Enhancing land use classification with hybrid machine learning and satellite imagery

DOI: https://doi.org/10.3846/ntcs.2025.23701

Abstract

The growing accessibility of satellite imagery and the rapid evolution of machine learning (ML) techniques have significantly advanced land use classification for environmental monitoring. However, challenges such as cloud coverage, varying image resolutions, and seasonal changes continue to hinder classification accuracy and consistency. This study aims to improve land use classification by proposing an integrated cloud interpolation, vegetation indices and ML based approach for classification of Sentinel-2 (S2) satellite data across the Baltic States. Specifically, a spatiotemporal interpolation module is introduced that reconstructs cloud-obscured pixels using multi-temporal coherence and derives optimized vegetation-index composites to enhance class separability under varying seasonal conditions. In order to achieve this aim and to choose the best ML algorithm for land use classification, we compare the performance of three classification algorithms, i.e., Random Forest (RF), K-Nearest Neighbours (KNN), and Support Vector Machines (SVM), and evaluate their effectiveness in handling noisy and incomplete data. Our experimental results show that all three methods achieve strong classification accuracy, with RF exceeding 90%, while KNN and SVM also demonstrate competitive results. These methodological enhancements have been demonstrated to reduce cloud-induced misclassification and provide a scalable, transferable framework for operational land-use mapping in challenging atmospheric and seasonal contexts. These findings highlight the robustness of the proposed approach and provide valuable insights for future applications of ML in land use classification and environmental analysis.

 

Keywords:

Sentinel-2, land use classification, image recognition, Random Forest, Support Vector Machine, machine learning, cloud interpolation

How to Cite

Jancevičius, J. (2025). Enhancing land use classification with hybrid machine learning and satellite imagery. New Trends in Computer Sciences, 3(1), 1–17. https://doi.org/10.3846/ntcs.2025.23701

Share

Published in Issue
May 26, 2025
Abstract Views
69

References

Ahmad, G. N., Fatima, H., Shaf, U., Salah Saidi, A., & Imdadullah. (2022). Efficient medical diagnosis of human heart diseases using machine learning techniques with and without GridSearchCV. IEEE Access, 10, 80151–80173. https://doi.org/10.1109/ACCESS.2022.3165792

Albertini, C., Gioia, A., Iacobellis, V., Petropoulos, G. P., & Manfreda, S. (2024). Assessing multi-source random forest classification and robustness of predictor variables in flooded areas mapping. Remote Sensing Applications: Society and Environment, 35, Article 101239. https://doi.org/10.1016/j.rsase.2024.101239

Aliabad, F. A., Malamiri, H. R. G., Shojaei, S., Sarsangi, A., Ferreira, C. S. S., & Kalantari, Z. (2022). Investigating the ability to identify new constructions in urban areas using images from unmanned aerial vehicles, Google Earth, and Sentinel-2. Remote Sensing, 14(13), Article 3227. https://doi.org/10.3390/rs14133227

Alshammari, T. (2024). Using artificial neural networks with GridSearchCV for predicting indoor temperature in a smart home. Engineering, Technology and Applied Science Research, 14(2), 13437–13443. https://doi.org/10.48084/etasr.7008

Anandakrishnan, J., Sundaram, V. M., & Paneer, P. (2024). CERMF-Net: A SAR-Optical feature fusion for cloud elimination from Sentinel-2 imagery using residual multiscale dilated network. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 17, 11741–11749. https://doi.org/10.1109/JSTARS.2024.3411032

Asmiwyati, I. G. A. A. R., Gargita, I. W. D., & Wiguna, P. P. K. (2025). Analysis of urban green open space development in North Denpasar District, Denpasar City, Bali, Indonesia. Geographia Technica, 20(1), 79–96. https://doi.org/10.21163/GT_2025.201.07

Bebie, M., Cavalaris, C., & Kyparissis, A. (2022). Assessing Durum wheat yield through Sentinel-2 imagery: A machine learning approach. Remote Sensing, 14(16), Article 3880. https://doi.org/10.3390/rs14163880

