FreqEdgeViT: A Scalable and Efficient Reliability-Aware Transformer for Large-Scale Agricultural Information Systems
DOI:
https://doi.org/10.4108/eetsis.11866Keywords:
Vision transformer, Satellite image time series, Crop type semantic segmentation, Scalable Data ProcessingAbstract
With the exponential growth of data in modern agriculture, satellite image time series (SITS) has become an important data source for scalable information systems that analyze global crop distribution. However, processing these massive, high-dimensional data streams poses significant challenges; existing semantic segmentation models suffer from prohibitive computational overhead and lack scalability. Furthermore, they are vulnerable to high-frequency non-phenological perturbations and mixed-pixel boundary ambiguity, which degrades reliability in agricultural Internet of Things (IoT) applications. In this work, we propose FreqEdgeViT, an efficient, reliability-aware, and boundary-guided Vision Transformer. Designed for scalable SITS processing, FreqEdgeViT integrates a factorized spatiotemporal architecture with two novel mechanisms. First, in the temporal domain, we introduce a Phenology-Aware Frequency Filter (PAFF) combined with Reliability-Aware Token Merging (Ra-ToMe). This combination utilizes spectral analysis to filter environmental noise and dynamically prunes temporal redundancy based on signal reliability, significantly reducing data throughput requirements. Second, in the spatial domain, we propose a Boundary-Guided Spatial Encoder (BGSE) that enforces explicit geometric constraints to resolve edge blurring in mixed pixels. Experimental results on two public SITS datasets demonstrate that FreqEdgeViT achieves state-of-the-art accuracy with significantly reduced computational costs. The proposed architecture offers a scalable solution for processing large-scale agricultural data, providing precise support for crop policy formulation and enhancing the value of agricultural information systems.
References
[1] Rustemi, A. and Dalipi, F. (2025) Synergizing iot, ai, and blockchain for smart agriculture: Challenges, opportunities, and future directions. Internet of Things : 101778.
[2] Zhang, S., Han, Q., Wang, H., Liu, J. and Li, B. (2025) Federated learning with dual dynamic quantization optimization in smart agriculture. Internet of Things : 101798.
[3] Zhang, Q., Ahmed, K., Sharda, N. and Wang, H. (2023) Australian animal species selection and image data collection. In 2023 27th International Conference Information Visualisation (IV) (IEEE): 55–63. doi:10.1109/IV60694.2023.00018.
[4] Sanchez, J., Rodriguez, J. and Espitia, H. (2020) Review of artificial intelligence applied in decision-making processes in agricultural public policy. Processes 8(11): 1374.
[5] Chandraprabha, M. and Dhanraj, R. (2023) Ensemble deep learning algorithm for forecasting of rice crop yield based on soil nutrition levels. EAI Endorsed Transactions on Scalable Information Systems 10(4).
[6] Hao, X., Li, X., Wang, H., Zheng, Z., Jiang, Y. and Zhang, Y. (2025) Itcohd-mrec: An independent topological preference-aware and cooperative hypergraph diffusion-based multimodal recommender model. ACM Trans. Inf. Syst. 44(1). doi:10.1145/3767337.
[7] Pham, T.T.L., Taherdoost, H. and Le, T.V. (2024) Scalable information systems for agribusiness: Developing farmers’ digital capabilities for e-commerce platform adoption. EAI Endorsed Transactions on Scalable Information Systems 12(1).
[8] Xie, W., Zhu, A., Ali, T., Zhang, Z., Chen, X., Wu, F., Huang, J. et al. (2023) Crop switching can enhance environmental sustainability and farmer incomes in China. Nature 616(7956): 300–305.
[9] Saleem, H., Ahmad, S., Shafeeque, U.B. and Khan, N.A. (2025) Fuzzy topsis method for sustainable supplier assortment in green supply chain management. EAI Endorsed Transactions on Scalable Information Systems 12(3).
[10] Ge, Y.F., Wang, H., Bertino, E., Cao, J., Zhang, Y. and Zheng, Z. (2025) Distributed bandit-based cooperative coevolution for large-scale multi-objective data publishing. IEEE Transactions on Services Computing doi:10.1109/TSC.2024.3517403. Early Access.
