Land Cover (LC) classification is an effective technique that categorizes the Earth's surface into urban, forest, and agricultural land classes by utilizing remote sensing data. Nevertheless, the hyperspectral remote sensing images are afflicted with a lack of labeled data, spectral variability, and the curse of dimensionality, which limit their competence in remote sensing applications. Hence, this research presents a Spatial Split Attention-enabled Distributed Learning-based Encoder Generative Bidirectional Network (S2A-DL-EGBNet) model for accurate LC classification using hyperspectral images (HSIs). The model integrates a distributed learning module to process large datasets, and training is done in parallel by reducing complexity while improving scalability. Also, a Generative Adversarial Network (GAN)-based data balancing is employed to address the class imbalance problem and enables the model's effectiveness. Thereafter, the parallel Bidirectional Long Short-Term Memory (BiLSTM) is integrated to speed up the training process and minimize computation time. The research applies multiple feature extraction techniques, capturing complex features, scaling variations in photographic distortions, and illumination changes from the aspects of input data. Notably, the S2A-DL-EGBNet model is validated using the Hyperspectral Remote Sensing Scenes dataset, and the S2A-DL-EGBNet model shows remarkable performance by achieving 98.44% sensitivity, 98.84% accuracy, and 99.24% sensitivity on the Indian Pines dataset for training data of 90%.
Citation: Afnan M. Alhassan, Nouf I. Altmami. S2A-DL-EGBNet: Land Cover classification using an Attention-enabled Distributed Learning-based Encoder Generative Bidirectional Network[J]. AIMS Mathematics, 2026, 11(3): 7945-7979. doi: 10.3934/math.2026328
Land Cover (LC) classification is an effective technique that categorizes the Earth's surface into urban, forest, and agricultural land classes by utilizing remote sensing data. Nevertheless, the hyperspectral remote sensing images are afflicted with a lack of labeled data, spectral variability, and the curse of dimensionality, which limit their competence in remote sensing applications. Hence, this research presents a Spatial Split Attention-enabled Distributed Learning-based Encoder Generative Bidirectional Network (S2A-DL-EGBNet) model for accurate LC classification using hyperspectral images (HSIs). The model integrates a distributed learning module to process large datasets, and training is done in parallel by reducing complexity while improving scalability. Also, a Generative Adversarial Network (GAN)-based data balancing is employed to address the class imbalance problem and enables the model's effectiveness. Thereafter, the parallel Bidirectional Long Short-Term Memory (BiLSTM) is integrated to speed up the training process and minimize computation time. The research applies multiple feature extraction techniques, capturing complex features, scaling variations in photographic distortions, and illumination changes from the aspects of input data. Notably, the S2A-DL-EGBNet model is validated using the Hyperspectral Remote Sensing Scenes dataset, and the S2A-DL-EGBNet model shows remarkable performance by achieving 98.44% sensitivity, 98.84% accuracy, and 99.24% sensitivity on the Indian Pines dataset for training data of 90%.
