No abstract

Landslide susceptibility assessment serves as a critical scientific reference for geohazard control, land use, and sustainable development planning. The existing research has not fully considered the potential impact of the spatial agglomeration and dispersion of landslides on assessments. This issue may cause a systematic evaluation bias when the field investigation data are insufficient, which is common due to limited human resources. Accordingly, this paper proposes two novel strategies, including a clustering algorithm and a preprocessing method, for these two ignored features to strengthen assessments, especially in high-susceptibility regions. Multiple machine learning models are compared in a case study of the city of Bijie (Guizhou Province, China). Then we generate the optimal susceptibility map and conduct two experiments to test the validity of the proposed methods. The primary conclusions of this study are as follows: (1) random forest (RF) was superior to other algorithms in the recognition of high-susceptibility areas and the portrayal of local spatial features; (2) the susceptibility map incorporating spatial feature messages showed a noticeable improvement over the spatial distribution and gradual change of susceptibility, as well as the accurate delineation of critical hazardous areas and the interpretation of historical hazards; and (3) the spatial distribution feature had a significant positive effect on modeling, as the accuracy increased by 5% and 10% after including the spatial agglomeration and dispersion consideration in the RF model, respectively. The benefit of the agglomeration is concentrated in high-susceptibility areas, and our work provides insight to improve the assessment accuracy in these areas, which is critical to risk assessment and prevention activities.

The typhoon is one major threat to human societies and natural ecosystems, and its risk perception is crucial for contextualizing and managing disaster risks in different social settings. Social media data are a new data source for studying risk perception, because such data are timely, widely distributed, and sensitive to emergencies. However, few studies have focused on crowd sensitivity variation in social media data-based typhoon risk perception. Based on the regional disaster system theory, a framework of analysis for crowd risk perception was established to explore the feasibility of using social media data for typhoon risk perception analysis and crowd sensitivity variation. The goal was to quantitatively analyze the impact of hazard intensity and social and geographical environments on risk perception and its variation among population groups. Taking the Sina Weibo data during Typhoon Lekima of 2019 as an example, we found that: (1) Typhoon Lekima-related Weibo public attention changed in accordance with the evolution of the typhoon track and the number of Weibo posts shows a significantly positive correlation with disaster losses, while socioeconomic factors, including population, gross domestic product, and land area, are not explanatory factors of the spatial distribution of disaster-related Weibo posts; (2) Females, nonlocals with travel plans, and people living in areas with high hazard intensity, low elevation, or near waterbodies affected by Lekima paid more attention to the typhoon disaster; and (3) Descriptions of rainfall intensity by females are closer to the meteorological observation data.