SavedAdd your journal

Journals / Türkiye Uzaktan Algılama Dergisi / 2026 / Volume: 8

Benchmarking machine learning and deep learning for multi-temporal land cover mapping: Evidence from a fragmented agro-ecosystem using Sentinel-2 time series

Melih Altay(HACETTEPE ÜNİVERSİTESİ, MÜHENDİSLİK FAKÜLTESİ, GEOMATİK MÜHENDİSLİĞİ BÖLÜMÜ, GEOMATİK MÜHENDİSLİĞİ PR. (İNGİLİZCE))0009-0005-0902-3713
Fatih Fehmi Şimşek(TÜBİTAK UZAY)0000-0003-4016-4408
Pages
—
Publication Date
2026-07-03
🏛️Bibliographic metadata and full text access for this article are provided via DergiPark.
DergiPark Record ↗
✨

AI Summary & Key Takeaways

AI Insight
⚡ TL;DR(Too Long; Didn't Read)

Support Vector Machines (SVM), Random Forest (RF), a baseline Convolutional Neural Network (CNN), and U-Net were benchmarked under identical conditions using Overall Accuracy (OA), class-wise F1-score, Cohen's Kappa coefficient, and mean Intersection over Union (mIoU).

📌 3 Key Takeaways

🎯
Objective & Hypothesis:Accurate land cover classification in fragmented agricultural landscapes remains a persistent challenge, demanding robust algorithms capable of exploiting both spectral and temporal complexity.
📊
Key Findings & Data:This study presents a rigorous, controlled comparison of traditional machine learning and deep learning frameworks for multi-temporal land cover classification using Sentinel-2 imagery over the Bafra Plain, northern Türkiye, a highly heterogeneous agro-ecosystem with sub-hectare parcels and pronounced phenological variability.
💡
Conclusion & Impact:Support Vector Machines (SVM), Random Forest (RF), a baseline Convolutional Neural Network (CNN), and U-Net were benchmarked under identical conditions using Overall Accuracy (OA), class-wise F1-score, Cohen's Kappa coefficient, and mean Intersection over Union (mIoU).
🔬Design:Modeling & Simulation
📍Scope:Comprehensive Sample
⚙️Variables:Land cover classification · Sentinel-2 time series · Deep learning

Abstract

Accurate land cover classification in fragmented agricultural landscapes remains a persistent challenge, demanding robust algorithms capable of exploiting both spectral and temporal complexity. This study presents a rigorous, controlled comparison of traditional machine learning and deep learning frameworks for multi-temporal land cover classification using Sentinel-2 imagery over the Bafra Plain, northern Türkiye, a highly heterogeneous agro-ecosystem with sub-hectare parcels and pronounced phenological variability. A temporally enriched dataset of 78 spectral-temporal variables, derived from ten Sentinel-2 bands and three vegetation indices (NDVI, NDWI, NDRE) across six acquisition dates, was constructed to capture intra-annual phenological dynamics. To ensure spatial independence and eliminate data leakage, a parcel-based stratified sampling scheme produced strictly non-overlapping training and testing partitions of approximately 2.94 million pixels each. Support Vector Machines (SVM), Random Forest (RF), a baseline Convolutional Neural Network (CNN), and U-Net were benchmarked under identical conditions using Overall Accuracy (OA), class-wise F1-score, Cohen's Kappa coefficient, and mean Intersection over Union (mIoU). U-Net achieved superior performance across all metrics (OA: 96.87%; Kappa: 0.957; mIoU: 89.42%), surpassing SVM by up to 5.09 percentage points and exceeding the widely adopted 85% mIoU excellence threshold, which only the CNN (86.84%) and U-Net reached, whereas SVM (81.15%) and RF (84.62%) fell below. Gains were most pronounced for spectrally ambiguous minority classes, including Artificial Surfaces (+15.25 pp F1-score vs. SVM), Tree Crops (+13.15 pp), and Grassland (+16.21 pp), underscoring the critical role of spatial context modeling. A systematic multi-temporal ablation study confirmed that temporal integration is indispensable, yielding accuracy improvements of 4.79–7.66 percentage points across all model families relative to single-date baselines. Although deep learning entails greater training overhead, its near real-time inference and robustness to severe class imbalance render it operationally viable for large-scale monitoring, providing evidence-based guidance on the accuracy–efficiency trade-off for algorithm selection in precision agriculture and environmental monitoring.

