Heterogeneous Sensor Data Fusion with Gated Abundance Networks for Urban Change Detection
Keywords:
sensor fusion, urban change detection, gated networks, heterogeneous data, remote sensing, socio-technical systems, governance, sustainabilityAbstract
Urban environments are undergoing rapid transformation driven by population growth, infrastructure expansion, and climate variability, creating an urgent need for reliable change detection systems that can fuse heterogeneous sensor data. This paper introduces a conceptual architecture for heterogeneous sensor data fusion using Gated Abundance Networks, a framework designed to reconcile the disparate spectral, spatial, temporal, and structural characteristics of multi-source remote sensing data—including optical imagery, synthetic aperture radar, hyperspectral data, and LiDAR point clouds. The Gated Abundance Network leverages learnable gating mechanisms and abundance-based representations to adaptively weight contributions from each sensor modality, thereby enhancing detection accuracy while maintaining interpretability. Rather than focusing on algorithmic details, this paper provides a system-level analysis of the architectural trade-offs, deployment infrastructure, governance challenges, and sustainability implications of such a fusion framework for urban change detection. We examine how gated abundance modeling can mitigate issues of missing data, varying acquisition schedules, and domain shifts across sensors, and discuss the computational and energy costs associated with large-scale deployment. Furthermore, we address fairness and robustness concerns, particularly in heterogeneous urban landscapes where sensor coverage may be uneven. The paper also explores policy implications, including data sharing regulations, privacy safeguards, and the need for standardized evaluation benchmarks. Through cross-domain comparisons with other socio-technical systems, we highlight the importance of modular, scalable fusion architectures that can adapt to evolving urban sensing ecosystems. The findings underscore that successful deployment of Gated Abundance Networks depends not only on technical performance but also on institutional coordination, transparent governance, and long-term sustainability planning.
References
1. Zhang, L., Zhang, L., & Du, B. (2016). Deep learning for remote sensing data: A technical tutorial on the state of the art. IEEE Geoscience and Remote Sensing Magazine, 4(2), 22–40.
2. Zhu, X. X., Tuia, D., Mou, L., Xia, G. S., Zhang, L., Xu, F., & Fraundorfer, F. (2017). Deep learning in remote sensing: A comprehensive review and list of resources. IEEE Geoscience and Remote Sensing Magazine, 5(4), 8–36.
3. Ghassemian, H. (2016). A review of remote sensing image fusion methods. Information Fusion, 32, 75–89.
4. Schmitt, M., & Zhu, X. X. (2016). Data fusion and remote sensing: An ever-growing relationship. IEEE Geoscience and Remote Sensing Magazine, 4(4), 6–23.
5. Ghamisi, P., Yokoya, N., Li, J., Liao, W., Liu, S., Plaza, J., ... & Benediktsson, J. A. (2019). Advances in hyperspectral image and signal processing: A comprehensive overview of the state of the art. IEEE Geoscience and Remote Sensing Magazine, 7(2), 48–85.
6. Hong, D., Gao, L., Yokoya, N., Yao, J., Chanussot, J., Du, Q., & Zhang, B. (2019). More diverse means better: Multimodal deep learning meets remote-sensing imagery classification. IEEE Transactions on Geoscience and Remote Sensing, 59(5), 4340–4354.
7. Wagner, W. (2016). A review of the use of synthetic aperture radar images for urban change detection. Remote Sensing, 8(4), 258.
8. Taubenböck, H., et al. (2012). The impact of urbanization on the urban heat island in Beijing using remote sensing data. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 5(3), 878–888.
9. Benediktsson, J. A., Palmason, J. A., & Sveinsson, J. R. (2005). Classification of hyperspectral data from urban areas based on extended morphological profiles. IEEE Transactions on Geoscience and Remote Sensing, 43(3), 480–491.
10. Huang, B., Zhang, H., & Song, H. (2019). Spatiotemporal urban change detection from remote sensing images: A review. International Journal of Remote Sensing, 40(9), 3331–3365.
11. Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2012). ImageNet classification with deep convolutional neural networks. Advances in Neural Information Processing Systems, 25, 1097–1105.
12. Goodfellow, I., Bengio, Y., & Courville, A. (2016). Deep Learning. MIT Press.
13. Xiong, Z., Xiong, W., Shi, J., Zhang, H., Song, Y., & Jacobs, N. (2024). Groundingbooth: Grounding text-to-image customization. arXiv preprint arXiv:2409.08520.
14. Yang, J. X., Wang, J., Li, Z., Sui, C., Long, Z., & Zhou, J. (2025). HSLiNets: Evaluating Band Ordering Strategies in Hyperspectral and LiDAR Fusion. IEEE Geoscience and Remote Sensing Letters.
15. Diakogiannis, F. I., Waldner, F., Caccetta, P., & 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.
16. Ronneberger, O., Fischer, P., & Brox, T. (2015). U-Net: Convolutional networks for biomedical image segmentation. Medical Image Computing and Computer-Assisted Intervention (MICCAI), 234–241.
17. He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 770–778.
18. Vaswani, A., et al. (2017). Attention is all you need. Advances in Neural Information Processing Systems, 30.
19. Ravanbakhsh, M., et al. (2019). Open-set domain adaptation for remote sensing image classification. IEEE Transactions on Geoscience and Remote Sensing, 57(8), 5649–5664.
20. Tuia, D., et al. (2020). Advances in deep learning for remote sensing: From deep learning to explainable AI. ISPRS Journal of Photogrammetry and Remote Sensing, 169, 178–191.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Journal of Advanced Artificial Intelligence Research
This work is licensed under a Creative Commons Attribution 4.0 International License.
This article is published under the Creative Commons Attribution 4.0 International License (CC BY 4.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.
