Background With the increased frequency of extreme weather, landslides induced by extremely heavy rainfall pose a major threat to human lives and property safety. In July 2020, a landslide occurred in the strongly weathered Laoshan Scenic Spot in Qingdao, China, and a short period of heavy rainfall was the main factor inducing the landslide. Method Based on the similarity criterion, three groups of laboratory model tests under different extreme rainfall conditions were conducted using a large landslide model test box. The rainfall infiltration responses under different rainfall intensities, deformation processes, and failure modes of the slope were analyzed. The inducing mechanism and rainfall disaster process of granite landslides induced by extreme rainfall in strongly weathered areas were summarized. Result The results showed that (1) a completely weathered granite landslide induced by rainfall had four stages, i.e., infiltration erosion, surface deformation, damage deepening, and overall instability, and the landslide was characterized by "sheet slip". (2) With greater rainfall intensities, the rainfall infiltration rate was higher, the changes in soil pressure, pore water pressure, water content, and matrix suction were faster, and the hysteresis effect was weaker. (3) A certain spatial distribution pattern was observed between slope deformation/damage and rainfall infiltration, and the research results could provide references for landslide warning and treatment in strongly weathered granite areas.

With the increased frequency of extreme weather, landslides induced by extremely heavy rainfall pose a major threat to human lives and property safety. Taking the 7.23 Fanling landslide in Laoshan, Qingdao, a typical strongly weathered granite area, as an example, based on the similarity criterion, three groups of indoor model tests under different extreme rainfall conditions were conducted using a large landslide model test box. The rainfall infiltration responses under different rainfall intensities, deformation processes, and failure modes of the slope were analyzed. The inducing mechanism and rainfall disaster process of granite landslides induced by extreme rainfall in strongly weathered areas were summarized. The results showed that (1) a completely weathered granite landslide induced by rainfall had four stages, i.e., infiltration erosion, surface deformation, damage deepening, and overall instability, and the slope was characterized by "sheet slip". (2) With greater rainfall intensities, the rainfall infiltration rate was higher, the changes in soil pressure, pore water pressure, water content, and matrix suction were faster, and the hysteresis effect was weaker. (3) A certain spatial distribution pattern was observed between slope deformation/damage and rainfall infiltration, and the research results could provide references for landslide warning and treatment in strongly weathered granite areas.

To reduce the significant losses caused by slope failures and landslides, it is of great significance to detect and predict these disasters scientifically. This study focused on Huangdao District of Qingdao City in Shandong Province, using the improved Faster R-CNN network to detect slope failures and landslides. This study introduced a multi-scale feature enhancement module into the Faster R-CNN model. The module enhances the network’s perception of different scales of slope failures and landslides by deeply fusing high-resolution weak semantic features with low-resolution strong semantic features. Our experiments show that the improved Faster R-CNN model outperformed the traditional version, and that ResNet50 performed better than VGG16 with an AP value of 90.68%, F1 value of 0.94, recall value of 90.68%, and precision value of 98.17%. While the targets predicted by VGG16 were more dispersed and the false detection rate was higher than that of ResNet50, VGG16 was shown to have an advantage in predicting small-scale slope failures and landslides. The trained Faster R-CNN network model detected geological hazards of slope failure and landslide in Huangdao District, missing only two landslides, thereby demonstrating high detection accuracy. This method can provide an effective technical means for slope failures and landslides target detection and has practical implications.