| [1] |
Z. Zhang, D. Shu, C. Liao, C. Liu, Y. Zhao, R. Wang, et al., FlexiSAM: A flexible SAM-based semantic segmentation model for land cover classification using high-resolution multimodal remote sensing imagery, ISPRS J. Photogramm. Remote Sens. , 227 (2025), 594-612.https://doi.org/10.1016/j.isprsjprs.2025.05.028 doi: 10.1016/j.isprsjprs.2025.05.028
|
| [2] |
A. Vali, S. Comai, M. Matteucci, Deep learning for land use and land cover classification based on hyperspectral and multispectral earth observation data: a review, Remote Sens. , 12 (2020), 2495.https://doi.org/10.3390/rs12152495 doi: 10.3390/rs12152495
|
| [3] |
M. Aljebreen, H. A. Mengash, M. Alamgeer, S. S. Alotaibi, A. S. Salama, M. A. Hamza, Land use and land cover classification using river formation dynamics algorithm with deep learning on remote sensing images, IEEE Access, 12 (2024), 11147-11156.https://doi.org/10.1109/ACCESS.2023.3349285 doi: 10.1109/ACCESS.2023.3349285
|
| [4] |
R. P. Sishodia, R. L. Ray, S. K. Singh, Applications of remote sensing in precision agriculture: a review, Remote Sens. , 12 (2020), 3136.https://doi.org/10.3390/rs12193136 doi: 10.3390/rs12193136
|
| [5] |
C. K. K. Reddy, A. Daduvy, R. M. Mohana, B. Assiri, M. Shuaib, S. Alam, et al., Enhancing precision agriculture and land cover classification: a self-attention 3D convolutional neural network approach for hyperspectral image analysis, IEEE Access, 12 (2024), 125592-125608.https://doi.org/10.1109/access.2024.3420089 doi: 10.1109/access.2024.3420089
|
| [6] |
M. Weiss, F. Jacob, G. Duveiller, Remote sensing for agricultural applications: a meta-review, Remote Sens. Environ. , 236 (2020), 111402.https://doi.org/10.1016/j.rse.2019.111402 doi: 10.1016/j.rse.2019.111402
|
| [7] |
A. Nițu, C. Florea, M. Ivanovici, A. Racoviteanu, NDVI and Beyond: vegetation indices as features for crop recognition and segmentation in hyperspectral data, Sensors (Basel), 25 (2025), 3817.https://doi.org/10.3390/s25123817 doi: 10.3390/s25123817
|
| [8] |
A. D. Campbell, T. Fatoyinbo, S. P. Charles, L. L. Bourgeau-Chavez, J. Goes, H. Gomes, et al., A review of carbon monitoring in wet carbon systems using remote sensing, Environ. Res. Lett. , 17 (2022), 025009.https://doi.org/10.1088/1748-9326/ac4d4d doi: 10.1088/1748-9326/ac4d4d
|
| [9] |
G. A. Sánchez-Azofeifa, K. L. Castro-Esau, W. A. Kurz, A. Joyce, Monitoring carbon stocks in the tropics and the remote sensing operational limitations: from local to regional projects, Ecol. Appl. , 19 (2009), 480-494.https://doi.org/10.1890/08-1149.1 doi: 10.1890/08-1149.1
|
| [10] |
X. Li, X. Fan, Q. Li, X. Zhao, Rs-net: Hyperspectral image land cover classification based on spectral imager combined with random forest algorithm, Electronics, 13 (2024), 4046.https://doi.org/10.3390/electronics13204046 doi: 10.3390/electronics13204046
|
| [11] |
X. Li, X. Fan, J. Fan, Q. Li, Y. Gao, X. Zhao, DASR-Net: Land cover classification methods for hybrid multiattention multispectral high spectral resolution remote sensing imagery, Forests, 15 (2024), 1826.https://doi.org/10.3390/f15101826 doi: 10.3390/f15101826
|
| [12] |
H. Yang, Z. Jiang, Y. Zhang, Y. Wu, H. Luo, P. Zhang, et al., A high-resolution remote sensing land use/land cover classification method based on multi-level features adaptation of segment anything model, Int. J. Appl. Earth Obs. Geoinf. , 141 (2025), 104659.https://doi.org/10.1016/j.jag.2025.104659 doi: 10.1016/j.jag.2025.104659
|
| [13] |
G. Wang, J. Chen, L. Mo, P. Wu, X. Yi, Border-enhanced triple attention mechanism for high-resolution remote sensing images and application to land cover classification, Remote Sens. , 16 (2024), 2814.https://doi.org/10.3390/rs16152814 doi: 10.3390/rs16152814
|
| [14] |
M. Fayaz, J. Nam, L. M. Dang, H. K. Song, H. Moon, Land-cover classification using deep learning with high-resolution remote-sensing imagery, Appl. Sci. , 14 (2024), 1844.https://doi.org/10.3390/app14051844 doi: 10.3390/app14051844
