Search

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. [ABSTRACT FROM AUTHOR]

Earthquake disaster assessment is one of the most critical aspects in reducing earthquake disaster losses. However, traditional seismic intensity assessment methods are not effective in disaster-stricken areas with insufficient observation data. Social media data contain a large amount of disaster information with the advantages of timeliness and multiple temporal-spatial scales, opening up a new channel for seismic intensity assessment. Based on the earthquake disaster information on the microblog platform obtained by the network technique, a multi-model coupled seismic intensity assessment method is proposed, which is based on the BERT-TextCNN model, constrained by the seismaesthesia intensity attenuation model, and supplemented by the method of ellipse-fitting inverse distance interpolation. Taking four earthquakes in Sichuan Province as examples, the earthquake intensity was evaluated in the affected areas from the perspective of seismaesthesia. The results show that (1) the microblog data contain a large amount of earthquake information, which can help identify the approximate scope of the disaster area; (2) the influences of the subjectivity and uneven spatial distribution of microblog data on the seismic intensity assessment can be reduced by using the seismaesthesia intensity attenuation model and the method of ellipse-fitting inverse distance interpolation; and (3) the accuracy of seismic intensity assessment based on the coupled model is 70.81%. Thus, the model has higher accuracy and universality. It can be used to assess seismic intensity in multiple regions and assist in the formulation of earthquake relief plans. [ABSTRACT FROM AUTHOR]

With the rapid development of big data, numerous industries have turned their focus from information research and construction to big data technologies. Earth science and geographic information systems industries are highly information-intensive, and thus there is an urgent need to study and integrate big data technologies to improve their level of information. However, there is a large gap between existing big data and traditional geographic information technologies. Owing to certain characteristics, it is difficult to quickly and easily apply big data to geographic information technologies. Through the research, development, and application practices achieved in recent years, we have gradually developed a common geospatial big data solution. Based on the formation of a set of geospatial big data frameworks, a complete geospatial big data platform system called BiGeo was developed. Through the management and analysis of massive amounts of spatial data from Sichuan Province, China, the basic framework of this platform can be better utilized to meet our needs. This paper summarizes the design, implementation, and experimental experience of BiGeo, which provides a new type of solution to the research and construction of geospatial big data. [ABSTRACT FROM AUTHOR]

On 8 August 2017 an earthquake (MS7.0) occurred within Jiuzhaigou County, Northern Aba Prefecture, Sichuan Province, China, triggering 4834 landslides with an individual area greater than 7.8 m2 over a more than 400 km2 region. Instead of correlating geological and topographic factors with the coseismic landslide distribution pattern, this study has attempted to reveal the control from seismic landslide susceptibility mapping, which relies on the calculation of critical acceleration values using a simplified Newmark block model. We calculated the average critical acceleration for each cell of the gridded study area (1 km×1 km), which represented the seismic landslide susceptibility of the cell. An index of the potential landslide area generation rate was defined, i.e., the possible landsliding area in each grid cell. In combination with PGA (peak ground acceleration) distribution, we calculated such indexes for each cell to predict the possible landslide hazard under seismic ground shaking. Results show that seismic landslide susceptibility plays an important role in determining the coseismic landslide pattern. The places with high seismic landslide susceptibility tends to host many landslides. Additionally, the areas with high potential landslide area generation rates have high real landslide occurrence rates, consistent with dominant small-medium scale landslides by this earthquake. This approach can aid assessment of seismic landslide hazards at a preliminary stage. Additionally, it forms a foundation for further research, such as the rapid evaluation of post-earthquake landslides and identifying highly impacted areas to help decision makers prioritize disaster relief efforts. [ABSTRACT FROM AUTHOR]