[11] You, M., Ge, Y.F., Yin, J., Wang, K., Zheng, Z., Zhang, Y. and Wang, H. (2025) Akief: Adaptive knowledge inheritance evolutionary framework for dynamic privacy-preserving data publishing. ACM Trans. Web doi:10.1145/3779413.
[12] Ge, Y.F., Wang, H., Bertino, E., Zhan, Z.H., Cao, J., Zhang, Y. and Zhang, J. (2024) Evolutionary dynamic database partitioning optimization for privacy and utility. IEEE Transactions on Dependable and Secure Computing 21(4): 2296–2311. doi:10.1109/TDSC.2023.3302284.
[13] Hoque, M., Islam, M. and Ahmed, I.e.a. (2024) Enhancing precision agriculture efficiency through edge computing-enabled wireless sensor networks: A data aggregation perspective. Engineering Proceedings 82(1): 90.
[14] Chen, G., Wang, M., Han, S., Yin, J., Wang, H. and Cao, J. (2025) Deep reinforcement learning based cloud-edge offloading for wbans. IEEE Transactions on Consumer Electronics 71(2): 4053–4064. doi:10.1109/TCE.2024.3504545.
[15] Ge, Y.F., Wang, H., Bertino, E., Cao, J. and Zhang, Y. (2025) Multiobjective privacy-preserving task assignment in spatial crowdsourcing. IEEE Transactions on Cybernetics 55(8): 3584–3597. doi:10.1109/TCYB.2025.3573292.
[16] Alexopoulos, A., Koutras, K. and Ali, S.e.a. (2023) Complementary use of ground-based proximal sensing and airborne/spaceborne remote sensing techniques in precision agriculture: A systematic review. Agronomy 13(7): 1942.
[17] Chen, X.e.a. (2025) Mask-guided frequency feature fusion for visible–infrared remote sensing object detection. IEEE Trans. Geosci. Remote Sens. 63: 1–15.
[18] Ghosh, H., Rahat, I. and Shaik, K.e.a. (2023) Potato leaf disease recognition and prediction using convolutional neural networks. EAI Endorsed Transactions on Scalable Information Systems 10(6).
[19] Huang, C.Q., Huang, Q.H., Huang, X., Wang, H., Li, M., Lin, K.J. and Chang, Y. (2024) Xkt: Toward explainable knowledge tracing model with cognitive learning theories for questions of multiple knowledge concepts. IEEE Transactions on Knowledge and Data Engineering 36(11): 7308–7325. doi:10.1109/TKDE.2024.3418098.
[20] Chatterjee, S., Satpathy, S. and Nibedita, A. (2023) Digital investigation of network traffic using machine learning. EAI Endorsed Transactions on Scalable Information Systems 11(1).
[21] Gayathri, B. (2024) Opin-itp: Optimized physics informed network with trimmed score regression based insider threats prediction in cloud computing. EAI Endorsed Transactions on Scalable Information Systems 12(1).
[22] Shi, F., Meng, Y., Zhao, Z., Yin, J., Cao, J. and Wang, H. (2026) Liteghost-yolo: scale-aware lightweight traffic sign recognition in complex environments. Journal of Real-Time Image Processing 23(1): 19. doi:10.1007/s11554-025-01584-6.
[23] Huang, E., Zhao, Z., Yin, J., Cao, J. and Wang, H. (2025) Transformer-enhanced adaptive graph convolutional network for traffic flow prediction. ACM Transactions on Intelligent Systems and Technology doi:10.1145/3702144, URL https://doi.org/10.1145/3702144. Just Accepted.
[24] Alvi, A.M., Khan, M.J., Manami, N.T., Miazi, Z.A., Wang, K., Siuly, S. and Wang, H. (2024) Xcr-net: A computer aided framework to detect covid-19. IEEE Transactions on Consumer Electronics 70(4): 7551–7561. doi:10.1109/TCE.2024.3446793.
[25] Tawhid, M.N.A., Siuly, S., Wang, K. and Wang, H. (2024) Genet: A generic neural network for detecting various neurological disorders from eeg. IEEE Transactions on Cognitive and Developmental Systems 16(5): 1829–1842. doi:10.1109/TCDS.2024.3386364.