🔖

Cite This Article

Altay, M., Şimşek, F. F. (2026). Benchmarking machine learning and deep learning for multi-temporal land cover mapping: Evidence from a fragmented agro-ecosystem using Sentinel-2 time series. Türkiye Uzaktan Algılama Dergisi, Volume: 8. https://doi.org/10.51489/tuzal.1917361

📄 Full Text PDF Viewer

📄

PDF görüntüleyici hazırlanıyor...

References (43)

  1. Belgiu, M., & Drăguț, L. (2016). Random forest in remote sensing: A review of applications and future directions. ISPRS Journal of Photogrammetry and Remote Sensing, 114, 24–31. https://doi.org/10.1016/j.isprsjprs.2016.01.011
  2. Breiman, L. (2001). Random forests. Machine Learning, 45(1), 5–32. https://doi.org/10.1023/A:1010933404324
  3. Bossard, M., Feranec, J., & Otahel, J. (2000). CORINE land cover technical guide: Addendum 2000 (Technical Report No. 40). European Environment Agency. https://www.eea.europa.eu/publications/tech40add Campbell, J. B., & Wynne, R. H. (2011). Introduction to remote sensing (5th ed.). Guilford Press.
  4. Cohen, J. (1960). A coefficient of agreement for nominal scales. Educational and Psychological Measurement, 20(1), 37–46. https://doi.org/10.1177/001316446002000104
  5. Congalton, R. G., & Green, K. (2019). Assessing the accuracy of remotely sensed data: Principles and practices (3rd ed.). CRC Press. https://doi.org/10.1201/9780429052729
  6. Dietterich, T. G. (1998). Approximate statistical tests for comparing supervised classification learning algorithms. Neural Computation, 10(7), 1895–1923. https://doi.org/10.1162/089976698300017197
  7. Danacıoğlu, Ş. (2023). Arazi örtüsü haritalamasında farklı makine öğrenmesi algoritmalarının değerlendirilmesi: İzmir ili örneği [Evaluation of different machine learning algorithms for land cover mapping: A case study of İzmir province]. Türk Coğrafya Dergisi (84), 105–117. https://doi.org/10.17211/tcd.1296893
  8. Di Gregorio, A., & Jansen, L. J. M. (2000). Land cover classification system (LCCS): Classification concepts and user manual. Food and Agriculture Organization of the United Nations (FAO).
  9. Drusch, M., Del Bello, U., Carlier, S., Colin, O., Fernandez, V., Gascon, F., Hoersch, B., Isola, C., Laberinti, P., Martimort, P., Meygret, A., Spoto, F., Sy, O., Marchese, F., & Bargellini, P. (2012). Sentinel-2: ESA's optical high-resolution mission for GMES operational services. Remote Sensing of Environment, 120, 25–36. https://doi.org/10.1016/j.rse.2011.11.026
  10. Foody, G. M. (2002). Status of land cover classification accuracy assessment. Remote Sensing of Environment, 80(1), 185–201. https://doi.org/10.1016/S0034-4257(01)00295-4
  11. Foody, G. M., & Mathur, A. (2004). A relative evaluation of multiclass image classification by support vector machines. IEEE Transactions on Geoscience and Remote Sensing, 42(6), 1335–1343. https://doi.org/10.1109/TGRS.2004.827257
  12. Gitelson, A. A. (2004). Wide dynamic range vegetation index for remote quantification of biophysical characteristics of vegetation. Journal of Plant Physiology, 161(2), 165–173. https://doi.org/10.1078/0176-1617-01176
  13. Griffiths, P., Nendel, C., & Hostert, P. (2019). Intra-annual reflectance composites from Sentinel-2 and Landsat for national-scale crop and land cover mapping. Remote Sensing of Environment, 220, 135–151. https://doi.org/10.1016/j.rse.2018.10.031
  14. Gündüz, H. İ. (2025). Land-use land-cover dynamics and future projections using GEE, ML, and QGIS-MOLUSCE: A case study in Manisa. Sustainability, 17(4), 1363. https://doi.org/10.3390/su17041363