Belayhun, M., Chere, Z., Abay, N. G., Nicola, Y., & Asmamaw, A. (2024). Spatiotemporal pattern of water hyacinth (Pontederia crassipes) distribution in Lake Tana, Ethiopia, using a random forest machine learning model. Frontiers in Environmental Science, 12, Article 1476014. https://doi.org/10.3389/fenvs.2024.1476014

Bill Donatien, L. M., Biona Clobite, B., & Lemvo Meris Midel, M. (2024). Comparing Sentinel-2 and Landsat 9 for land use and land cover mapping assessment in the north of Congo Republic: A case study in Sangha region. International Journal of Remote Sensing, 45(2), 8015–8036. https://doi.org/10.1080/01431161.2024.2394238

Casamitjana, M., Torres-Madroñero, M. C., Bernal-Riobo, J., & Varga, D. (2020). Soil moisture analysis by means of multispectral images according to land use and spatial resolution on andosols in the colombian andes. Applied Sciences, 10(16), Article 5540. https://doi.org/10.3390/app10165540

Chanev, M., Kamenova, I., Dimitrov, P., & Filchev, L. (2025). Evaluation of Sentinel-2 deep resolution 3.0 data for winter crop identification and organic barley yield prediction. Remote Sensing, 17(6), Article 957. https://doi.org/10.3390/rs17060957

Chi, Z., Chen, H., Chang, S., Li, Z. L., Ma, L., Hu, T., Xu, K., & Zhao, Z. (2025). Large-Scale Monitoring of potatoes late blight using multi-source time-series data and Google Earth engine. Remote Sensing, 17(6), Article 978. https://doi.org/10.3390/rs17060978

Dobrinić, D., Gašparović, M., & Medak, D. (2021). Sentinel-1 and 2 time-series for vegetation mapping using random forest classification: A case study of Northern Croatia. Remote Sensing, 13(12), Article 2321. https://doi.org/10.3390/rs13122321

Eisfelder, C., Boemke, B., Gessner, U., Sogno, P., Alemu, G., Hailu, R., Mesmer, C., & Huth, J. (2024). Cropland and crop type classification with Sentinel-1 and Sentinel-2 time series using Google Earth Engine for agricultural monitoring in Ethiopia. Remote Sensing, 16(5), Article 866. https://doi.org/10.3390/rs16050866

Fan, Z., Zhan, T., Gao, Z., Li, R., Liu, Y., Zhang, L., Jin, Z., & Xu, S. (2022). Land cover classification of resources survey remote sensing images based on segmentation model. IEEE Access, 10, 56267–56281. https://doi.org/10.1109/ACCESS.2022.3175978

Farhadi, H., Ebadi, H., Kiani, A., & Asgary, A. (2024). Near real-time flood monitoring using multi-sensor optical imagery and machine learning by GEE: An automatic feature-based multi-class classification approach. Remote Sensing, 16(23), Article 4454. https://doi.org/10.3390/rs16234454

Farhadiani, R., Homayouni, S., Bhattacharya, A., & Mahdianpari, M. (2024). Crop classification using multi-temporal RADARSAT constellation mission compact polarimetry SAR data. Canadian Journal of Remote Sensing, 50(1), Article 2384883. https://doi.org/10.1080/07038992.2024.2384883

Flohr, P., Bradbury, J., & ten Harkel, L. (2021). Tracing the patterns: Fields, villages, and burial places in Lebanon. Levant, 53(3), 315–335. https://doi.org/10.1080/00758914.2021.1968114

Gonzalez, S. T., Velez-Zea, A., & Barrera-Ramírez, J. F. (2024). High performance holographic video compression using spatio-temporal phase unwrapping. Optics and Lasers in Engineering, 181, Article 108381. https://doi.org/10.1016/j.optlaseng.2024.108381

Hejmanowska, B., & Kramarczyk, P. (2025). Assessing land cover changes using the LUCAS database and sentinel imagery: A comparative analysis of accuracy metrics. Applied Sciences, 15(1), Article 240. https://doi.org/10.3390/app15010240

