การเปรียบเทียบประสิทธิภาพสถาปัตยกรรม CNN ร่วมกับเทคนิคการเสริมข้อมูลสำหรับการจำแนกประเภทการใช้ประโยชน์ที่ดินจากภาพถ่ายดาวเทียม Sentinel-2

Anusorn Chirakitphattharakun; Sangdaow Noppitak

doi:10.14456/jcct.2025.8

Authors

Anusorn Chirakitphattharakun Student, Program in Information Technology, Faculty of Science, Buriram Rajabhat University, Buriram 32000, Thailand
Sangdaow Noppitak Lecturer, Dr., Program in Information Technology, Faculty of Science, Buriram Rajabhat University, Buriram 32000, Thailand

DOI:

https://doi.org/10.14456/jcct.2025.8

Keywords:

Land Use Classification, Deep Learning, Satellite Image, Data Augmentation

Abstract

Land use classification constitutes a critical component of effective natural resource management and urban planning, providing essential insights into land-use changes and their environmental impacts. This research study aims to construct and evaluate the performance of three Convolutional Neural Network (CNNs) architectures-ResNet50V2, DenseNet121, and EfficientNetV2B0-applied to Sentinel-2 satellite imagery. To address challenges related to data imbalance and overfitting, data augmentation techniques were employed to enhance model robustness. The study area, Tambon Sai Ta Ku, was classified into five distinct land use categories. Among the evaluated models, ResNet50V2 demonstrated superior performance, achieving an accuracy of 88% with data augmentation, followed by DenseNet121 with 77%, while EfficientNetV2B0 exhibited comparatively lower performance at 47%. These findings indicate that ResNet50V2, when combined with data augmentation, is the most effective model for land use classification tasks, underscoring its potential to improve precision in resource management and environmental planning.

Downloads

References

Alzahem, A., Boulila, W., Koubaa, A., Khan, Z., & Alturki, I. (2023). Improving Satellite Image Classification Accuracy Using GAN-based Data Augmentation and Vision Transformers. Earth Science Informatics, 16(4), 4169–4186. https://doi.org/10.1007/s12145-023-01153-x.

Belgiu, M., & Csillik, O. (2018). Sentinel-2 Cropland Mapping Using Pixel-based and Object-based Time-weighted Dynamic Time Warping Analysis. Remote Sensing of Environment, 204, 509–523. https://doi.org/10.1016/j.rse.2017.10.005.

Dobrinić, D., Medak, D., & Gašparović, M. (2020). Integration of Multitemporal Sentinel-1 and Sentinel-2 Imagery for Land-cover Classification Using Machine Learning Methods. The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, XLIII-B1-2020, 91–98. https://doi.org/10.5194/isprs-archives-XLIII-B1-2020-91-2020.

Gerdan Koc, D., Koc, C., Polat, H. E., & Koc, A. (2024). Artificial Intelligence-based Camel Face Identification System for Sustainable Livestock Farming. Neural Computing and Applications, 36(6), 3107–3124. https://doi.org/10.1007/s00521-023-09238-w.

Gibson, R., Danaher, T., Hehir, W., & Collins, L. (2020). A Remote Sensing Approach to Mapping Fire Severity in South-eastern Australia Using Sentinel 2 and Random Forest. Remote Sensing of Environment, 240, 111702. https://doi.org/10.1016/j.rse.2020.111702.

Hao, M., Dong, X., Jiang, D., Yu, X., Ding, F., & Zhuo, J. (2024). Land-use classification based on high-resolution remote sensing imagery and deep learning models. PLOS ONE, 19(4), e0300473. https://doi.org/10.1371/journal.pone.0300473.

Khan, M., Hanan, A., Kenzhebay, M., Gazzea, M., & Arghandeh, R. (2024). Transformer-based Land Use and Land Cover Classification with Explainability Using Satellite Imagery. Scientific Reports, 14(1), 16744. https://doi.org/10.1038/s41598-024-67186-4.

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.

Liang, J., Deng, Y., & Zeng, D. (2020). A Deep Neural Network Combined CNN and GCN for Remote Sensing Scene Classification. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 13, 4325–4338. https://doi.org/10.1109/JSTARS.2020.3011333.

Llodrà-Llabrés, J., Martínez-López, J., Postma, T., Pérez-Martínez, C., & Alcaraz-Segura, D. (2023). Retrieving water chlorophyll-a concentration in inland waters from Sentinel-2 imagery: Review of operability, performance and ways forward. International Journal of Applied Earth Observation and Geoinformation, 125, 103605. https://doi.org/10.1016/j.jag.2023.103605

Lu, L., Wang, L., Yang, Q., Zhao, P., Du, Y., Xiao, F., & Ling, F. (2023). Extracting a Connected River Network from DEM by Incorporating Surface River Occurrence Data and Sentinel-2 Imagery in the Danjiangkou Reservoir Area. Remote Sensing, 15(4), 1014. https://doi.org/10.3390/rs15041014.

