Lightweight Transformer Model for Agricultural Land Use and Land Cover Classification

Year 2025, Volume: 31 Issue: 4, 941 - 959, 30.09.2025

Kemal Çelik

https://doi.org/10.15832/ankutbd.1624812

Abstract

Observing agricultural land use via remote sensing images is essential for ensuring food security, estimating yields and planning efficient exports nonetheless precise classification continues to be difficult because of the varied and evolving characteristics of agricultural environments. This research aims to evaluate and optimize advanced deep learning architectures particularly Vision Transformer (ViT) models for agricultural land-use classification tasks. Specifically, we employed ViTBase-16 and other lightweight models DeiT-Tiny and EfficientNet-B0 applying techniques such as model layer compression and advanced data augmentation CutMix and Cutout to achieve high accuracy while significantly reducing computational complexity. Evaluation was performed using three benchmark remote sensing datasets EuroSAT, NWPU-RESISC45 and SIRI-WHU which include diverse spatial resolutions and agricultural classes relevant for practical monitoring.
Findings indicate that the optimized ViT algorithm is highly effective in recognizing global spatial connections, consistently achieving remarkable classification accuracy exceeding 99% on a newly assembled dataset containing around 200 samples of Google Earth imagery. Furthermore, the first time in agricultural image classification compressing the ViTBase model by pruning 50% of its layers significantly reduced complexity maintainingcompetitive accuracy 97.9% on SIRI-WHU. The resulting models are particularly suitable for deployment on devices with limited computational resources supporting real-world operational agricultural monitoring systems. This study emphasizes the revolutionary possibilities and practical use of optimized transformer-based models that offer scalable and efficient solutions specifically designed for precision agriculture applications.

