Accurate land cover classification is essential for environmental monitoring, urban planning, and resource management. Conventional classifiers trained on raw spectral bands are often limited by noise, inter-class spectral similarity, and intra-class variability. This study introduces a wavelet-based feature decomposition and machine learning framework to address these challenges. Landsat-8 Operational Land Imager (OLI) Level-2 surface reflectance data were pre-processed and decomposed using a one-dimensional discrete wavelet transform to isolate low- and high-frequency components. The decomposed features were concatenated with raw bands to form an enriched dataset, which was used to train and validate three supervised classifiers: Random Forest (RF), Gradient Boosting (GBM), and Decision Tree (DT). Model performance was evaluated using 5-fold cross-validation, and the best-performing model, the Random Forest Wavelet Transform (RF_WT), achieved the highest macro-F1 score (0.865). Explainable AI (Gini importance, permutation importance, SHAP (SHapley Additive exPlanations) values) confirmed the complementary role of raw and decomposed features, with wavelet-derived detail components in the Short-Wave Infrared (SWIR) and visible bands strongly influencing classification. The RF_WT model, when compared to RF, DT and GBM classifiers trained on raw spectral bands across all classes, achieved the highest macro-averaged accuracy values (UA = 0.876, PA = 0.864, F1 = 0.865), compared with RF (UA = 0.864, PA = 0.852, F1 = 0.853), GBM (UA = 0.849, PA = 0.832, F1 = 0.832), and DT (UA = 0.815, PA = 0.808, F1 = 0.809). The approach is valuable in support of ecological monitoring and resource management. However, challenges in settlement classification highlight the limitations of medium-resolution data. Future work could integrate higher-resolution imagery or multi-temporal data for improved performance.
References
[1]
Navin, M.S. and Agilandeeswari, L. (2020) Comprehensive Review on Land Use/Land Cover Change Classification in Remote Sensing. Journal of Spectral Imaging, 9, a8.
[2]
Ramachandra, T.V., Mondal, T. and Setturu, B. (2023) Relative Performance Evaluation of Machine Learning Algorithms for Land Use Classification Using Multispectral Moderate Resolution Data. SNAppliedSciences, 5, Article 274. https://doi.org/10.1007/s42452-023-05496-4
[3]
Ali, U., Esau, T.J., Farooque, A.A., Zaman, Q.U., Abbas, F. and Bilodeau, M.F. (2022) Limiting the Collection of Ground Truth Data for Land Use and Land Cover Maps with Machine Learning Algorithms. ISPRS International Journal of Geo-Information, 11, Article 333. https://doi.org/10.3390/ijgi11060333
[4]
Barman, P., Mustak, S., Kuffer, M. and Singh, S.K. (2023) Transfer-Ensemble Learning: A Novel Approach for Mapping Urban Land Use/Cover of the Indian Metropolitans. Sustainability, 15, Article 16593. https://doi.org/10.3390/su152416593
[5]
Qin, R. and Liu, T. (2022) A Review of Landcover Classification with Very-High Resolution Remotely Sensed Optical Images—Analysis Unit, Model Scalability and Transferability. RemoteSensing, 14, Article 646. https://doi.org/10.3390/rs14030646
[6]
Shimabukuro, Y.E., Arai, E., da Silva, G.M., Hoffmann, T.B., Duarte, V., Martini, P.R., et al. (2023) Mapping Land Use and Land Cover Classes in São Paulo State, Southeast of Brazil, Using Landsat-8 OLI Multispectral Data and the Derived Spectral Indices and Fraction Images. Forests, 14, Article 1669. https://doi.org/10.3390/f14081669
[7]
Talukdar, S., Singha, P., Mahato, S., Shahfahad,, Pal, S., Liou, Y., et al. (2020) Land-use Land-Cover Classification by Machine Learning Classifiers for Satellite Observations—A Review. RemoteSensing, 12, Article 1135. https://doi.org/10.3390/rs12071135
[8]