Mahakalanda, I., Demotte, P., Perera, I., Meedeniya, D., Wijesuriya, W., & Rodrigo, L. (2022). Deep Learning-based Prediction for Stand Age and Land Utilization of Rubber Plantation. In Khan, M. A., Khan, R., & Ansari, M. A. (Eds), Application of Machine Learning in Agriculture (131–156). Elsevier. https://doi.org/10.1016/B978-0-323-90550-3.00008-4.

Murel, J., & Kavlakoglu, E. (2024). What is Data Augmentation?. IBM. https://www.ibm.com/topics/data-augmentation.

Paramanantham, P. M., & Seenivasan, S. R. (2025). Optimized Deep Learning based Classification and Prediction of Land Use/ Land Cover Changes from Satellite Images. Signal, Image and Video Processing, 19(5), 415. https://doi.org/10.1007/s11760-025-03937-8.

Phiri, D., Simwanda, M., Salekin, S., Nyirenda, V., Murayama, Y., & Ranagalage, M. (2020). Sentinel-2 Data for Land Cover/Use Mapping: A Review. Remote Sensing, 12(14), 2291. https://doi.org/10.3390/rs12142291.

QGIS. (2024). Spatial without Compromise. https://www.qgis.org.

Rozario, P. F., Gadgil, R., Lee, J., Gomes, R., Keller, P., Liu, Y., Sipos, G., McDonnell, G., Impola, W., & Rudolph, J. (2024). Optimizing Mobile Vision Transformers for Land Cover Classification. Applied Sciences, 14(13), 5920. https://doi.org/10.3390/app14135920.

Seydi, S. T., Amani, M., & Ghorbanian, A. (2022). A Dual Attention Convolutional Neural Network for Crop Classification Using Time-Series Sentinel-2 Imagery. Remote Sensing, 14(3), 498. https://doi.org/10.3390/rs14030498.

Shorten, C., & Khoshgoftaar, T. M. (2019). A survey on Image Data Augmentation for Deep Learning. Journal of Big Data, 6(1), 60. https://doi.org/10.1186/s40537-019-0197-0.

Sierra, S., Ramo, R., Padilla, M., & Cobo, A. (2025). Optimizing Deep Neural Networks for High-resolution Land Cover Classification through Data Augmentation. Environmental Monitoring and Assessment, 197(4), 423. https://doi.org/10.1007/s10661-025-13870-5.

Singh, G., Singh, S., Sethi, G., & Sood, V. (2022). Deep Learning in the Mapping of Agricultural Land Use Using Sentinel-2 Satellite Data. Geographies, 2(4), 691–700. https://doi.org/10.3390/geographies2040042.

Sudta, P. (2023). Marketers and AI: Confusion Matrix and Principles for Evaluating ML Models. Everyday Marketing. https://everydaymarketing.co/business-and-marketing-case-study/ai/confusion-matrix-ml-evaluation. (In Thai)

Vali, A., Comai, S., & Matteucci, M. (2020). Deep Learning for Land Use and Land Cover Classification Based on Hyperspectral and Multispectral Earth Observation Data: A Review. Remote Sensing, 12(15), 2495. https://doi.org/10.3390/rs12152495.

Wang, Y., Zhang, Z., Feng, L., Ma, Y., & Du, Q. (2021). A New Attention-based CNN Approach for Crop Mapping Using Time Series Sentinel-2 Images. Computers and Electronics in Agriculture, 184, 106090. https://doi.org/10.1016/j.compag.2021.106090.

Wubineh, B. Z., Rusiecki, A., & Halawa, K. (2024). Classification of Cervical Cells from the Pap Smear Image Using the RES_DCGAN Data Augmentation and ResNet50V2 with Self-attention Architecture. Neural Computing and Applications, 36(34), 21801–21815. https://doi.org/10.1007/s00521-024-10404-x.

Zhang, T., Su, J., Xu, Z., Luo, Y., & Li, J. (2021). Sentinel-2 Satellite Imagery for Urban Land Cover Classification by Optimized Random Forest Classifier. Applied Sciences, 11(2), 543. https://doi.org/10.3390/app11020543.

Zhu, X. X., Tuia, D., Mou, L., Xia, G.-S., Zhang, L., Xu, F., & Fraundorfer, F. (2017). Deep Learning in Remote Sensing: A Comprehensive Review and List of Resources. IEEE Geoscience and Remote Sensing Magazine, 5(4), 8–36. https://doi.org/10.1109/MGRS.2017.2762307.