Keywords

Agriculture , Data augmentation , Deep learning , Vision transformers , Land use

References

• Ahmad M, Shabbir S, Roy S K, Hong D, Wu X, Yao J & Chanussot J (2022). Hyperspectral Image Classification - Traditional to Deep Models: A Survey for Future Prospects. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing 15: 968–999. doi: 10.1109/JSTARS.2021.3133021
• Albarakati H M, Khan M A, Hamza A, Khan F, Kraiem N, Jamel L & Alroobaea R (2024). A Novel Deep Learning Architecture for Agriculture Land Cover and Land Use Classification from Remote Sensing Images Based on Network-Level Fusion of Self-Attention Architecture. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 17, 6338–6353. doi: 10.1109/JSTARS.2024.3369950
• Albert A, Kaur J & Gonzalez M C (2017). Using convolutional networks and satellite imagery to identify patterns in urban environments at a large scale. Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Part F129685, 1357 1366. Association for Computing Machinery. doi: 10.1145/3097983.3098070
• Alzahrani M S & Alsaade F W (2023). Transform and Deep Learning Algorithms for the Early Detection and Recognition of Tomato Leaf Disease. Agronomy 13(5). doi: 10.3390/agronomy13051184
• Attri I, Awasthi L K, Sharma T P & Rathee P (2023). A review of deep learning techniques used in agriculture. Ecological Informatics, Vol. 77. Elsevier B.V. doi: 10.1016/j.ecoinf.2023.102217
• Basu S, Ganguly S, Mukhopadhyay S, DiBiano R, Karki M & Nemani R (2015). DeepSat - A learning framework for satellite imagery. GIS: Proceedings of the ACM International Symposium on Advances in Geographic Information Systems, 03-06-November-2015. Association for Computing Machinery. doi: 10.1145/2820783.2820816
• Bazi Y, Bashmal L, Al Rahhal M M, Dayil R Al & Ajlan N Al (2021). Vision transformers for remote sensing image classification. Remote Sensing, 13(3): 1–20. doi: 10.3390/rs13030516
• Beyer L, Zhai X & Kolesnikov A (2022). Better plain ViT baselines for ImageNet-1k. Retrieved from http://arxiv.org/abs/2205.01580
• Bowles C, Chen L, Guerrero R, Bentley P, Gunn R, Hammers A & Rueckert D (2018). GAN Augmentation: Augmenting Training Data using Generative Adversarial Networks. Retrieved from http://arxiv.org/abs/1810.10863
• Celik F, Balik Sanli F & Bozic D (2024). Transformer Networks to Classify Weeds and Crops in High-Resolution Aerial Images From North East Serbia. Turkish Journal of Field Crops 29(2): 112–120. doi: 10.17557/tjfc.1511404
• Chen W, Du X, Yang F, Beyer L, Zhai X, Lin T.-Y.& Zhou D (2021). A Simple Single-Scale Vision Transformer for Object Localization and Instance Segmentation. Retrieved from http://arxiv.org/abs/2112.09747
• Cheng G, Han J & Lu X (2017, October 1). Remote Sensing Image Scene Classification: Benchmark and State of the Art. Proceedings of the IEEE, Vol. 105, pp. 1865–1883. Institute of Electrical and Electronics Engineers Inc. doi: 10.1109/JPROC.2017.2675998
• Cubuk E D, Zoph B, Mane D, Vasudevan V & Le Q V (2019). Autoaugment: Learning augmentation strategies from data. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2019-June, 113–123. IEEE Computer Society. doi: 10.1109/CVPR.2019.00020
• DeVries T & Taylor G W (2017). Improved Regularization of Convolutional Neural Networks with Cutout. Retrieved from http://arxiv.org/abs/1708.04552
• Dosovitskiy A, Beyer L, Kolesnikov A, Weissenborn D, Zhai X, Unterthiner T & Houlsby N (2020). An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. Retrieved from http://arxiv.org/abs/2010.11929
• Gandhar A, Gupta K, Pandey A K & Raj D (2024, June 1). Fraud Detection Using Machine Learning and Deep Learning. SN Computer Science, Vol. 5. Springer. doi: 10.1007/s42979-024-02772-x
• Gong B, Dai K, Shao J, Jing L & Chen Y (2023). Fish-TViT: A novel fish species classification method in multi water areas based on transfer learning and vision transformer. Heliyon 9(6). doi: 10.1016/j.heliyon.2023.e16761
• Guo N, Jiang M, Gao L, Li K, Zheng F, Chen X & Wang M (2023). HFCC-Net: A Dual-Branch Hybrid Framework of CNN and CapsNet for Land-Use Scene Classification. Remote Sensing, 15(20). doi: 10.3390/rs15205044
• Hamza A, Khan M A, Ur Rehman S, Albarakati H M, Alroobaea R, Baqasah A M & Masood A (2023). An Integrated Parallel Inner Deep Learning Models Information Fusion with Bayesian Optimization for Land Scene Classification in Satellite Images. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 16, 9888–9903. doi: 10.1109/JSTARS.2023.3324494
• Hamza A, Khan M A, Ur Rehman S, Al-Khalidi M, Alzahrani A I, Alalwan N & Masood A (2024). A Novel Bottleneck Residual and SelfAttention Fusion-Assisted Architecture for Land Use Recognition in Remote Sensing Images. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 17: 2995–3009. doi: 10.1109/JSTARS.2023.3348874
