Landslide inventories could provide fundamental data for analyzing the causative factors and deformation mechanisms of landslide events. Considering that it is still hard to detect landslides automatically from remote sensing images, endeavors have been carried out to explore the potential of DCNNs on landslide detection, and obtained better performance than shallow machine learning methods. However, there is often confusion as to which structure, layer number, and sample size are better for a project. To fill this gap, this study conducted a comparative test on typical models for landside detection in the Wenchuan earthquake area, where about 200,000 secondary landslides were available. Multiple structures and layer numbers, including VGG16, VGG19, ResNet50, ResNet101, DenseNet120, DenseNet201, UNet−, UNet+, and ResUNet were investigated with different sample numbers (100, 1000, and 10,000). Results indicate that VGG models have the highest precision (about 0.9) but the lowest recall (below 0.76); ResNet models display the lowest precision (below 0.86) and a high recall (about 0.85); DenseNet models obtain moderate precision (below 0.88) and recall (about 0.8); while UNet+ also achieves moderate precision (0.8) and recall (0.84). Generally, a larger sample set can lead to better performance for VGG, ResNet, and DenseNet, and deeper layers could improve the detection results for ResNet and DenseNet. This study provides valuable clues for designing models’ type, layers, and sample set, based on tests with a large number of samples.
Correction to: Earthquake and Disaster Risk: Decade Retrospective of the Wenchuan Earthquake