  15. Hansen, M. C., & Reed, B. (2000). A comparison of the IGBP DISCover and University of Maryland 1 km global land cover products. International Journal of Remote Sensing, 21(6–7), 1365–1373. https://doi.org/10.1080/014311600210218
  16. Immitzer, M., Vuolo, F., & Atzberger, C. (2016). First experience with Sentinel-2 data for crop and tree species classifications in central Europe. Remote Sensing, 8(3), Article 166. https://doi.org/10.3390/rs8030166
  17. Inglada, J., Vincent, A., Arias, M., Tardy, B., Morin, D., & Rodes, I. (2017). Operational high resolution land cover map production at the country scale using satellite image time series. Remote Sensing, 9(1), Article 95. https://doi.org/10.3390/rs9010095
  18. Johnson, J. M., & Khoshgoftaar, T. M. (2019). Survey on deep learning with class imbalance. Journal of Big Data, 6(1), Article 27. https://doi.org/10.1186/s40537-019-0192-5
  19. Kattenborn, T., Leitloff, J., Schiefer, F., & Hinz, S. (2021). Review on convolutional neural networks (CNN) in vegetation remote sensing. ISPRS Journal of Photogrammetry and Remote Sensing, 173, 24–49. https://doi.org/10.1016/j.isprsjprs.2020.12.010
  20. Kingma, D. P., & Ba, J. (2015). Adam: A method for stochastic optimization. In Proceedings of the 3rd International Conference on Learning Representations (ICLR 2015). https://arxiv.org/abs/1412.6980
  21. Kussul, N., Lavreniuk, M., Skakun, S., & Shelestov, A. (2017). Deep learning classification of land cover and crop types using remote sensing data. IEEE Geoscience and Remote Sensing Letters, 14(5), 778–782. https://doi.org/10.1109/LGRS.2017.2681128
  22. LeCun, Y., Bengio, Y., & Hinton, G. (2015). Deep learning. Nature, 521(7553), 436–444. https://doi.org/10.1038/nature14539
  23. Long, J., Shelhamer, E., & Darrell, T. (2015). Fully convolutional networks for semantic segmentation. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (pp. 3431–3440). https://doi.org/10.1109/CVPR.2015.7298965
  24. Louis, J., Debaecker, V., Pflug, B., Main-Knorn, M., Bieniarz, J., Mueller-Wilm, U., Cadau, E., & Gascon, F. (2016). Sentinel-2 SEN2COR: L2A processor for users. In Proceedings of the Living Planet Symposium (ESA SP-740). ESA. Maggiori, E., Tarabalka, Y., Charpiat, G., & Alliez, P. (2017). Convolutional neural networks for large-scale remote-sensing image classification. IEEE Transactions on Geoscience and Remote Sensing, 55(2), 645–657. https://doi.org/10.1109/TGRS.2016.2612821
  25. Maxwell, A. E., Warner, T. A., & Fang, F. (2018). Implementation of machine-learning classification in remote sensing: An applied review. International Journal of Remote Sensing, 39(9), 2784–2817. https://doi.org/10.1080/01431161.2018.1433343
  26. 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. https://doi.org/10.1080/01431169608948714
  27. Mountrakis, G., Im, J., & Ogole, C. (2011). Support vector machines in remote sensing: A review. ISPRS Journal of Photogrammetry and Remote Sensing, 66(3), 247–259. https://doi.org/10.1016/j.isprsjprs.2010.11.001
  28. Pal, M., & Mather, P. M. (2005). Support vector machines for classification in remote sensing. International Journal of Remote Sensing, 26(5), 1007–1011. https://doi.org/10.1080/01431160512331314083
  29. Pelletier, C., Webb, G. I., & Petitjean, F. (2019). Temporal convolutional neural network for the classification of satellite image time series. Remote Sensing, 11(5), Article 523. https://doi.org/10.3390/rs11050523 Richards, J. A. (2022). Remote sensing digital image analysis: An introduction (6th ed.). Springer. https://doi.org/10.1007/978-3-030-82327-6