Ioannou, K. (2023). On the identification of agroforestry application areas using object-oriented programming. Agriculture, 13(1), Article 164. https://doi.org/10.3390/agriculture13010164

Jeromel, A., & Žalik, B. (2020). An efficient lossy cartoon image compression method. Multimedia Tools and Applications, 79(1–2), 433–451. https://doi.org/10.1007/s11042-019-08126-7

Juhász, L., Xu, J., & Parkinson, R. W. (2023). Beyond the tide: A comprehensive guide to sea-level-rise inundation mapping using FOSS4G. Geomatics, 3(4), 522–540. https://doi.org/10.3390/geomatics3040028

Kai, X., & Yuxiang, Z. (2024). Improving the performance of 3D image model compression based on optimized DEFLATE algorithm. Scientific Reports, 14(1), Article 14899. https://doi.org/10.1038/s41598-024-65539-7

Kamenova, I., Chanev, M., Dimitrov, P., Filchev, L., Bonchev, B., Zhu, L., & Dong, Q. (2024). Crop type mapping and winter wheat yield prediction utilizing Sentinel-2: A case study from Upper Thracian Lowland, Bulgaria. Remote Sensing, 16(7), Article 1144. https://doi.org/10.3390/rs16071144

Kluczek, M., Zagajewski, B., & Kycko, M. (2024). Combining multitemporal optical and radar satellite data for mapping the Tatra Mountains non-forest plant communities. Remote Sensing, 16(8), Article 1451. https://doi.org/10.3390/rs16081451

Kluczek, M., Zagajewski, B., & Zwijacz-Kozica, T. (2023). Mountain tree species mapping using Sentinel-2, PlanetScope, and Airborne HySpex hyperspectral imagery. Remote Sensing, 15(3), Article 844. https://doi.org/10.3390/rs15030844

Kycko, M., Zagajewski, B., Kluczek, M., Tardà, A., Pineda, L., Palà, V., & Corbera, J. (2022). Sentinel-2 and AISA airborne hyperspectral images for Mediterranean Shrubland Mapping in Catalonia. Remote Sensing, 14(21), Article 5531. https://doi.org/10.3390/rs14215531

Lee, J., Kim, K., & Lee, K. (2024). Multi-Sensor image classification using the random forest algorithm in Google Earth engine with KOMPSAT-3/5 and CAS500-1 images. Remote Sensing, 16(24), Article 4622. https://doi.org/10.3390/rs16244622

Lemenkova, P. (2022). GRASS GIS scripts for Satellite image analysis by raster calculations using modules r.mapcalc, d.rgb, r.slope.aspect. Tehnicki Vjesnik, 29(6), 1956–1963. https://doi.org/10.17559/TV-20220322091846

Liu, C., Huang, H., Hui, F., Zhang, Z., & Cheng, X. (2021). Fine-resolution mapping of pan-arctic lake ice-off phenology based on dense Sentinel-2 time series data. Remote Sensing, 13(14), Article 2742. https://doi.org/10.3390/rs13142742

Logan, T. L., Smyth, M. M., & Calef, F. J. (2024). Planetary orbital mapping and mosaicking (POMM) integrated open source software environment. Astronomy and Computing, 46, Article 100788. https://doi.org/10.1016/j.ascom.2024.100788

Marchetti, G., Bizzi, S., Belletti, B., Lastoria, B., Comiti, F., & Carbonneau, P. E. (2022). Mapping riverbed sediment size from Sentinel-2 satellite data. Earth Surface Processes and Landforms, 47(10), 2544–2559. https://doi.org/10.1002/esp.5394

Niazmardi, S., Homayouni, S., Safari, A., McNairn, H., Shang, J., & Beckett, K. (2018). Histogram-based spatio-temporal feature classification of vegetation indices time-series for crop mapping. International Journal of Applied Earth Observation and Geoinformation, 72, 34–41. https://doi.org/10.1016/j.jag.2018.05.014

