Debris flow susceptibility mapping is considered to be useful for hazard prevention and mitigation. As a frequent debris flow area, many hazardous events have occurred annually and caused a lot of damage in the Sichuan Province, China. Therefore, this study attempted to evaluate and compare the performance of four state-of-the-art machine-learning methods, namely Logistic Regression (LR), Support Vector Machines (SVM), Random Forest (RF), and Boosted Regression Trees (BRT), for debris flow susceptibility mapping in this region. Four models were constructed based on the debris flow inventory and a range of causal factors. A variety of datasets was obtained through the combined application of remote sensing (RS) and geographic information system (GIS). The mean altitude, altitude difference, aridity index, and groove gradient played the most important role in the assessment. The performance of these modes was evaluated using predictive accuracy (ACC) and the area under the receiver operating characteristic curve (AUC). The results of this study showed that all four models were capable of producing accurate and robust debris flow susceptibility maps (ACC and AUC values were well above 0.75 and 0.80 separately). With an excellent spatial prediction capability and strong robustness, the BRT model (ACC = 0.781, AUC = 0.852) outperformed other models and was the ideal choice. Our results also exhibited the importance of selecting suitable mapping units and optimal predictors. Furthermore, the debris flow susceptibility maps of the Sichuan Province were produced, which can provide helpful data for assessing and mitigating debris flow hazards.

Floods are the most destructive, widespread, and frequent natural hazards. The extent of flood events is accelerating in the context of climate change, where flood management and disaster mitigation remain important long-term issues. Different studies have been utilizing data and images from various types of sensors for mapping, assessment, forecasting, early warning, rescue, and other disaster prevention and mitigation activities before, during, and after floods, including flash floods, coastal floods, and urban floods. These monitoring processes evolved from early ground-based observations relying on in situ sensors to high-precision, high-resolution, and high-coverage monitoring by airborne and remote sensing sensors. In this study, we have analyzed the different kinds of sensors from the literature review, case studies, and other methods to explore the development history of flood sensors and the driving role of floods in different countries. It is found that there is a trend towards the integration of flood sensors with artificial intelligence, and their state-of-the-art determines the effectiveness of local flood management to a large extent. This study helps to improve the efficiency of flood monitoring advancement and flood responses as it explores the different types of sensors and their effectiveness.

Globally, poverty and illness are linked, attracting widespread attention. In China, illness contributes to about 40% of rural poverty. This study sought to investigate how healthcare-seeking behavior differs between impoverished and non-impoverished populations within the same Chinese healthcare delivery system. It also sought to understand how differences should be considered when assessing spatial accessibility to provide more accurate recommendations for healthcare resource optimization and promote village revitalization and health equity in China. Methodologically, a survey conducted in May 2019 in Enshi Prefecture (a national impoverished region in Hubei Province, China) collected data on healthcare resource utilization regarding the inpatient and outpatient needs of both impoverished and non-impoverished populations. A Chi-square test compared their respective healthcare-seeking behaviors in three respects (e.g., preference for healthcare institution type, transportation mode, and travel time). Baidu Map data with healthcare institution locations and real-life travel times were then incorporated to assess spatial access to different types of healthcare institutions. Results showed that in Enshi, the most widespread village clinics (low-level) were generally the most utilized healthcare institutions for outpatient visits, with patients usually walking for about 30 min. The middle-level Township Health Centers (THCs) and high-level public hospitals were the most used for inpatient visits, with patients willing to drive up to 30 min to THCs and 60 min to hospitals. Comparatively, the impoverished have more frequent service demands but tend to choose lower-level healthcare institutions, with longer travel times and limited transportation modes. Although 75% of Enshi’s area was covered within 30 min by village clinics and 51% of the villages were within 60 min’ drive to hospitals, considerable areas remain under-served compared with the shortest travel time targets in China. In conclusion, spatial access to healthcare resources in Enshi must be further improved, especially by strengthening the service capacity of primary healthcare institutions to address the healthcare needs of Enshi’s impoverished population. The disparity in healthcare-seeking behavior between different population groups should be fully considered to effectively allocate limited healthcare resources to promote health equity for vulnerable populations as proposed in international and domestic policies.