[26] Vardhan, K.B., Nidhish, M., Kiran C., S., Dudekula, N.S., Varanasi, S.C. and Bhavadharini, R. (2024) Eye disease detection using deep learning models with transfer learning techniques. EAI Endorsed Transactions on Scalable Information Systems 12(1).
[27] Singh, R., Subramani, S., Du, J., Zhang, Y., Wang, H., Miao, Y. and Ahmed, K. (2023) Antisocial behavior identification from twitter feeds using traditional machine learning algorithms and deep learning. EAI Endorsed Transactions on Scalable Information Systems 10(4).
[28] Rustowicz, R., Cheong, R., Wang, L., Ermon, S., Burke, M. and Lobell, D. (2019) Semantic segmentation of crop type in Africa: A novel dataset and analysis of deep learning methods. In Proc. IEEE/CVF Conf. Computer Vision and Pattern Recognition Workshops: 75–82.
[29] Garnot, V. and Landrieu, L. (2021) Panoptic segmentation of satellite image time series with convolutional temporal attention networks. In Proc. IEEE/CVF Int. Conf. Computer Vision (ICCV): 4872–4881.
[30] Tarasiou, M., Chavez, E. and Zafeiriou, S. (2023) Vits for sits: Vision transformers for satellite image time series. In Proc. IEEE/CVF Conf. Computer Vision and Pattern Recognition (CVPR): 10418–10428.
[31] Chen, L., Liu, W., Wang, H., Jeon, S.W., Jiang, Y. and Zheng, Z. (2025) Consistency-guided adaptive alternating training for semi-supervised salient object detection. IEEE Trans. Circuits Syst. Video Technol. 35(7): 7033–7046.
[32] Li, R., Zhang, D., Wang, Y., Jiang, Y., Zheng, Z., Jeon, S.W. and Wang, H. (2025) Open-vocabulary multi object tracking with domain generalized and temporally adaptive features. IEEE Transactions on Multimedia 27: 3009–3022. doi:10.1109/TMM.2025.3557619.
[33] Bolya, D., Fu, C. and Dai, X.e.a. (2022), Token merging: Your vit but faster, arXiv preprint arXiv:2210.09461.
[34] Park, N. and Kim, S. (2022) How do vision transformers work? In Proc. Int. Conf. Learning Representations (ICLR).
[35] Cheng, B., Girshick, R., Dollar, P., Berg, A. and Kirillov, A. (2021) Boundary iou: Improving object-centric image segmentation evaluation. In Proc. IEEE/CVF Conf. Computer Vision and Pattern Recognition (CVPR): 15334– 15342.
[36] Rao, Y., Zhao, W., Zhu, Z., Lu, J. and Zhou, J. (2021) Global filter networks for image classification. In Proc. Adv. Neural Inf. Process. Syst. (NeurIPS): 980–993.
[37] Garnot, V., Landrieu, L., Giordano, S. and Chehata, N. (2019) Time-space trade-off in deep learning models for crop classification on satellite multi-spectral image time series. In Proc. IEEE Int. Geosci. Remote Sens. Symp. (IGARSS): 6247–6250.
[38] Tarasiou, M. and Zafeiriou, S. (2022), Embedding earth: Self-supervised contrastive pre-training for dense land cover classification, arXiv preprint arXiv:2203.06041.
[39] Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X. and Unterthiner, T.e.a. (2021) An image is worth 16×16 words: Transformers for image recognition at scale. In Proc. Int. Conf. Learning Representations (ICLR).
[40] Kaselimi, M., Voulodimos, A., Daskalopoulos, I., Doulamis, N. and Doulamis, A. (2022) A vision transformer model for convolution-free multilabel classification of satellite imagery in deforestation monitoring. IEEE Trans. Neural Netw. Learn. Syst. 34(7): 3299–3307.
[41] Nguyen, T., Brandstetter, J., Kapoor, A., Gupta, J. and Grover, A. (2023), Climax: A foundation model for weather and climate, arXiv preprint arXiv:2301.10343.
[42] Knapen, R., de Wit, A., Buyukkaya, E., Petrou, P., Paudel, D., Janssen, S. and Athanasiadis, I. (2025) Efficient and scalable crop growth simulations using standard big data and distributed computing technologies. Computers and Electronics in Agriculture 236: 110392. doi:10.1016/j.compag.2025.110392.