• Han K, Wang Y, Chen H, Chen X, Guo J, Liu Z & Tao D (2020). A Survey on Visual Transformer. doi: 10.1109/TPAMI.2022.3152247
• He K, Zhang X, Ren S & Sun J (2016a). Deep residual learning for image recognition. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2016-December, 770–778. IEEE Computer Society. doi: 10.1109/CVPR.2016.90
• He K, Zhang X, Ren S & Sun J (2016b). Deep residual learning for image recognition. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2016-December, 770–778. IEEE Computer Society. doi: 10.1109/CVPR.2016.90
• Helber P, Bischke B, Dengel A & Borth D (2019). Eurosat: A novel dataset and deep learning benchmark for land use and land cover classification. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 12(7): 2217–2226. doi: 10.1109/JSTARS.2019.2918242
• Hinton G, Vinyals O & Dean J (2015). Distilling the Knowledge in a Neural Network. Retrieved from http://arxiv.org/abs/1503.02531
• Huete A, Didan K, Miura T, Rodriguez E P, Gao X & Ferreira L G (2002). Overview of the radiometric and biophysical performance of the MODIS vegetation indices. Retrieved from www.elsevier.com/locate/rse
• Jackson P T, Atapour-Abarghouei A, Bonner S, Breckon T & Obara B (2018). Style Augmentation: Data Augmentation via Style Randomization. Retrieved from http://arxiv.org/abs/1809.05375
• Joshi A, Pradhan B, Gite S & Chakraborty S (2023, April 1). Remote-Sensing Data and Deep-Learning Techniques in Crop Mapping and Yield Prediction: A Systematic Review. Remote Sensing, Vol. 15. MDPI. doi: 10.3390/rs15082014
• Khan S D & Basalamah S (2023). Multi-Branch Deep Learning Framework for Land Scene Classification in Satellite Imagery. Remote Sensing, 15(13). doi: 10.3390/rs15133408
• Khan S, Naseer M, Hayat M, Zamir S W, Khan F S & Shah M (2021). Transformers in Vision: A Survey. doi: 10.1145/3505244
• Li X & Li S (2022). Transformer Help CNN See Better: A Lightweight Hybrid Apple Disease Identification Model Based on Transformers. Agriculture (Switzerland), 12(6). doi: 10.3390/agriculture12060884
• Martins V S, Kaleita A L, Gelder B K, da Silveira H L F & Abe C A (2020). Exploring multiscale object-based convolutional neural network (multi-OCNN) for remote sensing image classification at high spatial resolution. ISPRS Journal of Photogrammetry and Remote Sensing, 168: 56–73. doi: 10.1016/j.isprsjprs.2020.08.004
• Maurício J, Domingues I & Bernardino J (2023, May 1). Comparing Vision Transformers and Convolutional Neural Networks for Image Classification: A Literature Review. Applied Sciences (Switzerland), Vol. 13. MDPI. doi: 10.3390/app13095521
• Miotto R, Wang F, Wang S, Jiang X & Dudley J T (2017). Deep learning for healthcare: Review, opportunities and challenges. Briefings in Bioinformatics, 19(6): 1236–1246. doi: 10.1093/bib/bbx044
• Nguyen T T, Hoang T D, Pham M T, Vu T T, Nguyen T H, Huynh Q T & Jo J (2020). Monitoring agriculture areas with satellite images and deep learning. Applied Soft Computing Journal, 95. doi: 10.1016/j.asoc.2020.106565
• Nie J, Yuan Y, Li Y, Wang H, Li J, Wang Y & Ercisli S (2024). Few-shot Learning in Intelligent Agriculture: A Review of Methods and Applications. Tarim Bilimleri Dergisi 30(2): 216–228. doi: 10.15832/ankutbd.1339516
• Papageorgiou E I, Markinos A T & Gemtos T A (2011). Fuzzy cognitive map based approach for predicting yield in cotton crop production as a basis for decision support system in precision agriculture application. Applied Soft Computing Journal, 11(4): 3643–3657. doi: 10.1016/j.asoc.2011.01.036
• Park S, Im J, Park S, Yoo C, Han H & Rhee J (2018). Classification and mapping of paddy rice by combining Landsat and SAR time series data. Remote Sensing, 10(3). doi: 10.3390/rs10030447
• Ranftl R, Bochkovskiy A & Koltun V (2021). Vision Transformers for Dense Prediction. Retrieved from https://github.com/intel-isl/DPT.
• Reedha R, Dericquebourg E, Canals R & Hafiane A (2022). Transformer Neural Network for Weed and Crop Classification of High Resolution UAV Images. Remote Sensing, 14(3). doi: 10.3390/rs14030592
• Sandler M, Howard A, Zhu M, Zhmoginov A & Chen L C (2018). MobileNetV2: Inverted Residuals and Linear Bottlenecks. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 4510–4520. IEEE Computer Society. doi: 10.1109/CVPR.2018.00474
• Shastry K A, Sanjay H A & Deexith G (2017). Quadratic-radial-basis-function-kernel for classifying multi-class agricultural datasets with continuous attributes. Applied Soft Computing Journal, 58: 65–74. doi: 10.1016/j.asoc.2017.04.049
