From Pixels to Patterns: A Review of Land Cover Analysis Techniques
Keywords:
land cover, remote sensing, GIS, machine learning, deep learning, convolutional neural networksAbstract
Land cover analysis is a crucial task in environmental studies and management. In recent years, deep learning methods have been increasingly applied to land cover analysis, showing promising results. In this literature review, we compare the performance of various land cover analysis studies using different datasets and deep learning methodologies. Our analysis shows that deep learning approaches have outperformed traditional methods in terms of overall accuracy. We found that studies using Sentinel-2 and Landsat 8 datasets produced the highest accuracies, with some studies achieving up to 97.8% accuracy. Deep learning-based methods such as deep belief networks, support vector machines, random forests, and deep neural networks have been used to classify land cover with high accuracy. These findings suggest that deep learning approaches are a powerful tool for land cover analysis and can provide valuable insights for environmental management and policy.
Introduction: Land cover analysis is an important aspect of natural resource management and has become increasingly important in recent years due to the need for accurate and timely information on land use changes. Land cover analysis is a crucial task in environmental monitoring and management.Various techniques have been developed to analyze land cover, including remote sensing, GIS, and machine learning. land cover analysis has been increasingly performed using deep learning techniques due to their high accuracy and efficiency and to summarize the current state of research on this topic. The accuracy of these techniques is critical to ensure the effectiveness of land use management strategies. This literature review paper aims to compare the accuracy of different land cover analysis techniques and summarize the current state of research on this topic.
Downloads
References
Li, J., Yuan, Y., & Zhang, Y. (2020). High-resolution land-cover mapping with a U-Net-based convolutional neural network. International Journal of Remote Sensing, 41(19), 7275-7290.
Wang, Y., Liu, S., Yang, H., & Zhang, Y. (2020). A deep learning-based change detection method for land cover using time-series Sentinel-2 data. Remote Sensing, 12(8), 1262.
Zhang, Y., Yan, B., & Yang, Q. (2021). Land-cover classification using a hybrid convolutional neural network model. International Journal of Remote Sensing, 42(3), 1073-1092.
Chen, K., Li, D., Liu, H., Xu, Q., & Zhang, X. (2021). Land cover change detection based on deep learning using Sentinel-2 images. ISPRS Journal of Photogrammetry and Remote Sensing, 181, 272-284.
He, C., Zhang, S., Liu, Y., & Lu, Y. (2021). Multi-task learning for urban land cover classification with high-resolution imagery. Remote Sensing, 13(12), 2343.
Wang, C., Jiang, Y., Wang, J., & Zhang, X. (2021). A deep learning-based approach for land cover classification from Sentinel-2 imagery. Remote Sensing, 13(9), 1785.
Wang, X., Huang, X., Liu, Y., Xu, Z., Zhang, L., & Zhou, Z. (2021). A deep learning-based method for land cover change detection using multi-temporal Landsat 8 data. Remote Sensing, 13(10), 2030.
Saha, S., & Pieczarka, E. (2010). Land cover classification of MODIS data using decision tree classifier. International Journal of Applied Earth Observation and Geoinformation, 12, S4-S9.
Deepthi, P., Rao, P. V. N., & Chakravarthi, V. (2015). Land cover classification using maximum likelihood classification on Landsat 8 data. International Journal of Scientific and Research Publications, 5(11), 228-233.
Yu, Y., Zhao, X., & Li, X. (2017). A support vector machine approach for land cover classification using Landsat 8 imagery. Remote Sensing, 9(9), 905.
Liu, J., Chen, J., & Chen, J. (2018). Random forest classification of Landsat 8 remote sensing data for land cover and land use mapping in Shenzhen. International Journal of Geosciences, 9(2), 186-200.
Chen, S., Chen, Y., & Lu, M. (2018). A deep learning-based approach to classification of land use and land cover on Sentinel-2 data. IEEE Geoscience and Remote Sensing Letters, 15(5), 749-753.
Ren, J., Hu, T., Zhang, S., & Wang, S. (2019). Deep residual networks for hyperspectral image classification. Remote Sensing, 11(3), 291.
Xia, Y., Li, X., Li, Z., & Wu, Y. (2019). A deep belief network classifier for high-resolution remote sensing imagery. Remote Sensing, 11(5), 577.
Yu, L., Gong, P., Clinton, N., Biging, G., Kelly, M., & Schirokauer, D. (2020). Deep learning-based multi-temporal cloud and cloud shadow detection for Landsat images. Remote Sensing of Environment, 236, 111479.
Wang, L., Xu, H., Zhang, W., & Wei, H. (2021). A deep learning-based approach for land cover mapping using Sentinel-2 imagery. International Journal of Remote Sensing, 42(1), 81-101.
He, L., Liu, Y., Cai, X., & Luo, Y. (2021). A multi-task learning framework for land-use and land-cover mapping from high-resolution imagery. Remote Sensing, 13(14), 2800.
Wang, Z., Zhang, L., Gao, Y., & Wu, W. (2021). Multi-temporal deep learning-based method for land cover classification from Landsat 8 images. Journal of Applied Remote Sensing, 15(1), 016522.
Chen, S., Chen, Y., Lu, M., & Wu, Q. (2021). A deep learning-based approach for land cover classification using Sentinel-2 imagery. IEEE Transactions on Geoscience and Remote Sensing, 59(3), 2528-2539.
L. S. Macarringue, É. L. Bolfe, and P. R. M. Pereira, “Developments in Land Use and Land Cover Classification Techniques in Remote Sensing: A Review,” J. Geogr. Inf. Syst., vol. 14, no. 01, pp. 1–28, 2022, doi: 10.4236/jgis.2022.141001.
D. Li, S. Wang, Q. He, and Y. Yang, “Cost-effective land cover classification for remote sensing images,” J. Cloud Comput., vol. 11, no. 1, 2022, doi: 10.1186/s13677-022-00335-0.
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
All papers should be submitted electronically. All submitted manuscripts must be original work that is not under submission at another journal or under consideration for publication in another form, such as a monograph or chapter of a book. Authors of submitted papers are obligated not to submit their paper for publication elsewhere until an editorial decision is rendered on their submission. Further, authors of accepted papers are prohibited from publishing the results in other publications that appear before the paper is published in the Journal unless they receive approval for doing so from the Editor-In-Chief.
IJISAE open access articles are licensed under a Creative Commons Attribution-ShareAlike 4.0 International License. This license lets the audience to give appropriate credit, provide a link to the license, and indicate if changes were made and if they remix, transform, or build upon the material, they must distribute contributions under the same license as the original.
