AI-Based Satellite Image Change Detection for Environmental Monitoring and Disaster Assessment Using Deep Learning and Explainable Artificial Intelligence

We presented a documented pipeline for five-class building-damage segmentation from bi-temporal imagery and evaluated it on a disaster event unseen during training. The model localises buildings with an F1 of 0.780, but its damage grading is weak (macro F1 0.286) and mostly errs towards under-grading, and training and validation behaviour diverge. The results are a starting point, not a demonstration of generalisation: they come from one test event and one seed without baselines. Until multi-event evaluation, ablations, footprint gating and expert validation are done, the system should not inform operational decisions.

[1]           United Nations Office for Disaster Risk Reduction, Human Cost of Disasters: An Overview of the Last 20 Years (2000–2019). Geneva, Switzerland, 2020. [2]           R. Gupta et al., “Creating xBD: A dataset for assessing building damage from satellite imagery,” in Proc. CVPR Workshops, 2019. [3]           X. X. Zhu et al., “Deep learning in remote sensing: A comprehensive review and list of resources,” IEEE Geosci. Remote Sens. Mag., vol. 5, no. 4, pp. 8–36, 2017. [4]           L. Ma et al., “Deep learning in remote sensing applications: A meta-analysis and review,” ISPRS J. Photogramm. Remote Sens., vol. 152, pp. 166–177, 2019. [5]           H. Chen and Z. Shi, “A spatial-temporal attention-based method and a new dataset for remote sensing image change detection,” Remote Sens., vol. 12, no. 10, art. 1662, 2020. [6]           R. C. Daudt, B. Le Saux, A. Boulch, and Y. Gousseau, “Urban change detection for multispectral earth observation using convolutional neural networks,” in Proc. IEEE IGARSS, 2018. [7]           Y. Shen et al., “BDANet: Multiscale convolutional neural network with cross-directional attention for building damage assessment from satellite images,” arXiv:2105.07364, 2021. [8]           Z. Zheng, Y. Zhong, J. Wang, A. Ma, and L. Zhang, “Building damage assessment for rapid disaster response with a deep object-based semantic change detection framework: From natural disasters to man-made disasters,” Remote Sens. Environ., vol. 265, art. 112636, 2021. [9]           A. Singh, “Digital change detection techniques using remotely-sensed data,” Int. J. Remote Sens., vol. 10, no. 6, pp. 989–1003, 1989. [10]          R. C. Daudt, B. Le Saux, and A. Boulch, “Fully convolutional Siamese networks for change detection,” in Proc. IEEE ICIP, 2018.