|
| [15] |
B. Chen, L. Liu, Z. Zou, Z. Shi, Target detection in hyperspectral remote sensing image: current status and challenges, Remote Sens. , 15 (2023), 3223.https://doi.org/10.3390/rs15133223 doi: 10.3390/rs15133223
|
| [16] |
R. Vidican, A. Mălinaș, O. Ranta, C. Moldovan, O. Marian, A. Ghețe, et al., Using remote sensing vegetation indices for the discrimination and monitoring of agricultural crops: a critical review, Agronomy, 13 (2023), 3040.https://doi.org/10.3390/agronomy13123040 doi: 10.3390/agronomy13123040
|
| [17] |
A. S. Alademomi, C. J. Okolie, O. E. Daramola, S. A. Akinnusi, E. Adediran, H. O. Olanrewaju, et al., The interrelationship between LST, NDVI, NDBI, and land cover change in a section of Lagos metropolis, Nigeria, Appl. Geomatics, 14 (2022), 299-314.https://doi.org/10.1007/s12518-022-00434-2 doi: 10.1007/s12518-022-00434-2
|
| [18] | A. Hussain, M. Imad, A. Khan, B. Ullah, Multi-class classification for the identification of COVID-19 in X-ray images using customized efficient neural network, In: AI and IoT for sustainable development in emerging countries, Springer, Cham, 2022,473-486.https://doi.org/10.1007/978-3-030-90618-4_23 |
| [19] |
S. Li, W. Song, L. Fang, Y. Chen, P. Ghamisi, J. A. Benediktsson, Deep learning for hyperspectral image classification: an overview, IEEE Trans. Geosci. Remote Sens. , 57 (2019), 6690-6709.https://doi.org/10.1109/TGRS.2019.2907932 doi: 10.1109/TGRS.2019.2907932
|
| [20] |
G. S. Chadha, A. Panambilly, A. Schwung, S. X. Ding, Bidirectional deep recurrent neural networks for process fault classification, ISA Trans. , 106 (2020), 330-342.https://doi.org/10.1016/j.isatra.2020.07.011 doi: 10.1016/j.isatra.2020.07.011
|
| [21] | M. Graña, M. A. Veganzons, B. Ayerdi, Hyperspectral remote sensing scenes dataset, 2025. Available from: https://www.ehu.eus/ccwintco/index.php/Hyperspectral_Remote_Sensing_Scenes. |
| [22] | V. Vani, V. R. Mandla, Comparative study of NDVI and SAVI vegetation indices in Anantapur district semi-arid areas, Int. J. Civ. Eng. Technol. , 8 (2017), 559-566. |
| [23] |
I. H. El-Shal, O. M. Fahmy, M. A. Elattar, License plate image analysis empowered by generative adversarial neural networks (GANs), IEEE Access, 10 (2022), 30846-30857.https://doi.org/10.1109/access.2022.3157714 doi: 10.1109/access.2022.3157714
|
| [24] | Z. Hameed, B. Garcia-Zapirain, Sentiment classification using a single-layered BiLSTM model, IEEE Access, 8 (2020), 73992-74001.https://doi.org/10.1109/access.2020.2988550 |
| [25] |
H. A. Al-Najjar, B. Pradhan, R. Sarkar, G. Beydoun, A. Alamri, A new integrated approach for landslide data balancing and spatial prediction based on generative adversarial networks (GAN), Remote Sens. , 13 (2021), 4011.https://doi.org/10.3390/rs13194011 doi: 10.3390/rs13194011
|
| [26] |
Y. Tan, X. Ding, Split-attention CNN and self-attention with RoPE and GCN for voice activity detection, IEEE Access, 12 (2024), 156673-156682.https://doi.org/10.1109/access.2024.3486003 doi: 10.1109/access.2024.3486003
|
| [27] |
H. Zhang, C. Wu, Z. Zhang, Y. Zhu, H. Lin, Z. Zhang, et al., Resnest: Split-attention networks, 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2022, 2735-2745.https://doi.org/10.1109/cvprw56347.2022.00309 doi: 10.1109/cvprw56347.2022.00309
|
| [28] | S. Woo, J. Park, J. Y. Lee, I. S. Kweon, Cbam: Convolutional block attention module, Computer Vision - ECCV, Springer, Cham, 2018, 3-19. https://doi.org/10.1007/978-3-030-01234-2_1 |
Figures(16) / Tables(7)
Afnan M. Alhassan, Nouf I. Altmami. S2A-DL-EGBNet: Land Cover classification using an Attention-enabled Distributed Learning-based Encoder Generative Bidirectional Network[J]. AIMS Mathematics, 2026, 11(3): 7945-7979. doi: 10.3934/math.2026328
DownLoad: