Relational Reasoning in Remote Sensing: A Review of Current Paradigms and the Case for a Co-Evolutionary Framework
How to cite (IJODS) :
Remote sensing activities entail modelling long distance dependencies beyond the neighbourhood. The classic CNNs, which are founded on fixed-grid Euclidean representation, suffer the inherent shortcoming of being unable to capture non-local dependency, and an uneven structure of geographical things. Despite the fact that Object-Based Image Analysis (OBIA) have proposed the context-dependent spatial primitives, they are nevertheless constrained by the fixed segmentation boundaries and the use of heuristic graph creation that makes them not adaptable. Graph Neural Networks (GNNs) provide a framework of non-Euclidean relational reasoning, however the current approaches presuppose the fixed graphs and fixed semantics of nodes, and restrict dynamic representation of spatial-temporal changes in remote sensing data. It is proposed in this paper that an end-to-end shift to common frameworks between adaptive spatial primitives and graph topologies should be undertaken. These structures recursively co-construct spatial entities and their association with task specific loss cues to allocate new differentiable layouts of groupings and the consequent emergence of edges modulated by the expanding node representation. This multi-modal and multiscale representation is unified in a way that directly facilitates easy inference, and it can also adapt to temporal change. The shortcomings of the lack of labels and computational access to scaling to feedback loops in both feature extraction and relational reasoning are addressed by these systems and finally lead to the enhancement of semantic coherence and representable form. We present the long-desired paradigm that combines UQ, encourages lifelong learning, and overcome the drawbacks of the current fixed-grid or heuristic-graph-based cycles of RS analytics to move to adaptable, and comparatively minimized spatial and relational representations.
Z. Xue, Q. Xu, and M. Zhang, "Local transformer with spatial partition restore for hyperspectral image classification," IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens., vol. 15, pp. 4307-4325, 2022, doi:10.1109/jstars.2022.3174135.
Z. Du, H. Ye, and F. Cao, "A novel local–global graph convolutional method for point cloud semantic segmentation," IEEE Trans. Neural Netw. Learn. Syst., vol. 35, no. 4, pp. 4798-4812, Apr. 2024, doi:10.1109/tnnls.2022.3155282.
S. Prasad, L. M. Bruce, and J. Chanussot, "Introduction," in Optical Remote Sensing, Springer, 2011, pp. 1-8, doi: 10.1007/978-3-642-14212-3_1.
Y. LeCun, Y. Bengio, and G. Hinton, "Deep learning," Nature, vol. 521, no. 7553, pp. 436-444, May 2015, doi:10.1038/nature14539.
J. Guo, K. Huang, X. Yi, Z. Su, and R. Zhang, "Rethinking spectral graph neural networks with spatially adaptive filtering," IEEE Trans. Neural Netw. Learn. Syst., pp. 1-15, 2026, doi: 10.1109/tnnls.2026.3673098.
M. Hussain, D. Chen, A. Cheng, H. Wei, and D. Stanley, "Change detection from remotely sensed images: From pixel-based to object-based approaches," ISPRS J. Photogramm. Remote Sens., vol. 80, pp. 91-106, Jun. 2013, doi:10.1016/j.isprsjprs.2013.03.006.
A. Knudby, "Remote sensing," Open Library, 2021. [Online]. Available: https://ecampusontario.pressbooks.pub/remotesensing/front-matter/welcome-to-remote-sensing/. [Accessed: Mar. 18, 2026].
W. Yuan, "Graph neural network-based multimodal sensor fusion for robust autonomous driving perception," in Second Int. Conf. Intell. Transp. Smart Cities (ICITSC 2025), SPIE, Jun. 2025, p. 44, doi: 10.1117/12.3073578.
J. Ju, E. D. Kolaczyk, and S. Gopal, "Gaussian mixture discriminant analysis and sub-pixel land cover characterization in remote sensing," Remote Sens. Environ., vol. 84, no. 4, pp. 550-560, Apr. 2003, doi:10.1016/s0034-4257(02)00172-4.
R. Haralick and H. Joo, "A context classifier," IEEE Trans. Geosci. Remote Sens., vol. GE-24, no. 6, pp. 997-1007, Nov. 1986, doi: 10.1109/tgrs.1986.289563.
