Analysis of Detailed Wetland Land Mapping Using Landsat Imagery: A Hybrid Segmented PCA and Machine Learning Approach Integrated with Spectral Indices

Abstract

Lakes serve as vital ecological assets, sustaining biodiversity, supporting human activities, and maintaining environmental balance. Effective mapping of land cover types is essential for assessing ecological health and monitoring biodiversity dynamics in such ecosystems. This study focuses on Pulicat Lake, the second-largest brackish water lagoon in India, which represents a complex and dynamic environment influenced by both riverine and marine inputs. A methodological framework integrating Segmented Principal Component Analysis (SPCA), Base maps for Water, Vegetation, Soil created using SVM algorithm and spectral indices was analyzed in enhanced land cover mapping accuracy using the RF algorithm in multispectral Landsat 8 imagery. The SPCA method selectively applies PCA to targeted spectral band combinations for specific land cover types, thereby improving spectral separability of the classes. The SPCA/RF/spectral indices approach yielded a significantly improved classification accuracy of 97.52% and a Kappa coefficient of 0.96. These results highlight the effectiveness of the SPCA framework with an RF classifier and integration of spectral indices in land cover mapping and ecosystem monitoring in complex and dynamic environments like Pulicat Lake.

Keywords

• Landsat
• Land Cover
• PCA
• Segmented PCA
• RF Algorithm
• Spectral Indices

Ethical Statement

The authors declare that there is no conflict of interest.

References

1. Kannan, V. (2022). Vulnerable ecosystem: The Pulicat Lake needs government's attention. Earthy Worthy, 1(1).
2. Mohsen, A., Elshemy, M., & Zeidan, B. (2021). Water quality monitoring of Lake Burullus (Egypt) using Landsat satellite imageries. Environmental Science and Pollution Research, 28, 15687–15700. https://doi.org/10.1007/s11356-020-11852-w
3. Illangovan, R. (2007). Restoration of polluted lakes—A new approach. In Proceedings of the 12th World Lake Conference (pp. 1321–1328).
4. Sanjeeva Raj, P. J. (2006). Macro fauna of Pulicat Lake. National Biodiversity Authority.
5. Syamala, R., & Hemavathy, E. (2018). Physico-chemical parameters and land use patterns of Pulicat Lake, Tamil Nadu, India. International Journal of Advanced Scientific and Technical Research, 6(8), 10–37.
6. Jiang, W., He, G., Long, T., & Ni, Y. (2018). Detecting water bodies in Landsat 8 OLI image using deep learning. The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, XLII-3, 669–672. https://doi.org/10.5194/isprs-archives-XLII-3-669-2018
7. Uddin, M. P., Mamun, M. A., & Hossain, M. A. (2020). PCA-based feature reduction for hyperspectral remote sensing image classification. IETE Technical Review. https://doi.org/10.1080/02564602.2020.1740615
8. Liu, L., Li, C.-F., Lei, Y.-M., Yin, J.-Y., & Zhao, J.-J. (2017). Feature extraction for hyperspectral remote sensing image using weighted PCA-ICA. Arabian Journal of Geosciences, 10, 307. https://doi.org/10.1007/s12517-017-3090-1

9. 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.
10. Gandhi, M., Parthiban, S., Thummalu, N., & Christy, A. (2015). NDVI: Vegetation change detection using remote sensing and GIS—A case study of Vellore District. Procedia Computer Science, 57, 1199–1210.
11. Nguyen, K.-A., Liou, Y.-A., Tran, H.-P., Hoang, P.-P., & Nguyen, T.-H. (2020). Soil salinity assessment using NIR channel and vegetation soil salinity index from Landsat 8 OLI data: A case study in Tra Vinh Province, Mekong Delta, Vietnam. Progress in Earth and Planetary Science, 7(1), 1–16.
12. Thirunavukkarasu, N., Gokulakrishnan, S., Premjothi, P. V. R., & Inbaraj, R. M. (2011). Need of coastal resource management in Pulicat Lake—Challenges ahead. Indian Journal of Science and Technology, 4(3), 322–326. https://doi.org/10.17485/ijst/2011/v4i3/29990
13. United States Geological Survey. (2024). EarthExplorer. https://earthexplorer.usgs.gov
14. Chander, G., Markham, B. L., & Helder, D. L. (2009). Summary of current radiometric calibration coefficients for Landsat MSS, TM, ETM+, and EO-1 ALI sensors. Remote Sensing of Environment, 113(5), 893–903. https://doi.org/10.1016/j.rse.2009.01.007
15. Makar, R. S., Shahin, S. A., El-Nazer, M., & Wheida, A. (2022). Development of a PCA-based land use/land cover classification utilizing Sentinel-2 time series. Middle East Journal of Agricultural Research, 11(2), 630–637. https://doi.org/10.36632/mejar/2022.11.2.42
16. Gupta, R., Tiwari, R., Saini, V., & Srivastava, N. (2013). A simplified approach for interpreting principal component images. Advances in Remote Sensing, 2, 111–119. https://doi.org/10.4236/ars.2013.22015
17. Kulkarni, K., & Vijaya, V. (2021). Separability analysis of the band combinations for land cover classification of satellite images. International Journal of Engineering Trends and Technology, 69, 138–144. https://doi.org/10.14445/22315381/IJETT-V69I8P217
18. Hashim, F., Dibs, H., & Jaber, H. S. (2021). Applying support vector machine algorithm on multispectral remotely sensed satellite image for geospatial analysis. In Proceedings of the 2nd International Conference on Physics and Applied Science (ICPAS 2021).
19. Albert, G., & Ammar, S. (2021). Application of random forest classification and remotely sensed data in geological mapping on the Jebel Meloussi area (Tunisia). Arabian Journal of Geosciences, 14, 2240. https://doi.org/10.1007/s12517-021-08509-x
20. Vasavi, S., Chintalapudi, V. K., & Vuppuluri, A. S. R. (2024). Classification of water bodies using ensemble of U-Net and random forest algorithm. Journal of Image and Graphics, 12(1), 76–89.
21. Xu, H. (2006). Modification of normalized difference water index (NDWI) to enhance open water features in remotely sensed imagery. International Journal of Remote Sensing, 27(14), 3025–3033.
22. Donatien, L. M. B., Clobite, B. B., & Midel, M. L. (2024). Land use land cover change detection using multi-temporal Landsat imagery in the north of Congo Republic: A case study in Sangha region. Geocarto International, 39(1), 2425184. https://doi.org/10.1080/10106049.2024.2425184
23. Pal, T., Paul, A., Maiti, C., & Podder, T. (2024). Spatiotemporal analysis of land use and land cover dynamics using multi-temporal remote sensed imagery and quantifying landscape fragmentation: A case study of Chandannagar Municipal Corporation, West Bengal, India. World Journal of Advanced Research and Reviews, 23(3), 966–995. https://doi.org/10.30574/wjarr.2024.23.3.2664
24. QGIS.org. (2024). QGIS geographic information system. https://qgis.org
25. Congedo, L. (2021). Semi-Automatic Classification Plugin: A Python tool for the download and processing of remote sensing images in QGIS. https://doi.org/10.13140/RG.2.2.29474.02242
26. Llano, X. (2025). AcATaMa–QGIS plugin for accuracy assessment of thematic maps (Version 24.12C) [Computer software]. SMByC–IDEAM. https://github.com/SMByC/AcATaMa