Ole Ørka, H., Gailis, J., Vege, M., Gobakken, T., & Hauglund, K. (2013). Analysis-ready satellite data mosaics from Landsat and Sentinel-2 imagery. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 6(5), 2088–2101. https://doi.org/10.1109/JSTARS.2012.2228167

Patel, P. N., Jiang, J. H., Gautam, R., Gadhavi, H., Kalashnikova, O., Garay, M. J., Gao, L., Xu, F., & Omar, A. (2024). A remote sensing algorithm for vertically resolved cloud condensation nuclei number concentrations from airborne and spaceborne lidar observations. Atmospheric Chemistry and Physics, 24(5), 2861–2883. https://doi.org/10.5194/acp-24-2861-2024

Pokhariya, H. S., Singh, D. P., & Prakash, R. (2023). Evaluation of different machine learning algorithms for LULC classification in heterogeneous landscape by using remote sensing and GIS techniques. Engineering Research Express, 5(4), Article 045052. https://doi.org/10.1088/2631-8695/acfa64

Poussin, C., Peduzzi, P., & Giuliani, G. (2025). Snow observation from space: An approach to improving snow cover detection using four decades of Landsat and Sentinel-2 imageries across Switzerland. Science of Remote Sensing, 11, Article 100182. https://doi.org/10.1016/j.srs.2024.100182

Psychalas, C., Vlachos, K., Moumtzidou, A., Gialampoukidis, I., Vrochidis, S., & Kompatsiaris, I. (2023). Towards a paradigm shift on mapping muddy waters with Sentinel-2 using machine learning. Sustainability, 15(18), Article 13441. https://doi.org/10.3390/su151813441

Ren, C., Jiang, H., Xi, Y., Liu, P., & Li, H. (2023). Quantifying temperate forest diversity by integrating GEDI LiDAR and multi-temporal Sentinel-2 imagery. Remote Sensing, 15(2), Article 375. https://doi.org/10.3390/rs15020375

Rodríguez-Puerta, F., Perroy, R. L., Barrera, C., Price, J. P., & García-Pascual, B. (2024). Five-year evaluation of Sentinel-2 cloud-free mosaic generation under varied cloud cover conditions in Hawai’i. Remote Sensing, 16(24), Article 4791. https://doi.org/10.3390/rs16244791

Roy, D. P., Li, J., Zhang, H. K., & Yan, L. (2016). Best practices for the reprojection and resampling of Sentinel-2 multi spectral instrument level 1C data. Remote Sensing Letters, 7(11), 1023–1032. https://doi.org/10.1080/2150704X.2016.1212419

Rynkiewicz, A., Hościło, A., Aune-Lundberg, L., Nilsen, A. B., & Lewandowska, A. (2025). Detection and quantification of vegetation losses with Sentinel-2 images using bi-temporal analysis of spectral indices and transferable random forest model. Remote Sensing, 17(6), Article 979. https://doi.org/10.3390/rs17060979

Sankaran, R., Al-Khayat, J. A., J, A., Chatting, M. E., Sadooni, F. N., & Al-Kuwari, H. A. S. (2023). Retrieval of suspended sediment concentration (SSC) in the Arabian Gulf water of arid region by Sentinel-2 data. Science of the Total Environment, 904, Article 166875. https://doi.org/10.1016/j.scitotenv.2023.166875

Schürz, M., Grigoropoulou, A., García Márquez, J., Torres-Cambas, Y., Tomiczek, T., Floury, M., Bremerich, V., Schürz, C., Amatulli, G., Grossart, H. P., & Domisch, S. (2023). hydrographr: An R package for scalable hydrographic data processing. Methods in Ecology and Evolution, 14(12), 2953–2963. https://doi.org/10.1111/2041-210X.14226

Shao, M., & Zou, Y. (2021). Multi-spectral cloud detection based on a multi-dimensional and multi-grained dense cascade forest. Journal of Applied Remote Sensing, 15(02), Article 028507. https://doi.org/10.1117/1.jrs.15.028507

Shepherd, J. D., Schindler, J., & Dymond, J. R. (2020). Automated mosaicking of Sentinel-2 satellite imagery. Remote Sensing, 12(22), Article 3680.. https://doi.org/10.3390/rs12223680