B. Jeon and D. A. Landgrebe, "Classification with spatio-temporal interpixel class dependency contexts," IEEE Trans. Geosci. Remote Sens., vol. 30, no. 4, pp. 663-672, Jul. 1992, doi: 10.1109/36.158859.
Y. Chen, Y. Zhou, Y. Ge, R. An, and Y. Chen, "Enhancing land cover mapping through integration of pixel-based and object-based classifications from remotely sensed imagery," Remote Sens., vol. 10, no. 1, p. 77, Jan. 2018, doi:10.3390/rs10010077.
M. Dalponte, L. Bruzzone, L. Vescovo, and D. Gianelle, "The role of spectral resolution and classifier complexity in the analysis of hyperspectral images of forest areas," Remote Sens. Environ., vol. 113, no. 11, pp. 2345-2355, Nov. 2009, doi: 10.1016/j.rse.2009.06.013.
E. Gromny, S. Lewiński, M. Rybicki, R. Malinowski, M. Krupiński, and A. Nowakowski, "Post-processing tools for land cover classification of Sentinel-2," in Photonics Appl. Astron. Commun. Ind. High-Energy Phys. Exp. 2019, SPIE, Nov. 2019, p. 232, doi: 10.1117/12.2537325.
S. Yang, M. Hou, and S. Li, "Three-dimensional point cloud semantic segmentation for cultural heritage: A comprehensive review," Remote Sens., vol. 15, no. 3, p. 548, Jan. 2023, doi: 10.3390/rs15030548.
G. Chen, Q. Weng, G. J. Hay, and Y. He, "Geographic object-based image analysis (GEOBIA): Emerging trends and future opportunities," GISci. Remote Sens., vol. 55, no. 2, pp. 159-182, Jan. 2018, doi:10.1080/15481603.2018.1426092.
S. T. M. Ataky, "Image classification methods based on texture analysis and characterization," Ph.D. dissertation, École de technologie supérieure, 2022.
B. Ez-zahouani, A. Teodoro, O. El Kharki, L. Jianhua, I. Kotaridis, X. Yuan, and L. Ma, "Remote sensing imagery segmentation in object-based analysis: A review of methods, optimization, and quality evaluation over the past 20 years," Remote Sens. Appl. Soc. Environ., vol. 32, p. 101031, Nov. 2023, doi: 10.1016/j.rsase.2023.101031.
M. D. Hossain and D. Chen, "Segmentation for object-based image analysis (OBIA): A review of algorithms and challenges from remote sensing perspective," ISPRS J. Photogramm. Remote Sens., vol. 150, pp. 115-134, Apr. 2019, doi: 10.1016/j.isprsjprs.2019.02.009.
M. Seyedhosseini and T. Tasdizen, "Semantic image segmentation with contextual hierarchical models," IEEE Trans. Pattern Anal. Mach. Intell., vol. 38, no. 5, pp. 951-964, May 2016, doi: 10.1109/tpami.2015.2473846.
A. Thapa, T. Horanont, B. Neupane, and J. Aryal, "Deep learning for remote sensing image scene classification: A review and meta-analysis," Remote Sens., vol. 15, no. 19, p. 4804, Oct. 2023, doi: 10.3390/rs15194804.
D. Yu, Q. Xu, H. Guo, C. Zhao, Y. Lin, and D. Li, "An efficient and lightweight convolutional neural network for remote sensing image scene classification," Sensors, vol. 20, no. 7, p. 1999, Apr. 2020, doi: 10.3390/s20071999.
J. Long, E. Shelhamer, and T. Darrell, "Fully convolutional networks for semantic segmentation," in 2015 IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), Jun. 2015, pp. 3431-3440, doi: 10.1109/cvpr.2015.7298965.
U. A. Bhatti, H. Tang, G. Wu, S. Marjan, and A. Hussain, "Deep learning with graph convolutional networks: An overview and latest applications in computational intelligence," Int. J. Intell. Syst., vol. 2023, no. 1, Jan. 2023, doi:10.1155/2023/8342104.
J. Ghosh and S. Gupta, "ADAM optimizer and categorical crossentropy loss function-based CNN method for diagnosing colorectal cancer," in 2023 Int. Conf. Comput. Intell. Sustain. Eng. Solutions (CISES), Apr. 2023, pp. 470-474, doi: 10.1109/cises58720.2023.10183491.
