Landslide Detection
Landslide detection research focuses on accurately identifying and mapping landslides using remote sensing data and advanced computational methods to mitigate their devastating impacts. Current efforts heavily utilize deep learning architectures, such as U-Net, LinkNet, and transformer-based models, often incorporating data fusion techniques that combine optical and radar imagery with elevation data to improve accuracy and interpretability. This work is crucial for improving landslide risk assessment, informing hazard mitigation strategies, and enabling more effective emergency response, particularly in light of increasing landslide frequency due to climate change.
Papers
Automating global landslide detection with heterogeneous ensemble deep-learning classification
Alexandra Jarna Ganerød, Gabriele Franch, Erin Lindsay, Martina Calovi
Selection of contributing factors for predicting landslide susceptibility using machine learning and deep learning models
Cheng Chen, Lei Fan
Hyper-pixel-wise Contrastive Learning Augmented Segmentation Network for Old Landslide Detection through Fusing High-Resolution Remote Sensing Images and Digital Elevation Model Data
Yiming Zhou, Yuexing Peng, Wei Li, Junchuan Yu, Daqing Ge, Wei Xiang
UCDFormer: Unsupervised Change Detection Using a Transformer-driven Image Translation
Qingsong Xu, Yilei Shi, Jianhua Guo, Chaojun Ouyang, Xiao Xiang Zhu