  30. Roberts, D. R., Bahn, V., Ciuti, S., Boyce, M. S., Elith, J., Guillera-Arroita, G., Hauenstein, S., Lahoz-Monfort, J. J., Schröder, B., Thuiller, W., Warton, D. I., Wintle, B. A., Hartig, F., & Dormann, C. F. (2017). Cross-validation strategies for data with temporal, spatial, hierarchical, or phylogenetic structure. Ecography, 40(8), 913–929. https://doi.org/10.1111/ecog.02881
  31. Ronneberger, O., Fischer, P., & Brox, T. (2015). U-Net: Convolutional networks for biomedical image segmentation. In MICCAI 2015 (pp. 234–241). Springer. https://doi.org/10.1007/978-3-319-24574-4_28
  32. Rußwurm, M., Pelletier, C., Zollner, M., Lefèvre, S., & Körner, M. (2020). BreizhCrops: A time series dataset for crop type mapping. The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, XLIII-B2-2020, 1545–1551. https://doi.org/10.5194/isprs-archives-XLIII-B2-2020-1545-2020
  33. Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., & Salakhutdinov, R. (2014). Dropout: A simple way to prevent neural networks from overfitting. Journal of Machine Learning Research, 15(1), 1929–1958. http://jmlr.org/papers/v15/srivastava14a.html
  34. Şimşek, F. F. (2023). Arazi Parsel Tanımlama Sistemi verileri kullanılarak ülkesel ölçekte arazi örtüsü ve arazi kullanım sınıflandırması. Türk Uzaktan Algılama ve CBS Dergisi, 4(2), 276–288. https://doi.org/10.48123/rsgis.1268155
  35. Şimşek, F. F., Üstüner, M., & Kalkan, K. (2026). Unlocking land cover classification potential: a comparative analysis of Pixxel TD-1 hyperspectral and Landsat-9 multispectral imagery. International Journal of Remote Sensing, 47(8), 3310–3327. https://doi.org/10.1080/01431161.2026.2631694
  36. Tucker, C. J. (1979). Red and photographic infrared linear combinations for monitoring vegetation. Remote Sensing of Environment, 8(2), 127–150. https://doi.org/10.1016/0034-4257(79)90013-0
  37. Turner, B. L., Janetos, A. C., Verburg, P. H., & Murray, A. T. (2013). Land system architecture. Global Environmental Change, 23(2), 395–397. https://doi.org/10.1016/j.gloenvcha.2012.12.009
  38. Turkish State Meteorological Service. (2024). Official meteorological records and long-term climate statistics of Samsun station (1991–2020). Ministry of Agriculture and Forestry. Retrieved April 15, 2024, from https://www.mgm.gov.tr/veridegerlendirme/il-ve-ilceler-istatistik.aspx?m=SAMSUN
  39. Ustuner, M., & Şimşek, F. F. (2025). An assessment of training data for agricultural land cover classification: A case study of Bafra, Türkiye. Earth Science Informatics, 18(1), 1–16. https://doi.org/10.1007/s12145-024-01555-5
  40. Vuolo, F., Neuwirth, M., Immitzer, M., Atzberger, C., & Ng, W. T. (2018). How much does multi-temporal Sentinel-2 data improve agricultural land cover classification? International Journal of Applied Earth Observation and Geoinformation, 72, 122–130. https://doi.org/10.1016/j.jag.2018.06.007
  41. Wulder, M. A., Coops, N. C., Roy, D. P., White, J. C., & Hermosilla, T. (2018). Land cover 2.0. International Journal of Remote Sensing, 39(12), 4254–4284. https://doi.org/10.1080/01431161.2018.1452075
  42. Xu, Y., Du, B., & Zhang, L. (2021). Self-attention context network for hyperspectral image classification. IEEE Transactions on Image Processing, 30, 8671–8685. https://doi.org/10.1109/TIP.2021.3118977
  43. Zhu, X. X., Tuia, D., Mou, L., Xia, G. S., Zhang, L., Xu, F., & Fraundorfer, F. (2017). Deep learning in remote sensing. IEEE Geoscience and Remote Sensing Magazine, 5(4), 8–36. https://doi.org/10.1109/MGRS.2017.2762307