S. Stabinger, D. Peer, and A. Rodríguez-Sánchez, "Arguments for the unsuitability of convolutional neural networks for non-local tasks," Neural Netw., vol. 142, pp. 171-179, Oct. 2021, doi: 10.1016/j.neunet.2021.05.001.
N. Rusk, "Deep learning," Nat. Methods, vol. 13, p. 35, 2016, doi: 10.1038/nmeth.3707.
X.-M. Zhang, L. Liang, L. Liu, and M.-J. Tang, "Graph neural networks and their current applications in bioinformatics," Front. Genet., vol. 12, Jul. 2021, doi: 10.3389/fgene.2021.690049.
J. R. Stevens, R. G. Resmini, and D. W. Messinger, "Spectral-density-based graph construction techniques for hyperspectral image analysis," IEEE Trans. Geosci. Remote Sens., vol. 55, no. 10, pp. 5966-5983, Oct. 2017, doi:10.1109/tgrs.2017.2718547.
D. Sarkar, S. Roy, S. Malakar, and R. Sarkar, "A modified GNN architecture with enhanced aggregator and message passing functions," Eng. Appl. Artif. Intell., vol. 122, p. 106077, Jun. 2023, doi: 10.1016/j.engappai.2023.106077.
N. Sheikh and S. Saha, "Graph neural networks for multi-sensor Earth observation," in Deep Learning for Multi-Sensor Earth Observation, Elsevier, 2025, pp. 211-230, doi: 10.1016/b978-0-44-326484-9.00020-8.
T. R. Harsha, V. P. Bhat, K. Prabhanjan, S. K. Vinay, and L. Thomas, "Graph neural networks for scene understanding: A review and future directions," in Graph Neural Networks: Essentials and Use Cases, Springer, 2025, pp. 277-339, doi: 10.1007/978-3-031-88538-9_13.
T. N. Kipf and M. Welling, "Semi-supervised classification with graph convolutional networks," arXiv preprint arXiv:1609.02907, 2016.
S. Khoshraftar and A. An, "A survey on graph representation learning methods," ACM Trans. Intell. Syst. Technol., vol. 15, no. 1, pp. 1-55, Jan. 2024, doi: 10.1145/3633518.
J. Zhang, K. A. Ehinger, J. Ding, and J. Yang, "A prior-based graph for salient object detection," in 2014 IEEE Int. Conf. Image Process. (ICIP), Oct. 2014, pp. 1175-1178, doi: 10.1109/icip.2014.7025234.
L. Wang, W. Huang, M. Zhang, S. Pan, X. Chang, and S. W. Su, "Pruning graph neural networks by evaluating edge properties," Knowl.-Based Syst., vol. 256, p. 109847, Nov. 2022, doi: 10.1016/j.knosys.2022.109847.
W. Bi, L. Du, Q. Fu, Y. Wang, S. Han, and D. Zhang, "MM-GNN: Mix-moment graph neural network towards modeling neighborhood feature distribution," in Proc. Sixteenth ACM Int. Conf. Web Search Data Min., Feb. 2023, pp. 132-140, doi: 10.1145/3539597.3570457.
A. Bera, Z. Wharton, Y. Liu, N. Bessis, and A. Behera, "SR-GNN: Spatial relation-aware graph neural network for fine-grained image categorization," IEEE Trans. Image Process., vol. 31, pp. 6017-6031, 2022, doi:10.1109/tip.2022.3205215.
L. Wang et al., "NTIRE 2024 challenge on stereo image super-resolution: Methods and results," in 2024 IEEE/CVF Conf. Comput. Vis. Pattern Recognit. Workshops (CVPRW), Jun. 2024, pp. 6198-6207, doi:10.1109/cvprw63382.2024.00624.
Z. Li, J. Yu, G. Zhang, and L. Xu, "Dynamic spatio-temporal graph network with adaptive propagation mechanism for multivariate time series forecasting," Expert Syst. Appl., vol. 216, p. 119374, Apr. 2023, doi:10.1016/j.eswa.2022.119374.
W. Kim, A. Kanezaki, and M. Tanaka, "Unsupervised learning of image segmentation based on differentiable feature clustering," IEEE Trans. Image Process., vol. 29, pp. 8055-8068, 2020, doi: 10.1109/tip.2020.3011269.
