109/ICACRS55517.2022.10029176. [ DOI:10.1109/ICACRS55517.2022.10029176] 2. A. S. Mahdi, "The Land Use and Land Cover Classification on the Urban Area," Iraqi J. Sci., pp. 4609-4619, Oct. 2022, doi: 10.24996/ijs.2022.63.10.42. [ DOI:10.24996/ijs.2022.63.10.42] 3. V. T. Chavan and S. J. Wagh, "Efficient Land Cover Classification for Urban Planning," in Object Detection by Stereo Vision Images, 1st ed., R. Arokia Priya, A. V. Patil, M. Bhende, A. Thakare, and S. Wagh, Eds., Wiley, 2022, pp. 185-194. doi: 10.1002/9781119842286.ch11. [ DOI:10.1002/9781119842286.ch11] 4. H. Xie and H. Huang, "Classification of Land Cover Remote-Sensing Images Based on Pattern Recognition," Sci. Program., vol. 2022, pp. 1-15, Sep. 2022, doi: 10.1155/2022/8319692. [ DOI:10.1155/2022/8319692] 5. S. Nalla, M. Totakura, D. Pidikiti, and K. Pranathi, "Monitoring Urban Growth Using Land Use Land Cover Classification," in Information and Communication Technology for Competitive Strategies (ICTCS 2022), vol. 615, M. S. Kaiser, J. Xie, and V. S. Rathore, Eds., in Lecture Notes in Networks and Systems, vol. 615. , Singapore: Springer Nature Singapore, 2023, pp. 275-283. doi: 10.1007/978-981-19-9304-6_27. [ DOI:10.1007/978-981-19-9304-6_27] 6. V. Nasiri, A. Deljouei, F. Moradi, S. M. M. Sadeghi, and S. A. Borz, "Land Use and Land Cover Mapping Using Sentinel-2, Landsat-8 Satellite Images, and Google Earth Engine: A Comparison of Two Composition Methods," Remote Sens., vol. 14, no. 9, p. 1977, Apr. 2022, doi: 10.3390/rs14091977. [ DOI:10.3390/rs14091977] 7. X. Yang and Z. Liu, "Using satellite imagery and GIS for land‐use and land‐cover change mapping in an estuarine watershed," Int. J. Remote Sens., vol. 26, no. 23, pp. 5275-5296, Dec. 2005, doi: 10.1080/01431160500219224. [ DOI:10.1080/01431160500219224] 8. A. Kumari and S. Karthikeyan, "Sentinel-2 Data for Land Use/Land Cover Mapping: A Meta-analysis and Review," SN Comput. Sci., vol. 4, no. 6, p. 815, Oct. 2023, doi: 10.1007/s42979-023-02214-0. [ DOI:10.1007/s42979-023-02214-0] 9. C. F. Brown et al., "Dynamic World, Near real-time global 10 m land use land cover mapping," Sci. Data, vol. 9, no. 1, p. 251, Jun. 2022, doi: 10.1038/s41597-022-01307-4. [ DOI:10.1038/s41597-022-01307-4] 10. E. Khankeshizadeh et al., "A Novel Weighted Ensemble Transferred U-Net Based Model (WETUM) for Postearthquake Building Damage Assessment From UAV Data: A Comparison of Deep Learning- and Machine Learning-Based Approaches," IEEE Trans. Geosci. Remote Sens., vol. 62, pp. 1-17, 2024, doi: 10.1109/TGRS.2024.3354737. [ DOI:10.1109/TGRS.2024.3354737] 11. S. Cuypers, A. Nascetti, and M. Vergauwen, "Land Use and Land Cover Mapping with VHR and Multi-Temporal Sentinel-2 Imagery," Remote Sens., vol. 15, no. 10, p. 2501, May 2023, doi: 10.3390/rs15102501. [ DOI:10.3390/rs15102501] 12. C. Lin and N. D. Doyog, "Challenges of Retrieving LULC Information in Rural-Forest Mosaic Landscapes Using Random Forest Technique," Forests, vol. 14, no. 4, p. 816, Apr. 2023, doi: 10.3390/f14040816. [ DOI:10.3390/f14040816] 13. C. J. A. Kouassi et al., "GOOGLE EARTH ENGINE FOR LANDSAT IMAGE PROCESSING AND ASSESSING LULC CLASSIFICATION IN SOUTHWESTERN CÔTE D'IVOIRE," Geod. Cartogr., vol. 49, no. 1, pp. 37-50, Mar. 2023, doi: 10.3846/gac.2023.16805. [ DOI:10.3846/gac.2023.16805] 14. D. A. Pantoja, D. Spenassato, and L. R. Emmendorfer, "Comparison Between Classification Algorithms: Gaussian Mixture Model - GMM and Random Forest - RF, for Landsat 8 Images," Rev. Gest. Soc. E Ambient., vol. 16, no. 3, p. e03234, Mar. 2023, doi: 10.24857/rgsa.v16n3-015. [ DOI:10.24857/rgsa.v16n3-015] 15. R. Saini and S. Rawat, "Land Use Land Cover Classification in Remote Sensing Using Machine Learning Techniques," in 2023 1st International Conference on Innovations in High Speed Communication and Signal Processing (IHCSP), BHOPAL, India: IEEE, Mar. 2023, pp. 99-104. doi: 10.1109/IHCSP56702.2023.10127126. [ DOI:10.1109/IHCSP56702.2023.10127126] 16. A. Jafari et al., "Enhancing a convolutional neural network model for land subsidence susceptibility mapping using hybrid meta-heuristic algorithms," Int. J. Coal Geol., vol. 277, p. 104350, Aug. 2023, doi: 10.1016/j.coal.2023.104350. [ DOI:10.1016/j.coal.2023.104350] 17. G. Mountrakis and S. S. Heydari, "Harvesting the Landsat archive