• Shin H, Jeon S, Seol Y, Kim S & Kang D (2023). Vision Transformer Approach for Classification of Alzheimer’s Disease Using 18F Florbetaben Brain Images. Applied Sciences (Switzerland), 13(6). doi: 10.3390/app13063453
• 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. doi: 10.3390/geographies2040042
• Slavkovikj V, Verstockt S, De Neve W, Van Hoecke S & Van De Walle R (2015). Hyperspectral image classification with convolutional neural networks. MM 2015 - Proceedings of the 2015 ACM Multimedia Conference, 1159–1162. Association for Computing Machinery, Inc. doi: 10.1145/2733373.2806306
• Suh H K, IJsselmuiden J, Hofstee J W & van Henten E J (2018). Transfer learning for the classification of sugar beet and volunteer potato under field conditions. Biosystems Engineering, 174: 50–65. doi: 10.1016/j.biosystemseng.2018.06.017
• Suravarapu V K & Patil H Y (2023). Person Identification and Gender Classification Based on Vision Transformers for Periocular Images. Applied Sciences (Switzerland), 13(5). doi: 10.3390/app13053116
• Szegedy C, Vanhoucke V, Ioffe S, Shlens J & Wojna Z (2016). Rethinking the Inception Architecture for Computer Vision. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2016-December, 2818–2826. IEEE Computer Society. doi: 10.1109/CVPR.2016.308
• Tan M & Le Q V (2019). EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks. Retrieved from http://arxiv.org/abs/1905.11946
• Tang X, Zhang X, Liu F & Jiao L (2018). Unsupervised deep feature learning for remote sensing image retrieval. Remote Sensing, 10(8). doi: 10.3390/rs10081243
• Temenos A, Temenos N, Kaselimi M, Doulamis A & Doulamis N (2023). Interpretable Deep Learning Framework for Land Use and Land Cover Classification in Remote Sensing Using SHAP. IEEE Geoscience and Remote Sensing Letters, 20. doi: 10.1109/LGRS.2023.3251652
• Thakur P S, Chaturvedi S, Khanna P, Sheorey T & Ojha A (2023). Vision transformer meets convolutional neural network for plant disease classification. Ecological Informatics, 77. doi: 10.1016/j.ecoinf.2023.102245
• Thirumaladevi S, Veera Swamy K & Sailaja M (2023a). Remote sensing image scene classification by transfer learning to augment the accuracy. Measurement: Sensors, 25. doi: 10.1016/j.measen.2022.100645
• Thirumaladevi S, Veera Swamy K & Sailaja M (2023b). Remote sensing image scene classification by transfer learning to augment the accuracy. Measurement: Sensors, 25. doi: 10.1016/j.measen.2022.100645
• Vaswani A, Brain G, Shazeer N, Parmar N, Uszkoreit J, Jones L & Polosukhin I (2017). Attention Is All You Need. Vohra R & Tiwari K C (2023). Land cover classification using multi-fusion based dense transpose convolution in fully convolutional network with feature alignment for remote sensing images. Earth Science Informatics, 16(1): 983–1003. doi: 10.1007/s12145-022-00891-8
• Xia Z, Pan X, Song S, Erran Li, L & Huang G (2022). Vision Transformer with Deformable Attention. Retrieved from https://github.com/LeapLabTHU/DAT.
• Yun S, Han D, Oh S J, Chun S, Choe J & Yoo Y (2019). CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features. Retrieved from http://arxiv.org/abs/1905.04899
• Zahra U, Khan M A, Alhaisoni M, Alasiry A, Marzougui M & Masood A (2024). An Integrated Framework of Two-Stream Deep Learning Models Optimal Information Fusion for Fruits Disease Recognition. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 17: 3038–3052. doi: 10.1109/JSTARS.2023.3339297
• Zhai X, Kolesnikov A, Houlsby N & Beyer L (2021). Scaling Vision Transformers. Retrieved from http://arxiv.org/abs/2106.04560
• Zhang H, Cisse M, Dauphin Y N & Lopez-Paz D (2017). mixup: Beyond Empirical Risk Minimization. Retrieved from http://arxiv.org/abs/1710.09412
• Zhang M, Lin H, Wang G, Sun H & Fu J (2018). Mapping paddy rice using a Convolutional Neural Network (CNN) with Landsat 8 datasets in the Dongting Lake Area, China. Remote Sensing, 10(11). doi: 10.3390/rs10111840
• Zhang X, Zhou X, Lin M & Sun J (2018). ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 6848–6856. IEEE Computer Society. doi: 10.1109/CVPR.2018.00716
• Zhao B, Zhong Y, Xia G S & Zhang L (2016). Dirichlet-derived multiple topic scene classification model for high spatial resolution remote sensing imagery. IEEE Transactions on Geoscience and Remote Sensing, 54(4), 2108–2123. doi: 10.1109/TGRS.2015.2496185
• Zhao S, Tu K, Ye S, Tang H, Hu Y & Xie C (2023, November 3). Land Use and Land Cover Classification Meets Deep Learning: A Review. Sensors (Basel, Switzerland), Vol. 23. doi: 10.3390/s23218966
• Zuo S, Xiao Y, Chang X & Wang X (2022). Vision transformers for dense prediction: A survey. Knowledge-Based Systems, 253. doi: 10.1016/j.knosys.2022.109552