H. Shen, H. Ding, Y. Zhang, X. Cong, Z.-Q. Zhao, and X. Jiang, "Spatial-frequency adaptive remote sensing image dehazing with mixture of experts," IEEE Trans. Geosci. Remote Sens., vol. 62, pp. 1-14, 2024, doi:10.1109/tgrs.2024.3458986.
Z. Wang, J. Wang, K. Yang, L. Wang, F. Su, and X. Chen, "Semantic segmentation of high-resolution remote sensing images based on a class feature attention mechanism fused with Deeplabv3+," Comput. Geosci., vol. 158, p. 104969, Jan. 2022, doi: 10.1016/j.cageo.2021.104969.
V.-A. Darvariu, S. Hailes, and M. Musolesi, "Goal-directed graph construction using reinforcement learning," Proc. R. Soc. A Math. Phys. Eng. Sci., vol. 477, no. 2254, Oct. 2021, doi: 10.1098/rspa.2021.0168.
P. Veličković, G. Cucurull, A. Casanova, A. Romero, P. Lio, and Y. Bengio, "Graph attention networks," arXiv preprint arXiv:1710.10903, 2017.
F. Rastakhiz, "GNN-CNN: An efficient hybrid model of convolutional and graph neural networks for text representation," SSRN, 2025, doi: 10.2139/ssrn.5346208.
A. A. Aleissaee et al., "Transformers in remote sensing: A survey," Remote Sens., vol. 15, no. 7, p. 1860, Mar. 2023, doi: 10.3390/rs15071860.
S. Aboagye-Ntow and X. Huang, "A survey of multimodal data fusion in Earth observation-remote sensing," Preprints, Oct. 2025, doi: 10.20944/preprints202510.0743.v1.
A. Irfan, Y. Li, X. E, and G. Sun, "Land use and land cover classification with deep learning-based fusion of SAR and optical data," Remote Sens., vol. 17, no. 7, p. 1298, Apr. 2025, doi: 10.3390/rs17071298.
C. Wen, X. Li, X. Yao, L. Peng, and T. Chi, "Airborne LiDAR point cloud classification with global-local graph attention convolution neural network," ISPRS J. Photogramm. Remote Sens., vol. 173, pp. 181-194, Mar. 2021, doi: 10.1016/j.isprsjprs.2021.01.007.
K. Wang, "An adaptive graph sampling framework for graph analytics," Soc. Netw. Anal. Min., vol. 14, no. 1, Dec. 2023, doi: 10.1007/s13278-023-01157-x.
L. Meng et al., "A survey of distributed graph algorithms on massive graphs," ACM Comput. Surv., vol. 57, no. 2, pp. 1-39, Oct. 2024, doi: 10.1145/3694966.
N. Rashid, B. U. Demirel, and M. Abdullah Al Faruque, "AHAR: Adaptive CNN for energy-efficient human activity recognition in low-power edge devices," IEEE Internet Things J., vol. 9, no. 15, pp. 13041-13051, Aug. 2022, doi: 10.1109/jiot.2022.3140465.
Z. Wu, S. Pan, F. Chen, G. Long, C. Zhang, and P. S. Yu, "A comprehensive survey on graph neural networks," IEEE Trans. Neural Netw. Learn. Syst., vol. 32, no. 1, pp. 4-24, Jan. 2021, doi:10.1109/tnnls.2020.2978386.
A. Mumuni and F. Mumuni, "Data augmentation: A comprehensive survey of modern approaches," Array, vol. 16, p. 100258, Dec. 2022, doi: 10.1016/j.array.2022.100258.
S. Gaur and R. Singh, "A comprehensive review on land use/land cover (LULC) change modeling for urban development: Current status and future prospects," Sustainability, vol. 15, no. 2, p. 903, Jan. 2023, doi:10.3390/su15020903.
L. Zhong, Z. Chen, Z. Wu, S. Du, Z. Chen, and S. Wang, "Learnable graph convolutional network with semisupervised graph information bottleneck," IEEE Trans. Neural Netw. Learn. Syst., vol. 36, no. 1, pp. 433-446, Jan. 2025, doi: 10.1109/tnnls.2023.3322739.
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Attribution-ShareAlike 4.0 International License
https://creativecommons.org/licenses/by-sa/4.0/