Li, R., Zheng, S., Duan, C., Wang, L. and Zhang, C. (2022) Land Cover Classification from Remote Sensing Images Based on Multi-Scale Fully Convolutional Network. Geo-spatialInformationScience, 25, 278-294. https://doi.org/10.1080/10095020.2021.2017237
[9]
Huang, C., Davis, L.S. and Townshend, J.R.G. (2002) An Assessment of Support Vector Machines for Land Cover Classification. InternationalJournalofRemoteSensing, 23, 725-749. https://doi.org/10.1080/01431160110040323
[10]
Nguyen, H.T.T., Doan, T.M. and Radeloff, V. (2018) Applying Random Forest Classification to Map Land Use/Land Cover Using Landsat 8 Oli. TheInternationalArchivesofthePhotogrammetry, RemoteSensingandSpatialInformationSciences, 3, 363-367. https://doi.org/10.5194/isprs-archives-xlii-3-w4-363-2018
[11]
Madarasinghe, S.K., Yapa, K.K.A.S. and Jayatissa, L.P. (2020) Google Earth Imagery Coupled with On-Screen Digitization for Urban Land Use Mapping: Case Study of Hambantota, Sri Lanka. JournaloftheNationalScienceFoundationofSriLanka, 48, 357-366. https://doi.org/10.4038/jnsfsr.v48i4.9795
[12]
Gómez, C., White, J.C. and Wulder, M.A. (2016) Optical Remotely Sensed Time Series Data for Land Cover Classification: A Review. ISPRSJournalofPhotogrammetryandRemoteSensing, 116, 55-72. https://doi.org/10.1016/j.isprsjprs.2016.03.008
[13]
Belgiu, M. and Drăguţ, L. (2016) Random Forest in Remote Sensing: A Review of Applications and Future Directions. ISPRSJournalofPhotogrammetryandRemoteSensing, 114, 24-31. https://doi.org/10.1016/j.isprsjprs.2016.01.011
[14]
Abdi, A.M. (2019) Land Cover and Land Use Classification Performance of Machine Learning Algorithms in a Boreal Landscape Using Sentinel-2 Data. GIScience&RemoteSensing, 57, 1-20. https://doi.org/10.1080/15481603.2019.1650447
[15]
Rodriguez-Galiano, V.F., Ghimire, B., Rogan, J., Chica-Olmo, M. and Rigol-Sanchez, J.P. (2012) An Assessment of the Effectiveness of a Random Forest Classifier for Land-Cover Classification. ISPRSJournalofPhotogrammetryandRemoteSensing, 67, 93-104. https://doi.org/10.1016/j.isprsjprs.2011.11.002
[16]
Fu, H., Sun, G., Ren, J., Zhang, A. and Jia, X. (2022) Fusion of PCA and Segmented-PCA Domain Multiscale 2-D-SSA for Effective Spectral-Spatial Feature Extraction and Data Classification in Hyperspectral Imagery. IEEETransactionsonGeoscienceandRemoteSensing, 60, 1-14. https://doi.org/10.1109/tgrs.2020.3034656
[17]
Shih, H., Stow, D.A. and Tsai, Y.H. (2018) Guidance on and Comparison of Machine Learning Classifiers for Landsat-Based Land Cover and Land Use Mapping. InternationalJournalofRemoteSensing, 40, 1248-1274. https://doi.org/10.1080/01431161.2018.1524179
[18]
Signoroni, A., Savardi, M., Baronio, A. and Benini, S. (2019) Deep Learning Meets Hyperspectral Image Analysis: A Multidisciplinary Review. JournalofImaging, 5, Article 52. https://doi.org/10.3390/jimaging5050052
[19]
Zabalza, J., Ren, J., Zheng, J., Han, J., Zhao, H., Li, S., et al. (2015) Novel Two-Dimensional Singular Spectrum Analysis for Effective Feature Extraction and Data Classification in Hyperspectral Imaging. IEEETransactionsonGeoscienceandRemoteSensing, 53, 4418-4433. https://doi.org/10.1109/tgrs.2015.2398468
[20]
Fu, H., Sun, G., Ren, J., Zabalza, J., Zhang, A. and Yao, Y. (2020) 2D-SSA Based Multiscale Feature Fusion for Feature Extraction and Data Classification in Hyperspectral Imagery. IGARSS 2020—2020 IEEE International Geoscience and Remote Sensing Symposium, Waikoloa, 26 September-2 October 2020, 76-79. https://doi.org/10.1109/igarss39084.2020.9323776
[21]
Kang, X., Duan, P. and Li, S. (2020) Hyperspectral Image Visualization with Edge-Preserving Filtering and Principal Component Analysis. InformationFusion, 57, 130-143. https://doi.org/10.1016/j.inffus.2019.12.003
[22]
Boamah Poku, M., Yakubu, I., Yevenyo Ziggah, Y., Poku, M.B., Yakubu, I. and Ziggah, Y.Y. (2023) Assessing the Performance of Machine Learning Algorithms for Urban Land Cover Classification using Multispectral Satellite Imagery. Ghana Journal of Technology, 7, 10-18.
