Seismic landslides are the most common and highly destructive earthquake-triggered geological hazards. They are large in scale and occur simultaneously in many places. Therefore, obtaining landslide information quickly after an earthquake is the key to disaster mitigation and relief. The survey results show that most of the landslide-information extraction methods involve too much manual participation, resulting in a low degree of automation and the inability to provide effective information for earthquake rescue in time. In order to solve the abovementioned problems and improve the efficiency of landslide identification, this paper proposes an automatic landslide identification method named improved U-Net model. The intelligent extraction of post-earthquake landslide information is realized through the automatic extraction of hierarchical features. The main innovations of this paper include the following: (1) On the basis of the three RGB bands, three new bands, DSM, slope, and aspect, with spatial information are added, and the number of feature parameters of the training samples is increased. (2) The U-Net model structure is rebuilt by adding residual learning units during the up-sampling and down-sampling processes, to solve the problem that the traditional U-Net model cannot fully extract the characteristics of the six-channel landslide for its shallow structure. At the end of the paper, the new method is used in Jiuzhaigou County, Sichuan Province, China. The results show that the accuracy of the new method is 91.3%, which is 13.8% higher than the traditional U-Net model. It is proved that the new method is effective and feasible for the automatic extraction of post-earthquake landslides.

Landslides are the most common and destructive secondary geological hazards caused by earthquakes. It is difficult to extract landslides automatically based on remote sensing data, which is import for the scenario of disaster emergency rescue. The literature review showed that the current landslides extraction methods mostly depend on expert interpretation which was low automation and thus was unable to provide sufficient information for earthquake rescue in time. To solve the above problem, an end-to-end improved Mask R-CNN model was proposed. The main innovations of this paper were (1) replacing the feature extraction layer with an effective ResNeXt module to extract the landslides. (2) Increasing the bottom-up channel in the feature pyramid network to make full use of low-level positioning and high-level semantic information. (3) Adding edge losses to the loss function to improve the accuracy of the landslide boundary detection accuracy. At the end of this paper, Jiuzhaigou County, Sichuan Province, was used as the study area to evaluate the new model. Results showed that the new method had a precision of 95.8%, a recall of 93.1%, and an overall accuracy (OA) of 94.7%. Compared with the traditional Mask R-CNN model, they have been significantly improved by 13.9%, 13.4%, and 9.9%, respectively. It was proved that the new method was effective in the landslides automatic extraction.

Fine sediments in debris-flow gullies are quaternary sediments with a particle size of less than 2 mm. Since they are easy to suspend in flowing water, their stability plays a key “probe” role in early debris-flow warning. The permeability coefficient is the main internal control factor of fine sediment stability in debris flow. However, there is no quantitative model between the permeability coefficient and its influencing factors, which seriously affects the quantitative evaluation of debris flow sediments. Taking the debris-flow gullies in Laobeichuan County, Sichuan Province, China as the research area, we carried out experiments on the permeability coefficient and its influencing factors. A model between the permeability coefficient and its influencing factors was established by the least-squares multivariate statistical analysis method. The results showed that cohesion was the closest factor to the permeability coefficient, followed by porosity and density. Each factor passed the t-test and significantly correlated with the model in 99.99% probability. With a correlation coefficient of 0.72, the model had a good prediction ability. Therefore, the model not only provides a theoretical basis for analyzing the stability of fine sediments in Laobeichuan County, but also points out the direction for detecting the fine sediment stability in debris-flow gullies.

Recurrent blooms of Ulva prolifera (U. prolifera) in the South Yellow Sea (SYS) have become a significant ecological and socio-economic challenge, disrupting marine ecosystems, aquaculture, and coastal tourism. Traditional methods for detecting and managing these blooms face notable limitations, especially in complex marine environments and under adverse observation conditions. To address these issues, this study employs Sentinel-1 synthetic aperture radar (SAR) imagery and deep learning (DL) techniques. A comprehensive dataset, SYSUPD-SAR, was constructed, containing over 440,000 annotated U. prolifera patches alongside lookalike samples. Pre-training was conducted using the Contrastive Mask Image Distillation (CMID) framework, while the Swin Transformer model was enhanced with multi-head self-attention mechanisms and deep supervision strategies to improve segmentation accuracy and robustness. Key results indicate that the refined model achieved an Intersection over Union (IoU) of 93.24% and a Dice loss of 18.13%, demonstrating its effectiveness in reducing false positives and enhancing detection precision. Additionally, the integration of texture features and consideration of incidence angle variations further strengthened the model’s performance. This study provides a robust framework for U. prolifera detection, offering valuable insights and tools for mitigating the environmental and economic impacts of green tides.

Cohesion is the attraction between adjacent particles within the same material, which is the main inter-controlled factor of fine-grained sediment stability, and thus plays an important role in debris flow hazard early warning. However, there is no quantitative model of cohesion and its inter-controlled factors, including effective internal friction angle, permeability coefficient and density. Therefore, establishing a quantitative model of cohesion and its inter-controlled factors is of considerable significance in debris flow hazard early warning. Taking Beichuan county in southwestern China as the study area, we carried out a series of experiments on cohesion and its inter-controlled factors. Using the value of cohesion as the dependent variable and values of normalized density, normalized logarithm of permeability coefficient and normalized effective internal friction angle as the independent variables, we established a quantitative model of cohesion and its inter-controlled factors by the least-squares multivariate statistical method. Fitting of the model showed that its determination coefficient (R²) was 0.61, indicating that the corresponding correlation coefficient (R) was 0.78. Furthermore, t-tests of the model showed that except for the p value of density, which was 0.05, those of other factors were less than 0.01, indicating that cohesion was significantly correlated to its inter-controlled factors, providing a scientific basis for debris flow hazard early warning.