Robust Hyperspectral Crop Classification Using Stable Band-Pair Learning Across Field Conditions
Keywords:
Hyperspectral imaging, classification, band selection, field holdout, spatial and spectral, logistic regression, interpretability.Abstract
Adjacent training and test pixels can have almost the same spectra and be split into different subsets in a random fashion, resulting in optimistic estimates of reliability for hyperspectral crop classification. This paper introduces a two-band extension of the Indian Pines logistic baseline called field-stable band-pair learning (FS-BPL). FS-BPL clusters the same units (crop fields), normalizes the between-field distance for all bands by the distance within fields, and identifies pairs of bands with low redundancy via nested complete-field validation. FS-BPL had a mean balanced accuracy of 68.4% across 12 holdout pasture-tree fields, 10.2 percentage points better than the mean baseline fixed two-band accuracy. This result also has to be understood in the context of the 88.6% superpixel-based selector accuracy reported for uniformly distributed pixel sampling across 16 target classes by an evaluated 2025 superpixel-based selector. The proposed solution yields an easily disclosed classifier with minimal sensors and a field-level estimate of generalization.
References
[1] M. F. Baumgardner, L. L. Biehl, and D. A. Landgrebe, “220 band AVIRIS hyperspectral image data set: June 12, 1992 Indian Pine Test Site 3,” Purdue University Research Repository, 2015. doi: 10.4231/R7RX991C.
[2] N. Audebert, B. Le Saux, and S. Lefèvre, “Deep learning for classification of hyperspectral data: A comparative review,” IEEE Geosci. Remote Sens. Mag., vol. 7, no. 2, pp. 159–173, Jun. 2019. doi: 10.1109/MGRS.2019.2912563.
[3] M. E. Paoletti, J. M. Haut, J. Plaza, and A. Plaza, “Deep learning classifiers for hyperspectral imaging: A review,” ISPRS J. Photogramm. Remote Sens., vol. 158, pp. 279–317, Dec. 2019. doi: 10.1016/j.isprsjprs.2019.09.006.
[4] Y. Chen, H. Jiang, C. Li, X. Jia, and P. Ghamisi, “Deep feature extraction and classification of hyperspectral images based on convolutional neural networks,” IEEE Trans. Geosci. Remote Sens., vol. 54, no. 10, pp. 6232–6251, Oct. 2016. doi: 10.1109/TGRS.2016.2584107.
[5] W. Li, G. Wu, F. Zhang, and Q. Du, “Hyperspectral image classification using deep pixel-pair features,” IEEE Trans. Geosci. Remote Sens., vol. 55, no. 2, pp. 844–853, Feb. 2017. doi: 10.1109/TGRS.2016.2616355.
[6] A. Santara, K. Mani, P. Hatwar, A. Singh, A. Garg, K. Padia, and P. Mitra, “BASS Net: Band-adaptive spectral-spatial feature learning neural network for hyperspectral image classification,” IEEE Trans. Geosci. Remote Sens., vol. 55, no. 9, pp. 5293–5301, Sep. 2017. doi: 10.1109/TGRS.2017.2705073.
[7] Z. Zhong, J. Li, Z. Luo, and M. Chapman, “Spectral–spatial residual network for hyperspectral image classification: A 3-D deep learning framework,” IEEE Trans. Geosci. Remote Sens., vol. 56, no. 2, pp. 847–858, Feb. 2018. doi: 10.1109/TGRS.2017.2755542.
[8] A. Ben Hamida, A. Benoit, P. Lambert, and C. Ben Amar, “3-D deep learning approach for remote sensing image classification,” IEEE Trans. Geosci. Remote Sens., vol. 56, no. 8, pp. 4420–4434, Aug. 2018. doi: 10.1109/TGRS.2018.2818945.