[23]
Phan, T.N., Kuch, V. and Lehnert, L.W. (2020) Land Cover Classification Using Google Earth Engine and Random Forest Classifier—The Role of Image Composition. RemoteSensing, 12, Article 2411. https://doi.org/10.3390/rs12152411
[24]
Tassi, A., Gigante, D., Modica, G., Di Martino, L. and Vizzari, M. (2021) Pixel-vs. Object-Based Landsat 8 Data Classification in Google Earth Engine Using Random Forest: The Case Study of Maiella National Park. RemoteSensing, 13, Article 2299. https://doi.org/10.3390/rs13122299
[25]
Vermote, E., Justice, C., Claverie, M. and Franch, B. (2016) Preliminary Analysis of the Performance of the Landsat 8/OLI Land Surface Reflectance Product. RemoteSensingofEnvironment, 185, 46-56. https://doi.org/10.1016/j.rse.2016.04.008
[26]
Gorelick, N., Hancher, M., Dixon, M., Ilyushchenko, S., Thau, D. and Moore, R. (2017) Google Earth Engine: Planetary-Scale Geospatial Analysis for Everyone. RemoteSensingofEnvironment, 202, 18-27. https://doi.org/10.1016/j.rse.2017.06.031
[27]
Bwangoy, J.B., Hansen, M.C., Roy, D.P., Grandi, G.D. and Justice, C.O. (2010) Wetland Mapping in the Congo Basin Using Optical and Radar Remotely Sensed Data and Derived Topographical Indices. RemoteSensingofEnvironment, 114, 73-86. https://doi.org/10.1016/j.rse.2009.08.004
[28]
de Sousa, C., Fatoyinbo, L., Neigh, C., Boucka, F., Angoue, V. and Larsen, T. (2020) Cloud-computing and Machine Learning in Support of Country-Level Land Cover and Ecosystem Extent Mapping in Liberia and Gabon. PLOSONE, 15, e0227438. https://doi.org/10.1371/journal.pone.0227438
[29]
Dong, J., Xiao, X., Sheldon, S., Biradar, C., Duong, N.D. and Hazarika, M. (2012) A Comparison of Forest Cover Maps in Mainland Southeast Asia from Multiple Sources: PALSAR, MERIS, MODIS and Fra. RemoteSensingofEnvironment, 127, 60-73. https://doi.org/10.1016/j.rse.2012.08.022
[30]
Hansen, M.C., Roy, D.P., Lindquist, E., Adusei, B., Justice, C.O. and Altstatt, A. (2008) A Method for Integrating MODIS and Landsat Data for Systematic Monitoring of Forest Cover and Change in the Congo Basin. RemoteSensingofEnvironment, 112, 2495-2513. https://doi.org/10.1016/j.rse.2007.11.012
[31]
Midekisa, A., Holl, F., Savory, D.J., Andrade-Pacheco, R., Gething, P.W., Bennett, A., et al. (2017) Mapping Land Cover Change over Continental Africa Using Landsat and Google Earth Engine Cloud Computing. PLOSONE, 12, e0184926. https://doi.org/10.1371/journal.pone.0184926
[32]
Cohen, A. and Kovacevic, J. (1996) Wavelets: The Mathematical Background. ProceedingsoftheIEEE, 84, 514-522. https://doi.org/10.1109/5.488697
[33]
C., E.W. and Daubechies, I. (1993) Ten Lectures on Wavelets. MathematicsofComputation, 61, 941-942. https://doi.org/10.2307/2153268
[34]
Mallat, S.G. (2009) A Theory for Multiresolution Signal Decomposition: The Wavelet Representation. In: Heil, C. and Walnut, D.F., Eds., FundamentalPapersinWaveletTheory, Princeton University Press, 494-513. https://doi.org/10.1515/9781400827268.494
[35]
Prabhu, N., Arora, M.K. and Balasubramanian, R. (2016) Wavelet Based Feature Extraction Techniques of Hyperspectral Data. JournaloftheIndianSocietyofRemoteSensing, 44, 373-384. https://doi.org/10.1007/s12524-015-0506-9
Breiman, L. (2001) Random Forests. MachineLearning, 45, 5-32. https://doi.org/10.1023/a:1010933404324
[38]
Friedman, J.H. (2001) Greedy Function Approximation: A Gradient Boosting Machine. TheAnnalsofStatistics, 29, 1189-1232. https://doi.org/10.1214/aos/1013203451
[39]
Dorogush, A., Ershov, V. and Gulin, A. (2018) CatBoost: Unbiased Boosting with Categorical Features. 32nd Conference on Neural Information Processing Systems (NeurIPS 2018), Montréal, 2-8 December 2018, 6638-6648.
[40]
Ke, G., Meng, Q., Finley, T., Wang, T., Chen, W., Ma, W., Ye, Q. and Liu, T.Y. (2017) LightGBM: A Highly Efficient Gradient Boosting Decision Tree. 31st Conference on Neural Information Processing Systems (NIPS 2017), Long Beach, 4-9 December 2017, 3147-3155.
[41]
Nsiah, R.A., Mantey, S. and Ziggah, Y.Y. (2024) Assessing the Contribution of RGB Vis in Improving Building Extraction from RGB-UAV Images. MersinPhotogrammetryJournal, 6, 9-21. https://doi.org/10.53093/mephoj.1399083
[42]
Ji, H., Li, X., Wei, X., Liu, W., Zhang, L. and Wang, L. (2020) Mapping 10-M Resolution Rural Settlements Using Multi-Source Remote Sensing Datasets with the Google Earth Engine Platform. RemoteSensing, 12, Article 2832. https://doi.org/10.3390/rs12172832
[43]
Sun, G., Chen, X., Ren, J., Zhang, A. and Jia, X. (2017) Stratified Spectral Mixture Analysis of Medium Resolution Imagery for Impervious Surface Mapping. InternationalJournalofAppliedEarthObservationandGeoinformation, 60, 38-48. https://doi.org/10.1016/j.jag.2017.04.006