Souza, F. E. S. de, & Rodrigues, J. I. de J. (2023). Evaluation of machine learning algorithms in the classification of multispectral images from the Sentinel-2A/2B orbital sensor for mapping the environmental dynamics of Ria Formosa (Algarve, Portugal). ISPRS International Journal of Geo-Information, 12(9), Article 361. https://doi.org/10.3390/ijgi12090361

Stachura, G., Ustrnul, Z., Sekuła, P., Bochenek, B., Kolonko, M., & Szczęch-Gajewska, M. (2024). Machine learning based post-processing of model-derived near-surface air temperature – A multimodel approach. Quarterly Journal of the Royal Meteorological Society, 150(759), 618–631. https://doi.org/10.1002/qj.4613

Terzi Türk, S., & Balçik, F. (2023). Rastgele orman algoritması ve Sentinel-2 MSI ile fındık ekili alanların belirlenmesi: Piraziz Örneği. Geomatik, 8(2), 91–98. https://doi.org/10.29128/geomatik.1127925

Trevisiol, F., Mandanici, E., Pagliarani, A., & Bitelli, G. (2024). Evaluation of Landsat-9 interoperability with Sentinel-2 and Landsat-8 over Europe and local comparison with field surveys. ISPRS Journal of Photogrammetry and Remote Sensing, 210, 55–68. https://doi.org/10.1016/j.isprsjprs.2024.02.021

Vazirani, H., Wu, X., Srivastava, A., Dhar, D., & Pathak, D. (2024). Highly efficient JR optimization technique for solving prediction problem of soil organic carbon on large scale. Sensors, 24(22), Article 7317. https://doi.org/10.3390/s24227317

Wang, Q., Wang, L., Zhu, X., Ge, Y., Tong, X., & Atkinson, P. M. (2022). Remote sensing image gap filling based on spatial-spectral random forests. Science of Remote Sensing, 5, Article 100048. https://doi.org/10.1016/j.srs.2022.100048

Wang, Y., Jin, S., & Dardanelli, G. (2024). Vegetation classification and evaluation of yancheng coastal wetlands based on random forest algorithm from Sentinel-2 Images. Remote Sensing, 16(7), Article 1124. https://doi.org/10.3390/rs16071124

Wang, Z. (2023). Spatial differentiation characteristics of rural areas based on machine learning and GIS statistical analysis – A case study of Yongtai County, Fuzhou City. Sustainability, 15(5), Article 4367. https://doi.org/10.3390/su15054367

Xue, H., Xu, X., Zhu, Q., Yang, G., Long, H., Li, H., Yang, X., Zhang, J., Yang, Y., Xu, S., Yang, M., & Li, Y. (2023). Object-oriented crop classification using time series sentinel images from Google Earth Engine. Remote Sensing, 15(5), Article 1353. https://doi.org/10.3390/rs15051353

Yu, H., Luo, Z., Wang, L., Ding, X., & Wang, S. (2023). Improving the accuracy of flood susceptibility prediction by combining machine learning models and the expanded flood inventory data. Remote Sensing, 15(14), Article 3601. https://doi.org/10.3390/rs15143601

Zhang, H., He, J., Chen, S., Zhan, Y., Bai, Y., & Qin, Y. (2023). Comparing three methods of selecting training samples in supervised classification of multispectral remote sensing images. Sensors, 23(20), Article 8530. https://doi.org/10.3390/s23208530

Zhou, J., Luo, X., Rong, W., & Xu, H. (2022). Cloud removal for optical remote sensing imagery using distortion coding network combined with compound loss functions. Remote Sensing, 14(14), Article 3452. https://doi.org/10.3390/rs14143452

View article in other formats

CrossMark check

CrossMark logo

Published

2025-05-26

Issue

Section

Articles

How to Cite

Jancevičius, J. (2025). Enhancing land use classification with hybrid machine learning and satellite imagery. New Trends in Computer Sciences, 3(1), 1–17. https://doi.org/10.3846/ntcs.2025.23701

Share