[9] S. K. Roy, G. Krishna, S. R. Dubey, and B. B. Chaudhuri, “HybridSN: Exploring 3-D–2-D CNN feature hierarchy for hyperspectral image classification,” IEEE Geosci. Remote Sens. Lett., vol. 17, no. 2, pp. 277–281, Feb. 2020. doi: 10.1109/LGRS.2019.2918719.
[10] J. He, L. Zhao, H. Yang, M. Zhang, and W. Li, “HSI-BERT: Hyperspectral image classification using the bidirectional encoder representation from transformers,” IEEE Trans. Geosci. Remote Sens., vol. 58, no. 1, pp. 165–178, Jan. 2020. doi: 10.1109/TGRS.2019.2934760.
[11] D. Hong, Z. Han, J. Yao, L. Gao, B. Zhang, A. Plaza, and J. Chanussot, “SpectralFormer: Rethinking hyperspectral image classification with transformers,” IEEE Trans. Geosci. Remote Sens., vol. 60, pp. 1–15, 2022, Art. no. 5518615. doi: 10.1109/TGRS.2021.3130716.
[12] H. Sun, X. Zheng, X. Lu, and S. Wu, “Spectral–spatial attention network for hyperspectral image classification,” IEEE Trans. Geosci. Remote Sens., vol. 58, no. 5, pp. 3232–3245, May 2020. doi: 10.1109/TGRS.2019.2951160.
[13] S. K. Roy, S. Das, T. Song, and B. Chanda, “DARecNet-BS: Unsupervised dual-attention reconstruction network for hyperspectral band selection,” IEEE Geosci. Remote Sens. Lett., vol. 18, no. 12, pp. 2152–2156, Dec. 2021. doi: 10.1109/LGRS.2020.3013235.
[14] C. O. Ayna, R. Mdrafi, Q. Du, and A. C. Gurbuz, “Learning-based optimization of hyperspectral band selection for classification,” Remote Sens., vol. 15, no. 18, Art. no. 4460, Sep. 2023. doi: 10.3390/rs15184460.
[15] L. Agilandeeswari, M. Prabukumar, V. Radhesyam, K. L. N. B. Phaneendra Kumar, and A. Farhan, “Crop classification for agricultural applications in hyperspectral remote sensing images,” Appl. Sci., vol. 12, no. 3, Art. no. 1670, Feb. 2022. doi: 10.3390/app12031670.
[16] Y. Tan, J. Gu, L. Lu, L. Zhang, J. Huang, L. Pan, Y. Lv, Y. Wang, and Y. Chen, “Hyperspectral band selection for crop identification and mapping of agriculture,” Remote Sens., vol. 17, no. 4, Art. no. 663, Feb. 2025. doi: 10.3390/rs17040663.
[17] J. Liang, J. Zhou, Y. Qian, L. Wen, X. Bai, and Y. Gao, “On the sampling strategy for evaluation of spectral-spatial methods in hyperspectral image classification,” IEEE Trans. Geosci. Remote Sens., vol. 55, no. 2, pp. 862–880, Feb. 2017. doi: 10.1109/TGRS.2016.2616489.
[18] X. Cao, C. Li, J. Feng, and L. Jiao, “Semi-supervised feature learning for disjoint hyperspectral imagery classification,” Neurocomputing, vol. 526, pp. 9–18, Mar. 2023. doi: 10.1016/j.neucom.2023.01.054.
[19] P. Zhang, H. Yu, P. Li, and R. Wang, “TransHSI: A hybrid CNN-Transformer method for disjoint sample-based hyperspectral image classification,” Remote Sens., vol. 15, no. 22, Art. no. 5331, Nov. 2023. doi: 10.3390/rs15225331.
[20] K. T. Decker and B. J. Borghetti, “A survey of sampling methods for hyperspectral remote sensing: Addressing bias induced by random sampling,” Remote Sens., vol. 17, no. 8, Art. no. 1373, Apr. 2025. doi: 10.3390/rs17081373.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Journal of Intelligent Engineering and Informatics
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
