Landslide Displacement Prediction via Attentive Graph Neural Network
Citation
Kuang, P., Li, R., Huang, Y., Wu, J., Luo, X., Zhou, F. (2022). Landslide Displacement Prediction via Attentive Graph Neural Network. Remote Sensing, 14(8): 1919. Link to paper
Abstract
This work presents a novel landslide prediction model based on graph neural networks, which utilizes graph convolutions to aggregate spatial correlations among different monitored locations. The research addresses a significant gap in existing approaches. Previous methods either focus on analyzing the landslide inventory maps obtained from aerial photography and satellite images or propose machine learning models—trained on historical land deformation data—to predict future displacement and sedimentation. However, existing approaches generally fail to capture complex spatial deformations and their inter-dependencies in different areas. This paper has been cited in subsequent research on landslide displacement prediction using graph neural networks and deep learning approaches, demonstrating its influence in the field.