[43] Sarkar, S., Ganapathysubramanian, B., Singh, A. et al. (2024) Cyber-agricultural systems for crop breeding and sustainable production. Trends in Plant Science 29(2): 130–149.
[44] Lopez-Morales, J.A., Martinez, J.A. and Skarmeta, A.F. (2020) Digital transformation of agriculture through the use of an interoperable platform. Sensors 20(4): 1153. doi:10.3390/s20041153.
[45] Choromanski, K., Likhosherstov, V., Dohan, D., Song, X., Gane, A. and Sarlos, T.e.a. (2020), Rethinking attention with performers, arXiv preprint arXiv:2009.14794 [cs.LG].
[46] Bolya, D., Fu, C., Dai, X., Zhang, P. and Hoffman, J. (2022), Hydra attention: Efficient attention with many heads, arXiv preprint arXiv:2209.07484
[cs.CV].
[47] Meng, L., Li, H., Chen, B., Lan, S., Wu, Z., Jiang, Y. and Lim, S. (2022) Adavit: Adaptive vision transformers for efficient image recognition. In Proc. IEEE/CVF Conf. Computer Vision and Pattern Recognition (CVPR).
[48] Liu, Z., Hu, H., Lin, Y., Yao, Z., Xie, Z. and Wei, Y.e.a. (2022) Swin transformer v2: Scaling up capacity and resolution. In Proc. IEEE/CVF Conf. Computer Vision and Pattern Recognition (CVPR).
[49] Dong, X., Bao, J., Chen, D., Zhang, W., Yu, N. and Yuan, L.e.a. (2022) Cswin transformer: A general vision transformer backbone with cross-shaped windows. In Proc. IEEE/CVF Conf. Computer Vision and Pattern Recognition (CVPR).
[50] Diakogiannis, F.I., Waldner, F., Caccetta, P. and Wu, C. (2020) Resunet-a: A deep learning framework for semantic segmentation of remotely sensed data. ISPRS Journal of Photogrammetry and Remote Sensing 162: 94– 114. doi:10.1016/j.isprsjprs.2020.01.013.
[51] Liu, H., Jiang, X. and Li, X.e.a. (2022) Nommer: Nominate synergistic context in vision transformer for visual recognition. In Proc. IEEE/CVF Conf. Computer Vision and Pattern Recognition (CVPR): 12073–12082.
[52] He, K., Zhang, X., Ren, S. and Sun, J. (2016) Deep residual learning for image recognition. In Proc. IEEE Conf. Computer Vision and Pattern Recognition (CVPR): 770–778.
[53] Liu, Z., Lin, Y., Cao, Y., Hu, H. and Wei, Y.e.a. (2021) Swin transformer: Hierarchical vision transformer using shifted windows. In Proc. IEEE/CVF Int. Conf. Computer Vision (ICCV): 10012–10022.
[54] Tarasiou, M., Guler, R. and Zafeiriou, S. (2022) Context-self contrastive pre-training for crop type semantic segmentation. IEEE Trans. Geosci. Remote Sens. 60: 1–11.
[55] Loshchilov, I. and Hutter, F. (2019) Decoupled weight decay regularization. In Proc. Int. Conf. Learning Representations (ICLR).
[56] Loshchilov, I. and Hutter, F. (2017) Sgdr: Stochastic gradient descent with warm restarts. In Proc. Int. Conf. Learning Representations (ICLR).
[57] Ruswurm, M. and Korner, M. (2018) Multi-temporal land cover classification with sequential recurrent encoders. ISPRS International Journal of Geo-Information 7(4): 129.
[58] Chamorro Martinez, J., Cue La Rosa, L., Queiroz Feitosa, R., Del’Arco Sanches, I. and Happ, P. (2021) Fully convolutional recurrent networks for multidate crop recognition from multitemporal image sequences. ISPRS Journal of Photogrammetry and Remote Sensing 171: 188–201.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Li Qu, Le Sun, Yimin Yu, Hemant Ghayvat
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
This is an open access article distributed under the terms of the CC BY-NC-SA 4.0, which permits copying, redistributing, remixing, transformation, and building upon the material in any medium so long as the original work is properly cited.