for land cover land use classification using deep neural networks: Comparison with traditional classifiers and multi-sensor benefits," ISPRS J. Photogramm. Remote Sens., vol. 200, pp. 106-119, Jun. 2023, doi: 10.1016/j.isprsjprs.2023.05.005. [ DOI:10.1016/j.isprsjprs.2023.05.005] 18. S. Garg, S. Jain, N. Dube, and N. Varghese, Eds., "Leveraging twin networks for land use land cover classification," in Earth Observation Data Analytics Using Machine and Deep Learning: Modern tools, applications and challenges, Institution of Engineering and Technology, 2023, pp. 51-65. doi: 10.1049/PBPC056E_ch4. [ DOI:10.1049/PBPC056E_ch4] 19. H. Dastour and Q. K. Hassan, "A Comparison of Deep Transfer Learning Methods for Land Use and Land Cover Classification," Sustainability, vol. 15, no. 10, p. 7854, May 2023, doi: 10.3390/su15107854. [ DOI:10.3390/su15107854] 20. G. Cecili, P. De Fioravante, P. Dichicco, L. Congedo, M. Marchetti, and M. Munafò, "Land Cover Mapping with Convolutional Neural Networks Using Sentinel-2 Images: Case Study of Rome," Land, vol. 12, no. 4, p. 879, Apr. 2023, doi: 10.3390/land12040879. [ DOI:10.3390/land12040879] 21. H. Fahmi and W. P. Sari, "Analysis of deep learning architecture for patch-based land cover classification," in 2022 6th International Conference on Information Technology, Information Systems and Electrical Engineering (ICITISEE), Yogyakarta, Indonesia: IEEE, Dec. 2022, pp. 1-5. doi: 10.1109/ICITISEE57756.2022.10057895. [ DOI:10.1109/ICITISEE57756.2022.10057895] 22. Microwave Remote Sensing and Global Data Processing, SDAPSA, National Remote Sensing Centre, Balanagar, Hyderabad, India-500037, D. S. Rao, A. V. V. Prasad, and T. Nair, "Application of Texture Characteristics for Urban Feature Extraction from Optical Satellite Images," Int. J. Image Graph. Signal Process., vol. 7, no. 1, pp. 16-24, Dec. 2014, doi: 10.5815/ijigsp.2015.01.03. [ DOI:10.5815/ijigsp.2015.01.03] 23. L. Rokach and O. Maimon, Data mining with decision trees: theory and applications, Second edition. Hackensack, New Jersey: World Scientific, 2015. 24. A. Zaidi and A. S. M. Al Luhayb, "Two Statistical Approaches to Justify the Use of the Logistic Function in Binary Logistic Regression," Math. Probl. Eng., vol. 2023, pp. 1-11, Apr. 2023, doi: 10.1155/2023/5525675. [ DOI:10.1155/2023/5525675] 25. Md. S. Chowdhury, "Comparison of accuracy and reliability of random forest, support vector machine, artificial neural network and maximum likelihood method in land use/cover classification of urban setting," Environ. Chall., vol. 14, p. 100800, Jan. 2024, doi: 10.1016/j.envc.2023.100800. [ DOI:10.1016/j.envc.2023.100800] 26. P. Ahmadi, T. Managhebi, H. Ebadi, and B. Asghari, "Improving the Classification of Hyperspectral Images Using the Combined Model of CapsNet and the Extreme Gradient Boosting," Iran. J. Remote Sens. GIS, vol. 15, no. 3, pp. 41-60, Aug. 2023, doi: 10.48308/gisj.2023.102347. [ DOI:10.52547/gisj.15.1.39] 27. E. Khankeshizadeh, A. Mohammadzadeh, A. Moghimi, and A. Mohsenifar, "FCD-R2U-net: Forest change detection in bi-temporal satellite images using the recurrent residual-based U-net," Earth Sci. Inform., vol. 15, Nov. 2022, doi: 10.1007/s12145-022-00885-6. [ DOI:10.1007/s12145-022-00885-6] 28. Z. Zhou, M. M. Rahman Siddiquee, N. Tajbakhsh, and J. Liang, UNet++: A Nested U-Net Architecture for Medical Image Segmentation. 2018. [ DOI:10.1007/978-3-030-00889-5_1] 29. "ResUNet-a: A deep learning framework for semantic segmentation of remotely sensed data," ISPRS J. Photogramm. Remote Sens., vol. 162, pp. 94-114, Apr. 2020, doi: 10.1016/j.isprsjprs.2020.01.013. [ DOI:10.1016/j.isprsjprs.2020.01.013] 30. N. Ibtehaz and M. S. Rahman, "MultiResUNet : Rethinking the U-Net architecture for multimodal biomedical image segmentation," Neural Netw., vol. 121, pp. 74-87, Jan. 2020, doi: 10.1016/j.neunet.2019.08.025. [ DOI:10.1016/j.neunet.2019.08.025] |
|
| Send email to the article author |
|
|
|
| Add your comments about this article |
|
|
|
|
Saeedi D, Khankeshizadeh E, Managhebi T, Karimi M, Mohammadzadeh A. Land Cover Classification Based on Machine Learning and Deep Learning Methods Using Sentinel-2 Satellite Images: A Case Study of the Urban Area in West Tehran. JGST 2024; 14 (2) : 4 URL: http://jgst.issgeac.ir/article-1-1185-en.html
|
